{"contract": {"schema": "noise-screen-v1", "formal_base": {"status": "selected", "method": "hnm", "version": "hnm-v2", "reason": "固定120録音で音量変動の再現誤差が平均約7.2%減少。振幅超過の頻度・程度も踏まえて事後に採否を見直し、雑音包絡を分離する実装を採用。日本語12録音の補助評価も実施。予測MOSや知覚品質の改善を保証するものではない。", "comparison_reference": "hnm", "comparison_reference_meaning": "実験開始時点の唯一の自作ベース。過去結果は当時の版を保持する。既存比較対象はWORLD（Harvest）。", "previous_version": "hnm-v1", "selection_report": "experiments/2026-10-12/jvs-supplement/results/run-001/index.html"}, "baseline_sha256": "ca2f7f56fe4bbf4c3d987c90ac81cd90cf394e4b636ef36988bdf34f220a7153", "sources": {"audio_report.py": "f46ff0cf69e7cb956ea94ee0c7013d44052c0400c5ffc64d7f9f90b4489aa980", "audio_samples.py": "b9b975c1f305cdaff47909b99bd2a3dce64996e90774d2a8305adc1c67ed6c17", "benchmark.py": "10a84680e1641fe5922b741ce05b6538b43b98be9daf27245661fe80bab732ba", "benchmark_io.py": "b27cca4d9457de305be7bbbd84aedf9b0d097791a933e2e9af55eb67e1edbb3d", "benchmark_pipeline.py": "a049034dcd272bbafda47cbf5719cc6b1cd8dae6f80682200cd3fc7b90e522cd", "benchmark_report.py": "c1a8153022a620bc62095f30c5709a34e217739cb9473860dc5b3daff5b87c88", "benchmark_summary.py": "8221086fe08bfc70cbfb9308a3a01d6fea976afb7de86af8cbacd7999e8281da", "build_world.py": "7d29d81c9a48d633edfeae0425c5cc055bc0a10d230232a51eab5720b2cc6974", "calibrate_pitch.py": "282c917bf87c6f549f32467647802852907e4b0b88128eb8017157b84566adec", "control.py": "bc41e73ff34b5f9cb52280a6f2317c989abc53f8b15f8f82db5ee3102b4b58bd", "corpus.py": "bc14cee2c3dd1a651cf2e5f0e9fe871fbd3a712d1a90d7c18a18547a625802e8", "extended_metrics.py": "ab3537d2c8e5d568a0cd2fa8aa36309de09c3bce7cf2f849214331a22fe3624f", "fixtures.py": "a1646c4d0f7c6966ea49a4673ec2c71e75f864943c8908395089d027325eac69", "hnm.py": "58f0378793b7433f80bf854972882298649799d8e3d0868674816e9bf6b63f74", "hnm_analysis.py": "3f45703667237333d76c4145c1513e4eb3342bd40f01a714c10303082440e26a", "hnm_control.py": "b2f5efbbb1e550569c231a08f12997d94b0bacb130bcc816fe6bd458b17a98bc", "hnm_diagnostics.py": "a3f47468d10db7e8040c78fc24546043b2eeae6b518f59da1f5904c674aae436", "hnm_parameters.py": "635bf222bac8ce41897c0977677e67be4366724f4239a9e85e153169fcea2cf0", "hnm_synthesis.py": "937721cd363f06afa3bf4c20c1ff182a8c337c4b19ac9f4b57314f6adea6b44c", "logging_utils.py": "c80eb5d9647516a4bc03980cb178f8b4bb130ac15877d1b3289797e7ad81e381", "methods.py": "b675f7bddf6d19515609713de11fcf4bbdf4c54a3a536030d8da16c3282dd97c", "metrics.py": "b8767feb49494058bd9ec08fd95ae2fb50ce7897fcdd6cebe319ff8a0ac51f22", "mos.py": "fb632aa5440245525289962372db4f3eb007cd2b3b493b2d05ecccb878e85f03", "mos_batch.py": "c7a732dfe52b08fa155201a7134d2f5561a10b16d1866e9f0526f61b2b244f64", "noise_screen.py": "ada7ed38f5c67b7892f1a18af226d738400934607dd4adb9e403b5ca7bdbf667", "noise_stability.py": "624dc434add0086c53c41b9fb7fd0e65b2c51b16c08d4485e4147a77f5534213", "report.py": "cefe7b865cbf768cc497c2fbf8085f0492875abab89dce34ff99831deb180bce", "run.py": "8b2713600f3890dae76d4b2b1b0ef992fdb621679bff3aecc73ca9b68d92e9d2", "site_summary.py": "9c1b03304cc94162deb95bbd465b05c727fa825aed0d1d4ad43c3febc3d76ad7", "supplement.py": "8b72b63b7059f3e94ecb13f575ab93060e00fee0cb89c5abcaa51719061b890d", "supplement_contract.py": "748bff65db3bd3709cdd472b02358af35518c5d1a96fbf212f6b02ba5fa45cd4", "supplement_report.py": "378abee381348bbe0e833d710b899c66d134fd78834e5afbd7a3a71ecdde510f", "temporal_metrics.py": "ce21b6a4767071a7b98ea0cdbfe54bdba15b596bf8d6b6127281a97095e7be91", "world.py": "d14558eed772e07031a9183f57facc55acb1c27deccb3dd4fa098ffcbe0cde3a", "__init__.py": "73738d70706824f85fdfac302306af505437a50b0ca4cdc68fd57aec211a308d"}, "candidate_sources": {"A": {"__init__.py": "73738d70706824f85fdfac302306af505437a50b0ca4cdc68fd57aec211a308d", "hnm.py": "58f0378793b7433f80bf854972882298649799d8e3d0868674816e9bf6b63f74", "hnm_analysis.py": "3f45703667237333d76c4145c1513e4eb3342bd40f01a714c10303082440e26a", "hnm_control.py": "b2f5efbbb1e550569c231a08f12997d94b0bacb130bcc816fe6bd458b17a98bc", "hnm_parameters.py": "635bf222bac8ce41897c0977677e67be4366724f4239a9e85e153169fcea2cf0", "hnm_synthesis.py": "2168d3b18d284b2aeac1f57ef4ab847fb4c14bf64fdd1e84b2c72597c790cbd2"}, "B": {"__init__.py": "73738d70706824f85fdfac302306af505437a50b0ca4cdc68fd57aec211a308d", "hnm.py": "58f0378793b7433f80bf854972882298649799d8e3d0868674816e9bf6b63f74", "hnm_analysis.py": "3f45703667237333d76c4145c1513e4eb3342bd40f01a714c10303082440e26a", "hnm_control.py": "b2f5efbbb1e550569c231a08f12997d94b0bacb130bcc816fe6bd458b17a98bc", "hnm_parameters.py": "635bf222bac8ce41897c0977677e67be4366724f4239a9e85e153169fcea2cf0", "hnm_synthesis.py": "e2478a1afd758cced692e05b83fa88443184d63406af4b5a1985cf8e3b86758b"}, "C": {"__init__.py": "73738d70706824f85fdfac302306af505437a50b0ca4cdc68fd57aec211a308d", "hnm.py": "58f0378793b7433f80bf854972882298649799d8e3d0868674816e9bf6b63f74", "hnm_analysis.py": "3f45703667237333d76c4145c1513e4eb3342bd40f01a714c10303082440e26a", "hnm_control.py": "b2f5efbbb1e550569c231a08f12997d94b0bacb130bcc816fe6bd458b17a98bc", "hnm_parameters.py": "635bf222bac8ce41897c0977677e67be4366724f4239a9e85e153169fcea2cf0", "hnm_synthesis.py": "640a1f8ae71a296357162c2bbf941bd39465946982c67f7bdb85bdfb1cd8419c"}, "D": {"__init__.py": "73738d70706824f85fdfac302306af505437a50b0ca4cdc68fd57aec211a308d", "hnm.py": "58f0378793b7433f80bf854972882298649799d8e3d0868674816e9bf6b63f74", "hnm_analysis.py": "3f45703667237333d76c4145c1513e4eb3342bd40f01a714c10303082440e26a", "hnm_control.py": "b2f5efbbb1e550569c231a08f12997d94b0bacb130bcc816fe6bd458b17a98bc", "hnm_parameters.py": "635bf222bac8ce41897c0977677e67be4366724f4239a9e85e153169fcea2cf0", "hnm_synthesis.py": "a4fda7d4cfcaff18f49862b09f5c289d3947a8517f4885b35b281102d953ef0c"}, "E": {"__init__.py": "73738d70706824f85fdfac302306af505437a50b0ca4cdc68fd57aec211a308d", "hnm.py": "58f0378793b7433f80bf854972882298649799d8e3d0868674816e9bf6b63f74", "hnm_analysis.py": "3f45703667237333d76c4145c1513e4eb3342bd40f01a714c10303082440e26a", "hnm_control.py": "b2f5efbbb1e550569c231a08f12997d94b0bacb130bcc816fe6bd458b17a98bc", "hnm_parameters.py": "635bf222bac8ce41897c0977677e67be4366724f4239a9e85e153169fcea2cf0", "hnm_synthesis.py": "96d7a9ae6af173785b8321ef4dbfc9d19b3d643d538ef074f6adca4357306ee5"}}, "manifest_sha256": "1ff7a449b5f44580d6b48c187209c9786522880a7630ebfacf081660b2df4520", "input_records": [{"id": "jvs_jvs004_falset10_BASIC5000_2951", "corpus": "jvs_ver1", "speaker": "jvs_jvs004", "language": "ja", "style": "falsetto", "speaker_gender_as_distributed": null, "source_utterance_id": "BASIC5000_2951", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs004/falset10/wav24kHz16bit/BASIC5000_2951.wav", "header_offset": 942343448, "compressed_bytes": 152445, "source_bytes": 216920, "compression": 8, "crc32": 3687763153}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 108438, "source_duration_seconds": 4.51825, "source_peak": 0.359771728515625, "source_rms_dbfs": -25.754466608205988, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -25.754466608205988, "decoded_pcm_sha256": "758793b201b00f5ffea4d70b620d133e969c4e8f6b127e223af8f007fcb697c7", "source_sha256": "6dbf7f1341417b5233ce719e562f37f898f703b1b97e9ca7ff12c581cdb69822", "wav_sha256": "6dbf7f1341417b5233ce719e562f37f898f703b1b97e9ca7ff12c581cdb69822", "local_source": "audio/jvs_jvs004_falset10_BASIC5000_2951.wav", "local_wav": "audio/jvs_jvs004_falset10_BASIC5000_2951.wav", "excerpt_start_sample": 0, "excerpt_samples": 108438}, {"id": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "corpus": "jvs_ver1", "speaker": "jvs_jvs004", "language": "ja", "style": "normal", "speaker_gender_as_distributed": null, "source_utterance_id": "VOICEACTRESS100_058", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs004/parallel100/wav24kHz16bit/VOICEACTRESS100_058.wav", "header_offset": 923973343, "compressed_bytes": 222327, "source_bytes": 309556, "compression": 8, "crc32": 531548112}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 154756, "source_duration_seconds": 6.448166666666666, "source_peak": 0.274444580078125, "source_rms_dbfs": -26.51626799702472, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -26.20342509158779, "decoded_pcm_sha256": "2ef6c4cb56367ba092ec8b5eabdf3931b3461b28c4f8cf68e4f2865f5f10d37b", "source_sha256": "f174986b46a7edcd627989f72ecc2094b30b42faef17b147c9dfab51f78b4540", "wav_sha256": "f174986b46a7edcd627989f72ecc2094b30b42faef17b147c9dfab51f78b4540", "local_source": "audio/jvs_jvs004_parallel100_VOICEACTRESS100_058.wav", "local_wav": "audio/jvs_jvs004_parallel100_VOICEACTRESS100_058.wav", "excerpt_start_sample": 0, "excerpt_samples": 144000}, {"id": "jvs_jvs004_whisper10_BASIC5000_0074", "corpus": "jvs_ver1", "speaker": "jvs_jvs004", "language": "ja", "style": "whisper", "speaker_gender_as_distributed": null, "source_utterance_id": "BASIC5000_0074", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs004/whisper10/wav24kHz16bit/BASIC5000_0074.wav", "header_offset": 935651854, "compressed_bytes": 122880, "source_bytes": 218164, "compression": 8, "crc32": 4183950326}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 109060, "source_duration_seconds": 4.5441666666666665, "source_peak": 0.031829833984375, "source_rms_dbfs": -51.09203551694498, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -51.09203551694498, "decoded_pcm_sha256": "8a2729f6e6b88649d73978b5840454d69e802da2f211934be9b5b14712461b43", "source_sha256": "1dc1b85502f10b17f18e1f869d9eaba17aab672d72df9a9f67b64e4b49f65b04", "wav_sha256": "1dc1b85502f10b17f18e1f869d9eaba17aab672d72df9a9f67b64e4b49f65b04", "local_source": "audio/jvs_jvs004_whisper10_BASIC5000_0074.wav", "local_wav": "audio/jvs_jvs004_whisper10_BASIC5000_0074.wav", "excerpt_start_sample": 0, "excerpt_samples": 109060}, {"id": "jvs_jvs018_falset10_VOICEACTRESS100_004", "corpus": "jvs_ver1", "speaker": "jvs_jvs018", "language": "ja", "style": "falsetto", "speaker_gender_as_distributed": null, "source_utterance_id": "VOICEACTRESS100_004", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs018/falset10/wav24kHz16bit/VOICEACTRESS100_004.wav", "header_offset": 3398430815, "compressed_bytes": 260042, "source_bytes": 432168, "compression": 8, "crc32": 3810555882}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 216062, "source_duration_seconds": 9.002583333333334, "source_peak": 0.37799072265625, "source_rms_dbfs": -30.175737918630894, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -29.30071709983901, "decoded_pcm_sha256": "9d50c2c26a1084d289dce329d8bf9f4b4e0142ff514d2355f35c63a498245d13", "source_sha256": "2f25f673cd4637e368b26d3baec4d20af21bfa899b114bdcc40c450476e9d396", "wav_sha256": "2f25f673cd4637e368b26d3baec4d20af21bfa899b114bdcc40c450476e9d396", "local_source": "audio/jvs_jvs018_falset10_VOICEACTRESS100_004.wav", "local_wav": "audio/jvs_jvs018_falset10_VOICEACTRESS100_004.wav", "excerpt_start_sample": 0, "excerpt_samples": 144000}, {"id": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "corpus": "jvs_ver1", "speaker": "jvs_jvs018", "language": "ja", "style": "normal", "speaker_gender_as_distributed": null, "source_utterance_id": "VOICEACTRESS100_053", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs018/parallel100/wav24kHz16bit/VOICEACTRESS100_053.wav", "header_offset": 3373387638, "compressed_bytes": 228876, "source_bytes": 358270, "compression": 8, "crc32": 3001497381}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 179113, "source_duration_seconds": 7.463041666666666, "source_peak": 0.300323486328125, "source_rms_dbfs": -27.27890180428648, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -26.53870587331253, "decoded_pcm_sha256": "c3579c72685e0999adafebb721bd42bc335d6cd615b07c9e95509516943c2f54", "source_sha256": "b763eeb5b4ce7a395fdff6d175bf1627c2328491c0da8fa95e8068f5bbf80e1e", "wav_sha256": "b763eeb5b4ce7a395fdff6d175bf1627c2328491c0da8fa95e8068f5bbf80e1e", "local_source": "audio/jvs_jvs018_parallel100_VOICEACTRESS100_053.wav", "local_wav": "audio/jvs_jvs018_parallel100_VOICEACTRESS100_053.wav", "excerpt_start_sample": 0, "excerpt_samples": 144000}, {"id": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "corpus": "jvs_ver1", "speaker": "jvs_jvs018", "language": "ja", "style": "whisper", "speaker_gender_as_distributed": null, "source_utterance_id": "VOICEACTRESS100_005", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs018/whisper10/wav24kHz16bit/VOICEACTRESS100_005.wav", "header_offset": 3388607101, "compressed_bytes": 386958, "source_bytes": 875190, "compression": 8, "crc32": 3930378928}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 437573, "source_duration_seconds": 18.232208333333332, "source_peak": 0.037628173828125, "source_rms_dbfs": -53.18760612768678, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -51.47251958187441, "decoded_pcm_sha256": "e95e1bb0ca185383d8b6b3f7b7367171455483ebcd1f6d4bd41ecb95bd74cc3b", "source_sha256": "163d3cbdf7e987c158925ce6d2946625b27edda6d3717a35d8e281fb170f1c3d", "wav_sha256": "163d3cbdf7e987c158925ce6d2946625b27edda6d3717a35d8e281fb170f1c3d", "local_source": "audio/jvs_jvs018_whisper10_VOICEACTRESS100_005.wav", "local_wav": "audio/jvs_jvs018_whisper10_VOICEACTRESS100_005.wav", "excerpt_start_sample": 0, "excerpt_samples": 144000}, {"id": "jvs_jvs066_falset10_BASIC5000_1205", "corpus": "jvs_ver1", "speaker": "jvs_jvs066", "language": "ja", "style": "falsetto", "speaker_gender_as_distributed": null, "source_utterance_id": "BASIC5000_1205", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs066/falset10/wav24kHz16bit/BASIC5000_1205.wav", "header_offset": 2546680799, "compressed_bytes": 136242, "source_bytes": 195580, "compression": 8, "crc32": 1385868073}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 97768, "source_duration_seconds": 4.073666666666667, "source_peak": 0.618865966796875, "source_rms_dbfs": -22.552656329931906, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -22.552656329931906, "decoded_pcm_sha256": "8bb0378c60bf90dece3e4e34abf994e4b31fddfb237ef6fddfbbd69c8b1fa82a", "source_sha256": "47b0702615325483b782b56a91932d87648a80b90aecd59350be65638a6be8ce", "wav_sha256": "47b0702615325483b782b56a91932d87648a80b90aecd59350be65638a6be8ce", "local_source": "audio/jvs_jvs066_falset10_BASIC5000_1205.wav", "local_wav": "audio/jvs_jvs066_falset10_BASIC5000_1205.wav", "excerpt_start_sample": 0, "excerpt_samples": 97768}, {"id": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "corpus": "jvs_ver1", "speaker": "jvs_jvs066", "language": "ja", "style": "normal", "speaker_gender_as_distributed": null, "source_utterance_id": "VOICEACTRESS100_025", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs066/parallel100/wav24kHz16bit/VOICEACTRESS100_025.wav", "header_offset": 2518403343, "compressed_bytes": 187657, "source_bytes": 247250, "compression": 8, "crc32": 3486532083}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 123603, "source_duration_seconds": 5.150125, "source_peak": 0.472930908203125, "source_rms_dbfs": -23.706487580888414, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -23.706487580888414, "decoded_pcm_sha256": "8ab43acb74cca30ae1e3fdd9a76fb7288130fbce511cf398836458ff852c6981", "source_sha256": "c7ebca7938b1e044488e290c866f97301681f0d657ca6975ddfd27da675b293d", "wav_sha256": "c7ebca7938b1e044488e290c866f97301681f0d657ca6975ddfd27da675b293d", "local_source": "audio/jvs_jvs066_parallel100_VOICEACTRESS100_025.wav", "local_wav": "audio/jvs_jvs066_parallel100_VOICEACTRESS100_025.wav", "excerpt_start_sample": 0, "excerpt_samples": 123603}, {"id": "jvs_jvs066_whisper10_BASIC5000_2372", "corpus": "jvs_ver1", "speaker": "jvs_jvs066", "language": "ja", "style": "whisper", "speaker_gender_as_distributed": null, "source_utterance_id": "BASIC5000_2372", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs066/whisper10/wav24kHz16bit/BASIC5000_2372.wav", "header_offset": 2539810955, "compressed_bytes": 116528, "source_bytes": 192462, "compression": 8, "crc32": 791090707}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 96209, "source_duration_seconds": 4.008708333333334, "source_peak": 0.051483154296875, "source_rms_dbfs": -44.38575419034756, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -44.38575419034756, "decoded_pcm_sha256": "97a4254221777a4b1bec3289499f9287ccf298e1e1d1d3cf642fe2c3fb8e4de7", "source_sha256": "0cd67a512b6770abd7e169b447a819db8221646446c692f9abefdc6e57b89cb6", "wav_sha256": "0cd67a512b6770abd7e169b447a819db8221646446c692f9abefdc6e57b89cb6", "local_source": "audio/jvs_jvs066_whisper10_BASIC5000_2372.wav", "local_wav": "audio/jvs_jvs066_whisper10_BASIC5000_2372.wav", "excerpt_start_sample": 0, "excerpt_samples": 96209}, {"id": "jvs_jvs082_falset10_BASIC5000_1728", "corpus": "jvs_ver1", "speaker": "jvs_jvs082", "language": "ja", "style": "falsetto", "speaker_gender_as_distributed": null, "source_utterance_id": "BASIC5000_1728", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs082/falset10/wav24kHz16bit/BASIC5000_1728.wav", "header_offset": 2052129811, "compressed_bytes": 168181, "source_bytes": 260174, "compression": 8, "crc32": 1372142113}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 130065, "source_duration_seconds": 5.419375, "source_peak": 0.220855712890625, "source_rms_dbfs": -28.300793168112545, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -28.300793168112545, "decoded_pcm_sha256": "c7de35fa3bfe83887f9c61f8f38a56132da6836a3a6eae0bee50f16a0465b83f", "source_sha256": "814e0d7ce300263f87677845a8de36c26e893df7df52f89458bca20434e530df", "wav_sha256": "814e0d7ce300263f87677845a8de36c26e893df7df52f89458bca20434e530df", "local_source": "audio/jvs_jvs082_falset10_BASIC5000_1728.wav", "local_wav": "audio/jvs_jvs082_falset10_BASIC5000_1728.wav", "excerpt_start_sample": 0, "excerpt_samples": 130065}, {"id": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "corpus": "jvs_ver1", "speaker": "jvs_jvs082", "language": "ja", "style": "normal", "speaker_gender_as_distributed": null, "source_utterance_id": "VOICEACTRESS100_079", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs082/parallel100/wav24kHz16bit/VOICEACTRESS100_079.wav", "header_offset": 2040731706, "compressed_bytes": 297507, "source_bytes": 437588, "compression": 8, "crc32": 2685562455}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 218772, "source_duration_seconds": 9.1155, "source_peak": 0.15533447265625, "source_rms_dbfs": -30.504221735377747, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -29.922882100947945, "decoded_pcm_sha256": "a636d3ab3504b45a1258fe0a67c7b1329af515afc77a9c8ad32ba0146c5573fb", "source_sha256": "b64d7a959a2691a86416c074b4f73bec7f6d8bee6f1830171b62cfa526f8b15a", "wav_sha256": "b64d7a959a2691a86416c074b4f73bec7f6d8bee6f1830171b62cfa526f8b15a", "local_source": "audio/jvs_jvs082_parallel100_VOICEACTRESS100_079.wav", "local_wav": "audio/jvs_jvs082_parallel100_VOICEACTRESS100_079.wav", "excerpt_start_sample": 0, "excerpt_samples": 144000}, {"id": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "corpus": "jvs_ver1", "speaker": "jvs_jvs082", "language": "ja", "style": "whisper", "speaker_gender_as_distributed": null, "source_utterance_id": "VOICEACTRESS100_001", "transcript": null, "source": {"archive_url": "https://drive.usercontent.google.com/download?id=19oAw8wWn3Y7z6CKChRdAyGOB9yupL_Xt&export=download&confirm=t", "archive_bytes": 3536595425, "member": "jvs_ver1/jvs082/whisper10/wav24kHz16bit/VOICEACTRESS100_001.wav", "header_offset": 2045295249, "compressed_bytes": 194999, "source_bytes": 439874, "compression": 8, "crc32": 155521290}, "metadata_unavailable_reason": "取得処理の通信停止前に性別・転記のメモリー上の情報を保存できなかったため未取得扱い", "sample_rate": 24000, "source_samples": 219915, "source_duration_seconds": 9.163125, "source_peak": 0.0279541015625, "source_rms_dbfs": -61.42939609224267, "full_scale_fraction": 0.0, "reasons": [], "excerpt_full_scale_fraction": 0.0, "excerpt_rms_dbfs": -61.95382949667153, "decoded_pcm_sha256": "2e9752009fa4e3b6da1c72a2a24d8e0847c58184f65c69de675ab526188ca823", "source_sha256": "959dfe29d97ec4c67eb776ad4eebf28a8f34e92c64e82fd19b086f80ada75ca5", "wav_sha256": "959dfe29d97ec4c67eb776ad4eebf28a8f34e92c64e82fd19b086f80ada75ca5", "local_source": "audio/jvs_jvs082_whisper10_VOICEACTRESS100_001.wav", "local_wav": "audio/jvs_jvs082_whisper10_VOICEACTRESS100_001.wav", "excerpt_start_sample": 0, "excerpt_samples": 144000}], "criteria_sha256": "19c16dbc3ed6478cd79cbc8b04e99e6fee6a693f0ba9b36e95d944ec710b1a9d", "lock_sha256": "c8b2bc28ebb1523bf8cfe0f4627d06bd5d03e0ba6a2bb5dc0905be77a3dc8823", "python": "3.12.14", "platform": "Windows-11-10.0.26200-SP0", "dependencies": {"numpy": "2.3.5", "scipy": "1.17.0", "pystoi": "0.4.1", "torch": "2.8.0+cpu", "torchaudio": "2.8.0+cpu", "torchvision": "0.23.0+cpu", "transformers": "4.51.3", "timm": "1.0.15", "librosa": "0.11.0", "utmosv2": "1.3.1.dev0"}, "methods": ["hnm", "A", "B", "C", "D", "E"], "noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "mos_noise_seed": 0, "mos_extraction_seed": 20261012, "mos_repetitions": 1, "mos_threads": 1, "workers": 2, "threads_per_worker": 1, "alignment": "none", "normalization": "none", "analysis": "single_current_base_encode_per_recording", "world": "not_run; historical_reference_only", "role": "candidate_screening_not_automatic_adoption"}, "finished_at": "2026-10-12T06:53:35.798326+00:00", "stage": "all", "status": "completed", "parts": [{"case": {"id": "jvs_jvs004_falset10_BASIC5000_2951", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs004", "source_utterance_id": "BASIC5000_2951", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 108438, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs004_falset10_BASIC5000_2951.wav", "source_file_sha256": "6dbf7f1341417b5233ce719e562f37f898f703b1b97e9ca7ff12c581cdb69822", "decoded_pcm_sha256": "758793b201b00f5ffea4d70b620d133e969c4e8f6b127e223af8f007fcb697c7", "original_source_sha256": "6dbf7f1341417b5233ce719e562f37f898f703b1b97e9ca7ff12c581cdb69822", "corpus_entry_id": "jvs_jvs004_falset10_BASIC5000_2951"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 3.1964282989501953, "predicted_mos": 3.1964282989501953, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 108438, "input_sample_rate": 24000, "input_seconds": 4.51825, "input_float32_sha256": "84f43b9942c00905fb27154315308069f5cf2a633d5da28c545d07f9d98f65fe", "internal_samples": 72292, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 43.36582119995728}, "waveform_sha256": "d057493783316e914981a3b3ab5d87910159e19ac7543c9b841d5883219a7a3d"}, "rows": [{"case": "jvs_jvs004_falset10_BASIC5000_2951", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 2.4720141887664795, "predicted_mos": 2.4720141887664795, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 108438, "input_sample_rate": 24000, "input_seconds": 4.51825, "input_float32_sha256": "75c43fca96f74ee5bb4a68d62b24cf10dca833503cbc43570a4163192e412ffb", "internal_samples": 72292, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.757358599919826}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9943614856698549, "全帯域_10ms_rms_envelope_nrmse": 0.08413795354842858, "全帯域_10ms_envelope_correlation": 0.9934640643529913, "全帯域_10ms_modulation_mae_db": 0.3418247526567917, "全帯域_40ms_log_rms_mae_db": 0.7176830550678871, "全帯域_40ms_rms_envelope_nrmse": 0.05213921785713583, "全帯域_40ms_envelope_correlation": 0.9972528134328876, "全帯域_40ms_modulation_mae_db": 0.29984734454171114, "300–1000 Hz_10ms_log_rms_mae_db": 0.7174736221729178, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.093100019178883, "300–1000 Hz_10ms_envelope_correlation": 0.9925578608936337, "300–1000 Hz_10ms_modulation_mae_db": 0.27826457505676255, "300–1000 Hz_40ms_log_rms_mae_db": 0.5255454632511394, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05878301130637623, "300–1000 Hz_40ms_envelope_correlation": 0.9967674393209743, "300–1000 Hz_40ms_modulation_mae_db": 0.32048229030323266, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1175148057526152, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09337196276692789, "1000–3000 Hz_10ms_envelope_correlation": 0.9940942929305877, "1000–3000 Hz_10ms_modulation_mae_db": 0.4839524172439207, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7309073544641397, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06307455182749092, "1000–3000 Hz_40ms_envelope_correlation": 0.9973859110029364, "1000–3000 Hz_40ms_modulation_mae_db": 0.6780075085912703, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3188478970985613, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15788212080159172, "3000–6000 Hz_10ms_envelope_correlation": 0.9819085335960329, "3000–6000 Hz_10ms_modulation_mae_db": 1.21098675245621, "3000–6000 Hz_40ms_log_rms_mae_db": 0.889143154583139, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09707909263027752, "3000–6000 Hz_40ms_envelope_correlation": 0.9939041746471045, "3000–6000 Hz_40ms_modulation_mae_db": 0.7722544162984019, "mr_stft_db": 5.589305483408431, "band_mae_db": 1.5987761732972943, "rms_gain_error_db": -0.0244180678948213, "output_peak": 0.3654046932475506}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.971141274979294, "全帯域_10ms_rms_envelope_nrmse": 0.07360551681326405, "全帯域_10ms_envelope_correlation": 0.995085158556724, "全帯域_10ms_modulation_mae_db": 0.3564320752199073, "全帯域_40ms_log_rms_mae_db": 0.619848603124111, "全帯域_40ms_rms_envelope_nrmse": 0.042253711763698895, "全帯域_40ms_envelope_correlation": 0.9982559470437015, "全帯域_40ms_modulation_mae_db": 0.09854037238050888, "300–1000 Hz_10ms_log_rms_mae_db": 0.7139408467492959, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07982712534954123, "300–1000 Hz_10ms_envelope_correlation": 0.9946130733239085, "300–1000 Hz_10ms_modulation_mae_db": 0.3893119593474131, "300–1000 Hz_40ms_log_rms_mae_db": 0.49647766540200955, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04658871808374126, "300–1000 Hz_40ms_envelope_correlation": 0.9980332253668679, "300–1000 Hz_40ms_modulation_mae_db": 0.34053185008312975, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1041119013400773, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09429734573618227, "1000–3000 Hz_10ms_envelope_correlation": 0.9937439266872972, "1000–3000 Hz_10ms_modulation_mae_db": 0.14731447842074977, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6936735106542048, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05542316939026574, "1000–3000 Hz_40ms_envelope_correlation": 0.9977191306444089, "1000–3000 Hz_40ms_modulation_mae_db": 0.7943070593177204, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2812472249981839, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1163895442552473, "3000–6000 Hz_10ms_envelope_correlation": 0.9903662905169373, "3000–6000 Hz_10ms_modulation_mae_db": 0.9428113271450238, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7946551329429037, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06976336052706231, "3000–6000 Hz_40ms_envelope_correlation": 0.9969715763575715, "3000–6000 Hz_40ms_modulation_mae_db": 1.1122275402471664, "mr_stft_db": 5.594092706908978, "band_mae_db": 1.7813540149183946, "rms_gain_error_db": 0.06146856453529223, "output_peak": 0.3667089645921234}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9416610993820923, "全帯域_10ms_rms_envelope_nrmse": 0.0793517911395691, "全帯域_10ms_envelope_correlation": 0.9943131746473498, "全帯域_10ms_modulation_mae_db": 0.6705912276217352, "全帯域_40ms_log_rms_mae_db": 0.6621059595761546, "全帯域_40ms_rms_envelope_nrmse": 0.0447252636078777, "全帯域_40ms_envelope_correlation": 0.9981596390154377, "全帯域_40ms_modulation_mae_db": 0.6801005646945392, "300–1000 Hz_10ms_log_rms_mae_db": 0.693888746169091, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09101658148457577, "300–1000 Hz_10ms_envelope_correlation": 0.9929548060682774, "300–1000 Hz_10ms_modulation_mae_db": 0.6575738373255694, "300–1000 Hz_40ms_log_rms_mae_db": 0.4881669011082838, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.051137818370692166, "300–1000 Hz_40ms_envelope_correlation": 0.997706485397096, "300–1000 Hz_40ms_modulation_mae_db": 0.8215369670201422, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0773311236901226, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08892755303527622, "1000–3000 Hz_10ms_envelope_correlation": 0.9946639318099084, "1000–3000 Hz_10ms_modulation_mae_db": 0.7572073642835008, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7010105178291504, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06374911431684938, "1000–3000 Hz_40ms_envelope_correlation": 0.9972817374707843, "1000–3000 Hz_40ms_modulation_mae_db": 0.5184999860264016, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2751916429287702, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1447492099593825, "3000–6000 Hz_10ms_envelope_correlation": 0.9840823783877246, "3000–6000 Hz_10ms_modulation_mae_db": 1.0471268586119402, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8074926511498409, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0848855169053514, "3000–6000 Hz_40ms_envelope_correlation": 0.9944286366927951, "3000–6000 Hz_40ms_modulation_mae_db": 0.8397782922218741, "mr_stft_db": 5.608019130165373, "band_mae_db": 1.7447996693622472, "rms_gain_error_db": -0.1251201230068453, "output_peak": 0.3527754672305711}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9692448582622099, "全帯域_10ms_rms_envelope_nrmse": 0.06737317814847592, "全帯域_10ms_envelope_correlation": 0.9958699307154668, "全帯域_10ms_modulation_mae_db": 0.4146123401856485, "全帯域_40ms_log_rms_mae_db": 0.699440549979024, "全帯域_40ms_rms_envelope_nrmse": 0.03717488060190594, "全帯域_40ms_envelope_correlation": 0.9986932470742701, "全帯域_40ms_modulation_mae_db": 0.43412633875293977, "300–1000 Hz_10ms_log_rms_mae_db": 0.7068607413590946, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07503877879584236, "300–1000 Hz_10ms_envelope_correlation": 0.9951682471559211, "300–1000 Hz_10ms_modulation_mae_db": 0.350741381571867, "300–1000 Hz_40ms_log_rms_mae_db": 0.49313935224293864, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04158833924927726, "300–1000 Hz_40ms_envelope_correlation": 0.998411665518836, "300–1000 Hz_40ms_modulation_mae_db": 0.34370523206754516, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1044353413988457, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09645525750171402, "1000–3000 Hz_10ms_envelope_correlation": 0.9936274679300726, "1000–3000 Hz_10ms_modulation_mae_db": 0.46930053211201567, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7147019654437514, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05994300312038499, "1000–3000 Hz_40ms_envelope_correlation": 0.9976426070121662, "1000–3000 Hz_40ms_modulation_mae_db": 1.2038928722897648, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3163850895315248, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14625816660334384, "3000–6000 Hz_10ms_envelope_correlation": 0.9850678310574948, "3000–6000 Hz_10ms_modulation_mae_db": 1.1213264767552729, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8596717055698543, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09445850254037619, "3000–6000 Hz_40ms_envelope_correlation": 0.9947010293858239, "3000–6000 Hz_40ms_modulation_mae_db": 0.9281630649526634, "mr_stft_db": 5.59119230144375, "band_mae_db": 1.6948959043375162, "rms_gain_error_db": -0.08928271317351467, "output_peak": 0.4022433256117107}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0092555388688307, "全帯域_10ms_rms_envelope_nrmse": 0.08301655584355647, "全帯域_10ms_envelope_correlation": 0.9937092389025277, "全帯域_10ms_modulation_mae_db": 0.7780535958850049, "全帯域_40ms_log_rms_mae_db": 0.6670113889557189, "全帯域_40ms_rms_envelope_nrmse": 0.04661897289082708, "全帯域_40ms_envelope_correlation": 0.997929383963972, "全帯域_40ms_modulation_mae_db": 0.9748772726517019, "300–1000 Hz_10ms_log_rms_mae_db": 0.7703224817697228, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09285676930231636, "300–1000 Hz_10ms_envelope_correlation": 0.9926839062310208, "300–1000 Hz_10ms_modulation_mae_db": 0.7331194985263423, "300–1000 Hz_40ms_log_rms_mae_db": 0.5378486978320233, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05412304564438034, "300–1000 Hz_40ms_envelope_correlation": 0.9974461314070547, "300–1000 Hz_40ms_modulation_mae_db": 1.0236018856998028, "1000–3000 Hz_10ms_log_rms_mae_db": 1.077251669194038, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08622210865752344, "1000–3000 Hz_10ms_envelope_correlation": 0.9946987533007579, "1000–3000 Hz_10ms_modulation_mae_db": 0.8639964002977013, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6956063650558971, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05049823858541653, "1000–3000 Hz_40ms_envelope_correlation": 0.9980668065453739, "1000–3000 Hz_40ms_modulation_mae_db": 0.29514396859411546, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2928447101534049, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1402337057995951, "3000–6000 Hz_10ms_envelope_correlation": 0.9852299735711576, "3000–6000 Hz_10ms_modulation_mae_db": 1.1438733548197686, "3000–6000 Hz_40ms_log_rms_mae_db": 0.770257040615772, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08019608431992113, "3000–6000 Hz_40ms_envelope_correlation": 0.9952958733741408, "3000–6000 Hz_40ms_modulation_mae_db": 1.2706194906589285, "mr_stft_db": 5.596525438778536, "band_mae_db": 1.6782714550857876, "rms_gain_error_db": -0.1079551730116105, "output_peak": 0.35223342230561316}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9164345358803139, "全帯域_10ms_rms_envelope_nrmse": 0.07223477857595441, "全帯域_10ms_envelope_correlation": 0.9952094434746734, "全帯域_10ms_modulation_mae_db": 0.541772041297317, "全帯域_40ms_log_rms_mae_db": 0.6367658759935194, "全帯域_40ms_rms_envelope_nrmse": 0.036846227945087205, "全帯域_40ms_envelope_correlation": 0.9986796429545522, "全帯域_40ms_modulation_mae_db": 1.0480646288616755, "300–1000 Hz_10ms_log_rms_mae_db": 0.7063299003353917, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08038716217951623, "300–1000 Hz_10ms_envelope_correlation": 0.9944635278475157, "300–1000 Hz_10ms_modulation_mae_db": 0.5863674465262981, "300–1000 Hz_40ms_log_rms_mae_db": 0.4938103853894265, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04363386211201386, "300–1000 Hz_40ms_envelope_correlation": 0.9982753834532662, "300–1000 Hz_40ms_modulation_mae_db": 1.1898543430022805, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1004374314659384, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10066801714474388, "1000–3000 Hz_10ms_envelope_correlation": 0.992755357920447, "1000–3000 Hz_10ms_modulation_mae_db": 0.25338387640695875, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7196149487822797, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.057564103428257206, "1000–3000 Hz_40ms_envelope_correlation": 0.9974981147959046, "1000–3000 Hz_40ms_modulation_mae_db": 0.2870103924300869, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3085669986571895, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1430125271582951, "3000–6000 Hz_10ms_envelope_correlation": 0.9847864540966845, "3000–6000 Hz_10ms_modulation_mae_db": 1.042618612009499, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8262593123886888, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0806251371335578, "3000–6000 Hz_40ms_envelope_correlation": 0.9954915581372976, "3000–6000 Hz_40ms_modulation_mae_db": 0.42333750006182136, "mr_stft_db": 5.602055462076906, "band_mae_db": 1.7457966522142419, "rms_gain_error_db": -0.06795312045195859, "output_peak": 0.3736764146460904}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9673659749827154, "全帯域_10ms_rms_envelope_nrmse": 0.07120112025103259, "全帯域_10ms_envelope_correlation": 0.9954675377261969, "全帯域_10ms_modulation_mae_db": 0.4815811456291012, "全帯域_40ms_log_rms_mae_db": 0.6657141599345872, "全帯域_40ms_rms_envelope_nrmse": 0.03837639831146089, "全帯域_40ms_envelope_correlation": 0.9987211035116421, "全帯域_40ms_modulation_mae_db": 0.4212142719035857, "300–1000 Hz_10ms_log_rms_mae_db": 0.6877747464039027, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.080613550675673, "300–1000 Hz_10ms_envelope_correlation": 0.9945367788385985, "300–1000 Hz_10ms_modulation_mae_db": 0.5368392158992736, "300–1000 Hz_40ms_log_rms_mae_db": 0.4798966223193371, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043198138027922925, "300–1000 Hz_40ms_envelope_correlation": 0.9984547457311788, "300–1000 Hz_40ms_modulation_mae_db": 0.6144616526972978, "1000–3000 Hz_10ms_log_rms_mae_db": 1.125195568574003, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09133045339034845, "1000–3000 Hz_10ms_envelope_correlation": 0.9941056355895762, "1000–3000 Hz_10ms_modulation_mae_db": 0.5026761994113057, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6757632355678688, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.048678819691071254, "1000–3000 Hz_40ms_envelope_correlation": 0.9983031657148276, "1000–3000 Hz_40ms_modulation_mae_db": 0.6876242796412381, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3084531287131314, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14953157704541228, "3000–6000 Hz_10ms_envelope_correlation": 0.9829918201803785, "3000–6000 Hz_10ms_modulation_mae_db": 0.748203929518251, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8300028102821349, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09092805092130463, "3000–6000 Hz_40ms_envelope_correlation": 0.9935530117284797, "3000–6000 Hz_40ms_modulation_mae_db": 0.5290051126023043, "mr_stft_db": 5.605235987655507, "band_mae_db": 1.6474019362797818, "rms_gain_error_db": -0.13126584276164852, "output_peak": 0.3483062993056976}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9833160969635086, "全帯域_10ms_rms_envelope_nrmse": 0.07512048988070776, "全帯域_10ms_envelope_correlation": 0.9947983051247945, "全帯域_10ms_modulation_mae_db": 0.19325306948667242, "全帯域_40ms_log_rms_mae_db": 0.6359129336632675, "全帯域_40ms_rms_envelope_nrmse": 0.04152028362516826, "全帯域_40ms_envelope_correlation": 0.9982551407739833, "全帯域_40ms_modulation_mae_db": 0.24536304596572026, "300–1000 Hz_10ms_log_rms_mae_db": 0.7584322804189025, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08455652147620475, "300–1000 Hz_10ms_envelope_correlation": 0.9938511180602473, "300–1000 Hz_10ms_modulation_mae_db": 0.10937475151810398, "300–1000 Hz_40ms_log_rms_mae_db": 0.5455074484734854, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04825916209353081, "300–1000 Hz_40ms_envelope_correlation": 0.9978149114032885, "300–1000 Hz_40ms_modulation_mae_db": 0.1103532024400865, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1048064593940201, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07954639719858284, "1000–3000 Hz_10ms_envelope_correlation": 0.9954868206601584, "1000–3000 Hz_10ms_modulation_mae_db": 0.38480326581061286, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6766468325615976, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04174999217920509, "1000–3000 Hz_40ms_envelope_correlation": 0.9986762881307804, "1000–3000 Hz_40ms_modulation_mae_db": 0.1399895874073638, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2928527511841434, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14416815827560386, "3000–6000 Hz_10ms_envelope_correlation": 0.9842272478701617, "3000–6000 Hz_10ms_modulation_mae_db": 1.1170714305775666, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8217727391284776, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.083886168754237, "3000–6000 Hz_40ms_envelope_correlation": 0.9946075188714082, "3000–6000 Hz_40ms_modulation_mae_db": 0.6244968241819708, "mr_stft_db": 5.593220738127438, "band_mae_db": 1.7100174889481357, "rms_gain_error_db": 0.0036585341170696384, "output_peak": 0.35314916684853165}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 108438, "output_samples": 108438, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.424766334155549, "spectral_convergence": 0.19391441619278332, "spectral_convergence_status": "ok", "amplitude_floor": 1.3518293902907786e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.766853335469251, "spectral_convergence": 0.21256714442458294, "spectral_convergence_status": "ok", "amplitude_floor": 1.2606433835114825e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.576296780600494, "spectral_convergence": 0.21707474561541984, "spectral_convergence_status": "ok", "amplitude_floor": 9.263870496871738e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.1242940814223918e-07, "output_power": 1.1908140488952848e-06, "delta_db": 10.249640252607747, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0005754412253654517, "output_power": 0.0005590623998243826, "delta_db": -0.12540687667761852, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0015091092814657461, "output_power": 0.0015333470942817385, "delta_db": 0.06919784381235158, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00043576714857085195, "output_power": 0.000420606954486651, "delta_db": -0.1537803752443671, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 9.403622080703858e-05, "output_power": 8.696731714632295e-05, "delta_db": -0.3393909433902944, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.140246786176929e-05, "output_power": 2.974135790876013e-05, "delta_db": -0.23602986480626628, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2121205040710494e-05, "output_power": 1.2171511210184873e-05, "delta_db": 0.017987056542414448, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.5987761732972943, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.0244180678948213, "pitch": null, "output_rms_dbfs": -25.77888467610081, "output_peak": 0.3654046932475506, "reference_rms_dbfs": -25.754466608205988, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.589305483408431}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 108438, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.0001921686173284563, "log_rms_mae_db": 0.9943614856698549, "rms_envelope_nrmse": 0.08413795354842858, "envelope_correlation": 0.9934640643529913, "rms_gain_error_db": -0.024418052707164132, "reference_mean_power": 0.002662852134818696, "output_mean_power": 0.0026479223538559216}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.762380071709748e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00040104774940998337, "output_power": 0.0004286334087287365, "reference_active": true, "delta_db": 0.28889934471865975}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0004799671480036487, "output_power": 0.00046654894494076724, "reference_active": true, "delta_db": -0.12314300876870242}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.699212681223788e-05, "output_power": 4.080204314182117e-05, "reference_active": true, "delta_db": -0.6134319044830129}], "active_band_count": 3, "active_band_mae_db": 0.3418247526567917}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.0001703510251571522, "log_rms_mae_db": 0.7176830550678871, "rms_envelope_nrmse": 0.05213921785713583, "envelope_correlation": 0.9972528134328876, "rms_gain_error_db": -0.02441802952361931, "reference_mean_power": 0.002680683564334513, "output_mean_power": 0.0026656538223406513}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.5184553835408784e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00038984224450005464, "output_power": 0.00041928239731008434, "reference_active": true, "delta_db": 0.3161773103322155}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00026155775461828376, "output_power": 0.00023855850332896197, "reference_active": true, "delta_db": -0.3997269900487743}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.971121679142551e-06, "output_power": 5.1858286999359295e-06, "reference_active": true, "delta_db": 0.1836377332441436}], "active_band_count": 3, "active_band_mae_db": 0.29984734454171114}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.00018970614972877868, "log_rms_mae_db": 0.7174736221729178, "rms_envelope_nrmse": 0.093100019178883, "envelope_correlation": 0.9925578608936337, "rms_gain_error_db": 0.005953683279076966, "reference_mean_power": 0.002063788383698964, "output_mean_power": 0.0020666195429448315}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.5811898835528837e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0004324343375320338, "output_power": 0.0004713041130187852, "reference_active": true, "delta_db": 0.37381057928352446}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00038978360738039315, "output_power": 0.00038058917437020905, "reference_active": true, "delta_db": -0.10367139728611084}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.8057706966220433e-05, "output_power": 3.5051890231520906e-05, "reference_active": true, "delta_db": -0.3573117486006523}], "active_band_count": 3, "active_band_mae_db": 0.27826457505676255}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.00016763715453010979, "log_rms_mae_db": 0.5255454632511394, "rms_envelope_nrmse": 0.05878301130637623, "envelope_correlation": 0.9967674393209743, "rms_gain_error_db": 0.005953670899008679, "reference_mean_power": 0.0020776083853168846, "output_mean_power": 0.0020804584972742737}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.3894681028634614e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00045948597327573326, "output_power": 0.0004988340371432371, "reference_active": true, "delta_db": 0.35683820986729703}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019541576327049997, "output_power": 0.00018048793649026002, "reference_active": true, "delta_db": -0.3451141358909384}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.955911260526715e-06, "output_power": 4.668464588017868e-06, "reference_active": true, "delta_db": -0.2594945251514625}], "active_band_count": 3, "active_band_mae_db": 0.32048229030323266}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 7.813214815208366e-05, "log_rms_mae_db": 1.1175148057526152, "rms_envelope_nrmse": 0.09337196276692789, "envelope_correlation": 0.9940942929305877, "rms_gain_error_db": -0.21347858570034006, "reference_mean_power": 0.0003994594973118105, "output_mean_power": 0.0003802987453056517}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 3.1530674989036126e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00010755692941582863, "output_power": 9.988347573985851e-05, "reference_active": true, "delta_db": -0.3214474879325253}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.79686087945957e-05, "output_power": 7.870015307201116e-05, "reference_active": true, "delta_db": -0.483521466836038}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.8229526666890895e-06, "output_power": 4.155508452316868e-06, "reference_active": true, "delta_db": -0.6468882969631988}], "active_band_count": 3, "active_band_mae_db": 0.4839524172439207}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 7.396069876288682e-05, "log_rms_mae_db": 0.7309073544641397, "rms_envelope_nrmse": 0.06307455182749092, "envelope_correlation": 0.9973859110029364, "rms_gain_error_db": -0.21347860638058755, "reference_mean_power": 0.00040213443933265886, "output_mean_power": 0.00038284537737451346}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 2.8654358479348363e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000106294645864879, "output_power": 9.790689346252199e-05, "reference_active": true, "delta_db": -0.3569811852339447}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.178329128126849e-05, "output_power": 4.456378843723146e-05, "reference_active": true, "delta_db": -0.6520754640349902}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.031671442188497e-07, "output_power": 5.104835126918848e-07, "reference_active": true, "delta_db": 1.0249658765048761}], "active_band_count": 3, "active_band_mae_db": 0.6780075085912703}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 2.8330015424642833e-05, "log_rms_mae_db": 1.3188478970985613, "rms_envelope_nrmse": 0.15788212080159172, "envelope_correlation": 0.9819085335960329, "rms_gain_error_db": -0.4459027127491677, "reference_mean_power": 5.860864109462446e-05, "output_mean_power": 5.2889733734243985e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 4.4003495001587196e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.626242950468029e-05, "output_power": 1.4130640738465647e-05, "reference_active": true, "delta_db": -0.610235720650629}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.532829538176888e-06, "output_power": 7.969097465176605e-06, "reference_active": true, "delta_db": -0.7781268878160017}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7599215302222477e-06, "output_power": 1.0496234852037127e-06, "reference_active": true, "delta_db": -2.244597648901999}], "active_band_count": 3, "active_band_mae_db": 1.21098675245621}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 2.5104708341377363e-05, "log_rms_mae_db": 0.889143154583139, "rms_envelope_nrmse": 0.09707909263027752, "envelope_correlation": 0.9939041746471045, "rms_gain_error_db": -0.44590274159641646, "reference_mean_power": 5.900110522587256e-05, "output_mean_power": 5.324390169116208e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 3.7677668262047306e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.375501004524296e-05, "output_power": 1.1767061936542632e-05, "reference_active": true, "delta_db": -0.677928724984461}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.792095126848191e-06, "output_power": 4.89405956311751e-06, "reference_active": true, "delta_db": -0.7316643528524613}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0124260162334744e-07, "output_power": 8.215732294555291e-08, "reference_active": true, "delta_db": -0.9071701710582833}], "active_band_count": 3, "active_band_mae_db": 0.7722544162984019}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.7852838707160454, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "56266b774a0f0ff0f6273570fa4268bf32d8fabad98b35356f4edcd3011f9165", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9941470233536006, "standard_deviation": 0.0008229136382661535, "minimum": 0.992755357920447, "maximum": 0.9954868206601584, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1013855376012076, "standard_deviation": 0.016976728914785726, "minimum": 1.077251669194038, "maximum": 1.125195568574003, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.48282931674834567, "standard_deviation": 0.23783979306743275, "minimum": 0.14731447842074977, "maximum": 0.8639964002977013, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09135238692891237, "standard_deviation": 0.006515401231908275, "minimum": 0.07954639719858284, "maximum": 0.10066801714474388, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978217201646478, "standard_deviation": 0.0004856484709545072, "minimum": 0.9972817374707843, "maximum": 0.9986762881307804, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7009905912948612, "standard_deviation": 0.01978978530164801, "minimum": 0.6757632355678688, "maximum": 0.7309073544641397, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5755594567872452, "standard_deviation": 0.34238195575049285, "minimum": 0.1399895874073638, "maximum": 1.2038928722897648, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05508512406736764, "standard_deviation": 0.007640683232764269, "minimum": 0.04174999217920509, "maximum": 0.06374911431684938, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9848325661595715, "standard_deviation": 0.0024987144673582276, "minimum": 0.9819085335960329, "maximum": 0.9903662905169373, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2992986804081137, "standard_deviation": 0.01618655054991339, "minimum": 1.2751916429287702, "maximum": 1.3188478970985613, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.0467523427366916, "standard_deviation": 0.14484653240718293, "minimum": 0.748203929518251, "maximum": 1.21098675245621, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14277812623730896, "standard_deviation": 0.01191969599834721, "minimum": 0.1163895442552473, "maximum": 0.15788212080159172, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9948691723993277, "standard_deviation": 0.0010652864172908162, "minimum": 0.9935530117284797, "maximum": 0.9969715763575715, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8249068183326014, "standard_deviation": 0.03698945988516856, "minimum": 0.770257040615772, "maximum": 0.889143154583139, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.8124852801531414, "standard_deviation": 0.28849704575251967, "minimum": 0.42333750006182136, "maximum": 1.2706194906589285, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.085227739216511, "standard_deviation": 0.008829500514990929, "minimum": 0.06976336052706231, "maximum": 0.09707909263027752, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9938536648023903, "standard_deviation": 0.0009999144379160812, "minimum": 0.9925578608936337, "maximum": 0.9951682471559211, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.7193779206722899, "standard_deviation": 0.029590463472472482, "minimum": 0.6877747464039027, "maximum": 0.7703224817697228, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4551990832214538, "standard_deviation": 0.20983611368382696, "minimum": 0.10937475151810398, "maximum": 0.7331194985263423, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08467456355531908, "standard_deviation": 0.006859733022230749, "minimum": 0.07503877879584236, "maximum": 0.093100019178883, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9978637484498203, "standard_deviation": 0.000567081642878822, "minimum": 0.9967674393209743, "maximum": 0.9984547457311788, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5075490670023304, "standard_deviation": 0.02490573619316085, "minimum": 0.4798966223193371, "maximum": 0.5455074484734854, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5955659279141896, "standard_deviation": 0.38310611137420325, "minimum": 0.1103532024400865, "maximum": 1.1898543430022805, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.048414011860991854, "standard_deviation": 0.005946535510359303, "minimum": 0.04158833924927726, "maximum": 0.05878301130637623, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.700164161805425, "standard_deviation": 0.0589599801565879, "minimum": 1.5987761732972943, "maximum": 1.7813540149183946, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.597455906070615, "standard_deviation": 0.006856102038976068, "minimum": 5.589305483408431, "maximum": 5.608019130165373, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.36431221922348606, "standard_deviation": 0.017700654014845073, "minimum": 0.3483062993056976, "maximum": 0.4022433256117107, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06010849270600463, "standard_deviation": 0.06825674185691627, "minimum": -0.13126584276164852, "maximum": 0.06146856453529223, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9947396066875905, "standard_deviation": 0.0008469798881946211, "minimum": 0.9934640643529913, "maximum": 0.9958699307154668, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9690976081236025, "standard_deviation": 0.029243915937411935, "minimum": 0.9164345358803139, "maximum": 1.0092555388688307, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4722650309977723, "standard_deviation": 0.18874070968159476, "minimum": 0.19325306948667242, "maximum": 0.7780535958850049, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.0757551730251236, "standard_deviation": 0.005908209880943854, "minimum": 0.06737317814847592, "maximum": 0.08413795354842858, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9982433647213058, "standard_deviation": 0.0004939707821239137, "minimum": 0.9972528134328876, "maximum": 0.9987211035116421, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6630603157867837, "standard_deviation": 0.033007271453468545, "minimum": 0.619848603124111, "maximum": 0.7176830550678871, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5252667299690478, "standard_deviation": 0.34430668231349504, "minimum": 0.09854037238050888, "maximum": 1.0480646288616755, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.042456869575395226, "standard_deviation": 0.0052530807673494065, "minimum": 0.036846227945087205, "maximum": 0.05213921785713583, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_falset10_BASIC5000_2951", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 2.0514683723449707, "predicted_mos": 2.0514683723449707, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 108438, "input_sample_rate": 24000, "input_seconds": 4.51825, "input_float32_sha256": "7d49553bc474af97ac20cde82b9f0a8ef19b315fb7ae8845606aecf7ac07e37c", "internal_samples": 72292, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.009626499842852}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.005774245575992, "全帯域_10ms_rms_envelope_nrmse": 0.08719352427594802, "全帯域_10ms_envelope_correlation": 0.9929823640529148, "全帯域_10ms_modulation_mae_db": 0.29391161752772477, "全帯域_40ms_log_rms_mae_db": 0.7394833983941614, "全帯域_40ms_rms_envelope_nrmse": 0.05559243188000751, "全帯域_40ms_envelope_correlation": 0.9968823482680791, "全帯域_40ms_modulation_mae_db": 0.4097790400320767, "300–1000 Hz_10ms_log_rms_mae_db": 0.7087546853219528, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09670583597189007, "300–1000 Hz_10ms_envelope_correlation": 0.99197112745247, "300–1000 Hz_10ms_modulation_mae_db": 0.2213100370851188, "300–1000 Hz_40ms_log_rms_mae_db": 0.5053136345859803, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.06252992541254637, "300–1000 Hz_40ms_envelope_correlation": 0.9963437551114612, "300–1000 Hz_40ms_modulation_mae_db": 0.28184895368223445, "1000–3000 Hz_10ms_log_rms_mae_db": 1.108543395667495, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09326923832976483, "1000–3000 Hz_10ms_envelope_correlation": 0.9941737109362784, "1000–3000 Hz_10ms_modulation_mae_db": 0.5974017524943546, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7128102900286282, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06455862908897636, "1000–3000 Hz_40ms_envelope_correlation": 0.9973107070395231, "1000–3000 Hz_40ms_modulation_mae_db": 0.5494442256837102, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2532937936857937, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15562472603748795, "3000–6000 Hz_10ms_envelope_correlation": 0.9831839823822913, "3000–6000 Hz_10ms_modulation_mae_db": 1.2752409807983611, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8176116654030442, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10341213019148508, "3000–6000 Hz_40ms_envelope_correlation": 0.9936662318538737, "3000–6000 Hz_40ms_modulation_mae_db": 0.9391814154797968, "mr_stft_db": 5.5036488199737255, "band_mae_db": 1.611466771351296, "rms_gain_error_db": -0.03382672621285078, "output_peak": 0.3645161408936929}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9727457431956228, "全帯域_10ms_rms_envelope_nrmse": 0.0746870816257763, "全帯域_10ms_envelope_correlation": 0.9949631065685172, "全帯域_10ms_modulation_mae_db": 0.2861724957409704, "全帯域_40ms_log_rms_mae_db": 0.6202499493044152, "全帯域_40ms_rms_envelope_nrmse": 0.042962283523851445, "全帯域_40ms_envelope_correlation": 0.9982182479670072, "全帯域_40ms_modulation_mae_db": 0.07385469648182527, "300–1000 Hz_10ms_log_rms_mae_db": 0.707639723291651, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08157109012643494, "300–1000 Hz_10ms_envelope_correlation": 0.9944162966135197, "300–1000 Hz_10ms_modulation_mae_db": 0.3023621783113676, "300–1000 Hz_40ms_log_rms_mae_db": 0.49771077371106565, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04773777961425729, "300–1000 Hz_40ms_envelope_correlation": 0.9979717735268551, "300–1000 Hz_40ms_modulation_mae_db": 0.27757330492563165, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1046812790096168, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09092436714673355, "1000–3000 Hz_10ms_envelope_correlation": 0.9941710097288321, "1000–3000 Hz_10ms_modulation_mae_db": 0.2342215929519668, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6759270958625908, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.053218279554388154, "1000–3000 Hz_40ms_envelope_correlation": 0.9978872163115133, "1000–3000 Hz_40ms_modulation_mae_db": 0.5852800841106379, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2486728466901886, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11714013414732419, "3000–6000 Hz_10ms_envelope_correlation": 0.9903949940119788, "3000–6000 Hz_10ms_modulation_mae_db": 0.8406913529515109, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7625849633993254, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0721901516788838, "3000–6000 Hz_40ms_envelope_correlation": 0.9969090592107652, "3000–6000 Hz_40ms_modulation_mae_db": 1.086525138173508, "mr_stft_db": 5.508244952764137, "band_mae_db": 1.7819207730548492, "rms_gain_error_db": 0.07276016426615216, "output_peak": 0.3621608759296587}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9406869008705745, "全帯域_10ms_rms_envelope_nrmse": 0.07858994139991282, "全帯域_10ms_envelope_correlation": 0.9944081776097723, "全帯域_10ms_modulation_mae_db": 0.7159619045781266, "全帯域_40ms_log_rms_mae_db": 0.6499412629210036, "全帯域_40ms_rms_envelope_nrmse": 0.04373844781671524, "全帯域_40ms_envelope_correlation": 0.998225985299311, "全帯域_40ms_modulation_mae_db": 0.7516830745052129, "300–1000 Hz_10ms_log_rms_mae_db": 0.697568634452, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0909505147053216, "300–1000 Hz_10ms_envelope_correlation": 0.9929324355501986, "300–1000 Hz_10ms_modulation_mae_db": 0.7087246155211654, "300–1000 Hz_40ms_log_rms_mae_db": 0.4867675402446018, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.050376431709678635, "300–1000 Hz_40ms_envelope_correlation": 0.9977329065297904, "300–1000 Hz_40ms_modulation_mae_db": 0.8820247087324505, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1025284980448542, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08850062737537344, "1000–3000 Hz_10ms_envelope_correlation": 0.9947816042072312, "1000–3000 Hz_10ms_modulation_mae_db": 0.8641600264352448, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7089754675362135, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06344225810174367, "1000–3000 Hz_40ms_envelope_correlation": 0.9973817288889862, "1000–3000 Hz_40ms_modulation_mae_db": 0.7120470297608185, "3000–6000 Hz_10ms_log_rms_mae_db": 1.220468190307246, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13937892394077384, "3000–6000 Hz_10ms_envelope_correlation": 0.9856021232266357, "3000–6000 Hz_10ms_modulation_mae_db": 1.0003732567947912, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7666816916703197, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08483208874480237, "3000–6000 Hz_40ms_envelope_correlation": 0.9948833662894334, "3000–6000 Hz_40ms_modulation_mae_db": 0.9460572067058227, "mr_stft_db": 5.521031391252802, "band_mae_db": 1.7067790575228534, "rms_gain_error_db": -0.11733437483914355, "output_peak": 0.3563323379301592}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9689990087683744, "全帯域_10ms_rms_envelope_nrmse": 0.06961185592118718, "全帯域_10ms_envelope_correlation": 0.9955748194102574, "全帯域_10ms_modulation_mae_db": 0.42217843916627623, "全帯域_40ms_log_rms_mae_db": 0.7181833603780132, "全帯域_40ms_rms_envelope_nrmse": 0.037987544274836416, "全帯域_40ms_envelope_correlation": 0.9986184546686204, "全帯域_40ms_modulation_mae_db": 0.5089336129954725, "300–1000 Hz_10ms_log_rms_mae_db": 0.7079881331727937, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07765883168582517, "300–1000 Hz_10ms_envelope_correlation": 0.9948147732019752, "300–1000 Hz_10ms_modulation_mae_db": 0.3695815623870143, "300–1000 Hz_40ms_log_rms_mae_db": 0.5049170797420214, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0425644400176296, "300–1000 Hz_40ms_envelope_correlation": 0.9983213546673552, "300–1000 Hz_40ms_modulation_mae_db": 0.4209742492196238, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1157653046384814, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09676938568844924, "1000–3000 Hz_10ms_envelope_correlation": 0.9935864137266422, "1000–3000 Hz_10ms_modulation_mae_db": 0.4829211188150954, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6936633245444058, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0593575783091729, "1000–3000 Hz_40ms_envelope_correlation": 0.9976996015180496, "1000–3000 Hz_40ms_modulation_mae_db": 1.186559324618747, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2653850899401116, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1439704281703722, "3000–6000 Hz_10ms_envelope_correlation": 0.9861681848384803, "3000–6000 Hz_10ms_modulation_mae_db": 1.0867669896072243, "3000–6000 Hz_40ms_log_rms_mae_db": 0.803123495933748, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09629019144471526, "3000–6000 Hz_40ms_envelope_correlation": 0.9950897468352525, "3000–6000 Hz_40ms_modulation_mae_db": 1.0335544357410098, "mr_stft_db": 5.5078124323977855, "band_mae_db": 1.6801947541338151, "rms_gain_error_db": -0.08357468854964617, "output_peak": 0.4073545615461529}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0141374328855017, "全帯域_10ms_rms_envelope_nrmse": 0.08188417496193216, "全帯域_10ms_envelope_correlation": 0.9938841898759613, "全帯域_10ms_modulation_mae_db": 0.7245965506228086, "全帯域_40ms_log_rms_mae_db": 0.6865460696426263, "全帯域_40ms_rms_envelope_nrmse": 0.046035663553678115, "全帯域_40ms_envelope_correlation": 0.9979836467140786, "全帯域_40ms_modulation_mae_db": 0.9757574279842306, "300–1000 Hz_10ms_log_rms_mae_db": 0.7444515676997764, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09111695822303584, "300–1000 Hz_10ms_envelope_correlation": 0.9929591046737685, "300–1000 Hz_10ms_modulation_mae_db": 0.7031771280250982, "300–1000 Hz_40ms_log_rms_mae_db": 0.5146494758606234, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05321712552789612, "300–1000 Hz_40ms_envelope_correlation": 0.9975309535091366, "300–1000 Hz_40ms_modulation_mae_db": 1.0637600338773163, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0845480572106465, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0894962730021725, "1000–3000 Hz_10ms_envelope_correlation": 0.9942831042763283, "1000–3000 Hz_10ms_modulation_mae_db": 0.7991608975377223, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6882527481768964, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05076558297435669, "1000–3000 Hz_40ms_envelope_correlation": 0.9980413157405653, "1000–3000 Hz_40ms_modulation_mae_db": 0.18255149949572902, "3000–6000 Hz_10ms_log_rms_mae_db": 1.257485448661522, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13772271443609757, "3000–6000 Hz_10ms_envelope_correlation": 0.9860161702010222, "3000–6000 Hz_10ms_modulation_mae_db": 1.0665765062621249, "3000–6000 Hz_40ms_log_rms_mae_db": 0.739969828713665, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08011745139717383, "3000–6000 Hz_40ms_envelope_correlation": 0.9956330126057897, "3000–6000 Hz_40ms_modulation_mae_db": 1.2300734434655898, "mr_stft_db": 5.508036597085208, "band_mae_db": 1.644427259830627, "rms_gain_error_db": -0.10657233384920786, "output_peak": 0.3442703882714492}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9478142729174283, "全帯域_10ms_rms_envelope_nrmse": 0.07247987506820827, "全帯域_10ms_envelope_correlation": 0.9951818577716112, "全帯域_10ms_modulation_mae_db": 0.5389358489133629, "全帯域_40ms_log_rms_mae_db": 0.6585347300525657, "全帯域_40ms_rms_envelope_nrmse": 0.03672178193289723, "全帯域_40ms_envelope_correlation": 0.9986974878273311, "全帯域_40ms_modulation_mae_db": 1.0457378895417224, "300–1000 Hz_10ms_log_rms_mae_db": 0.7152650700115263, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08110621235685957, "300–1000 Hz_10ms_envelope_correlation": 0.9943607606003074, "300–1000 Hz_10ms_modulation_mae_db": 0.5844934390201693, "300–1000 Hz_40ms_log_rms_mae_db": 0.4909212199195484, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04368649942303805, "300–1000 Hz_40ms_envelope_correlation": 0.9982687088295018, "300–1000 Hz_40ms_modulation_mae_db": 1.1848874325038878, "1000–3000 Hz_10ms_log_rms_mae_db": 1.101111672933916, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10306824170707694, "1000–3000 Hz_10ms_envelope_correlation": 0.9924072459057174, "1000–3000 Hz_10ms_modulation_mae_db": 0.2522861470324778, "1000–3000 Hz_40ms_log_rms_mae_db": 0.720022507222683, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05918291901499574, "1000–3000 Hz_40ms_envelope_correlation": 0.9973646298545766, "1000–3000 Hz_40ms_modulation_mae_db": 0.26826257310738605, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2705909161291569, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13907381390635248, "3000–6000 Hz_10ms_envelope_correlation": 0.9861120804553295, "3000–6000 Hz_10ms_modulation_mae_db": 1.136964484602944, "3000–6000 Hz_40ms_log_rms_mae_db": 0.795816600419819, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08212235936357648, "3000–6000 Hz_40ms_envelope_correlation": 0.9958643760751187, "3000–6000 Hz_40ms_modulation_mae_db": 0.6012163888201033, "mr_stft_db": 5.51716702927067, "band_mae_db": 1.765063730341772, "rms_gain_error_db": -0.07341736674899414, "output_peak": 0.3733967892735617}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9547915664036125, "全帯域_10ms_rms_envelope_nrmse": 0.07049825050261943, "全帯域_10ms_envelope_correlation": 0.9956088691260853, "全帯域_10ms_modulation_mae_db": 0.4138345536746657, "全帯域_40ms_log_rms_mae_db": 0.6666347054288685, "全帯域_40ms_rms_envelope_nrmse": 0.038529970104094625, "全帯域_40ms_envelope_correlation": 0.9987694648917832, "全帯域_40ms_modulation_mae_db": 0.3336215338711237, "300–1000 Hz_10ms_log_rms_mae_db": 0.6830252230115867, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07968212321062214, "300–1000 Hz_10ms_envelope_correlation": 0.9947142423073093, "300–1000 Hz_10ms_modulation_mae_db": 0.48116207996394467, "300–1000 Hz_40ms_log_rms_mae_db": 0.48198787921398506, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043409678412440623, "300–1000 Hz_40ms_envelope_correlation": 0.998496724103963, "300–1000 Hz_40ms_modulation_mae_db": 0.5238033020666034, "1000–3000 Hz_10ms_log_rms_mae_db": 1.133950092121848, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09225841641513668, "1000–3000 Hz_10ms_envelope_correlation": 0.9939819176350766, "1000–3000 Hz_10ms_modulation_mae_db": 0.5144369699776468, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6615364443332475, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.049078430128467306, "1000–3000 Hz_40ms_envelope_correlation": 0.9982742373013929, "1000–3000 Hz_40ms_modulation_mae_db": 0.6510119886016142, "3000–6000 Hz_10ms_log_rms_mae_db": 1.270803030139229, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1438057381311815, "3000–6000 Hz_10ms_envelope_correlation": 0.9845698259760253, "3000–6000 Hz_10ms_modulation_mae_db": 0.807035433297751, "3000–6000 Hz_40ms_log_rms_mae_db": 0.823741343100864, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09048678708259897, "3000–6000 Hz_40ms_envelope_correlation": 0.9939765345315681, "3000–6000 Hz_40ms_modulation_mae_db": 0.42994910259916086, "mr_stft_db": 5.517770306978361, "band_mae_db": 1.6611324100116625, "rms_gain_error_db": -0.1486951587188146, "output_peak": 0.357041761440181}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9829958572503873, "全帯域_10ms_rms_envelope_nrmse": 0.07648721247017225, "全帯域_10ms_envelope_correlation": 0.9946030001011844, "全帯域_10ms_modulation_mae_db": 0.12778946778763414, "全帯域_40ms_log_rms_mae_db": 0.6346523148089822, "全帯域_40ms_rms_envelope_nrmse": 0.04226739159388929, "全帯域_40ms_envelope_correlation": 0.9981903700399186, "全帯域_40ms_modulation_mae_db": 0.3623912722865296, "300–1000 Hz_10ms_log_rms_mae_db": 0.7502764568449893, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08648286612750326, "300–1000 Hz_10ms_envelope_correlation": 0.9935658297851169, "300–1000 Hz_10ms_modulation_mae_db": 0.11230187052418893, "300–1000 Hz_40ms_log_rms_mae_db": 0.5229046358016401, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04915211954000536, "300–1000 Hz_40ms_envelope_correlation": 0.9977328290658597, "300–1000 Hz_40ms_modulation_mae_db": 0.17784371098307694, "1000–3000 Hz_10ms_log_rms_mae_db": 1.129939258779575, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07813736852286272, "1000–3000 Hz_10ms_envelope_correlation": 0.9956447500848695, "1000–3000 Hz_10ms_modulation_mae_db": 0.4825824166532069, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6975507666971653, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04100871157625619, "1000–3000 Hz_40ms_envelope_correlation": 0.998726121343442, "1000–3000 Hz_40ms_modulation_mae_db": 0.2099438338215235, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2437345188250528, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13925067964121535, "3000–6000 Hz_10ms_envelope_correlation": 0.9856830768837838, "3000–6000 Hz_10ms_modulation_mae_db": 1.2112637917794091, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7837170817310464, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08688894758156634, "3000–6000 Hz_40ms_envelope_correlation": 0.9946485353758195, "3000–6000 Hz_40ms_modulation_mae_db": 0.8719382476911205, "mr_stft_db": 5.508449883617939, "band_mae_db": 1.688487558568673, "rms_gain_error_db": -0.0022349845869717748, "output_peak": 0.3539533345960475}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 108438, "output_samples": 108438, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.371510974271538, "spectral_convergence": 0.19564672280593565, "spectral_convergence_status": "ok", "amplitude_floor": 1.3518293902907786e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.666689154465134, "spectral_convergence": 0.2149406680816454, "spectral_convergence_status": "ok", "amplitude_floor": 1.2606433835114825e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.472746331184504, "spectral_convergence": 0.21985208208300755, "spectral_convergence_status": "ok", "amplitude_floor": 9.263870496871738e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.1242940814223918e-07, "output_power": 1.1402361240919002e-06, "delta_db": 10.06114871442369, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0005754412253654517, "output_power": 0.0005585550755498593, "delta_db": -0.1293496952707258, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0015091092814657461, "output_power": 0.0015320691793602268, "delta_db": 0.06557685807102132, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00043576714857085195, "output_power": 0.0004188641886045297, "delta_db": -0.17181255418070468, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 9.403622080703858e-05, "output_power": 8.584435719893776e-05, "delta_db": -0.39583414088629226, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.140246786176929e-05, "output_power": 2.9132782605912395e-05, "delta_db": -0.3258181174301845, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2121205040710494e-05, "output_power": 1.1761780379860999e-05, "delta_db": -0.13072731919645578, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.611466771351296, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.03382672621285078, "pitch": null, "output_rms_dbfs": -25.78829333441884, "output_peak": 0.3645161408936929, "reference_rms_dbfs": -25.754466608205988, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.5036488199737255}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 108438, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.0001921686173284563, "log_rms_mae_db": 1.005774245575992, "rms_envelope_nrmse": 0.08719352427594802, "envelope_correlation": 0.9929823640529148, "rms_gain_error_db": -0.03382671357970061, "reference_mean_power": 0.002662852134818696, "output_mean_power": 0.002642192040103765}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.762380071709748e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00040104774940998337, "output_power": 0.0004309550388652942, "reference_active": true, "delta_db": 0.31235879468740996}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0004799671480036487, "output_power": 0.0004672430924638652, "reference_active": true, "delta_db": -0.11668622862148842}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.699212681223788e-05, "output_power": 4.2340513251735123e-05, "reference_active": true, "delta_db": -0.452689829274276}], "active_band_count": 3, "active_band_mae_db": 0.29391161752772477}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.0001703510251571522, "log_rms_mae_db": 0.7394833983941614, "rms_envelope_nrmse": 0.05559243188000751, "envelope_correlation": 0.9968823482680791, "rms_gain_error_db": -0.033826680613678994, "reference_mean_power": 0.002680683564334513, "output_mean_power": 0.0026598851422773274}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.5184553835408784e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00038984224450005464, "output_power": 0.0004241123068664248, "reference_active": true, "delta_db": 0.3659197616240478}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00026155775461828376, "output_power": 0.00023703979895598653, "reference_active": true, "delta_db": -0.4274633031305494}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.971121679142551e-06, "output_power": 5.496038915107974e-06, "reference_active": true, "delta_db": 0.43595405534163295}], "active_band_count": 3, "active_band_mae_db": 0.4097790400320767}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.00018970614972877868, "log_rms_mae_db": 0.7087546853219528, "rms_envelope_nrmse": 0.09670583597189007, "envelope_correlation": 0.99197112745247, "rms_gain_error_db": 0.0026902048814405055, "reference_mean_power": 0.002063788383698964, "output_mean_power": 0.002065067178099398}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.5811898835528837e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0004324343375320338, "output_power": 0.00047586316774567264, "reference_active": true, "delta_db": 0.41561919412785636}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00038978360738039315, "output_power": 0.0003830558097795243, "reference_active": true, "delta_db": -0.0756151697201616}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.8057706966220433e-05, "output_power": 3.657404905945424e-05, "reference_active": true, "delta_db": -0.17269574740733845}], "active_band_count": 3, "active_band_mae_db": 0.2213100370851188}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.00016763715453010979, "log_rms_mae_db": 0.5053136345859803, "rms_envelope_nrmse": 0.06252992541254637, "envelope_correlation": 0.9963437551114612, "rms_gain_error_db": 0.002690198706114016, "reference_mean_power": 0.0020776083853168846, "output_mean_power": 0.00207889574011053}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.3894681028634614e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00045948597327573326, "output_power": 0.0005056623594977504, "reference_active": true, "delta_db": 0.4158836859593378}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019541576327049997, "output_power": 0.0001802371650609316, "reference_active": true, "delta_db": -0.35115245510147525}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.955911260526715e-06, "output_power": 5.04631775295564e-06, "reference_active": true, "delta_db": 0.07851071998589021}], "active_band_count": 3, "active_band_mae_db": 0.28184895368223445}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 7.813214815208366e-05, "log_rms_mae_db": 1.108543395667495, "rms_envelope_nrmse": 0.09326923832976483, "envelope_correlation": 0.9941737109362784, "rms_gain_error_db": -0.233060420042399, "reference_mean_power": 0.0003994594973118105, "output_mean_power": 0.00037858788232328816}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 3.1530674989036126e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00010755692941582863, "output_power": 0.00010028785236775297, "reference_active": true, "delta_db": -0.30390064157178187}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.79686087945957e-05, "output_power": 7.666665155413908e-05, "reference_active": true, "delta_db": -0.597212280576087}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.8229526666890895e-06, "output_power": 3.928292032843711e-06, "reference_active": true, "delta_db": -0.891092335335195}], "active_band_count": 3, "active_band_mae_db": 0.5974017524943546}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 7.396069876288682e-05, "log_rms_mae_db": 0.7128102900286282, "rms_envelope_nrmse": 0.06455862908897636, "envelope_correlation": 0.9973107070395231, "rms_gain_error_db": -0.2330604383631345, "reference_mean_power": 0.00040213443933265886, "output_mean_power": 0.0003811230579783589}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 2.8654358479348363e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000106294645864879, "output_power": 9.840533900609532e-05, "reference_active": true, "delta_db": -0.3349272753411876}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.178329128126849e-05, "output_power": 4.342586818312283e-05, "reference_active": true, "delta_db": -0.7644114043765289}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.031671442188497e-07, "output_power": 4.574930829309767e-07, "reference_active": true, "delta_db": 0.548993997333414}], "active_band_count": 3, "active_band_mae_db": 0.5494442256837102}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 2.8330015424642833e-05, "log_rms_mae_db": 1.2532937936857937, "rms_envelope_nrmse": 0.15562472603748795, "envelope_correlation": 0.9831839823822913, "rms_gain_error_db": -0.5387364281678314, "reference_mean_power": 5.860864109462446e-05, "output_mean_power": 5.1771173478483656e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 4.4003495001587196e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.626242950468029e-05, "output_power": 1.4165746564591325e-05, "reference_active": true, "delta_db": -0.5994595927809255}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.532829538176888e-06, "output_power": 7.69473102585361e-06, "reference_active": true, "delta_db": -0.9302838383361135}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7599215302222477e-06, "output_power": 1.0372784449750035e-06, "reference_active": true, "delta_db": -2.295979511278045}], "active_band_count": 3, "active_band_mae_db": 1.2752409807983611}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 2.5104708341377363e-05, "log_rms_mae_db": 0.8176116654030442, "rms_envelope_nrmse": 0.10341213019148508, "envelope_correlation": 0.9936662318538737, "rms_gain_error_db": -0.5387364563249981, "reference_mean_power": 5.900110522587256e-05, "output_mean_power": 5.2117851177189024e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 3.7677668262047306e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.375501004524296e-05, "output_power": 1.1857675236313319e-05, "reference_active": true, "delta_db": -0.6446136038316259}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.792095126848191e-06, "output_power": 4.761097386101552e-06, "reference_active": true, "delta_db": -0.8512862104783374}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0124260162334744e-07, "output_power": 7.467906183769712e-08, "reference_active": true, "delta_db": -1.3216444321294274}], "active_band_count": 3, "active_band_mae_db": 0.9391814154797968}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.7847151919515367, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "c587af902f0b07e8f7b3adac8d6ddc19c6977a365bf89d78fe42840d2b8b833a", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9941287195626219, "standard_deviation": 0.0009282373620643714, "minimum": 0.9924072459057174, "maximum": 0.9956447500848695, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.110133444800804, "standard_deviation": 0.016112616224501247, "minimum": 1.0845480572106465, "maximum": 1.133950092121848, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5283963652372144, "standard_deviation": 0.2261320225910059, "minimum": 0.2342215929519668, "maximum": 0.8641600264352448, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09155298977344624, "standard_deviation": 0.007143188656967945, "minimum": 0.07813736852286272, "maximum": 0.10306824170707694, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978356947497562, "standard_deviation": 0.0005003190629635914, "minimum": 0.9973107070395231, "maximum": 0.998726121343442, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6948423305502288, "standard_deviation": 0.019551583288111317, "minimum": 0.6615364443332475, "maximum": 0.720022507222683, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5431375699000208, "standard_deviation": 0.3322157774464557, "minimum": 0.18255149949572902, "maximum": 1.186559324618747, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05507654859354463, "standard_deviation": 0.008026772091119993, "minimum": 0.04100871157625619, "maximum": 0.06455862908897636, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9859663047469434, "standard_deviation": 0.0020557271288815407, "minimum": 0.9831839823822913, "maximum": 0.9903949940119788, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2538042292972875, "standard_deviation": 0.016723388201666578, "minimum": 1.220468190307246, "maximum": 1.270803030139229, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.0531140995117647, "standard_deviation": 0.16525134395565658, "minimum": 0.807035433297751, "maximum": 1.2752409807983611, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.13949589480135063, "standard_deviation": 0.010703214226234742, "minimum": 0.11714013414732419, "maximum": 0.15562472603748795, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9950838578472025, "standard_deviation": 0.0010493334790547888, "minimum": 0.9936662318538737, "maximum": 0.9969090592107652, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.786655833796479, "standard_deviation": 0.028921802309630377, "minimum": 0.739969828713665, "maximum": 0.823741343100864, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.8923119223345141, "standard_deviation": 0.2607043876721776, "minimum": 0.42994910259916086, "maximum": 1.2300734434655898, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08704251343560027, "standard_deviation": 0.009732225792374519, "minimum": 0.0721901516788838, "maximum": 0.10341213019148508, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9937168212730831, "standard_deviation": 0.0010256643504582721, "minimum": 0.99197112745247, "maximum": 0.9948147732019752, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.7143711867257845, "standard_deviation": 0.022606298218264667, "minimum": 0.6830252230115867, "maximum": 0.7502764568449893, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4353891138547584, "standard_deviation": 0.22135685427372662, "minimum": 0.11230187052418893, "maximum": 0.7087246155211654, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08565930405093658, "standard_deviation": 0.006736525250515271, "minimum": 0.07765883168582517, "maximum": 0.09670583597189007, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9977998756679904, "standard_deviation": 0.0006770184436935719, "minimum": 0.9963437551114612, "maximum": 0.998496724103963, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5006465298849332, "standard_deviation": 0.01401783126644657, "minimum": 0.48198787921398506, "maximum": 0.5229046358016401, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6015894619988531, "standard_deviation": 0.3887591162895414, "minimum": 0.17784371098307694, "maximum": 1.1848874325038878, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04908424995718651, "standard_deviation": 0.006603014095020256, "minimum": 0.0425644400176296, "maximum": 0.06252992541254637, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.6924340393519435, "standard_deviation": 0.05793375927790683, "minimum": 1.611466771351296, "maximum": 1.7819207730548492, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.511520176667579, "standard_deviation": 0.006203789367522172, "minimum": 5.5036488199737255, "maximum": 5.521031391252802, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.36487827373511295, "standard_deviation": 0.019134108312568777, "minimum": 0.3442703882714492, "maximum": 0.4073545615461529, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.0616119336549346, "standard_deviation": 0.07139942727933558, "minimum": -0.1486951587188146, "maximum": 0.07276016426615216, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9946507980645379, "standard_deviation": 0.0008931314186420547, "minimum": 0.9929823640529148, "maximum": 0.9956088691260853, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9734931284834367, "standard_deviation": 0.026431821107638233, "minimum": 0.9406869008705745, "maximum": 1.0141374328855017, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.44042260975144615, "standard_deviation": 0.2105840227317454, "minimum": 0.12778946778763414, "maximum": 0.7245965506228086, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07642898952821955, "standard_deviation": 0.005983120107182003, "minimum": 0.06961185592118718, "maximum": 0.08719352427594802, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9981982507095162, "standard_deviation": 0.0006013057247171699, "minimum": 0.9968823482680791, "maximum": 0.9987694648917832, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6717782238663296, "standard_deviation": 0.040826657253890425, "minimum": 0.6202499493044152, "maximum": 0.7394833983941614, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5577198184622743, "standard_deviation": 0.3374916150308835, "minimum": 0.07385469648182527, "maximum": 1.0457378895417224, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.04297943933499623, "standard_deviation": 0.006016483981393989, "minimum": 0.03672178193289723, "maximum": 0.05559243188000751, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_falset10_BASIC5000_2951", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 2.336930274963379, "predicted_mos": 2.336930274963379, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 108438, "input_sample_rate": 24000, "input_seconds": 4.51825, "input_float32_sha256": "13d08ef7ed0d3ea4fdcd329474bd4f15de9cd91476fec2290787a1ed3c63a788", "internal_samples": 72292, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.7699372000060976}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9780109603494876, "全帯域_10ms_rms_envelope_nrmse": 0.08108711950750148, "全帯域_10ms_envelope_correlation": 0.9941398566068917, "全帯域_10ms_modulation_mae_db": 0.48080392440108755, "全帯域_40ms_log_rms_mae_db": 0.6025940933143209, "全帯域_40ms_rms_envelope_nrmse": 0.0423698897936317, "全帯域_40ms_envelope_correlation": 0.9984921935729905, "全帯域_40ms_modulation_mae_db": 0.9176551830786704, "300–1000 Hz_10ms_log_rms_mae_db": 0.870468917781871, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09363854306467115, "300–1000 Hz_10ms_envelope_correlation": 0.9926172892160381, "300–1000 Hz_10ms_modulation_mae_db": 0.4085242874486518, "300–1000 Hz_40ms_log_rms_mae_db": 0.5987999325957416, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.049359041291463325, "300–1000 Hz_40ms_envelope_correlation": 0.9979994658005831, "300–1000 Hz_40ms_modulation_mae_db": 1.0079486899899304, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2860881835995257, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09031766894726079, "1000–3000 Hz_10ms_envelope_correlation": 0.9945012554070901, "1000–3000 Hz_10ms_modulation_mae_db": 0.7189430777421336, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8295446037062975, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05410758628087041, "1000–3000 Hz_40ms_envelope_correlation": 0.9981855374544321, "1000–3000 Hz_40ms_modulation_mae_db": 0.905029700432635, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6997828875130447, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1801634293221427, "3000–6000 Hz_10ms_envelope_correlation": 0.9754092166252541, "3000–6000 Hz_10ms_modulation_mae_db": 1.6056974169104639, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1267434304134756, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09813969729823381, "3000–6000 Hz_40ms_envelope_correlation": 0.9931191267055745, "3000–6000 Hz_40ms_modulation_mae_db": 1.1039473651761573, "mr_stft_db": 5.900670348931335, "band_mae_db": 1.7344816308135798, "rms_gain_error_db": -0.15794399393031097, "output_peak": 0.3404475978764374}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9808664836059726, "全帯域_10ms_rms_envelope_nrmse": 0.07504065803014638, "全帯域_10ms_envelope_correlation": 0.9948590302641152, "全帯域_10ms_modulation_mae_db": 0.4822489738318439, "全帯域_40ms_log_rms_mae_db": 0.7055655087156205, "全帯域_40ms_rms_envelope_nrmse": 0.040554861157421254, "全帯域_40ms_envelope_correlation": 0.9984347371369495, "全帯域_40ms_modulation_mae_db": 0.4087861347716306, "300–1000 Hz_10ms_log_rms_mae_db": 0.8912719460989981, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08403303781580826, "300–1000 Hz_10ms_envelope_correlation": 0.9939602175811528, "300–1000 Hz_10ms_modulation_mae_db": 0.43197028886674915, "300–1000 Hz_40ms_log_rms_mae_db": 0.5989227625575807, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.046420717842535715, "300–1000 Hz_40ms_envelope_correlation": 0.9980617625506374, "300–1000 Hz_40ms_modulation_mae_db": 0.40812776796905065, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2472680671818799, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09357597944056784, "1000–3000 Hz_10ms_envelope_correlation": 0.9939098697820103, "1000–3000 Hz_10ms_modulation_mae_db": 0.9842211655925809, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7982820511038125, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.057038310878178254, "1000–3000 Hz_40ms_envelope_correlation": 0.9977461590200759, "1000–3000 Hz_40ms_modulation_mae_db": 0.958595986972826, "3000–6000 Hz_10ms_log_rms_mae_db": 1.64344197582768, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16632679715220527, "3000–6000 Hz_10ms_envelope_correlation": 0.9788819671935513, "3000–6000 Hz_10ms_modulation_mae_db": 0.7700967376707423, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0752643991181494, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09482800519578449, "3000–6000 Hz_40ms_envelope_correlation": 0.9930599726689953, "3000–6000 Hz_40ms_modulation_mae_db": 0.5056013674607212, "mr_stft_db": 5.9010499589497485, "band_mae_db": 1.6827134408878612, "rms_gain_error_db": -0.09223900378201805, "output_peak": 0.3406063073271648}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9480865585064535, "全帯域_10ms_rms_envelope_nrmse": 0.0808569557805227, "全帯域_10ms_envelope_correlation": 0.9940115899544146, "全帯域_10ms_modulation_mae_db": 0.558820668547176, "全帯域_40ms_log_rms_mae_db": 0.5806542310796241, "全帯域_40ms_rms_envelope_nrmse": 0.04653918349435931, "全帯域_40ms_envelope_correlation": 0.997878675582049, "全帯域_40ms_modulation_mae_db": 0.7936998332017997, "300–1000 Hz_10ms_log_rms_mae_db": 0.8459725235516764, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09108451250298369, "300–1000 Hz_10ms_envelope_correlation": 0.9929004850816644, "300–1000 Hz_10ms_modulation_mae_db": 0.5011293358521512, "300–1000 Hz_40ms_log_rms_mae_db": 0.614684428462939, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.053914002793771405, "300–1000 Hz_40ms_envelope_correlation": 0.9973529227773401, "300–1000 Hz_40ms_modulation_mae_db": 0.7841491469608366, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3004152255160093, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09455638024325282, "1000–3000 Hz_10ms_envelope_correlation": 0.9937201079224837, "1000–3000 Hz_10ms_modulation_mae_db": 0.7769013196473477, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8373269607897178, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.054636172541542946, "1000–3000 Hz_40ms_envelope_correlation": 0.9978824986076476, "1000–3000 Hz_40ms_modulation_mae_db": 0.6114052903869145, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6747129006041148, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16599793059038379, "3000–6000 Hz_10ms_envelope_correlation": 0.9787750207111962, "3000–6000 Hz_10ms_modulation_mae_db": 1.3478051296131568, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0390785283058641, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08468984605832469, "3000–6000 Hz_40ms_envelope_correlation": 0.9940495831280547, "3000–6000 Hz_40ms_modulation_mae_db": 0.7562141272233225, "mr_stft_db": 5.90103007872159, "band_mae_db": 1.6836585599565563, "rms_gain_error_db": -0.0729140450419633, "output_peak": 0.3498347223547926}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9789437503084604, "全帯域_10ms_rms_envelope_nrmse": 0.07577136138153605, "全帯域_10ms_envelope_correlation": 0.9947336734875214, "全帯域_10ms_modulation_mae_db": 0.37640222812273977, "全帯域_40ms_log_rms_mae_db": 0.6767509433594849, "全帯域_40ms_rms_envelope_nrmse": 0.044051694106868926, "全帯域_40ms_envelope_correlation": 0.99809048012911, "全帯域_40ms_modulation_mae_db": 0.8207493583696349, "300–1000 Hz_10ms_log_rms_mae_db": 0.8359517938450471, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08385138943957787, "300–1000 Hz_10ms_envelope_correlation": 0.993969779688439, "300–1000 Hz_10ms_modulation_mae_db": 0.38390867662549794, "300–1000 Hz_40ms_log_rms_mae_db": 0.6070548635826354, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04941834070410803, "300–1000 Hz_40ms_envelope_correlation": 0.9977543026523756, "300–1000 Hz_40ms_modulation_mae_db": 0.8903239811306477, "1000–3000 Hz_10ms_log_rms_mae_db": 1.237343266093479, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07946440300330691, "1000–3000 Hz_10ms_envelope_correlation": 0.995628754382441, "1000–3000 Hz_10ms_modulation_mae_db": 0.4293476803235073, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7949106730402572, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04386078212597869, "1000–3000 Hz_40ms_envelope_correlation": 0.998706915465086, "1000–3000 Hz_40ms_modulation_mae_db": 0.6184861253500393, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7130234830071605, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16573810486883464, "3000–6000 Hz_10ms_envelope_correlation": 0.9790261893188131, "3000–6000 Hz_10ms_modulation_mae_db": 1.124989262951483, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1104152563372018, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09326120290426271, "3000–6000 Hz_40ms_envelope_correlation": 0.9932686571377648, "3000–6000 Hz_40ms_modulation_mae_db": 0.6502858080652971, "mr_stft_db": 5.890127083278839, "band_mae_db": 1.5791814390715164, "rms_gain_error_db": -0.06818596950735689, "output_peak": 0.34343649285272615}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.952454975666194, "全帯域_10ms_rms_envelope_nrmse": 0.07351581014942472, "全帯域_10ms_envelope_correlation": 0.9951585177408985, "全帯域_10ms_modulation_mae_db": 0.7231025583447224, "全帯域_40ms_log_rms_mae_db": 0.6520926878003418, "全帯域_40ms_rms_envelope_nrmse": 0.03936542514660656, "全帯域_40ms_envelope_correlation": 0.9986339492704404, "全帯域_40ms_modulation_mae_db": 0.8086373823991794, "300–1000 Hz_10ms_log_rms_mae_db": 0.861291797755263, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08237434309536695, "300–1000 Hz_10ms_envelope_correlation": 0.9943778643050624, "300–1000 Hz_10ms_modulation_mae_db": 0.647298347462128, "300–1000 Hz_40ms_log_rms_mae_db": 0.5905592770704874, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04601695355491008, "300–1000 Hz_40ms_envelope_correlation": 0.9983211841874925, "300–1000 Hz_40ms_modulation_mae_db": 0.9756403289714962, "1000–3000 Hz_10ms_log_rms_mae_db": 1.250910926053622, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10065745064859118, "1000–3000 Hz_10ms_envelope_correlation": 0.9927694576644976, "1000–3000 Hz_10ms_modulation_mae_db": 0.4581724769995396, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8305594607880394, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05666775925214674, "1000–3000 Hz_40ms_envelope_correlation": 0.9975662483723392, "1000–3000 Hz_40ms_modulation_mae_db": 0.28007512171470067, "3000–6000 Hz_10ms_log_rms_mae_db": 1.694837190515297, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16050873188763928, "3000–6000 Hz_10ms_envelope_correlation": 0.9804570601203073, "3000–6000 Hz_10ms_modulation_mae_db": 1.3815850591106298, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0536648902600014, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08474438447740618, "3000–6000 Hz_40ms_envelope_correlation": 0.9946832203339826, "3000–6000 Hz_40ms_modulation_mae_db": 0.8112991039783375, "mr_stft_db": 5.891240133945392, "band_mae_db": 1.7068241106421698, "rms_gain_error_db": -0.12607012139689583, "output_peak": 0.3721373551748351}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9253221206066524, "全帯域_10ms_rms_envelope_nrmse": 0.06993210942583047, "全帯域_10ms_envelope_correlation": 0.9954888951225703, "全帯域_10ms_modulation_mae_db": 0.3044829924493765, "全帯域_40ms_log_rms_mae_db": 0.6178127083917725, "全帯域_40ms_rms_envelope_nrmse": 0.04091501922035293, "全帯域_40ms_envelope_correlation": 0.9983167630496864, "全帯域_40ms_modulation_mae_db": 0.3831700838312846, "300–1000 Hz_10ms_log_rms_mae_db": 0.8599755821494139, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08388534964588747, "300–1000 Hz_10ms_envelope_correlation": 0.9939478938693115, "300–1000 Hz_10ms_modulation_mae_db": 0.22449361111444355, "300–1000 Hz_40ms_log_rms_mae_db": 0.590760211102385, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.052310961850438806, "300–1000 Hz_40ms_envelope_correlation": 0.9974501860454509, "300–1000 Hz_40ms_modulation_mae_db": 0.48979312181416995, "1000–3000 Hz_10ms_log_rms_mae_db": 1.278768690889097, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08561157462930456, "1000–3000 Hz_10ms_envelope_correlation": 0.9948443992545416, "1000–3000 Hz_10ms_modulation_mae_db": 0.4596847104755181, "1000–3000 Hz_40ms_log_rms_mae_db": 0.830530985881085, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04686976377231567, "1000–3000 Hz_40ms_envelope_correlation": 0.9984156197136151, "1000–3000 Hz_40ms_modulation_mae_db": 0.3890624098589936, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6588600779524947, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17110758285113684, "3000–6000 Hz_10ms_envelope_correlation": 0.9780035612032913, "3000–6000 Hz_10ms_modulation_mae_db": 1.0201050943711298, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0938262806779326, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09695622880031932, "3000–6000 Hz_40ms_envelope_correlation": 0.9933524722581448, "3000–6000 Hz_40ms_modulation_mae_db": 0.6328332132764553, "mr_stft_db": 5.885273850738659, "band_mae_db": 1.733914397002819, "rms_gain_error_db": -0.0352947619287416, "output_peak": 0.3682018923018007}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0014965023590814, "全帯域_10ms_rms_envelope_nrmse": 0.07506019472908226, "全帯域_10ms_envelope_correlation": 0.9948029385420731, "全帯域_10ms_modulation_mae_db": 0.4734281782955845, "全帯域_40ms_log_rms_mae_db": 0.7085323783489034, "全帯域_40ms_rms_envelope_nrmse": 0.03780037342877405, "全帯域_40ms_envelope_correlation": 0.9985760263949935, "全帯域_40ms_modulation_mae_db": 0.3611400029208783, "300–1000 Hz_10ms_log_rms_mae_db": 0.940349588984962, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08793636197941111, "300–1000 Hz_10ms_envelope_correlation": 0.9933381480007748, "300–1000 Hz_10ms_modulation_mae_db": 0.328330594470418, "300–1000 Hz_40ms_log_rms_mae_db": 0.6254794985087979, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04502817024837989, "300–1000 Hz_40ms_envelope_correlation": 0.9981159998507617, "300–1000 Hz_40ms_modulation_mae_db": 0.3549779862893108, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2865006196191175, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08659498558036799, "1000–3000 Hz_10ms_envelope_correlation": 0.9947535299092722, "1000–3000 Hz_10ms_modulation_mae_db": 0.6678660801265507, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8565308166797914, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05389667848047856, "1000–3000 Hz_40ms_envelope_correlation": 0.997920597871598, "1000–3000 Hz_40ms_modulation_mae_db": 0.6902402435289198, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6239548532403645, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14916021768335774, "3000–6000 Hz_10ms_envelope_correlation": 0.9830750561784064, "3000–6000 Hz_10ms_modulation_mae_db": 0.9469216308843672, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0932035701025387, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08945514926803053, "3000–6000 Hz_40ms_envelope_correlation": 0.9937314047898579, "3000–6000 Hz_40ms_modulation_mae_db": 0.6542153419219549, "mr_stft_db": 5.8948602035485, "band_mae_db": 1.7819829369053009, "rms_gain_error_db": -0.04804062162575541, "output_peak": 0.34420471421484544}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.983683030168569, "全帯域_10ms_rms_envelope_nrmse": 0.07136832439715171, "全帯域_10ms_envelope_correlation": 0.9953730443541452, "全帯域_10ms_modulation_mae_db": 0.25945491529245385, "全帯域_40ms_log_rms_mae_db": 0.6816906405566348, "全帯域_40ms_rms_envelope_nrmse": 0.03631633976754807, "全帯域_40ms_envelope_correlation": 0.9987837696810737, "全帯域_40ms_modulation_mae_db": 0.6521307795066356, "300–1000 Hz_10ms_log_rms_mae_db": 0.8640193557334409, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08694864288892412, "300–1000 Hz_10ms_envelope_correlation": 0.9935444696174135, "300–1000 Hz_10ms_modulation_mae_db": 0.25533556822076164, "300–1000 Hz_40ms_log_rms_mae_db": 0.6167117277177504, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.046775940130140234, "300–1000 Hz_40ms_envelope_correlation": 0.9980582331535263, "300–1000 Hz_40ms_modulation_mae_db": 0.8842112799441014, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2121376781386675, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07944281059335383, "1000–3000 Hz_10ms_envelope_correlation": 0.9956109108199133, "1000–3000 Hz_10ms_modulation_mae_db": 0.7606575276424216, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7870354639304905, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04450567995485274, "1000–3000 Hz_40ms_envelope_correlation": 0.998625441086259, "1000–3000 Hz_40ms_modulation_mae_db": 0.2680269239544147, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6593847339126349, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17777397372085255, "3000–6000 Hz_10ms_envelope_correlation": 0.9759119791470676, "3000–6000 Hz_10ms_modulation_mae_db": 1.1550825054108953, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0935239505230052, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10492460482856769, "3000–6000 Hz_40ms_envelope_correlation": 0.9916232648719017, "3000–6000 Hz_40ms_modulation_mae_db": 0.5147267279319355, "mr_stft_db": 5.901996602563358, "band_mae_db": 1.660957041809101, "rms_gain_error_db": -0.10014719132703484, "output_peak": 0.3574767561606337}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 108438, "output_samples": 108438, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.783439682224291, "spectral_convergence": 0.1989842825624178, "spectral_convergence_status": "ok", "amplitude_floor": 1.3518293902907786e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.132796419409622, "spectral_convergence": 0.21443815035983405, "spectral_convergence_status": "ok", "amplitude_floor": 1.2606433835114825e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.785774945160094, "spectral_convergence": 0.21676924050215537, "spectral_convergence_status": "ok", "amplitude_floor": 9.263870496871738e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.1242940814223918e-07, "output_power": 1.464387123385683e-06, "delta_db": 11.147759769677915, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0005754412253654517, "output_power": 0.000561768699276562, "delta_db": -0.10443434649917267, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0015091092814657461, "output_power": 0.0014517632148732596, "delta_db": -0.1682490220443913, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00043576714857085195, "output_power": 0.0004182976970099876, "delta_db": -0.17769013210996973, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 9.403622080703858e-05, "output_power": 8.590168619686698e-05, "delta_db": -0.3929347822884294, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.140246786176929e-05, "output_power": 3.1341582424895154e-05, "delta_db": -0.008428597593404103, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2121205040710494e-05, "output_power": 1.2523717837994896e-05, "delta_db": 0.14187476548177802, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.7344816308135798, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.15794399393031097, "pitch": null, "output_rms_dbfs": -25.912410602136298, "output_peak": 0.3404475978764374, "reference_rms_dbfs": -25.754466608205988, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.900670348931335}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 108438, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.0001921686173284563, "log_rms_mae_db": 0.9780109603494876, "rms_envelope_nrmse": 0.08108711950750148, "envelope_correlation": 0.9941398566068917, "rms_gain_error_db": -0.15794399239064671, "reference_mean_power": 0.002662852134818696, "output_mean_power": 0.0025677494920857127}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.762380071709748e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00040104774940998337, "output_power": 0.00037138563846082355, "reference_active": true, "delta_db": -0.3337097802497146}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0004799671480036487, "output_power": 0.0004240421379117635, "reference_active": true, "delta_db": -0.5380249707873909}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.699212681223788e-05, "output_power": 4.120570973808835e-05, "reference_active": true, "delta_db": -0.5706770221661572}], "active_band_count": 3, "active_band_mae_db": 0.48080392440108755}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.0001703510251571522, "log_rms_mae_db": 0.6025940933143209, "rms_envelope_nrmse": 0.0423698897936317, "envelope_correlation": 0.9984921935729905, "rms_gain_error_db": -0.15794402878918437, "reference_mean_power": 0.002680683564334513, "output_mean_power": 0.002584944057940147}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.5184553835408784e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00038984224450005464, "output_power": 0.00035876180509613963, "reference_active": true, "delta_db": -0.36082698328109014}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00026155775461828376, "output_power": 0.00023290033192848724, "reference_active": true, "delta_db": -0.5039749295107829}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.971121679142551e-06, "output_power": 3.2183852556367383e-06, "reference_active": true, "delta_db": -1.8881636364441383}], "active_band_count": 3, "active_band_mae_db": 0.9176551830786704}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.00018970614972877868, "log_rms_mae_db": 0.870468917781871, "rms_envelope_nrmse": 0.09363854306467115, "envelope_correlation": 0.9926172892160381, "rms_gain_error_db": -0.15822838076566428, "reference_mean_power": 0.002063788383698964, "output_mean_power": 0.0019899507386871586}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.5811898835528837e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0004324343375320338, "output_power": 0.0004000339972488658, "reference_active": true, "delta_db": -0.33823270084283175}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00038978360738039315, "output_power": 0.0003492257825472737, "reference_active": true, "delta_db": -0.47717271416869533}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.8057706966220433e-05, "output_power": 3.462787755031538e-05, "reference_active": true, "delta_db": -0.41016744733442834}], "active_band_count": 3, "active_band_mae_db": 0.4085242874486518}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.00016763715453010979, "log_rms_mae_db": 0.5987999325957416, "rms_envelope_nrmse": 0.049359041291463325, "envelope_correlation": 0.9979994658005831, "rms_gain_error_db": -0.15822838911101864, "reference_mean_power": 0.0020776083853168846, "output_mean_power": 0.002003276288293388}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.3894681028634614e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00045948597327573326, "output_power": 0.0004199880110889302, "reference_active": true, "delta_db": -0.3903536494712473}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019541576327049997, "output_power": 0.00017922972625518583, "reference_active": true, "delta_db": -0.3754955181363162}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.955911260526715e-06, "output_power": 2.9466179569655644e-06, "reference_active": true, "delta_db": -2.2579969023622275}], "active_band_count": 3, "active_band_mae_db": 1.0079486899899304}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 7.813214815208366e-05, "log_rms_mae_db": 1.2860881835995257, "rms_envelope_nrmse": 0.09031766894726079, "envelope_correlation": 0.9945012554070901, "rms_gain_error_db": -0.21089447939488887, "reference_mean_power": 0.0003994594973118105, "output_mean_power": 0.0003805250951336297}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 3.1530674989036126e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00010755692941582863, "output_power": 9.834167393084953e-05, "reference_active": true, "delta_db": -0.3890079889559899}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.79686087945957e-05, "output_power": 7.055285369439782e-05, "reference_active": true, "delta_db": -0.9581313912743793}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.8229526666890895e-06, "output_power": 4.0026168047549765e-06, "reference_active": true, "delta_db": -0.8096898529960318}], "active_band_count": 3, "active_band_mae_db": 0.7189430777421336}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 7.396069876288682e-05, "log_rms_mae_db": 0.8295446037062975, "rms_envelope_nrmse": 0.05410758628087041, "envelope_correlation": 0.9981855374544321, "rms_gain_error_db": -0.2108944931907547, "reference_mean_power": 0.00040213443933265886, "output_mean_power": 0.000383073243538455}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 2.8654358479348363e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000106294645864879, "output_power": 9.72810563387999e-05, "reference_active": true, "delta_db": -0.3848311156313252}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.178329128126849e-05, "output_power": 4.1228336549905666e-05, "reference_active": true, "delta_db": -0.9899383762470249}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.031671442188497e-07, "output_power": 2.961100662466946e-07, "reference_active": true, "delta_db": -1.3403196094195546}], "active_band_count": 3, "active_band_mae_db": 0.905029700432635}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 2.8330015424642833e-05, "log_rms_mae_db": 1.6997828875130447, "rms_envelope_nrmse": 0.1801634293221427, "envelope_correlation": 0.9754092166252541, "rms_gain_error_db": -0.36414645768331333, "reference_mean_power": 5.860864109462446e-05, "output_mean_power": 5.389481756132463e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 4.4003495001587196e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.626242950468029e-05, "output_power": 1.4783483225284193e-05, "reference_active": true, "delta_db": -0.4140865412168027}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.532829538176888e-06, "output_power": 7.285807366526647e-06, "reference_active": true, "delta_db": -1.167441427238725}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7599215302222477e-06, "output_power": 8.354815736872992e-07, "reference_active": true, "delta_db": -3.2355642822758646}], "active_band_count": 3, "active_band_mae_db": 1.6056974169104639}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 2.5104708341377363e-05, "log_rms_mae_db": 1.1267434304134756, "rms_envelope_nrmse": 0.09813969729823381, "envelope_correlation": 0.9931191267055745, "rms_gain_error_db": -0.36414660081444183, "reference_mean_power": 5.900110522587256e-05, "output_mean_power": 5.425571447957736e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 3.7677668262047306e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.375501004524296e-05, "output_power": 1.2185087643765268e-05, "reference_active": true, "delta_db": -0.5263225460484762}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.792095126848191e-06, "output_power": 4.323247008770862e-06, "reference_active": true, "delta_db": -1.270256362480344}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0124260162334744e-07, "output_power": 7.142281744094983e-08, "reference_active": true, "delta_db": -1.5152631869996516}], "active_band_count": 3, "active_band_mae_db": 1.1039473651761573}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.7937111415259572, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "a865ab4e882c3bae2d776b6749da08f4fd895ded3b34d2ee92021e847895ec8c", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9944672856427812, "standard_deviation": 0.0009734914638651992, "minimum": 0.9927694576644976, "maximum": 0.995628754382441, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.2624290821364248, "standard_deviation": 0.03016660802579244, "minimum": 1.2121376781386675, "maximum": 1.3004152255160093, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6569742548186999, "standard_deviation": 0.19509748406284652, "minimum": 0.4293476803235073, "maximum": 0.9842211655925809, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08877765663575074, "standard_deviation": 0.0074506266662924875, "minimum": 0.07944281059335383, "maximum": 0.10065745064859118, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9981311271988815, "standard_deviation": 0.00041972817308956077, "minimum": 0.9975662483723392, "maximum": 0.998706915465086, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8205901269899365, "standard_deviation": 0.024299458383403274, "minimum": 0.7870354639304905, "maximum": 0.8565308166797914, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5901152252749304, "standard_deviation": 0.26363404472842056, "minimum": 0.2680269239544147, "maximum": 0.958595986972826, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.051447841660795496, "standard_deviation": 0.005457017257477931, "minimum": 0.04386078212597869, "maximum": 0.057038310878178254, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.978692506312236, "standard_deviation": 0.0024337041057241908, "minimum": 0.9754092166252541, "maximum": 0.9830750561784064, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.670999762821599, "standard_deviation": 0.030311260668668724, "minimum": 1.6239548532403645, "maximum": 1.7130234830071605, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.1690353546153585, "standard_deviation": 0.2674245567709929, "minimum": 0.7700967376707423, "maximum": 1.6056974169104639, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1670970960095691, "standard_deviation": 0.009780412760533062, "minimum": 0.14916021768335774, "maximum": 0.1801634293221427, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9933609627367845, "standard_deviation": 0.000889386343791678, "minimum": 0.9916232648719017, "maximum": 0.9946832203339826, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.0857150382172711, "standard_deviation": 0.02875430679594776, "minimum": 1.0390785283058641, "maximum": 1.1267434304134756, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7036403818792727, "standard_deviation": 0.19265479866722526, "minimum": 0.5056013674607212, "maximum": 1.1039473651761573, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09337488985386617, "standard_deviation": 0.006931601944215679, "minimum": 0.08468984605832469, "maximum": 0.10492460482856769, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.993582018419982, "standard_deviation": 0.0005996072221720683, "minimum": 0.9926172892160381, "maximum": 0.9943778643050624, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.871162688237584, "standard_deviation": 0.032380892306248014, "minimum": 0.8359517938450471, "maximum": 0.940349588984962, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.39762383875760016, "standard_deviation": 0.13604565078084882, "minimum": 0.22449361111444355, "maximum": 0.647298347462128, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08671902255407883, "standard_deviation": 0.0039787952736675646, "minimum": 0.08237434309536695, "maximum": 0.09363854306467115, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.997889257127271, "standard_deviation": 0.0003395545145210484, "minimum": 0.9973529227773401, "maximum": 0.9983211841874925, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.6053715876997896, "standard_deviation": 0.012762445703139046, "minimum": 0.5905592770704874, "maximum": 0.6254794985087979, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.724396537883693, "standard_deviation": 0.2650345184890302, "minimum": 0.3549779862893108, "maximum": 1.0079486899899304, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04865551605196843, "standard_deviation": 0.0031788945590810287, "minimum": 0.04502817024837989, "maximum": 0.053914002793771405, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.6954641946361129, "standard_deviation": 0.06050938110582327, "minimum": 1.5791814390715164, "maximum": 1.7819829369053009, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.895781032584678, "standard_deviation": 0.006343596259783446, "minimum": 5.885273850738659, "maximum": 5.901996602563358, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3520432297829045, "standard_deviation": 0.012535988678820421, "minimum": 0.3404475978764374, "maximum": 0.3721373551748351, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.08760446356750962, "standard_deviation": 0.04053313305944952, "minimum": -0.15794399393031097, "maximum": -0.0352947619287416, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9948209432590788, "standard_deviation": 0.0005336203096724023, "minimum": 0.9940115899544146, "maximum": 0.9954888951225703, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9686080476963588, "standard_deviation": 0.024524451504092677, "minimum": 0.9253221206066524, "maximum": 1.0014965023590814, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4573430549106231, "standard_deviation": 0.1470823870499016, "minimum": 0.25945491529245385, "maximum": 0.7231025583447224, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07532906667514946, "standard_deviation": 0.004002969484028294, "minimum": 0.06993210942583047, "maximum": 0.08108711950750148, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9984008243521616, "standard_deviation": 0.00029693859327741294, "minimum": 0.997878675582049, "maximum": 0.9987837696810737, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6532116489458378, "standard_deviation": 0.048177519907494075, "minimum": 0.5806542310796241, "maximum": 0.7085323783489034, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6432460947599642, "standard_deviation": 0.22648625021531055, "minimum": 0.3611400029208783, "maximum": 0.9176551830786704, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.040989098264445356, "standard_deviation": 0.0033149558629220165, "minimum": 0.03631633976754807, "maximum": 0.04653918349435931, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_falset10_BASIC5000_2951", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 2.456702709197998, "predicted_mos": 2.456702709197998, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 108438, "input_sample_rate": 24000, "input_seconds": 4.51825, "input_float32_sha256": "53eacbee93c0953773e2fee0c75a5b3775a30bfa7cab73269a53ad580ead57ff", "internal_samples": 72292, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.278194000013173}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.034169178087262, "全帯域_10ms_rms_envelope_nrmse": 0.07752889048333159, "全帯域_10ms_envelope_correlation": 0.9944492958978721, "全帯域_10ms_modulation_mae_db": 0.47864759960899655, "全帯域_40ms_log_rms_mae_db": 0.6909143972697827, "全帯域_40ms_rms_envelope_nrmse": 0.03778947625668342, "全帯域_40ms_envelope_correlation": 0.9985629623125353, "全帯域_40ms_modulation_mae_db": 0.534959142330251, "300–1000 Hz_10ms_log_rms_mae_db": 0.6841427949706248, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08642651284014509, "300–1000 Hz_10ms_envelope_correlation": 0.9935668330520069, "300–1000 Hz_10ms_modulation_mae_db": 0.45884433730135243, "300–1000 Hz_40ms_log_rms_mae_db": 0.48689786052750345, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043316422714344015, "300–1000 Hz_40ms_envelope_correlation": 0.9982418261358892, "300–1000 Hz_40ms_modulation_mae_db": 0.7642226662613864, "1000–3000 Hz_10ms_log_rms_mae_db": 1.029805550403323, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08611266024618204, "1000–3000 Hz_10ms_envelope_correlation": 0.9947974080007982, "1000–3000 Hz_10ms_modulation_mae_db": 1.1348331435186867, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6545843329473062, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.046499048627105195, "1000–3000 Hz_40ms_envelope_correlation": 0.9985003980201277, "1000–3000 Hz_40ms_modulation_mae_db": 0.5245235870131633, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1790260740820568, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1333798093426741, "3000–6000 Hz_10ms_envelope_correlation": 0.9875085702188431, "3000–6000 Hz_10ms_modulation_mae_db": 0.8037297246027469, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7365975020177571, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08733372203867772, "3000–6000 Hz_40ms_envelope_correlation": 0.9952507088734724, "3000–6000 Hz_40ms_modulation_mae_db": 0.4144677436143278, "mr_stft_db": 5.55260032213755, "band_mae_db": 1.7139020164733998, "rms_gain_error_db": -0.03284522365068897, "output_peak": 0.37188576497430476}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.997950991991142, "全帯域_10ms_rms_envelope_nrmse": 0.06714810345008873, "全帯域_10ms_envelope_correlation": 0.9958482608776807, "全帯域_10ms_modulation_mae_db": 0.5925191792696604, "全帯域_40ms_log_rms_mae_db": 0.6577368076340477, "全帯域_40ms_rms_envelope_nrmse": 0.032892560794160794, "全帯域_40ms_envelope_correlation": 0.9989185745519056, "全帯域_40ms_modulation_mae_db": 0.5624255515466122, "300–1000 Hz_10ms_log_rms_mae_db": 0.690986534035436, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08001277450303475, "300–1000 Hz_10ms_envelope_correlation": 0.9944912731919834, "300–1000 Hz_10ms_modulation_mae_db": 0.5317919522414362, "300–1000 Hz_40ms_log_rms_mae_db": 0.49811530952176863, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04152262025319282, "300–1000 Hz_40ms_envelope_correlation": 0.9983900189666025, "300–1000 Hz_40ms_modulation_mae_db": 0.7175967983991766, "1000–3000 Hz_10ms_log_rms_mae_db": 1.025103408950993, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08149756849481662, "1000–3000 Hz_10ms_envelope_correlation": 0.9953299372076612, "1000–3000 Hz_10ms_modulation_mae_db": 0.30087441460188935, "1000–3000 Hz_40ms_log_rms_mae_db": 0.637402939439671, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04930423010369628, "1000–3000 Hz_40ms_envelope_correlation": 0.9982462165618794, "1000–3000 Hz_40ms_modulation_mae_db": 0.7372702318324352, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1623153829703212, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13941255037684486, "3000–6000 Hz_10ms_envelope_correlation": 0.9865885319432564, "3000–6000 Hz_10ms_modulation_mae_db": 1.3023390752564772, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7378503146904718, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08911194272083599, "3000–6000 Hz_40ms_envelope_correlation": 0.9955001742634221, "3000–6000 Hz_40ms_modulation_mae_db": 0.9284996580949813, "mr_stft_db": 5.5417283487054965, "band_mae_db": 1.749760174151412, "rms_gain_error_db": -0.029125722345073726, "output_peak": 0.38145721443758296}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9429423861298732, "全帯域_10ms_rms_envelope_nrmse": 0.06275593078396248, "全帯域_10ms_envelope_correlation": 0.9964177417286245, "全帯域_10ms_modulation_mae_db": 0.5766238858722582, "全帯域_40ms_log_rms_mae_db": 0.6461378184451915, "全帯域_40ms_rms_envelope_nrmse": 0.03208384693249358, "全帯域_40ms_envelope_correlation": 0.9990214036829405, "全帯域_40ms_modulation_mae_db": 0.41406105339995714, "300–1000 Hz_10ms_log_rms_mae_db": 0.6015006397535987, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07034669132082003, "300–1000 Hz_10ms_envelope_correlation": 0.9957573817339419, "300–1000 Hz_10ms_modulation_mae_db": 0.6236625517950113, "300–1000 Hz_40ms_log_rms_mae_db": 0.4045304064393309, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03531880022979189, "300–1000 Hz_40ms_envelope_correlation": 0.9988566903194498, "300–1000 Hz_40ms_modulation_mae_db": 0.5222252704036396, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0008142736880672, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08498498500345958, "1000–3000 Hz_10ms_envelope_correlation": 0.995177943820041, "1000–3000 Hz_10ms_modulation_mae_db": 1.1494134805455192, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6250913939619994, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05463520501455275, "1000–3000 Hz_40ms_envelope_correlation": 0.998139029412653, "1000–3000 Hz_40ms_modulation_mae_db": 0.6942359983889763, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2370686839561744, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13772318392063324, "3000–6000 Hz_10ms_envelope_correlation": 0.9867841801419848, "3000–6000 Hz_10ms_modulation_mae_db": 0.8944744666386386, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7947187506072506, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09198894799407624, "3000–6000 Hz_40ms_envelope_correlation": 0.9947997843984542, "3000–6000 Hz_40ms_modulation_mae_db": 0.6773112805314091, "mr_stft_db": 5.546250946467363, "band_mae_db": 1.8709984467982033, "rms_gain_error_db": -0.07146938373309411, "output_peak": 0.3428484805316873}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9783235380611852, "全帯域_10ms_rms_envelope_nrmse": 0.07228994986121329, "全帯域_10ms_envelope_correlation": 0.9952022838785636, "全帯域_10ms_modulation_mae_db": 0.499462340763295, "全帯域_40ms_log_rms_mae_db": 0.6743265367940607, "全帯域_40ms_rms_envelope_nrmse": 0.03923479810133726, "全帯域_40ms_envelope_correlation": 0.9984956906387699, "全帯域_40ms_modulation_mae_db": 0.6560203410838444, "300–1000 Hz_10ms_log_rms_mae_db": 0.6843351185406791, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08029672974634357, "300–1000 Hz_10ms_envelope_correlation": 0.9944677383792083, "300–1000 Hz_10ms_modulation_mae_db": 0.5323485232631798, "300–1000 Hz_40ms_log_rms_mae_db": 0.469154167635977, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04481545645333901, "300–1000 Hz_40ms_envelope_correlation": 0.9981638412634697, "300–1000 Hz_40ms_modulation_mae_db": 0.9711822868504859, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0493293786226758, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10681045825506828, "1000–3000 Hz_10ms_envelope_correlation": 0.9919249224545668, "1000–3000 Hz_10ms_modulation_mae_db": 0.34013643419276113, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6254552145284479, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06168840099847831, "1000–3000 Hz_40ms_envelope_correlation": 0.9972648660079689, "1000–3000 Hz_40ms_modulation_mae_db": 0.307829910348161, "3000–6000 Hz_10ms_log_rms_mae_db": 1.178175160484294, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12268436722701415, "3000–6000 Hz_10ms_envelope_correlation": 0.9885581744691507, "3000–6000 Hz_10ms_modulation_mae_db": 0.9898770099639257, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7027955057876378, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.066178873442185, "3000–6000 Hz_40ms_envelope_correlation": 0.9966120535609512, "3000–6000 Hz_40ms_modulation_mae_db": 0.5241756648359707, "mr_stft_db": 5.548806647335212, "band_mae_db": 1.8989891807911623, "rms_gain_error_db": -0.0706133995999496, "output_peak": 0.3664174165269687}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9828584709496905, "全帯域_10ms_rms_envelope_nrmse": 0.08215120072060017, "全帯域_10ms_envelope_correlation": 0.993923427426533, "全帯域_10ms_modulation_mae_db": 0.7811200235584903, "全帯域_40ms_log_rms_mae_db": 0.7130437356006115, "全帯域_40ms_rms_envelope_nrmse": 0.04800144267069588, "全帯域_40ms_envelope_correlation": 0.9977893209987712, "全帯域_40ms_modulation_mae_db": 0.39427870165232637, "300–1000 Hz_10ms_log_rms_mae_db": 0.6671840695364026, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09234901128715081, "300–1000 Hz_10ms_envelope_correlation": 0.993016222114205, "300–1000 Hz_10ms_modulation_mae_db": 0.7689082322103316, "300–1000 Hz_40ms_log_rms_mae_db": 0.45292103071896606, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.057009756980474016, "300–1000 Hz_40ms_envelope_correlation": 0.9972506239101895, "300–1000 Hz_40ms_modulation_mae_db": 0.532837892263008, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0499165593288322, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08218213402913904, "1000–3000 Hz_10ms_envelope_correlation": 0.9952880911509249, "1000–3000 Hz_10ms_modulation_mae_db": 0.866501893041208, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6373273603928623, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04827752181574569, "1000–3000 Hz_40ms_envelope_correlation": 0.9983730069375633, "1000–3000 Hz_40ms_modulation_mae_db": 0.7817478343317429, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2198025451625627, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1319586612249987, "3000–6000 Hz_10ms_envelope_correlation": 0.9881503756481615, "3000–6000 Hz_10ms_modulation_mae_db": 1.374977434636125, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7734558640025474, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08048435606691397, "3000–6000 Hz_40ms_envelope_correlation": 0.9966896391329924, "3000–6000 Hz_40ms_modulation_mae_db": 1.3214629855264566, "mr_stft_db": 5.537938214413503, "band_mae_db": 1.801152225507741, "rms_gain_error_db": 0.08374667870242003, "output_peak": 0.38426960752134215}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9967072200363198, "全帯域_10ms_rms_envelope_nrmse": 0.07721114767065466, "全帯域_10ms_envelope_correlation": 0.9945335074719888, "全帯域_10ms_modulation_mae_db": 0.7446935238429667, "全帯域_40ms_log_rms_mae_db": 0.6396083259671449, "全帯域_40ms_rms_envelope_nrmse": 0.041636077096502855, "全帯域_40ms_envelope_correlation": 0.9983010351297201, "全帯域_40ms_modulation_mae_db": 0.5501337227488992, "300–1000 Hz_10ms_log_rms_mae_db": 0.6902207418150328, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0803376621810323, "300–1000 Hz_10ms_envelope_correlation": 0.9944940364989218, "300–1000 Hz_10ms_modulation_mae_db": 0.8222057224232785, "300–1000 Hz_40ms_log_rms_mae_db": 0.46738088824534835, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04423166307824777, "300–1000 Hz_40ms_envelope_correlation": 0.9982424115119108, "300–1000 Hz_40ms_modulation_mae_db": 0.7517217930784775, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0672022779707353, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10027889189129002, "1000–3000 Hz_10ms_envelope_correlation": 0.9928092940237003, "1000–3000 Hz_10ms_modulation_mae_db": 0.14234130703471326, "1000–3000 Hz_40ms_log_rms_mae_db": 0.707116456828217, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.059057407226306396, "1000–3000 Hz_40ms_envelope_correlation": 0.9973594575962255, "1000–3000 Hz_40ms_modulation_mae_db": 0.8093200916193745, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1852732725741608, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14023469194701005, "3000–6000 Hz_10ms_envelope_correlation": 0.9856157668940619, "3000–6000 Hz_10ms_modulation_mae_db": 0.5184886240790337, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7281983478124353, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0900637667453516, "3000–6000 Hz_40ms_envelope_correlation": 0.9943618492647909, "3000–6000 Hz_40ms_modulation_mae_db": 0.2832925727584513, "mr_stft_db": 5.542615855508129, "band_mae_db": 1.8897128264411776, "rms_gain_error_db": -0.06519689223670165, "output_peak": 0.33489185146388656}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9176438913336197, "全帯域_10ms_rms_envelope_nrmse": 0.06463121949668672, "全帯域_10ms_envelope_correlation": 0.9961560617936311, "全帯域_10ms_modulation_mae_db": 0.49867843158609415, "全帯域_40ms_log_rms_mae_db": 0.6038577526250781, "全帯域_40ms_rms_envelope_nrmse": 0.03159514342858829, "全帯域_40ms_envelope_correlation": 0.9990010901299492, "全帯域_40ms_modulation_mae_db": 0.31312624045860443, "300–1000 Hz_10ms_log_rms_mae_db": 0.6797266744085511, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07108395275523048, "300–1000 Hz_10ms_envelope_correlation": 0.9956625261814885, "300–1000 Hz_10ms_modulation_mae_db": 0.5042430375247199, "300–1000 Hz_40ms_log_rms_mae_db": 0.47710465162317367, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03628894403675342, "300–1000 Hz_40ms_envelope_correlation": 0.9987705436956551, "300–1000 Hz_40ms_modulation_mae_db": 0.4625851557635652, "1000–3000 Hz_10ms_log_rms_mae_db": 1.057510809031035, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08708703094555192, "1000–3000 Hz_10ms_envelope_correlation": 0.9946650560590798, "1000–3000 Hz_10ms_modulation_mae_db": 0.4140381476663649, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6637873420497286, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05103868011998422, "1000–3000 Hz_40ms_envelope_correlation": 0.9981508488293934, "1000–3000 Hz_40ms_modulation_mae_db": 0.4465263498231527, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2001075650143398, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12887325835356883, "3000–6000 Hz_10ms_envelope_correlation": 0.9885009653859729, "3000–6000 Hz_10ms_modulation_mae_db": 1.3528116487953994, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7599580044851173, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07856102404223898, "3000–6000 Hz_40ms_envelope_correlation": 0.9965699480946546, "3000–6000 Hz_40ms_modulation_mae_db": 1.1672980187760504, "mr_stft_db": 5.544605126114361, "band_mae_db": 1.9555816434289324, "rms_gain_error_db": -0.03062141375072211, "output_peak": 0.33893329797388916}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0120477908128627, "全帯域_10ms_rms_envelope_nrmse": 0.07686913412009755, "全帯域_10ms_envelope_correlation": 0.9945612399770569, "全帯域_10ms_modulation_mae_db": 0.8409423534305698, "全帯域_40ms_log_rms_mae_db": 0.6872693730131899, "全帯域_40ms_rms_envelope_nrmse": 0.03996856516855161, "全帯域_40ms_envelope_correlation": 0.9984094909156546, "全帯域_40ms_modulation_mae_db": 0.8152418248902423, "300–1000 Hz_10ms_log_rms_mae_db": 0.7074594170816415, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08453546499551202, "300–1000 Hz_10ms_envelope_correlation": 0.9938570239750254, "300–1000 Hz_10ms_modulation_mae_db": 0.7250923433209251, "300–1000 Hz_40ms_log_rms_mae_db": 0.4812190130332827, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04614188236617726, "300–1000 Hz_40ms_envelope_correlation": 0.9980223348159384, "300–1000 Hz_40ms_modulation_mae_db": 0.7676179477566195, "1000–3000 Hz_10ms_log_rms_mae_db": 1.04656542142823, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09274058378934089, "1000–3000 Hz_10ms_envelope_correlation": 0.9939905986104494, "1000–3000 Hz_10ms_modulation_mae_db": 0.5183937527249024, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6665190236905383, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05433277122349171, "1000–3000 Hz_40ms_envelope_correlation": 0.9979611210927796, "1000–3000 Hz_40ms_modulation_mae_db": 0.34199006498177104, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2029931626128592, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1315055555219072, "3000–6000 Hz_10ms_envelope_correlation": 0.9875068443509142, "3000–6000 Hz_10ms_modulation_mae_db": 0.910002777022465, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7459699500314246, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08412551163101903, "3000–6000 Hz_40ms_envelope_correlation": 0.9952507463965087, "3000–6000 Hz_40ms_modulation_mae_db": 0.8536653700928395, "mr_stft_db": 5.537927368392611, "band_mae_db": 1.7627532785505107, "rms_gain_error_db": -0.045429228121965634, "output_peak": 0.3945919674362232}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 108438, "output_samples": 108438, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.308054873158788, "spectral_convergence": 0.19269689524998643, "spectral_convergence_status": "ok", "amplitude_floor": 1.3518293902907786e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.733986132813569, "spectral_convergence": 0.20960924523373692, "spectral_convergence_status": "ok", "amplitude_floor": 1.2606433835114825e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.615759960440292, "spectral_convergence": 0.21032280122809005, "spectral_convergence_status": "ok", "amplitude_floor": 9.263870496871738e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.1242940814223918e-07, "output_power": 1.5261142354259074e-06, "delta_db": 11.327071189906246, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0005754412253654517, "output_power": 0.0005765918713162941, "delta_db": 0.008675433972978715, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0015091092814657461, "output_power": 0.0015064894237349657, "delta_db": -0.007546030843823923, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00043576714857085195, "output_power": 0.0004239652530694123, "delta_db": -0.11924222168133722, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 9.403622080703858e-05, "output_power": 8.630887363955798e-05, "delta_db": -0.37239718120472004, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.140246786176929e-05, "output_power": 3.140490511373967e-05, "delta_db": 0.0003370575880277545, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2121205040710494e-05, "output_power": 1.1677269347591867e-05, "delta_db": -0.162045000116665, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.7139020164733998, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.03284522365068897, "pitch": null, "output_rms_dbfs": -25.787311831856673, "output_peak": 0.37188576497430476, "reference_rms_dbfs": -25.754466608205988, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.55260032213755}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 108438, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.0001921686173284563, "log_rms_mae_db": 1.034169178087262, "rms_envelope_nrmse": 0.07752889048333159, "envelope_correlation": 0.9944492958978721, "rms_gain_error_db": -0.03284520745490431, "reference_mean_power": 0.002662852134818696, "output_mean_power": 0.0026427892433487075}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.762380071709748e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00040104774940998337, "output_power": 0.00040710685646660875, "reference_active": true, "delta_db": 0.06512333280069493}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0004799671480036487, "output_power": 0.00046199890131573936, "reference_active": true, "delta_db": -0.16570569766249207}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.699212681223788e-05, "output_power": 3.5605224161630436e-05, "reference_active": true, "delta_db": -1.2051137683638027}], "active_band_count": 3, "active_band_mae_db": 0.47864759960899655}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.0001703510251571522, "log_rms_mae_db": 0.6909143972697827, "rms_envelope_nrmse": 0.03778947625668342, "envelope_correlation": 0.9985629623125353, "rms_gain_error_db": -0.032845204508744494, "reference_mean_power": 0.002680683564334513, "output_mean_power": 0.002660486326227513}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.5184553835408784e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00038984224450005464, "output_power": 0.0003944155583078067, "reference_active": true, "delta_db": 0.05065139185930696}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00026155775461828376, "output_power": 0.0002507154017683836, "reference_active": true, "delta_db": -0.18386586396482915}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.971121679142551e-06, "output_power": 3.625921324137425e-06, "reference_active": true, "delta_db": -1.3703601711666167}], "active_band_count": 3, "active_band_mae_db": 0.534959142330251}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.00018970614972877868, "log_rms_mae_db": 0.6841427949706248, "rms_envelope_nrmse": 0.08642651284014509, "envelope_correlation": 0.9935668330520069, "rms_gain_error_db": -0.017926036765880886, "reference_mean_power": 0.002063788383698964, "output_mean_power": 0.0020552874008178163}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.5811898835528837e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0004324343375320338, "output_power": 0.00044470112745065136, "reference_active": true, "delta_db": 0.1214805862936082}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00038978360738039315, "output_power": 0.00038324521378592944, "reference_active": true, "delta_db": -0.07346830800452783}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.8057706966220433e-05, "output_power": 2.8992402550761953e-05, "reference_active": true, "delta_db": -1.1815841176059212}], "active_band_count": 3, "active_band_mae_db": 0.45884433730135243}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.00016763715453010979, "log_rms_mae_db": 0.48689786052750345, "rms_envelope_nrmse": 0.043316422714344015, "envelope_correlation": 0.9982418261358892, "rms_gain_error_db": -0.017926046877250357, "reference_mean_power": 0.0020776083853168846, "output_mean_power": 0.0020690504714345605}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.3894681028634614e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00045948597327573326, "output_power": 0.00046812267759174624, "reference_active": true, "delta_db": 0.08087422245389887}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019541576327049997, "output_power": 0.00019402311977641143, "reference_active": true, "delta_db": -0.03106109786243368}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.955911260526715e-06, "output_power": 2.999509581343205e-06, "reference_active": true, "delta_db": -2.1807326784678267}], "active_band_count": 3, "active_band_mae_db": 0.7642226662613864}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 7.813214815208366e-05, "log_rms_mae_db": 1.029805550403323, "rms_envelope_nrmse": 0.08611266024618204, "envelope_correlation": 0.9947974080007982, "rms_gain_error_db": -0.130862132072609, "reference_mean_power": 0.0003994594973118105, "output_mean_power": 0.0003876024717894781}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 3.1530674989036126e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00010755692941582863, "output_power": 0.00010426668812126032, "reference_active": true, "delta_db": -0.13492816260295148}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.79686087945957e-05, "output_power": 7.787082735887049e-05, "reference_active": true, "delta_db": -0.5295293475202948}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.8229526666890895e-06, "output_power": 2.5663081764955138e-06, "reference_active": true, "delta_db": -2.7400419204328137}], "active_band_count": 3, "active_band_mae_db": 1.1348331435186867}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 7.396069876288682e-05, "log_rms_mae_db": 0.6545843329473062, "rms_envelope_nrmse": 0.046499048627105195, "envelope_correlation": 0.9985003980201277, "rms_gain_error_db": -0.1308621366121718, "reference_mean_power": 0.00040213443933265886, "output_mean_power": 0.0003901980139739217}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 2.8654358479348363e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000106294645864879, "output_power": 0.00010229310898644139, "reference_active": true, "delta_db": -0.16665011072316321}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.178329128126849e-05, "output_power": 4.444993530246765e-05, "reference_active": true, "delta_db": -0.66318517005828}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.031671442188497e-07, "output_power": 3.397125445783006e-07, "reference_active": true, "delta_db": -0.7437354802580464}], "active_band_count": 3, "active_band_mae_db": 0.5245235870131633}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 2.8330015424642833e-05, "log_rms_mae_db": 1.1790260740820568, "rms_envelope_nrmse": 0.1333798093426741, "envelope_correlation": 0.9875085702188431, "rms_gain_error_db": -0.4143138047963656, "reference_mean_power": 5.860864109462446e-05, "output_mean_power": 5.327583576373023e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 4.4003495001587196e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.626242950468029e-05, "output_power": 1.5268888929669034e-05, "reference_active": true, "delta_db": -0.2737799104341369}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.532829538176888e-06, "output_power": 8.199438426313497e-06, "reference_active": true, "delta_db": -0.6543771834746701}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7599215302222477e-06, "output_power": 1.2508064046036254e-06, "reference_active": true, "delta_db": -1.4830320798994336}], "active_band_count": 3, "active_band_mae_db": 0.8037297246027469}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 2.5104708341377363e-05, "log_rms_mae_db": 0.7365975020177571, "rms_envelope_nrmse": 0.08733372203867772, "envelope_correlation": 0.9952507088734724, "rms_gain_error_db": -0.41431385689195643, "reference_mean_power": 5.900110522587256e-05, "output_mean_power": 5.3632588906326825e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 3.7677668262047306e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.375501004524296e-05, "output_power": 1.2909362496486099e-05, "reference_active": true, "delta_db": -0.2755611587389934}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.792095126848191e-06, "output_power": 4.8834370595848665e-06, "reference_active": true, "delta_db": -0.7411009124572245}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0124260162334744e-07, "output_power": 9.609243103317862e-08, "reference_active": true, "delta_db": -0.22674115964676542}], "active_band_count": 3, "active_band_mae_db": 0.4144677436143278}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.7842155572369849, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "df84f68f1859f198a47a6eaa33fceb800c53a8875f92c7c473d42bbc479c86fc", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9942479064159027, "standard_deviation": 0.0012607128206669324, "minimum": 0.9919249224545668, "maximum": 0.9953299372076612, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.0407809599279865, "standard_deviation": 0.021150987006478526, "minimum": 1.0008142736880672, "maximum": 1.0672022779707353, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6083165716657556, "standard_deviation": 0.3902507725131527, "minimum": 0.14234130703471326, "maximum": 1.1494134805455192, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09021178908185605, "standard_deviation": 0.009083396408290895, "minimum": 0.08149756849481662, "maximum": 0.10681045825506828, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9979993680573238, "standard_deviation": 0.00045425990486265897, "minimum": 0.9972648660079689, "maximum": 0.9985003980201277, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6521605079798463, "standard_deviation": 0.027388994697537344, "minimum": 0.6250913939619994, "maximum": 0.707116456828217, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5804305085423471, "standard_deviation": 0.20095853662010896, "minimum": 0.307829910348161, "maximum": 0.8093200916193745, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05310415814117007, "standard_deviation": 0.005326665228480849, "minimum": 0.046499048627105195, "maximum": 0.06168840099847831, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9874016761315432, "standard_deviation": 0.0010254573550253939, "minimum": 0.9856157668940619, "maximum": 0.9885581744691507, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.195595230857096, "standard_deviation": 0.02441667708129422, "minimum": 1.1623153829703212, "maximum": 1.2370686839561744, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.0183375951243514, "standard_deviation": 0.3032009594517793, "minimum": 0.5184886240790337, "maximum": 1.374977434636125, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1332215097393314, "standard_deviation": 0.005883169526437007, "minimum": 0.12268436722701415, "maximum": 0.14023469194701005, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9956293629981559, "standard_deviation": 0.0008922505631253807, "minimum": 0.9943618492647909, "maximum": 0.9966896391329924, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7474430299293302, "standard_deviation": 0.028394820246338107, "minimum": 0.7027955057876378, "maximum": 0.7947187506072506, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7712716617788109, "standard_deviation": 0.36378454110857333, "minimum": 0.2832925727584513, "maximum": 1.3214629855264566, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08348101808516231, "standard_deviation": 0.008411166023086378, "minimum": 0.066178873442185, "maximum": 0.09198894799407624, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9944141293908476, "standard_deviation": 0.0009532241472242644, "minimum": 0.993016222114205, "maximum": 0.9957573817339419, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.6756944987677458, "standard_deviation": 0.03205646067151057, "minimum": 0.6015006397535987, "maximum": 0.7074594170816415, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6208870875100294, "standard_deviation": 0.1357237732423168, "minimum": 0.45884433730135243, "maximum": 0.8222057224232785, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08067359995365864, "standard_deviation": 0.007402925956336235, "minimum": 0.07034669132082003, "maximum": 0.09234901128715081, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9982422863273881, "standard_deviation": 0.0004951622992013743, "minimum": 0.9972506239101895, "maximum": 0.9988566903194498, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.46716541596816885, "standard_deviation": 0.028719345810407595, "minimum": 0.4045304064393309, "maximum": 0.49811530952176863, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6862487263470448, "standard_deviation": 0.1688707935538154, "minimum": 0.4625851557635652, "maximum": 0.9711822868504859, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04358069326404002, "standard_deviation": 0.0067037498088118545, "minimum": 0.03531880022979189, "maximum": 0.057009756980474016, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.8303562240178173, "standard_deviation": 0.0853959035648628, "minimum": 1.7139020164733998, "maximum": 1.9555816434289324, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.544059103634279, "standard_deviation": 0.005115421304883418, "minimum": 5.537927368392611, "maximum": 5.55260032213755, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.36441195010823557, "standard_deviation": 0.022807148011264426, "minimum": 0.33489185146388656, "maximum": 0.3945919674362232, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.03269432309197197, "standard_deviation": 0.05033532987072014, "minimum": -0.07146938373309411, "maximum": 0.08374667870242003, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9951364773814939, "standard_deviation": 0.0009126363936496812, "minimum": 0.993923427426533, "maximum": 0.9964177417286245, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9828304334252443, "standard_deviation": 0.03736149976533902, "minimum": 0.9176438913336197, "maximum": 1.034169178087262, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.6265859172415413, "standard_deviation": 0.14234871674358254, "minimum": 0.47864759960899655, "maximum": 0.8409423534305698, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.0725731970733294, "standard_deviation": 0.007022701016015638, "minimum": 0.06275593078396248, "maximum": 0.08215120072060017, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9985624460450307, "standard_deviation": 0.0004181230314898119, "minimum": 0.9977893209987712, "maximum": 0.9990214036829405, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6641118434186384, "standard_deviation": 0.034533632846386796, "minimum": 0.6038577526250781, "maximum": 0.7130437356006115, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5300308222638421, "standard_deviation": 0.15929385758605144, "minimum": 0.31312624045860443, "maximum": 0.8152418248902423, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03790023880612671, "standard_deviation": 0.005615330791181919, "minimum": 0.03159514342858829, "maximum": 0.04800144267069588, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_falset10_BASIC5000_2951", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 2.483137369155884, "predicted_mos": 2.483137369155884, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 108438, "input_sample_rate": 24000, "input_seconds": 4.51825, "input_float32_sha256": "a1ef4f4640699a7b40bcab6b8fd5699820169bde5f125df461cc9696ce0b56d6", "internal_samples": 72292, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.039131700061262}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9834991112389778, "全帯域_10ms_rms_envelope_nrmse": 0.08413876851549094, "全帯域_10ms_envelope_correlation": 0.9934638762275622, "全帯域_10ms_modulation_mae_db": 0.34202055032995365, "全帯域_40ms_log_rms_mae_db": 0.7045987898120559, "全帯域_40ms_rms_envelope_nrmse": 0.052140738599166875, "全帯域_40ms_envelope_correlation": 0.9972526265343183, "全帯域_40ms_modulation_mae_db": 0.2998417488603237, "300–1000 Hz_10ms_log_rms_mae_db": 0.7190151323822459, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09310552190523276, "300–1000 Hz_10ms_envelope_correlation": 0.9925568220635568, "300–1000 Hz_10ms_modulation_mae_db": 0.2783067821663901, "300–1000 Hz_40ms_log_rms_mae_db": 0.5265473352806197, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.058785038835939704, "300–1000 Hz_40ms_envelope_correlation": 0.9967670627794096, "300–1000 Hz_40ms_modulation_mae_db": 0.32052018215815875, "1000–3000 Hz_10ms_log_rms_mae_db": 1.123971196417261, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09337630244739867, "1000–3000 Hz_10ms_envelope_correlation": 0.994094059167033, "1000–3000 Hz_10ms_modulation_mae_db": 0.48397089401057397, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7384617524176514, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06307622730853196, "1000–3000 Hz_40ms_envelope_correlation": 0.9973860255579339, "1000–3000 Hz_40ms_modulation_mae_db": 0.6779901727526524, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3591746280614272, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15786396260682242, "3000–6000 Hz_10ms_envelope_correlation": 0.9819094940784108, "3000–6000 Hz_10ms_modulation_mae_db": 1.2115130663691285, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9648107101161061, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09703190088113538, "3000–6000 Hz_40ms_envelope_correlation": 0.9939072119320812, "3000–6000 Hz_40ms_modulation_mae_db": 0.7732621130587084, "mr_stft_db": 5.609750983129277, "band_mae_db": 1.5927373609583984, "rms_gain_error_db": -0.024403979651548675, "output_peak": 0.3653936914519935}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9642036319413336, "全帯域_10ms_rms_envelope_nrmse": 0.07361211813556716, "全帯域_10ms_envelope_correlation": 0.9950841965261416, "全帯域_10ms_modulation_mae_db": 0.3560361691160319, "全帯域_40ms_log_rms_mae_db": 0.5989341637251506, "全帯域_40ms_rms_envelope_nrmse": 0.04225971288447733, "全帯域_40ms_envelope_correlation": 0.998255374600292, "全帯域_40ms_modulation_mae_db": 0.09808709009191308, "300–1000 Hz_10ms_log_rms_mae_db": 0.714954815092701, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07983559926362015, "300–1000 Hz_10ms_envelope_correlation": 0.994612016874759, "300–1000 Hz_10ms_modulation_mae_db": 0.3893677957942634, "300–1000 Hz_40ms_log_rms_mae_db": 0.4976426907733883, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04659252903931581, "300–1000 Hz_40ms_envelope_correlation": 0.9980329406765159, "300–1000 Hz_40ms_modulation_mae_db": 0.3405856670770568, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1076955443343408, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09430348948657287, "1000–3000 Hz_10ms_envelope_correlation": 0.9937433187825044, "1000–3000 Hz_10ms_modulation_mae_db": 0.1472001352495403, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6967281795276825, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05542622712753628, "1000–3000 Hz_40ms_envelope_correlation": 0.9977190624037969, "1000–3000 Hz_40ms_modulation_mae_db": 0.7942231338565834, "3000–6000 Hz_10ms_log_rms_mae_db": 1.313092171810487, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11637085100756925, "3000–6000 Hz_10ms_envelope_correlation": 0.9903666993146002, "3000–6000 Hz_10ms_modulation_mae_db": 0.9427067939376276, "3000–6000 Hz_40ms_log_rms_mae_db": 0.857689283613957, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06970531969781911, "3000–6000 Hz_40ms_envelope_correlation": 0.9969740318364919, "3000–6000 Hz_40ms_modulation_mae_db": 1.113036533569434, "mr_stft_db": 5.613101362012979, "band_mae_db": 1.7731808292939186, "rms_gain_error_db": 0.061433540210859866, "output_peak": 0.36676324933267496}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9275086271440635, "全帯域_10ms_rms_envelope_nrmse": 0.07936034743430866, "全帯域_10ms_envelope_correlation": 0.9943118511893285, "全帯域_10ms_modulation_mae_db": 0.6707626759107086, "全帯域_40ms_log_rms_mae_db": 0.6547258266397625, "全帯域_40ms_rms_envelope_nrmse": 0.04472708051327557, "全帯域_40ms_envelope_correlation": 0.9981594069688763, "全帯域_40ms_modulation_mae_db": 0.6801630190822744, "300–1000 Hz_10ms_log_rms_mae_db": 0.6950110883377855, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09102147847324696, "300–1000 Hz_10ms_envelope_correlation": 0.9929541118904718, "300–1000 Hz_10ms_modulation_mae_db": 0.6575769175438589, "300–1000 Hz_40ms_log_rms_mae_db": 0.4891510843676348, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05113879230831163, "300–1000 Hz_40ms_envelope_correlation": 0.99770638750535, "300–1000 Hz_40ms_modulation_mae_db": 0.8215842762824703, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0839718189454572, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08893052081828728, "1000–3000 Hz_10ms_envelope_correlation": 0.9946639024009646, "1000–3000 Hz_10ms_modulation_mae_db": 0.7572022235507215, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7124120172087193, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06374940142737832, "1000–3000 Hz_40ms_envelope_correlation": 0.9972818965058846, "1000–3000 Hz_40ms_modulation_mae_db": 0.5185947871087384, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3078426008324344, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1447627831334, "3000–6000 Hz_10ms_envelope_correlation": 0.9840775526174672, "3000–6000 Hz_10ms_modulation_mae_db": 1.0473396088291502, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8688513139955579, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08487355299220004, "3000–6000 Hz_40ms_envelope_correlation": 0.9944272042337274, "3000–6000 Hz_40ms_modulation_mae_db": 0.8400182676461712, "mr_stft_db": 5.626527524372556, "band_mae_db": 1.7379066175443973, "rms_gain_error_db": -0.12510385786790099, "output_peak": 0.3528005797409734}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9563920039999922, "全帯域_10ms_rms_envelope_nrmse": 0.06738317221866515, "全帯域_10ms_envelope_correlation": 0.9958687332334056, "全帯域_10ms_modulation_mae_db": 0.4145643194183904, "全帯域_40ms_log_rms_mae_db": 0.6772851427788205, "全帯域_40ms_rms_envelope_nrmse": 0.037181711487103794, "全帯域_40ms_envelope_correlation": 0.9986927650763445, "全帯域_40ms_modulation_mae_db": 0.43399467141437614, "300–1000 Hz_10ms_log_rms_mae_db": 0.7081778732619928, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0750459160817981, "300–1000 Hz_10ms_envelope_correlation": 0.9951674278089186, "300–1000 Hz_10ms_modulation_mae_db": 0.3507780807592517, "300–1000 Hz_40ms_log_rms_mae_db": 0.49489435684982047, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0415916082201098, "300–1000 Hz_40ms_envelope_correlation": 0.998411507759812, "300–1000 Hz_40ms_modulation_mae_db": 0.3437698537464668, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1124103277014916, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0964582398882369, "1000–3000 Hz_10ms_envelope_correlation": 0.9936273564662236, "1000–3000 Hz_10ms_modulation_mae_db": 0.469269061976453, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7223889370119672, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05994326422746855, "1000–3000 Hz_40ms_envelope_correlation": 0.9976427977973336, "1000–3000 Hz_40ms_modulation_mae_db": 1.2040594956153619, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3433232749440032, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14624646203115269, "3000–6000 Hz_10ms_envelope_correlation": 0.9850654965538921, "3000–6000 Hz_10ms_modulation_mae_db": 1.1211227427660124, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9234559373790507, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09440734885784473, "3000–6000 Hz_40ms_envelope_correlation": 0.9947028031915827, "3000–6000 Hz_40ms_modulation_mae_db": 0.9283428160385269, "mr_stft_db": 5.61076547681347, "band_mae_db": 1.6883391455369436, "rms_gain_error_db": -0.08929671068225488, "output_peak": 0.4021112513873755}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0015372115198116, "全帯域_10ms_rms_envelope_nrmse": 0.08302935302265124, "全帯域_10ms_envelope_correlation": 0.9937073049195682, "全帯域_10ms_modulation_mae_db": 0.778296846581485, "全帯域_40ms_log_rms_mae_db": 0.6546807166327159, "全帯域_40ms_rms_envelope_nrmse": 0.046625966816776936, "全帯域_40ms_envelope_correlation": 0.9979287607125089, "全帯域_40ms_modulation_mae_db": 0.974953247354064, "300–1000 Hz_10ms_log_rms_mae_db": 0.7713229716097785, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09286351689084744, "300–1000 Hz_10ms_envelope_correlation": 0.9926828594291158, "300–1000 Hz_10ms_modulation_mae_db": 0.7331974453695448, "300–1000 Hz_40ms_log_rms_mae_db": 0.5385110060881083, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.054126575786185877, "300–1000 Hz_40ms_envelope_correlation": 0.9974457888539144, "300–1000 Hz_40ms_modulation_mae_db": 1.0237073517192263, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0858959611997037, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0862276664249715, "1000–3000 Hz_10ms_envelope_correlation": 0.9946984008240589, "1000–3000 Hz_10ms_modulation_mae_db": 0.863930549256533, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7080780024536261, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05049993999086663, "1000–3000 Hz_40ms_envelope_correlation": 0.9980668408227369, "1000–3000 Hz_40ms_modulation_mae_db": 0.2952159809226534, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3153530917378438, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14026176772839932, "3000–6000 Hz_10ms_envelope_correlation": 0.985221011751292, "3000–6000 Hz_10ms_modulation_mae_db": 1.1438617647099056, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8185617745301845, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08019638280720147, "3000–6000 Hz_40ms_envelope_correlation": 0.9952916198555747, "3000–6000 Hz_40ms_modulation_mae_db": 1.2710295680686956, "mr_stft_db": 5.616003668829855, "band_mae_db": 1.6681012900265766, "rms_gain_error_db": -0.107960892793069, "output_peak": 0.35214309892894274}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9084404859389705, "全帯域_10ms_rms_envelope_nrmse": 0.0722355146928455, "全帯域_10ms_envelope_correlation": 0.995209343115721, "全帯域_10ms_modulation_mae_db": 0.5418515704296477, "全帯域_40ms_log_rms_mae_db": 0.6312150885770852, "全帯域_40ms_rms_envelope_nrmse": 0.03684907100039266, "全帯域_40ms_envelope_correlation": 0.9986794167221049, "全帯域_40ms_modulation_mae_db": 1.047951739115838, "300–1000 Hz_10ms_log_rms_mae_db": 0.7073368053391031, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08039235870376764, "300–1000 Hz_10ms_envelope_correlation": 0.9944628819976393, "300–1000 Hz_10ms_modulation_mae_db": 0.5863834723333929, "300–1000 Hz_40ms_log_rms_mae_db": 0.49428043161431584, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04363685561480253, "300–1000 Hz_40ms_envelope_correlation": 0.9982752301670837, "300–1000 Hz_40ms_modulation_mae_db": 1.1898619650676618, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1094225755267435, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10067306985221311, "1000–3000 Hz_10ms_envelope_correlation": 0.9927547641708694, "1000–3000 Hz_10ms_modulation_mae_db": 0.2534546478688777, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7346625278867938, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.057566426216756686, "1000–3000 Hz_40ms_envelope_correlation": 0.9974979933296055, "1000–3000 Hz_40ms_modulation_mae_db": 0.28698354003701526, "3000–6000 Hz_10ms_log_rms_mae_db": 1.339684619179892, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14301815443457708, "3000–6000 Hz_10ms_envelope_correlation": 0.9847821029245657, "3000–6000 Hz_10ms_modulation_mae_db": 1.0426729355845605, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8820512954013583, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08059140807985787, "3000–6000 Hz_40ms_envelope_correlation": 0.9954916755669093, "3000–6000 Hz_40ms_modulation_mae_db": 0.4226371015387808, "mr_stft_db": 5.6216222076449744, "band_mae_db": 1.7420516672603557, "rms_gain_error_db": -0.06793036642796736, "output_peak": 0.3736234120976638}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9605511965674934, "全帯域_10ms_rms_envelope_nrmse": 0.07120793672131749, "全帯域_10ms_envelope_correlation": 0.9954666954288567, "全帯域_10ms_modulation_mae_db": 0.4810481528253492, "全帯域_40ms_log_rms_mae_db": 0.6508331154461727, "全帯域_40ms_rms_envelope_nrmse": 0.03837548216547394, "全帯域_40ms_envelope_correlation": 0.9987212889650375, "全帯域_40ms_modulation_mae_db": 0.42051319599310993, "300–1000 Hz_10ms_log_rms_mae_db": 0.688758520327995, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08062033919396756, "300–1000 Hz_10ms_envelope_correlation": 0.9945357551397587, "300–1000 Hz_10ms_modulation_mae_db": 0.5368735774423298, "300–1000 Hz_40ms_log_rms_mae_db": 0.4803726024315907, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043200440673396276, "300–1000 Hz_40ms_envelope_correlation": 0.9984544705335184, "300–1000 Hz_40ms_modulation_mae_db": 0.6145199058474244, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1278072354401638, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09133651718852162, "1000–3000 Hz_10ms_envelope_correlation": 0.9941051270022198, "1000–3000 Hz_10ms_modulation_mae_db": 0.5027103046891436, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6787413212329227, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04868108884952316, "1000–3000 Hz_40ms_envelope_correlation": 0.9983031242576723, "1000–3000 Hz_40ms_modulation_mae_db": 0.6876318643407853, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3361900394398254, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14954352992633346, "3000–6000 Hz_10ms_envelope_correlation": 0.9829869565439466, "3000–6000 Hz_10ms_modulation_mae_db": 0.7480412763007012, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8783616532626161, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09093323770459802, "3000–6000 Hz_40ms_envelope_correlation": 0.9935487303403073, "3000–6000 Hz_40ms_modulation_mae_db": 0.5285067478448301, "mr_stft_db": 5.6237334732832975, "band_mae_db": 1.6374923648058994, "rms_gain_error_db": -0.13131579817901998, "output_peak": 0.34828757666167626}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9775424062479624, "全帯域_10ms_rms_envelope_nrmse": 0.07512938121657609, "全帯域_10ms_envelope_correlation": 0.9947971008359923, "全帯域_10ms_modulation_mae_db": 0.19329645864184233, "全帯域_40ms_log_rms_mae_db": 0.6322753268959259, "全帯域_40ms_rms_envelope_nrmse": 0.041524493767078736, "全帯域_40ms_envelope_correlation": 0.9982547930829911, "全帯域_40ms_modulation_mae_db": 0.24546172985102355, "300–1000 Hz_10ms_log_rms_mae_db": 0.7602347297271358, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0845649319566362, "300–1000 Hz_10ms_envelope_correlation": 0.9938499203039518, "300–1000 Hz_10ms_modulation_mae_db": 0.10945304065536177, "300–1000 Hz_40ms_log_rms_mae_db": 0.545933426441354, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.048262332892956616, "300–1000 Hz_40ms_envelope_correlation": 0.9978146304594152, "300–1000 Hz_40ms_modulation_mae_db": 0.11043212031330467, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1139592144276307, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07955110845238951, "1000–3000 Hz_10ms_envelope_correlation": 0.9954865626593525, "1000–3000 Hz_10ms_modulation_mae_db": 0.3848183246217049, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6913122894734727, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.041752127860793076, "1000–3000 Hz_40ms_envelope_correlation": 0.9986763074550566, "1000–3000 Hz_40ms_modulation_mae_db": 0.1400458115278557, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3263356535811406, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1441717083304806, "3000–6000 Hz_10ms_envelope_correlation": 0.984224451066263, "3000–6000 Hz_10ms_modulation_mae_db": 1.1172464865975849, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8882177985444101, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08388266733492412, "3000–6000 Hz_40ms_envelope_correlation": 0.9946048369621286, "3000–6000 Hz_40ms_modulation_mae_db": 0.6249701305768198, "mr_stft_db": 5.612024793126166, "band_mae_db": 1.7024597223499474, "rms_gain_error_db": 0.003656934988601133, "output_peak": 0.3530782115578385}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 108438, "output_samples": 108438, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.43988712898373, "spectral_convergence": 0.1939129672579262, "spectral_convergence_status": "ok", "amplitude_floor": 1.3518293902907786e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.7893159110115455, "spectral_convergence": 0.21256823661706906, "spectral_convergence_status": "ok", "amplitude_floor": 1.2606433835114825e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.600049909392553, "spectral_convergence": 0.21707815689125473, "spectral_convergence_status": "ok", "amplitude_floor": 9.263870496871738e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.1242940814223918e-07, "output_power": 1.1809761190741716e-06, "delta_db": 10.213611912531537, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0005754412253654517, "output_power": 0.0005590745475134276, "delta_db": -0.1253125112363751, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0015091092814657461, "output_power": 0.0015333463147738802, "delta_db": 0.0691956359883775, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00043576714857085195, "output_power": 0.00042061148744947736, "delta_db": -0.15373357073690408, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 9.403622080703858e-05, "output_power": 8.697487862638267e-05, "delta_db": -0.33901335714074365, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.140246786176929e-05, "output_power": 2.9749149656020333e-05, "delta_db": -0.23489223361185887, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2121205040710494e-05, "output_power": 1.2158668794114007e-05, "delta_db": 0.013402305462992243, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.5927373609583984, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.024403979651548675, "pitch": null, "output_rms_dbfs": -25.778870587857536, "output_peak": 0.3653936914519935, "reference_rms_dbfs": -25.754466608205988, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.609750983129277}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 108438, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.0001921686173284563, "log_rms_mae_db": 0.9834991112389778, "rms_envelope_nrmse": 0.08413876851549094, "envelope_correlation": 0.9934638762275622, "rms_gain_error_db": -0.024403965596544022, "reference_mean_power": 0.002662852134818696, "output_mean_power": 0.0026479309428749315}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.762380071709748e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00040104774940998337, "output_power": 0.00042863924625020943, "reference_active": true, "delta_db": 0.2889584905073187}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0004799671480036487, "output_power": 0.0004665434542535945, "reference_active": true, "delta_db": -0.12319412000148175}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.699212681223788e-05, "output_power": 4.0797560686943626e-05, "reference_active": true, "delta_db": -0.6139090404810605}], "active_band_count": 3, "active_band_mae_db": 0.34202055032995365}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.0001703510251571522, "log_rms_mae_db": 0.7045987898120559, "rms_envelope_nrmse": 0.052140738599166875, "envelope_correlation": 0.9972526265343183, "rms_gain_error_db": -0.02440394674259006, "reference_mean_power": 0.002680683564334513, "output_mean_power": 0.0026656624662174467}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.5184553835408784e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00038984224450005464, "output_power": 0.00041928062141322644, "reference_active": true, "delta_db": 0.31615891547843344}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00026155775461828376, "output_power": 0.0002385529444483251, "reference_active": true, "delta_db": -0.39982819035312656}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.971121679142551e-06, "output_power": 5.185709779775255e-06, "reference_active": true, "delta_db": 0.18353814074941105}], "active_band_count": 3, "active_band_mae_db": 0.2998417488603237}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.00018970614972877868, "log_rms_mae_db": 0.7190151323822459, "rms_envelope_nrmse": 0.09310552190523276, "envelope_correlation": 0.9925568220635568, "rms_gain_error_db": 0.0059681901575554756, "reference_mean_power": 0.002063788383698964, "output_mean_power": 0.0020666264461521922}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.5811898835528837e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0004324343375320338, "output_power": 0.0004713035099978278, "reference_active": true, "delta_db": 0.3738050225986883}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00038978360738039315, "output_power": 0.000380583717300825, "reference_active": true, "delta_db": -0.10373366894992922}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.8057706966220433e-05, "output_power": 3.50513260221919e-05, "reference_active": true, "delta_db": -0.35738165495055274}], "active_band_count": 3, "active_band_mae_db": 0.2783067821663901}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.00016763715453010979, "log_rms_mae_db": 0.5265473352806197, "rms_envelope_nrmse": 0.058785038835939704, "envelope_correlation": 0.9967670627794096, "rms_gain_error_db": 0.0059681756943109595, "reference_mean_power": 0.0020776083853168846, "output_mean_power": 0.002080465445710482}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.3894681028634614e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00045948597327573326, "output_power": 0.0004988306763840736, "reference_active": true, "delta_db": 0.3568089503547583}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019541576327049997, "output_power": 0.00018048656795429603, "reference_active": true, "delta_db": -0.3451470660624677}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.955911260526715e-06, "output_power": 4.6683463393353305e-06, "reference_active": true, "delta_db": -0.2596045300572502}], "active_band_count": 3, "active_band_mae_db": 0.32052018215815875}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 7.813214815208366e-05, "log_rms_mae_db": 1.123971196417261, "rms_envelope_nrmse": 0.09337630244739867, "envelope_correlation": 0.994094059167033, "rms_gain_error_db": -0.21340587857563637, "reference_mean_power": 0.0003994594973118105, "output_mean_power": 0.000380305112105348}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 3.1530674989036126e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00010755692941582863, "output_power": 9.988400629769771e-05, "reference_active": true, "delta_db": -0.3214244192789542}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.79686087945957e-05, "output_power": 7.869835689108816e-05, "reference_active": true, "delta_db": -0.4836205874012297}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.8229526666890895e-06, "output_power": 4.155528183970982e-06, "reference_active": true, "delta_db": -0.646867675351538}], "active_band_count": 3, "active_band_mae_db": 0.48397089401057397}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 7.396069876288682e-05, "log_rms_mae_db": 0.7384617524176514, "rms_envelope_nrmse": 0.06307622730853196, "envelope_correlation": 0.9973860255579339, "rms_gain_error_db": -0.2134059071466091, "reference_mean_power": 0.00040213443933265886, "output_mean_power": 0.0003828517861132337}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 2.8654358479348363e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000106294645864879, "output_power": 9.79069366135839e-05, "reference_active": true, "delta_db": -0.3569792711436003}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.178329128126849e-05, "output_power": 4.456273563696755e-05, "reference_active": true, "delta_db": -0.6521780654434779}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.031671442188497e-07, "output_power": 5.104655647721687e-07, "reference_active": true, "delta_db": 1.0248131816708788}], "active_band_count": 3, "active_band_mae_db": 0.6779901727526524}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 2.8330015424642833e-05, "log_rms_mae_db": 1.3591746280614272, "rms_envelope_nrmse": 0.15786396260682242, "envelope_correlation": 0.9819094940784108, "rms_gain_error_db": -0.44520835221441124, "reference_mean_power": 5.860864109462446e-05, "output_mean_power": 5.28981905489838e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 4.4003495001587196e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.626242950468029e-05, "output_power": 1.4131812523844938e-05, "reference_active": true, "delta_db": -0.6098755962695149}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.532829538176888e-06, "output_power": 7.968356392163914e-06, "reference_active": true, "delta_db": -0.778530771552026}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7599215302222477e-06, "output_power": 1.0492525206196884e-06, "reference_active": true, "delta_db": -2.2461328312858444}], "active_band_count": 3, "active_band_mae_db": 1.2115130663691285}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 2.5104708341377363e-05, "log_rms_mae_db": 0.9648107101161061, "rms_envelope_nrmse": 0.09703190088113538, "envelope_correlation": 0.9939072119320812, "rms_gain_error_db": -0.4452084044124599, "reference_mean_power": 5.900110522587256e-05, "output_mean_power": 5.325241484933611e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 3.7677668262047306e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.375501004524296e-05, "output_power": 1.1768128197565664e-05, "reference_active": true, "delta_db": -0.6775352110368364}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.792095126848191e-06, "output_power": 4.893454115392134e-06, "reference_active": true, "delta_db": -0.7322016550012678}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0124260162334744e-07, "output_power": 8.210287202303663e-08, "reference_active": true, "delta_db": -0.9100494731380206}], "active_band_count": 3, "active_band_mae_db": 0.7732621130587084}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.7854111863359243, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "f65436c9ff6164b995c60bd03ff4e8a172044ef38e162190af8acaefb299caf7", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9941466864341533, "standard_deviation": 0.0008230190853408324, "minimum": 0.9927547641708694, "maximum": 0.9954865626593525, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1081417342490991, "standard_deviation": 0.01590268009526979, "minimum": 1.0839718189454572, "maximum": 1.1278072354401638, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4828195176529435, "standard_deviation": 0.23783695459665072, "minimum": 0.1472001352495403, "maximum": 0.863930549256533, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09135711431982393, "standard_deviation": 0.006515350526425623, "minimum": 0.07955110845238951, "maximum": 0.10067306985221311, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978217560162526, "standard_deviation": 0.0004856135633613001, "minimum": 0.9972818965058846, "maximum": 0.9986763074550566, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7103481284016044, "standard_deviation": 0.020985765546077333, "minimum": 0.6787413212329227, "maximum": 0.7384617524176514, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5755930982702058, "standard_deviation": 0.3423999337694456, "minimum": 0.1400458115278557, "maximum": 1.2040594956153619, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05508683787610684, "standard_deviation": 0.007640180580193343, "minimum": 0.041752127860793076, "maximum": 0.06374940142737832, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9848292206063047, "standard_deviation": 0.0024992772664056873, "minimum": 0.9819094940784108, "maximum": 0.9903666993146002, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.3301245099483816, "standard_deviation": 0.017588297006567524, "minimum": 1.3078426008324344, "maximum": 1.3591746280614272, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.0468130843868337, "standard_deviation": 0.1449864284146595, "minimum": 0.7480412763007012, "maximum": 1.2115130663691285, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14277990239984184, "standard_deviation": 0.011922351558370839, "minimum": 0.11637085100756925, "maximum": 0.15786396260682242, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9948685142398503, "standard_deviation": 0.0010662500912470777, "minimum": 0.9935487303403073, "maximum": 0.9969740318364919, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8852499708554051, "standard_deviation": 0.0436412624407638, "minimum": 0.8185617745301845, "maximum": 0.9648107101161061, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.8127254097927459, "standard_deviation": 0.2888648448106402, "minimum": 0.4226371015387808, "maximum": 1.2710295680686956, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08520272729444758, "standard_deviation": 0.008830478564025924, "minimum": 0.06970531969781911, "maximum": 0.09703190088113538, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9938527244385215, "standard_deviation": 0.0009999466144318665, "minimum": 0.9925568220635568, "maximum": 0.9951674278089186, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.7206014920098422, "standard_deviation": 0.029705712155676706, "minimum": 0.688758520327995, "maximum": 0.7713229716097785, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.45524213900804916, "standard_deviation": 0.20982599783996272, "minimum": 0.10945304065536177, "maximum": 0.7331974453695448, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08468120780863961, "standard_deviation": 0.006859148754681841, "minimum": 0.0750459160817981, "maximum": 0.09310552190523276, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9978635023418774, "standard_deviation": 0.0005671382166928131, "minimum": 0.9967670627794096, "maximum": 0.9984544705335184, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.508416616730854, "standard_deviation": 0.024779872115726836, "minimum": 0.4803726024315907, "maximum": 0.545933426441354, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5956226652764712, "standard_deviation": 0.3830996792701778, "minimum": 0.11043212031330467, "maximum": 1.1898619650676618, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.048416771671377284, "standard_deviation": 0.005946241293155002, "minimum": 0.0415916082201098, "maximum": 0.058785038835939704, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.6927836247220547, "standard_deviation": 0.0594211497009814, "minimum": 1.5927373609583984, "maximum": 1.7731808292939186, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.616691186151572, "standard_deviation": 0.006426257753970303, "minimum": 5.609750983129277, "maximum": 5.626527524372556, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3642751338948923, "standard_deviation": 0.017672531968547373, "minimum": 0.34828757666167626, "maximum": 0.4021112513873755, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.060115141300287486, "standard_deviation": 0.06825495403261951, "minimum": -0.13131579817901998, "maximum": 0.061433540210859866, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9947386376845719, "standard_deviation": 0.0008470442087847967, "minimum": 0.9934638762275622, "maximum": 0.9958687332334056, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9599593343248256, "standard_deviation": 0.0300721411937032, "minimum": 0.9084404859389705, "maximum": 1.0015372115198116, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.47223459290667613, "standard_deviation": 0.1888316782710373, "minimum": 0.19329645864184233, "maximum": 0.778296846581485, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07576207399467777, "standard_deviation": 0.005908049224156581, "minimum": 0.06738317221866515, "maximum": 0.08413876851549094, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9982430540828092, "standard_deviation": 0.0004940177011908941, "minimum": 0.9972526265343183, "maximum": 0.9987212889650375, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6505685213134611, "standard_deviation": 0.03171888650712941, "minimum": 0.5989341637251506, "maximum": 0.7045987898120559, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5251208052203653, "standard_deviation": 0.3444050499901792, "minimum": 0.09808709009191308, "maximum": 1.047951739115838, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.04246053215421823, "standard_deviation": 0.005252931940179448, "minimum": 0.03684907100039266, "maximum": 0.052140738599166875, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_falset10_BASIC5000_2951", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 2.416156530380249, "predicted_mos": 2.416156530380249, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 108438, "input_sample_rate": 24000, "input_seconds": 4.51825, "input_float32_sha256": "74dc0e7ebdb242266e186803e3d037933ab4103b775ceb67a5d3e8d6603a64e2", "internal_samples": 72292, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.900053299963474}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9220118149081821, "全帯域_10ms_rms_envelope_nrmse": 0.08000419428024061, "全帯域_10ms_envelope_correlation": 0.9941938221038643, "全帯域_10ms_modulation_mae_db": 0.49157947449285455, "全帯域_40ms_log_rms_mae_db": 0.586756613228924, "全帯域_40ms_rms_envelope_nrmse": 0.04283577258418764, "全帯域_40ms_envelope_correlation": 0.9983122224860798, "全帯域_40ms_modulation_mae_db": 0.8120515958536152, "300–1000 Hz_10ms_log_rms_mae_db": 0.7136047996856453, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09237900662612951, "300–1000 Hz_10ms_envelope_correlation": 0.9927584550969901, "300–1000 Hz_10ms_modulation_mae_db": 0.4370456684086681, "300–1000 Hz_40ms_log_rms_mae_db": 0.48925601890511927, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05174346124725515, "300–1000 Hz_40ms_envelope_correlation": 0.9976943162740308, "300–1000 Hz_40ms_modulation_mae_db": 0.9689348324866275, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0696994990419229, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08156356198887339, "1000–3000 Hz_10ms_envelope_correlation": 0.9953177702886098, "1000–3000 Hz_10ms_modulation_mae_db": 0.8501326664530628, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6360321533336316, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04579296056990943, "1000–3000 Hz_40ms_envelope_correlation": 0.9985000654103494, "1000–3000 Hz_40ms_modulation_mae_db": 0.5991240490686339, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3158307204088926, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14351279283101567, "3000–6000 Hz_10ms_envelope_correlation": 0.9852075087338659, "3000–6000 Hz_10ms_modulation_mae_db": 1.2475524221916758, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8196936331458448, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08646629646387309, "3000–6000 Hz_40ms_envelope_correlation": 0.9953433180034897, "3000–6000 Hz_40ms_modulation_mae_db": 0.8116301372319207, "mr_stft_db": 5.580897776401407, "band_mae_db": 1.6912425748916404, "rms_gain_error_db": -0.11149404614066662, "output_peak": 0.3307326767700523}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9955140907000938, "全帯域_10ms_rms_envelope_nrmse": 0.07522754569187089, "全帯域_10ms_envelope_correlation": 0.99480216209881, "全帯域_10ms_modulation_mae_db": 0.5536256803169407, "全帯域_40ms_log_rms_mae_db": 0.6374929225438455, "全帯域_40ms_rms_envelope_nrmse": 0.036404465345165664, "全帯域_40ms_envelope_correlation": 0.9987132246533579, "全帯域_40ms_modulation_mae_db": 0.9117378138956287, "300–1000 Hz_10ms_log_rms_mae_db": 0.7128938932296899, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08271070234856451, "300–1000 Hz_10ms_envelope_correlation": 0.9941163208937164, "300–1000 Hz_10ms_modulation_mae_db": 0.6163887967288434, "300–1000 Hz_40ms_log_rms_mae_db": 0.47751836422301047, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04154926106151456, "300–1000 Hz_40ms_envelope_correlation": 0.9984073851395132, "300–1000 Hz_40ms_modulation_mae_db": 1.0193613378213235, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1058285122977896, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09740894080134846, "1000–3000 Hz_10ms_envelope_correlation": 0.9934593317968328, "1000–3000 Hz_10ms_modulation_mae_db": 0.410349668415682, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7003045325267002, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0583040936808063, "1000–3000 Hz_40ms_envelope_correlation": 0.9977618469610594, "1000–3000 Hz_40ms_modulation_mae_db": 0.34739783056330387, "3000–6000 Hz_10ms_log_rms_mae_db": 1.253228940015243, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14424007439683267, "3000–6000 Hz_10ms_envelope_correlation": 0.9847580370537325, "3000–6000 Hz_10ms_modulation_mae_db": 1.118037019674129, "3000–6000 Hz_40ms_log_rms_mae_db": 0.784896893304709, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08347624788209364, "3000–6000 Hz_40ms_envelope_correlation": 0.9954065097575914, "3000–6000 Hz_40ms_modulation_mae_db": 0.8004159067115925, "mr_stft_db": 5.584070348608395, "band_mae_db": 1.7212800667011847, "rms_gain_error_db": -0.06954566037921553, "output_peak": 0.3672125826688718}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9572579528804417, "全帯域_10ms_rms_envelope_nrmse": 0.07048782388849087, "全帯域_10ms_envelope_correlation": 0.9954691905849545, "全帯域_10ms_modulation_mae_db": 0.6188086611275131, "全帯域_40ms_log_rms_mae_db": 0.5974569871961971, "全帯域_40ms_rms_envelope_nrmse": 0.035810509330439826, "全帯域_40ms_envelope_correlation": 0.9987819327308073, "全帯域_40ms_modulation_mae_db": 0.6837737749336661, "300–1000 Hz_10ms_log_rms_mae_db": 0.6941755288154475, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0782015878967042, "300–1000 Hz_10ms_envelope_correlation": 0.9947811002072192, "300–1000 Hz_10ms_modulation_mae_db": 0.6501901418164556, "300–1000 Hz_40ms_log_rms_mae_db": 0.5022804284695188, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04193917732489342, "300–1000 Hz_40ms_envelope_correlation": 0.9984282615675217, "300–1000 Hz_40ms_modulation_mae_db": 0.7299730157408245, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0631462784180103, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08343989574845426, "1000–3000 Hz_10ms_envelope_correlation": 0.9951250683315533, "1000–3000 Hz_10ms_modulation_mae_db": 0.5346615981923107, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6355523229545283, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0449234630801497, "1000–3000 Hz_40ms_envelope_correlation": 0.9986061727766838, "1000–3000 Hz_40ms_modulation_mae_db": 0.3240531299641259, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3193300073141407, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1483763110252743, "3000–6000 Hz_10ms_envelope_correlation": 0.9834725498857926, "3000–6000 Hz_10ms_modulation_mae_db": 0.8758054162299448, "3000–6000 Hz_40ms_log_rms_mae_db": 0.795713378595624, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0850375245304837, "3000–6000 Hz_40ms_envelope_correlation": 0.9947569028408221, "3000–6000 Hz_40ms_modulation_mae_db": 0.48850210776962966, "mr_stft_db": 5.568736060481452, "band_mae_db": 1.724990681523122, "rms_gain_error_db": -0.07675466115367394, "output_peak": 0.3630840963085141}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8990904875523786, "全帯域_10ms_rms_envelope_nrmse": 0.0643373092021315, "全帯域_10ms_envelope_correlation": 0.9961874854105951, "全帯域_10ms_modulation_mae_db": 0.4411837192935906, "全帯域_40ms_log_rms_mae_db": 0.5646243686929634, "全帯域_40ms_rms_envelope_nrmse": 0.032250797374191904, "全帯域_40ms_envelope_correlation": 0.998960042473265, "全帯域_40ms_modulation_mae_db": 0.39268093963084155, "300–1000 Hz_10ms_log_rms_mae_db": 0.6302532823288869, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07007731049703465, "300–1000 Hz_10ms_envelope_correlation": 0.9957809955892348, "300–1000 Hz_10ms_modulation_mae_db": 0.4669240488678364, "300–1000 Hz_40ms_log_rms_mae_db": 0.4071876249708753, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03494915957875463, "300–1000 Hz_40ms_envelope_correlation": 0.9988545709179133, "300–1000 Hz_40ms_modulation_mae_db": 0.46764052947742635, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0925677338304864, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09306412257911968, "1000–3000 Hz_10ms_envelope_correlation": 0.9942626890935953, "1000–3000 Hz_10ms_modulation_mae_db": 0.51959094489755, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7043379283994666, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05617023410727255, "1000–3000 Hz_40ms_envelope_correlation": 0.998172589245147, "1000–3000 Hz_40ms_modulation_mae_db": 0.5288251639867799, "3000–6000 Hz_10ms_log_rms_mae_db": 1.290310027826565, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14084715235921702, "3000–6000 Hz_10ms_envelope_correlation": 0.9849509432037082, "3000–6000 Hz_10ms_modulation_mae_db": 0.5269769979316807, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8054871075007224, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07713718097158523, "3000–6000 Hz_40ms_envelope_correlation": 0.9955110029195738, "3000–6000 Hz_40ms_modulation_mae_db": 0.455398275853887, "mr_stft_db": 5.579448676232066, "band_mae_db": 1.6730627500409325, "rms_gain_error_db": -0.03535479078459427, "output_peak": 0.3623933323285966}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9482939830517492, "全帯域_10ms_rms_envelope_nrmse": 0.07603340058850971, "全帯域_10ms_envelope_correlation": 0.9946785244367582, "全帯域_10ms_modulation_mae_db": 0.41931277278992124, "全帯域_40ms_log_rms_mae_db": 0.6470707498443452, "全帯域_40ms_rms_envelope_nrmse": 0.04153501404314797, "全帯域_40ms_envelope_correlation": 0.9982574571648438, "全帯域_40ms_modulation_mae_db": 0.24203580096914581, "300–1000 Hz_10ms_log_rms_mae_db": 0.6788336201335421, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08269227895215096, "300–1000 Hz_10ms_envelope_correlation": 0.9941677328720633, "300–1000 Hz_10ms_modulation_mae_db": 0.34510512993006043, "300–1000 Hz_40ms_log_rms_mae_db": 0.46203861815778186, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.045790460165116176, "300–1000 Hz_40ms_envelope_correlation": 0.9980653395749374, "300–1000 Hz_40ms_modulation_mae_db": 0.23146688061006515, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0660702784428107, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1057472553531505, "1000–3000 Hz_10ms_envelope_correlation": 0.9921175379016575, "1000–3000 Hz_10ms_modulation_mae_db": 0.7094497730022988, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6790080601253861, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06785335991010276, "1000–3000 Hz_40ms_envelope_correlation": 0.9966693600944083, "1000–3000 Hz_40ms_modulation_mae_db": 0.26899840956734006, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3285403837500191, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14637006382346296, "3000–6000 Hz_10ms_envelope_correlation": 0.9845425213689684, "3000–6000 Hz_10ms_modulation_mae_db": 1.0094643477943486, "3000–6000 Hz_40ms_log_rms_mae_db": 0.861277719193443, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0943778993564186, "3000–6000 Hz_40ms_envelope_correlation": 0.9940991805242123, "3000–6000 Hz_40ms_modulation_mae_db": 0.8007055769150226, "mr_stft_db": 5.561295203967711, "band_mae_db": 1.6735887958271718, "rms_gain_error_db": 0.011708875277098709, "output_peak": 0.3703899347451195}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9360025867405632, "全帯域_10ms_rms_envelope_nrmse": 0.08281340266487046, "全帯域_10ms_envelope_correlation": 0.9937352637954058, "全帯域_10ms_modulation_mae_db": 0.38639456110501813, "全帯域_40ms_log_rms_mae_db": 0.6368848993801614, "全帯域_40ms_rms_envelope_nrmse": 0.04679466114685358, "全帯域_40ms_envelope_correlation": 0.9978993008032676, "全帯域_40ms_modulation_mae_db": 1.0447674651761334, "300–1000 Hz_10ms_log_rms_mae_db": 0.7008561707553282, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09392690214446814, "300–1000 Hz_10ms_envelope_correlation": 0.992431585953154, "300–1000 Hz_10ms_modulation_mae_db": 0.2911939736614569, "300–1000 Hz_40ms_log_rms_mae_db": 0.49735799754198934, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05425032635189192, "300–1000 Hz_40ms_envelope_correlation": 0.9973259803608576, "300–1000 Hz_40ms_modulation_mae_db": 1.116142093062695, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0755576228721404, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09103112982186984, "1000–3000 Hz_10ms_envelope_correlation": 0.994312470910682, "1000–3000 Hz_10ms_modulation_mae_db": 0.8697196917919827, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6672697929532951, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0495351104749625, "1000–3000 Hz_40ms_envelope_correlation": 0.9984481447817498, "1000–3000 Hz_40ms_modulation_mae_db": 0.6521379712815889, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2133688123724775, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15145554767713537, "3000–6000 Hz_10ms_envelope_correlation": 0.9836792595171231, "3000–6000 Hz_10ms_modulation_mae_db": 1.0100825534132751, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7610358968246954, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1018448961665638, "3000–6000 Hz_40ms_envelope_correlation": 0.9932379669528132, "3000–6000 Hz_40ms_modulation_mae_db": 0.7467394176401202, "mr_stft_db": 5.57344025672727, "band_mae_db": 1.6928905647407315, "rms_gain_error_db": -0.09245412346897222, "output_peak": 0.340450370530635}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0000521645366998, "全帯域_10ms_rms_envelope_nrmse": 0.07726252197496113, "全帯域_10ms_envelope_correlation": 0.9944927917997723, "全帯域_10ms_modulation_mae_db": 0.22946997707379935, "全帯域_40ms_log_rms_mae_db": 0.6599190872747955, "全帯域_40ms_rms_envelope_nrmse": 0.04303845554123629, "全帯域_40ms_envelope_correlation": 0.9981456852829964, "全帯域_40ms_modulation_mae_db": 0.4195571430761624, "300–1000 Hz_10ms_log_rms_mae_db": 0.7545586390534171, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08555288734444344, "300–1000 Hz_10ms_envelope_correlation": 0.9937126957829299, "300–1000 Hz_10ms_modulation_mae_db": 0.19826833344466413, "300–1000 Hz_40ms_log_rms_mae_db": 0.5304478041435934, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05010313877682476, "300–1000 Hz_40ms_envelope_correlation": 0.9976479753358101, "300–1000 Hz_40ms_modulation_mae_db": 0.17362894709383406, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0844780267537268, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09455930331679671, "1000–3000 Hz_10ms_envelope_correlation": 0.99425836956038, "1000–3000 Hz_10ms_modulation_mae_db": 0.7496312720756251, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7005725992168814, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06159818141542495, "1000–3000 Hz_40ms_envelope_correlation": 0.9979020142784165, "1000–3000 Hz_40ms_modulation_mae_db": 0.5614999431184479, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3095859408954036, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14561759974746588, "3000–6000 Hz_10ms_envelope_correlation": 0.9842359401508933, "3000–6000 Hz_10ms_modulation_mae_db": 0.6789594921579147, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7903914231268044, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08686263330333813, "3000–6000 Hz_40ms_envelope_correlation": 0.9946442687057695, "3000–6000 Hz_40ms_modulation_mae_db": 0.40082017055151087, "mr_stft_db": 5.579073122602168, "band_mae_db": 1.7260455299575834, "rms_gain_error_db": -0.047626242709675415, "output_peak": 0.3580966577112192}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9657032812156531, "全帯域_10ms_rms_envelope_nrmse": 0.07931131002773242, "全帯域_10ms_envelope_correlation": 0.9942010447338118, "全帯域_10ms_modulation_mae_db": 0.4407410651613655, "全帯域_40ms_log_rms_mae_db": 0.6560686174937815, "全帯域_40ms_rms_envelope_nrmse": 0.04137062999633359, "全帯域_40ms_envelope_correlation": 0.9983008995903732, "全帯域_40ms_modulation_mae_db": 0.3857922996396333, "300–1000 Hz_10ms_log_rms_mae_db": 0.6727863391853024, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09121874911721899, "300–1000 Hz_10ms_envelope_correlation": 0.9928355086674625, "300–1000 Hz_10ms_modulation_mae_db": 0.4688505817200534, "300–1000 Hz_40ms_log_rms_mae_db": 0.4688765083931839, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05037378774153006, "300–1000 Hz_40ms_envelope_correlation": 0.9976519715538609, "300–1000 Hz_40ms_modulation_mae_db": 0.4946017283295981, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0900306873655379, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08125478945969235, "1000–3000 Hz_10ms_envelope_correlation": 0.9952849299227993, "1000–3000 Hz_10ms_modulation_mae_db": 0.3527932456615612, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6584511974009077, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0490025616618229, "1000–3000 Hz_40ms_envelope_correlation": 0.9981772957148711, "1000–3000 Hz_40ms_modulation_mae_db": 0.21956042548366284, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2558106988001732, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13620818460213494, "3000–6000 Hz_10ms_envelope_correlation": 0.9863958837551696, "3000–6000 Hz_10ms_modulation_mae_db": 0.9258621675956952, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7718242303101484, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08013396005227715, "3000–6000 Hz_40ms_envelope_correlation": 0.9956662933538962, "3000–6000 Hz_40ms_modulation_mae_db": 0.7832617019201091, "mr_stft_db": 5.571936039505377, "band_mae_db": 1.6492206345617473, "rms_gain_error_db": -0.05557902939494624, "output_peak": 0.3660516764011972}, "full_scale": {"sample_count": 108438, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 108438, "output_samples": 108438, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.399434780326743, "spectral_convergence": 0.193608338531782, "spectral_convergence_status": "ok", "amplitude_floor": 1.3518293902907786e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.746338440035055, "spectral_convergence": 0.21184658474930876, "spectral_convergence_status": "ok", "amplitude_floor": 1.2606433835114825e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.596920108842424, "spectral_convergence": 0.211930999881449, "spectral_convergence_status": "ok", "amplitude_floor": 9.263870496871738e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.1242940814223918e-07, "output_power": 1.4220379190990193e-06, "delta_db": 11.020312527198604, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0005754412253654517, "output_power": 0.0005674834351837017, "delta_db": -0.060477830826453846, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0015091092814657461, "output_power": 0.0014622627702561902, "delta_db": -0.13695267313413373, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00043576714857085195, "output_power": 0.00043037616550378196, "delta_db": -0.05406274906591423, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 9.403622080703858e-05, "output_power": 8.676013756676323e-05, "delta_db": -0.3497493511582744, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.140246786176929e-05, "output_power": 3.0101872029621285e-05, "delta_db": -0.18370274689256982, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2121205040710494e-05, "output_power": 1.2214897088460244e-05, "delta_db": 0.0334401459655335, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.6912425748916404, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.11149404614066662, "pitch": null, "output_rms_dbfs": -25.865960654346654, "output_peak": 0.3307326767700523, "reference_rms_dbfs": -25.754466608205988, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.580897776401407}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 108438, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.0001921686173284563, "log_rms_mae_db": 0.9220118149081821, "rms_envelope_nrmse": 0.08000419428024061, "envelope_correlation": 0.9941938221038643, "rms_gain_error_db": -0.11149404027139254, "reference_mean_power": 0.002662852134818696, "output_mean_power": 0.002595360240514368}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.762380071709748e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00040104774940998337, "output_power": 0.00037363070398705974, "reference_active": true, "delta_db": -0.307535253186237}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0004799671480036487, "output_power": 0.0004416904504870726, "reference_active": true, "delta_db": -0.36093502772926334}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.699212681223788e-05, "output_power": 3.9029976240494126e-05, "reference_active": true, "delta_db": -0.8062681425630633}], "active_band_count": 3, "active_band_mae_db": 0.49157947449285455}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.0001703510251571522, "log_rms_mae_db": 0.586756613228924, "rms_envelope_nrmse": 0.04283577258418764, "envelope_correlation": 0.9983122224860798, "rms_gain_error_db": -0.11149401128151726, "reference_mean_power": 0.002680683564334513, "output_mean_power": 0.002612739737119961}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.5184553835408784e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00038984224450005464, "output_power": 0.00035853384228914063, "reference_active": true, "delta_db": -0.36358743478676764}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00026155775461828376, "output_power": 0.00024109768244534696, "reference_active": true, "delta_db": -0.3537456470462659}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.971121679142551e-06, "output_power": 3.346356630115536e-06, "reference_active": true, "delta_db": -1.7188217057278121}], "active_band_count": 3, "active_band_mae_db": 0.8120515958536152}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 0.00018970614972877868, "log_rms_mae_db": 0.7136047996856453, "rms_envelope_nrmse": 0.09237900662612951, "envelope_correlation": 0.9927584550969901, "rms_gain_error_db": -0.12520505276187793, "reference_mean_power": 0.002063788383698964, "output_mean_power": 0.002005139804543854}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.5811898835528837e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0004324343375320338, "output_power": 0.00039621064518286045, "reference_active": true, "delta_db": -0.3799403212866947}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00038978360738039315, "output_power": 0.00035899831696855657, "reference_active": true, "delta_db": -0.35731158057089707}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.8057706966220433e-05, "output_power": 3.334679559963453e-05, "reference_active": true, "delta_db": -0.5738851033684125}], "active_band_count": 3, "active_band_mae_db": 0.4370456684086681}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 0.00016763715453010979, "log_rms_mae_db": 0.48925601890511927, "rms_envelope_nrmse": 0.05174346124725515, "envelope_correlation": 0.9976943162740308, "rms_gain_error_db": -0.12520506655962435, "reference_mean_power": 0.0020776083853168846, "output_mean_power": 0.002018567064008332}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.3894681028634614e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00045948597327573326, "output_power": 0.0004132018930398728, "reference_active": true, "delta_db": -0.4610995569522104}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019541576327049997, "output_power": 0.00018098174223832352, "reference_active": true, "delta_db": -0.33324828613665974}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.955911260526715e-06, "output_power": 3.047037898654756e-06, "reference_active": true, "delta_db": -2.1124566543710124}], "active_band_count": 3, "active_band_mae_db": 0.9689348324866275}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 7.813214815208366e-05, "log_rms_mae_db": 1.0696994990419229, "rms_envelope_nrmse": 0.08156356198887339, "envelope_correlation": 0.9953177702886098, "rms_gain_error_db": -0.10102568112007022, "reference_mean_power": 0.0003994594973118105, "output_mean_power": 0.0003902745063174626}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 3.1530674989036126e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00010755692941582863, "output_power": 0.00010410780016072057, "reference_active": true, "delta_db": -0.14155125532853136}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.79686087945957e-05, "output_power": 7.65973138446943e-05, "reference_active": true, "delta_db": -0.6011418391746455}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.8229526666890895e-06, "output_power": 3.180845017648353e-06, "reference_active": true, "delta_db": -1.8077049048560117}], "active_band_count": 3, "active_band_mae_db": 0.8501326664530628}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 7.396069876288682e-05, "log_rms_mae_db": 0.6360321533336316, "rms_envelope_nrmse": 0.04579296056990943, "envelope_correlation": 0.9985000654103494, "rms_gain_error_db": -0.10102570732275913, "reference_mean_power": 0.00040213443933265886, "output_mean_power": 0.00039288793956098855}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 2.8654358479348363e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000106294645864879, "output_power": 0.00010167222713058405, "reference_active": true, "delta_db": -0.19309052475828511}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.178329128126849e-05, "output_power": 4.470213667929972e-05, "reference_active": true, "delta_db": -0.6386136809099352}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.031671442188497e-07, "output_power": 3.2278871149142155e-07, "reference_active": true, "delta_db": -0.9656679415376813}], "active_band_count": 3, "active_band_mae_db": 0.5991240490686339}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 902, "rms_floor": 2.8330015424642833e-05, "log_rms_mae_db": 1.3158307204088926, "rms_envelope_nrmse": 0.14351279283101567, "envelope_correlation": 0.9852075087338659, "rms_gain_error_db": -0.41582604856388755, "reference_mean_power": 5.860864109462446e-05, "output_mean_power": 5.325728797444289e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 4.4003495001587196e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.626242950468029e-05, "output_power": 1.5076129615657968e-05, "reference_active": true, "delta_db": -0.32895564367827534}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.532829538176888e-06, "output_power": 7.700730676600158e-06, "reference_active": true, "delta_db": -0.9268989247884276}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7599215302222477e-06, "output_power": 9.926886000509583e-07, "reference_active": true, "delta_db": -2.486802698108325}], "active_band_count": 3, "active_band_mae_db": 1.2475524221916758}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108360, "uncovered_tail_samples": 78, "metrics": {"frame_count": 896, "rms_floor": 2.5104708341377363e-05, "log_rms_mae_db": 0.8196936331458448, "rms_envelope_nrmse": 0.08646629646387309, "envelope_correlation": 0.9953433180034897, "rms_gain_error_db": -0.41582612503329236, "reference_mean_power": 5.900110522587256e-05, "output_mean_power": 5.361391661382863e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 3.7677668262047306e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.375501004524296e-05, "output_power": 1.263721571452814e-05, "reference_active": true, "delta_db": -0.3680951302370079}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.792095126848191e-06, "output_power": 4.561370422187072e-06, "reference_active": true, "delta_db": -1.0374034382156483}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0124260162334744e-07, "output_power": 7.9877435339799e-08, "reference_active": true, "delta_db": -1.0293918432431057}], "active_band_count": 3, "active_band_mae_db": 0.8116301372319207}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.7882674845249289, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "550dbad1a92b2d7666cd5fb755681f81310eae2d13bc9a672b1f7299a1de44b3", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9942672709757637, "standard_deviation": 0.0010791038684340845, "minimum": 0.9921175379016575, "maximum": 0.9953177702886098, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.080922329877803, "standard_deviation": 0.014846076744441347, "minimum": 1.0631462784180103, "maximum": 1.1058285122977896, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6245411075612592, "standard_deviation": 0.19736798706682704, "minimum": 0.3527932456615612, "maximum": 0.8697196917919827, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09100862488366315, "standard_deviation": 0.00859116112086527, "minimum": 0.08125478945969235, "maximum": 0.1057472553531505, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9980296861578357, "standard_deviation": 0.0006221432884438087, "minimum": 0.9966693600944083, "maximum": 0.9986061727766838, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6726910733638496, "standard_deviation": 0.02812380261501963, "minimum": 0.6355523229545283, "maximum": 0.7043379283994666, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.4376996153792354, "standard_deviation": 0.16595471931061, "minimum": 0.21956042548366284, "maximum": 0.6521379712815889, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.054147495612556384, "standard_deviation": 0.008171008746498011, "minimum": 0.0449234630801497, "maximum": 0.06785335991010276, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9846553304586567, "standard_deviation": 0.0009237084150885027, "minimum": 0.9834725498857926, "maximum": 0.9863958837551696, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2857506914228642, "standard_deviation": 0.040787685330904266, "minimum": 1.2133688123724775, "maximum": 1.3285403837500191, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.924092552123583, "standard_deviation": 0.23208653784950498, "minimum": 0.5269769979316807, "maximum": 1.2475524221916758, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14457846580781736, "standard_deviation": 0.004648225180211682, "minimum": 0.13620818460213494, "maximum": 0.15145554767713537, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.994833180382271, "standard_deviation": 0.0008338752170057464, "minimum": 0.9932379669528132, "maximum": 0.9956662933538962, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7987900352502488, "standard_deviation": 0.03119540562671318, "minimum": 0.7610358968246954, "maximum": 0.861277719193443, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6609341618242242, "standard_deviation": 0.17875128521889497, "minimum": 0.40082017055151087, "maximum": 0.8116301372319207, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08691707984082916, "standard_deviation": 0.007889766308949503, "minimum": 0.07713718097158523, "maximum": 0.1018448961665638, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9938230493828463, "standard_deviation": 0.0011347231045013167, "minimum": 0.992431585953154, "maximum": 0.9957809955892348, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.6947452841484074, "standard_deviation": 0.036243133208617065, "minimum": 0.6302532823288869, "maximum": 0.7545586390534171, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4342458343222548, "standard_deviation": 0.15407626912444003, "minimum": 0.19826833344466413, "maximum": 0.6501901418164556, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.0845949281158393, "standard_deviation": 0.00802920303048223, "minimum": 0.07007731049703465, "maximum": 0.09392690214446814, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9980094750905556, "standard_deviation": 0.0005176876188497572, "minimum": 0.9973259803608576, "maximum": 0.9988545709179133, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.47937042060063406, "standard_deviation": 0.036212360193122094, "minimum": 0.4071876249708753, "maximum": 0.5304478041435934, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6502186705777993, "standard_deviation": 0.36279351236285334, "minimum": 0.17362894709383406, "maximum": 1.116142093062695, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04633734653097259, "standard_deviation": 0.006487074141718345, "minimum": 0.03494915957875463, "maximum": 0.05425032635189192, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.6940401997805141, "standard_deviation": 0.02828563225152824, "minimum": 1.6492206345617473, "maximum": 1.7260455299575834, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.574862185565731, "standard_deviation": 0.007484871611940472, "minimum": 5.561295203967711, "maximum": 5.584070348608395, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3573014159330257, "standard_deviation": 0.014121729230793821, "minimum": 0.3307326767700523, "maximum": 0.3703899347451195, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.05963745984433069, "standard_deviation": 0.037792474154365326, "minimum": -0.11149404614066662, "maximum": 0.011708875277098709, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9947200356204966, "standard_deviation": 0.0007829228653072238, "minimum": 0.9937352637954058, "maximum": 0.9961874854105951, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9529907951982202, "standard_deviation": 0.03459648771365547, "minimum": 0.8990904875523786, "maximum": 1.0000521645366998, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4476394889201254, "standard_deviation": 0.1163143682034571, "minimum": 0.22946997707379935, "maximum": 0.6188086611275131, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07568468853985094, "standard_deviation": 0.0058702596243123744, "minimum": 0.0643373092021315, "maximum": 0.08281340266487046, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9984213456481239, "standard_deviation": 0.00036000092788151654, "minimum": 0.9978993008032676, "maximum": 0.998960042473265, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6232842807068767, "standard_deviation": 0.03548014554437022, "minimum": 0.5646243686929634, "maximum": 0.6599190872747955, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6115496041468533, "standard_deviation": 0.2916650389459513, "minimum": 0.24203580096914581, "maximum": 1.0447674651761334, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.04000503817019456, "standard_deviation": 0.004754032466088709, "minimum": 0.032250797374191904, "maximum": 0.04679466114685358, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "language": "ja", "style": "normal", "speaker": "jvs_jvs004", "source_utterance_id": "VOICEACTRESS100_058", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 144000, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs004_parallel100_VOICEACTRESS100_058.wav", "source_file_sha256": "f174986b46a7edcd627989f72ecc2094b30b42faef17b147c9dfab51f78b4540", "decoded_pcm_sha256": "2ef6c4cb56367ba092ec8b5eabdf3931b3461b28c4f8cf68e4f2865f5f10d37b", "original_source_sha256": "f174986b46a7edcd627989f72ecc2094b30b42faef17b147c9dfab51f78b4540", "corpus_entry_id": "jvs_jvs004_parallel100_VOICEACTRESS100_058"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 4.027536392211914, "predicted_mos": 4.027536392211914, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "25b43d4fe9395220290001653c7ebbe93efc0ecea91427843ae82409254e19b1", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.141500999685377}, "waveform_sha256": "ecff16cb4b0e207fa55b6b5b0abcda6003f5762bce5962f5029d6f049ba2e568"}, "rows": [{"case": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 1.726351022720337, "predicted_mos": 1.726351022720337, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "4dfa5aff75bc3d8b01f84d5cce29bc7773a468bccf38774bdddb78128eddc9da", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.305418800096959}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9315370829212671, "全帯域_10ms_rms_envelope_nrmse": 0.051693232467442805, "全帯域_10ms_envelope_correlation": 0.9971954814779149, "全帯域_10ms_modulation_mae_db": 0.41678015462287066, "全帯域_40ms_log_rms_mae_db": 0.5116617492719032, "全帯域_40ms_rms_envelope_nrmse": 0.026753457254298018, "全帯域_40ms_envelope_correlation": 0.9992275494247637, "全帯域_40ms_modulation_mae_db": 0.34589150528069884, "300–1000 Hz_10ms_log_rms_mae_db": 1.1365509885149694, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06383961023070336, "300–1000 Hz_10ms_envelope_correlation": 0.9966277164996011, "300–1000 Hz_10ms_modulation_mae_db": 0.8372726632455678, "300–1000 Hz_40ms_log_rms_mae_db": 0.7351398843440036, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03507992262888125, "300–1000 Hz_40ms_envelope_correlation": 0.9989410559869288, "300–1000 Hz_40ms_modulation_mae_db": 0.9530806987723741, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4672327648170134, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15771610259563876, "1000–3000 Hz_10ms_envelope_correlation": 0.9835703868414086, "1000–3000 Hz_10ms_modulation_mae_db": 0.5828082133275129, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0679743349209412, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09223510795440695, "1000–3000 Hz_40ms_envelope_correlation": 0.9956445072559341, "1000–3000 Hz_40ms_modulation_mae_db": 1.217159182234351, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2545480398102624, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14464679117014592, "3000–6000 Hz_10ms_envelope_correlation": 0.9861605561836949, "3000–6000 Hz_10ms_modulation_mae_db": 0.5091776406922336, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8150399522905027, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09978432500578513, "3000–6000 Hz_40ms_envelope_correlation": 0.9931150303518009, "3000–6000 Hz_40ms_modulation_mae_db": 0.3302134953411204, "mr_stft_db": 5.568922089614408, "band_mae_db": 0.22192980125645817, "rms_gain_error_db": -0.05339151548452438, "output_peak": 0.28244664107237416}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8858283549790755, "全帯域_10ms_rms_envelope_nrmse": 0.05334251970294716, "全帯域_10ms_envelope_correlation": 0.9972045904407417, "全帯域_10ms_modulation_mae_db": 0.6425622034771262, "全帯域_40ms_log_rms_mae_db": 0.5258574056870038, "全帯域_40ms_rms_envelope_nrmse": 0.03179684758841035, "全帯域_40ms_envelope_correlation": 0.9991177277020348, "全帯域_40ms_modulation_mae_db": 0.7022868667613923, "300–1000 Hz_10ms_log_rms_mae_db": 1.0980082190268, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06272049470343595, "300–1000 Hz_10ms_envelope_correlation": 0.9968960999262032, "300–1000 Hz_10ms_modulation_mae_db": 1.2434102930483346, "300–1000 Hz_40ms_log_rms_mae_db": 0.7083533539901659, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03538287544155167, "300–1000 Hz_40ms_envelope_correlation": 0.9990931165882463, "300–1000 Hz_40ms_modulation_mae_db": 1.515889048287925, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4744773430766955, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.14007258864132008, "1000–3000 Hz_10ms_envelope_correlation": 0.9892501846698829, "1000–3000 Hz_10ms_modulation_mae_db": 1.5052811193225935, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0775886831666246, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10326477760201425, "1000–3000 Hz_40ms_envelope_correlation": 0.995891959581781, "1000–3000 Hz_40ms_modulation_mae_db": 1.7438437392022357, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2553083499172493, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.20454524101720248, "3000–6000 Hz_10ms_envelope_correlation": 0.9744939832414824, "3000–6000 Hz_10ms_modulation_mae_db": 2.170418263255421, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8338308016809989, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13246381496099474, "3000–6000 Hz_40ms_envelope_correlation": 0.9917925902473186, "3000–6000 Hz_40ms_modulation_mae_db": 2.368605627676801, "mr_stft_db": 5.568124854196441, "band_mae_db": 0.3729806875917494, "rms_gain_error_db": -0.1367272729407908, "output_peak": 0.28392376384758033}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9327525601580096, "全帯域_10ms_rms_envelope_nrmse": 0.05565506530324218, "全帯域_10ms_envelope_correlation": 0.996838802756841, "全帯域_10ms_modulation_mae_db": 0.4642128605446085, "全帯域_40ms_log_rms_mae_db": 0.5565273508136043, "全帯域_40ms_rms_envelope_nrmse": 0.0318792293473368, "全帯域_40ms_envelope_correlation": 0.9990035850281109, "全帯域_40ms_modulation_mae_db": 0.5151746271668034, "300–1000 Hz_10ms_log_rms_mae_db": 1.022464415311564, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06557506751521572, "300–1000 Hz_10ms_envelope_correlation": 0.9965099858606918, "300–1000 Hz_10ms_modulation_mae_db": 1.0710130078553524, "300–1000 Hz_40ms_log_rms_mae_db": 0.6756640224286403, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03616020766626794, "300–1000 Hz_40ms_envelope_correlation": 0.9989812864989998, "300–1000 Hz_40ms_modulation_mae_db": 0.9333610270897253, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4917416667701664, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15296835339467477, "1000–3000 Hz_10ms_envelope_correlation": 0.9859686725298614, "1000–3000 Hz_10ms_modulation_mae_db": 0.811659679435008, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1373771064871894, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11243477479215715, "1000–3000 Hz_40ms_envelope_correlation": 0.9939415822474751, "1000–3000 Hz_40ms_modulation_mae_db": 0.37196223757637387, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2473902946554891, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16975996646779357, "3000–6000 Hz_10ms_envelope_correlation": 0.9806664356972185, "3000–6000 Hz_10ms_modulation_mae_db": 0.3563093006605896, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7741860740415161, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08332780110882966, "3000–6000 Hz_40ms_envelope_correlation": 0.9953232371978954, "3000–6000 Hz_40ms_modulation_mae_db": 0.44347482231294083, "mr_stft_db": 5.563514129583034, "band_mae_db": 0.23774376790640228, "rms_gain_error_db": -0.1059088129585081, "output_peak": 0.2731227831998249}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9446679040530638, "全帯域_10ms_rms_envelope_nrmse": 0.05492051304415141, "全帯域_10ms_envelope_correlation": 0.9968674922094136, "全帯域_10ms_modulation_mae_db": 0.4586553511513333, "全帯域_40ms_log_rms_mae_db": 0.5332169287662863, "全帯域_40ms_rms_envelope_nrmse": 0.02702712563542005, "全帯域_40ms_envelope_correlation": 0.9992602165313816, "全帯域_40ms_modulation_mae_db": 0.43703352870139905, "300–1000 Hz_10ms_log_rms_mae_db": 1.099073994206039, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07229047378358974, "300–1000 Hz_10ms_envelope_correlation": 0.9956833916014548, "300–1000 Hz_10ms_modulation_mae_db": 0.6822096280413467, "300–1000 Hz_40ms_log_rms_mae_db": 0.7291289446623481, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03859136837015717, "300–1000 Hz_40ms_envelope_correlation": 0.9987505629163652, "300–1000 Hz_40ms_modulation_mae_db": 0.7225095697076424, "1000–3000 Hz_10ms_log_rms_mae_db": 1.387603484607726, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11395349406823475, "1000–3000 Hz_10ms_envelope_correlation": 0.9916985206739513, "1000–3000 Hz_10ms_modulation_mae_db": 0.5120049681761211, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0182465312882671, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07239252895249199, "1000–3000 Hz_40ms_envelope_correlation": 0.9972640242774019, "1000–3000 Hz_40ms_modulation_mae_db": 0.8694938026768657, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2722286503492164, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17047456732306362, "3000–6000 Hz_10ms_envelope_correlation": 0.9829142493107461, "3000–6000 Hz_10ms_modulation_mae_db": 1.4420079239861507, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8302832993192215, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11319294277732857, "3000–6000 Hz_40ms_envelope_correlation": 0.9942681973533753, "3000–6000 Hz_40ms_modulation_mae_db": 1.4958425837213547, "mr_stft_db": 5.555275517184, "band_mae_db": 0.24645425085711406, "rms_gain_error_db": -0.08023086588573639, "output_peak": 0.27835030163170005}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9180992571633848, "全帯域_10ms_rms_envelope_nrmse": 0.05390611339407192, "全帯域_10ms_envelope_correlation": 0.9970494493287586, "全帯域_10ms_modulation_mae_db": 0.31879765765588525, "全帯域_40ms_log_rms_mae_db": 0.49969557159076605, "全帯域_40ms_rms_envelope_nrmse": 0.02977376173759695, "全帯域_40ms_envelope_correlation": 0.9991553812223616, "全帯域_40ms_modulation_mae_db": 0.3027982055676269, "300–1000 Hz_10ms_log_rms_mae_db": 1.0547230000723318, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0625735111165327, "300–1000 Hz_10ms_envelope_correlation": 0.9968691779106539, "300–1000 Hz_10ms_modulation_mae_db": 0.6814754558829792, "300–1000 Hz_40ms_log_rms_mae_db": 0.6954223374181712, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03455757427796215, "300–1000 Hz_40ms_envelope_correlation": 0.9990950208882379, "300–1000 Hz_40ms_modulation_mae_db": 0.8464260229974219, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4199995296812091, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13645258261813414, "1000–3000 Hz_10ms_envelope_correlation": 0.98818727861777, "1000–3000 Hz_10ms_modulation_mae_db": 0.6261466349785599, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0524056626282645, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08782690312088844, "1000–3000 Hz_40ms_envelope_correlation": 0.996172576932903, "1000–3000 Hz_40ms_modulation_mae_db": 0.6094916712190007, "3000–6000 Hz_10ms_log_rms_mae_db": 1.229285721349663, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16762098469479333, "3000–6000 Hz_10ms_envelope_correlation": 0.9837355494225896, "3000–6000 Hz_10ms_modulation_mae_db": 2.177700406407332, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7994800294864668, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12104795390978441, "3000–6000 Hz_40ms_envelope_correlation": 0.9929917810741391, "3000–6000 Hz_40ms_modulation_mae_db": 2.51194813997323, "mr_stft_db": 5.573383731452392, "band_mae_db": 0.362273071592274, "rms_gain_error_db": -0.10697375025968767, "output_peak": 0.2727423009064838}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9516114090001099, "全帯域_10ms_rms_envelope_nrmse": 0.05524573488580637, "全帯域_10ms_envelope_correlation": 0.9968892484430428, "全帯域_10ms_modulation_mae_db": 0.4785741883439823, "全帯域_40ms_log_rms_mae_db": 0.5493065678626626, "全帯域_40ms_rms_envelope_nrmse": 0.030542290580230523, "全帯域_40ms_envelope_correlation": 0.9991016937419337, "全帯域_40ms_modulation_mae_db": 0.86793741822297, "300–1000 Hz_10ms_log_rms_mae_db": 1.0681696644500858, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06840180772760367, "300–1000 Hz_10ms_envelope_correlation": 0.996198341877156, "300–1000 Hz_10ms_modulation_mae_db": 0.8591902744842318, "300–1000 Hz_40ms_log_rms_mae_db": 0.7364061210684443, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03984152036877412, "300–1000 Hz_40ms_envelope_correlation": 0.9987198749923969, "300–1000 Hz_40ms_modulation_mae_db": 1.0688729648074802, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4368015149314701, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1287647654775081, "1000–3000 Hz_10ms_envelope_correlation": 0.9892077906253991, "1000–3000 Hz_10ms_modulation_mae_db": 1.4021533752182627, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0672919590892906, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08412524577257793, "1000–3000 Hz_40ms_envelope_correlation": 0.9960231784048451, "1000–3000 Hz_40ms_modulation_mae_db": 1.5482403681797716, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2668254157418686, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19772533358042768, "3000–6000 Hz_10ms_envelope_correlation": 0.9761791797288097, "3000–6000 Hz_10ms_modulation_mae_db": 2.2119020651380854, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8501526028088277, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1259756867780373, "3000–6000 Hz_40ms_envelope_correlation": 0.9926414918950908, "3000–6000 Hz_40ms_modulation_mae_db": 2.660692435413812, "mr_stft_db": 5.557245655763499, "band_mae_db": 0.2976222013564835, "rms_gain_error_db": -0.10570937460654552, "output_peak": 0.2718293109304641}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9128546413992533, "全帯域_10ms_rms_envelope_nrmse": 0.04823893243575403, "全帯域_10ms_envelope_correlation": 0.9976454267121504, "全帯域_10ms_modulation_mae_db": 0.46859010455024896, "全帯域_40ms_log_rms_mae_db": 0.5051910312616704, "全帯域_40ms_rms_envelope_nrmse": 0.02535228853366979, "全帯域_40ms_envelope_correlation": 0.9994051771591549, "全帯域_40ms_modulation_mae_db": 0.5736366601273998, "300–1000 Hz_10ms_log_rms_mae_db": 1.0407002998220223, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05834461067554184, "300–1000 Hz_10ms_envelope_correlation": 0.9972560410340113, "300–1000 Hz_10ms_modulation_mae_db": 0.5996303046313217, "300–1000 Hz_40ms_log_rms_mae_db": 0.6828874192647948, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03215710506089301, "300–1000 Hz_40ms_envelope_correlation": 0.9991926711006439, "300–1000 Hz_40ms_modulation_mae_db": 0.7179733812173553, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5217527372325885, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16373339559000907, "1000–3000 Hz_10ms_envelope_correlation": 0.9823942503841389, "1000–3000 Hz_10ms_modulation_mae_db": 0.4133055307488091, "1000–3000 Hz_40ms_log_rms_mae_db": 1.118467440549839, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10525917034092833, "1000–3000 Hz_40ms_envelope_correlation": 0.9939460004048651, "1000–3000 Hz_40ms_modulation_mae_db": 0.7238854456122784, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2874962317515593, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1458066934994391, "3000–6000 Hz_10ms_envelope_correlation": 0.986740151137068, "3000–6000 Hz_10ms_modulation_mae_db": 1.0578650538715728, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8402757897853901, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08165079512143848, "3000–6000 Hz_40ms_envelope_correlation": 0.9967684194825882, "3000–6000 Hz_40ms_modulation_mae_db": 1.2283398865072426, "mr_stft_db": 5.562072275546544, "band_mae_db": 0.2922417615507093, "rms_gain_error_db": -0.09683588334369532, "output_peak": 0.27951111881345303}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8888530202150072, "全帯域_10ms_rms_envelope_nrmse": 0.04991690908535338, "全帯域_10ms_envelope_correlation": 0.9974507120823616, "全帯域_10ms_modulation_mae_db": 0.43877042347724265, "全帯域_40ms_log_rms_mae_db": 0.5099004065988977, "全帯域_40ms_rms_envelope_nrmse": 0.02435402635788422, "全帯域_40ms_envelope_correlation": 0.9994442313768965, "全帯域_40ms_modulation_mae_db": 0.7064016467078806, "300–1000 Hz_10ms_log_rms_mae_db": 1.038643639038708, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0624157401994961, "300–1000 Hz_10ms_envelope_correlation": 0.9968497632511798, "300–1000 Hz_10ms_modulation_mae_db": 0.6966770102244588, "300–1000 Hz_40ms_log_rms_mae_db": 0.6903431411687331, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.033218117203996735, "300–1000 Hz_40ms_envelope_correlation": 0.9991373927172548, "300–1000 Hz_40ms_modulation_mae_db": 0.8903765931218292, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4558690233564842, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13247752504463187, "1000–3000 Hz_10ms_envelope_correlation": 0.9892010222563747, "1000–3000 Hz_10ms_modulation_mae_db": 1.23627301930841, "1000–3000 Hz_40ms_log_rms_mae_db": 1.08442784573558, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08530364418268649, "1000–3000 Hz_40ms_envelope_correlation": 0.9967531583831205, "1000–3000 Hz_40ms_modulation_mae_db": 1.4220777722357407, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2784370820817053, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1543526925714573, "3000–6000 Hz_10ms_envelope_correlation": 0.9841443334437865, "3000–6000 Hz_10ms_modulation_mae_db": 1.256266913178645, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8143271630598721, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08395108290372759, "3000–6000 Hz_40ms_envelope_correlation": 0.9953703859939492, "3000–6000 Hz_40ms_modulation_mae_db": 1.5668489413338207, "mr_stft_db": 5.55543236414091, "band_mae_db": 0.23710058113222754, "rms_gain_error_db": -0.09019341346300494, "output_peak": 0.27790134819381246}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.631064715334125, "spectral_convergence": 0.15193538388193928, "spectral_convergence_status": "ok", "amplitude_floor": 9.829298518478812e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.56933011431307, "spectral_convergence": 0.15486942780858903, "spectral_convergence_status": "ok", "amplitude_floor": 9.065329093063253e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.506371439196029, "spectral_convergence": 0.15943123640791518, "spectral_convergence_status": "ok", "amplitude_floor": 8.043941450863317e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.0001149513766055836, "output_power": 0.00012026647701011067, "delta_db": 0.19630412731358426, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0017363654374162414, "output_power": 0.001713190873017743, "delta_db": -0.0583538052605751, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0004421876194377549, "output_power": 0.0004343178887874255, "delta_db": -0.0779886129222562, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.7408011480563064e-05, "output_power": 2.5287590963071834e-05, "delta_db": -0.349700695362135, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7412343207141002e-05, "output_power": 2.384271386354779e-05, "delta_db": -0.605904737757281, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.428426915438781e-05, "output_power": 3.639854710286942e-05, "delta_db": 0.2598915259946617, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.433275239990599e-05, "output_power": 1.4350469462922997e-05, "delta_db": 0.005365104184713898, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.22192980125645817, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.05339151548452438, "pitch": null, "output_rms_dbfs": -26.256816607072317, "output_peak": 0.28244664107237416, "reference_rms_dbfs": -26.20342509158779, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.568922089614408}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014020226421084518, "log_rms_mae_db": 0.9315370829212671, "rms_envelope_nrmse": 0.051693232467442805, "envelope_correlation": 0.9971954814779149, "rms_gain_error_db": -0.05339153292308067, "reference_mean_power": 0.002398940884341968, "output_mean_power": 0.0023696291994594965}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.599888913877476e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003971876344997112, "output_power": 0.0003838095519743819, "reference_active": true, "delta_db": -0.14879940358601018}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.277425400163653e-05, "output_power": 4.9013662656672664e-05, "reference_active": true, "delta_db": -0.3210494562687063}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.46569016072901e-05, "output_power": 1.2245964948172287e-05, "reference_active": true, "delta_db": -0.7804916040138956}], "active_band_count": 3, "active_band_mae_db": 0.41678015462287066}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001294702248118231, "log_rms_mae_db": 0.5116617492719032, "rms_envelope_nrmse": 0.026753457254298018, "envelope_correlation": 0.9992275494247637, "rms_gain_error_db": -0.05339153955583726, "reference_mean_power": 0.0024110057038516162, "output_mean_power": 0.0023815466001997202}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 8.923189531660561e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00035367674920645624, "output_power": 0.0003407416994912563, "reference_active": true, "delta_db": -0.16181224960919974}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.2909806376051565e-05, "output_power": 2.1838254644364314e-05, "reference_active": true, "delta_db": -0.20803492969529952}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.181144761591823e-07, "output_power": 7.015059253801477e-07, "reference_active": true, "delta_db": -0.6678273365375973}], "active_band_count": 3, "active_band_mae_db": 0.34589150528069884}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00013300454501172858, "log_rms_mae_db": 1.1365509885149694, "rms_envelope_nrmse": 0.06383961023070336, "envelope_correlation": 0.9966277164996011, "rms_gain_error_db": -0.06106361620071183, "reference_mean_power": 0.0013111812883454625, "output_mean_power": 0.0012928745342516924}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.210472671322603e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002971533743381409, "output_power": 0.00028310978267440806, "reference_active": true, "delta_db": -0.2102578988447215}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.9363200025831e-05, "output_power": 4.158859865369613e-05, "reference_active": true, "delta_db": -0.7442901870766289}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.44718666084695e-06, "output_power": 6.600479795682356e-06, "reference_active": true, "delta_db": -1.557269903815353}], "active_band_count": 3, "active_band_mae_db": 0.8372726632455678}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00012063998479701045, "log_rms_mae_db": 0.7351398843440036, "rms_envelope_nrmse": 0.03507992262888125, "envelope_correlation": 0.9989410559869288, "rms_gain_error_db": -0.06106360143338582, "reference_mean_power": 0.0013177756236779122, "output_mean_power": 0.001299376803686575}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.775720236374225e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00027184637186405784, "output_power": 0.00025606595871536554, "reference_active": true, "delta_db": -0.25971693756154857}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0948015125222398e-05, "output_power": 1.832341824182049e-05, "reference_active": true, "delta_db": -0.5813638408740507}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.00249959518115e-07, "output_power": 4.3998407793600393e-07, "reference_active": true, "delta_db": -2.018161317881523}], "active_band_count": 3, "active_band_mae_db": 0.9530806987723741}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.4324234792903394e-05, "log_rms_mae_db": 1.4672327648170134, "rms_envelope_nrmse": 0.15771610259563876, "envelope_correlation": 0.9835703868414086, "rms_gain_error_db": -0.45954078601003484, "reference_mean_power": 3.621970358575803e-05, "output_mean_power": 3.2582980853892276e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.144567073932934e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6016299479105344e-05, "output_power": 1.368048174358135e-05, "reference_active": true, "delta_db": -0.6846078995064169}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.217328435986187e-06, "output_power": 4.191404170761098e-06, "reference_active": true, "delta_db": -0.9508863563742609}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.162268250073546e-07, "output_power": 6.004095083180606e-07, "reference_active": true, "delta_db": -0.11293038410186096}], "active_band_count": 3, "active_band_mae_db": 0.5828082133275129}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9150097924886824e-05, "log_rms_mae_db": 1.0679743349209412, "rms_envelope_nrmse": 0.09223510795440695, "envelope_correlation": 0.9956445072559341, "rms_gain_error_db": -0.4595408834258593, "reference_mean_power": 3.640185858193717e-05, "output_mean_power": 3.2746845423742204e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.976051267531115e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.575058419062026e-05, "output_power": 1.3329881717411574e-05, "reference_active": true, "delta_db": -0.7247037072405464}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5755236704985135e-06, "output_power": 2.037901275480276e-06, "reference_active": true, "delta_db": -1.016824045169569}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.671987913674402e-08, "output_power": 4.297939239020041e-08, "reference_active": true, "delta_db": -1.9099497942929375}], "active_band_count": 3, "active_band_mae_db": 1.217159182234351}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.268273320274525e-05, "log_rms_mae_db": 1.2545480398102624, "rms_envelope_nrmse": 0.14464679117014592, "envelope_correlation": 0.9861605561836949, "rms_gain_error_db": 0.029331099913004692, "reference_mean_power": 3.4234790780271314e-05, "output_mean_power": 3.446678603212711e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.011440004206466e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3904345626991894e-05, "output_power": 1.5273510184477067e-05, "reference_active": true, "delta_db": 0.4078830412989499}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.336600248325665e-06, "output_power": 4.693191104252158e-06, "reference_active": true, "delta_db": -0.5579643327089382}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.037307900027025e-06, "output_power": 1.790144606778378e-06, "reference_active": true, "delta_db": -0.5616855480688125}], "active_band_count": 3, "active_band_mae_db": 0.5091776406922336}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.282155756745637e-05, "log_rms_mae_db": 0.8150399522905027, "rms_envelope_nrmse": 0.09978432500578513, "envelope_correlation": 0.9931150303518009, "rms_gain_error_db": 0.029331125705469516, "reference_mean_power": 3.440696652445238e-05, "output_mean_power": 3.464012874701815e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.8610527191429872e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5067699650347801e-05, "output_power": 1.621951428347422e-05, "reference_active": true, "delta_db": 0.3199088982532674}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.7890585183930857e-06, "output_power": 2.5249016362857827e-06, "reference_active": true, "delta_db": -0.4321316269296801}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4153621023540917e-07, "output_power": 1.3397000287748948e-07, "reference_active": true, "delta_db": -0.23859996084041368}], "active_band_count": 3, "active_band_mae_db": 0.3302134953411204}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9013501246093946, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "b44c50fa6baf18434dd73b6d5198874f89359d616d339ec9fa4b8c84ca35875d", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9874347633248484, "standard_deviation": 0.0031801742003090537, "minimum": 0.9823942503841389, "maximum": 0.9916985206739513, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4569347580591692, "standard_deviation": 0.04209547378697561, "minimum": 1.387603484607726, "maximum": 1.5217527372325885, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8862040675644096, "standard_deviation": 0.4310953036121972, "minimum": 0.4133055307488091, "maximum": 1.5052811193225935, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14076735092876894, "standard_deviation": 0.01653753290579688, "minimum": 0.11395349406823475, "maximum": 0.16373339559000907, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9957046234360407, "standard_deviation": 0.0012006779184891877, "minimum": 0.9939415822474751, "maximum": 0.9972640242774019, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.0779724454832496, "standard_deviation": 0.03712037957159998, "minimum": 1.0182465312882671, "maximum": 1.1373771064871894, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.0632692773670773, "standard_deviation": 0.4909690206680043, "minimum": 0.37196223757637387, "maximum": 1.7438437392022357, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09285526908976895, "standard_deviation": 0.013219059947111941, "minimum": 0.07239252895249199, "maximum": 0.11243477479215715, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9818793047706744, "standard_deviation": 0.004473884558983318, "minimum": 0.9744939832414824, "maximum": 0.986740151137068, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2614399732071266, "standard_deviation": 0.018630289451141407, "minimum": 1.229285721349663, "maximum": 1.2874962317515593, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.3977059458987537, "standard_deviation": 0.7444883212556823, "minimum": 0.3563093006605896, "maximum": 2.2119020651380854, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1693665337905404, "standard_deviation": 0.022160903845676042, "minimum": 0.14464679117014592, "maximum": 0.20454524101720248, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9940338916995197, "standard_deviation": 0.0016849620723116713, "minimum": 0.9917925902473186, "maximum": 0.9967684194825882, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8196969640590995, "standard_deviation": 0.024475521109817173, "minimum": 0.7741860740415161, "maximum": 0.8501526028088277, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.5757457415350402, "standard_deviation": 0.8978349804682982, "minimum": 0.3302134953411204, "maximum": 2.660692435413812, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10517430032074074, "standard_deviation": 0.020715033909359037, "minimum": 0.08165079512143848, "maximum": 0.13246381496099474, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.996611314745119, "standard_deviation": 0.00048730310305466785, "minimum": 0.9956833916014548, "maximum": 0.9972560410340113, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0697917775553152, "standard_deviation": 0.03853849126284518, "minimum": 1.022464415311564, "maximum": 1.1365509885149694, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.833859829676699, "standard_deviation": 0.2218519030549337, "minimum": 0.5996303046313217, "maximum": 1.2434102930483346, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06452016449401489, "standard_deviation": 0.004252985043159555, "minimum": 0.05834461067554184, "maximum": 0.07229047378358974, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9989888727111342, "standard_deviation": 0.00017615801263135114, "minimum": 0.9987198749923969, "maximum": 0.9991926711006439, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7066681530431627, "standard_deviation": 0.024266576319538026, "minimum": 0.6756640224286403, "maximum": 0.7364061210684443, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.9560611632502192, "standard_deviation": 0.25473358865332274, "minimum": 0.7179733812173553, "maximum": 1.515889048287925, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03562358637731051, "standard_deviation": 0.002568471696885495, "minimum": 0.03215710506089301, "maximum": 0.03984152036877412, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.2835432654054273, "standard_deviation": 0.05842901187463163, "minimum": 0.22192980125645817, "maximum": 0.3729806875917494, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.562996327185154, "standard_deviation": 0.0067647328491967544, "minimum": 5.555275517184, "maximum": 5.573383731452392, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.2774784460744616, "standard_deviation": 0.004545192397587916, "minimum": 0.2718293109304641, "maximum": 0.28392376384758033, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.09699636111781164, "standard_deviation": 0.024089749726598112, "minimum": -0.1367272729407908, "maximum": -0.05339151548452438, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.997142650431403, "standard_deviation": 0.00029160837809099997, "minimum": 0.996838802756841, "maximum": 0.9976454267121504, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9207755287361464, "standard_deviation": 0.024175583401799525, "minimum": 0.8858283549790755, "maximum": 0.9516114090001099, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.46086786797791224, "standard_deviation": 0.08945711714906167, "minimum": 0.31879765765588525, "maximum": 0.6425622034771262, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05286487753984616, "standard_deviation": 0.0026847244927531468, "minimum": 0.04823893243575403, "maximum": 0.05565506530324218, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9992144452733298, "standard_deviation": 0.00015187628145074358, "minimum": 0.9990035850281109, "maximum": 0.9994442313768965, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5239196264815993, "standard_deviation": 0.020984056842186804, "minimum": 0.49969557159076605, "maximum": 0.5565273508136043, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5563950573170214, "standard_deviation": 0.19483022625656635, "minimum": 0.3027982055676269, "maximum": 0.86793741822297, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.02843487837935584, "standard_deviation": 0.0029365879994685206, "minimum": 0.02435402635788422, "maximum": 0.0318792293473368, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 1.6755502223968506, "predicted_mos": 1.6755502223968506, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "af97e8a130bb249fc4c1dce71428f5fecaa3e6af5bd35bd6b3f01320a079f25f", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.8606146001257}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9411538770896221, "全帯域_10ms_rms_envelope_nrmse": 0.0521933003431814, "全帯域_10ms_envelope_correlation": 0.997137104488685, "全帯域_10ms_modulation_mae_db": 0.377479454471551, "全帯域_40ms_log_rms_mae_db": 0.5325382425161125, "全帯域_40ms_rms_envelope_nrmse": 0.027199101553551017, "全帯域_40ms_envelope_correlation": 0.9991964400722844, "全帯域_40ms_modulation_mae_db": 0.3059406624177777, "300–1000 Hz_10ms_log_rms_mae_db": 1.1121065666118484, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06539946498101191, "300–1000 Hz_10ms_envelope_correlation": 0.9964496604578903, "300–1000 Hz_10ms_modulation_mae_db": 0.8063890307849008, "300–1000 Hz_40ms_log_rms_mae_db": 0.7195616629362839, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03617520674453919, "300–1000 Hz_40ms_envelope_correlation": 0.9988630259636206, "300–1000 Hz_40ms_modulation_mae_db": 0.9509585484973595, "1000–3000 Hz_10ms_log_rms_mae_db": 1.433448563802321, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15652110514769135, "1000–3000 Hz_10ms_envelope_correlation": 0.9839104904812761, "1000–3000 Hz_10ms_modulation_mae_db": 0.6059667490452315, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0276375184082776, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09046005436370384, "1000–3000 Hz_40ms_envelope_correlation": 0.9959499247119342, "1000–3000 Hz_40ms_modulation_mae_db": 1.2690563135840636, "3000–6000 Hz_10ms_log_rms_mae_db": 1.247193040967928, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.151548645887612, "3000–6000 Hz_10ms_envelope_correlation": 0.9850541014246249, "3000–6000 Hz_10ms_modulation_mae_db": 0.5018292462203348, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8364085922765053, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1097124882831333, "3000–6000 Hz_40ms_envelope_correlation": 0.9919334369214893, "3000–6000 Hz_40ms_modulation_mae_db": 0.3604956797911946, "mr_stft_db": 5.522983567540862, "band_mae_db": 0.24527521695433596, "rms_gain_error_db": -0.05015860173432095, "output_peak": 0.2818607089367985}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8858488264916603, "全帯域_10ms_rms_envelope_nrmse": 0.05344937592734435, "全帯域_10ms_envelope_correlation": 0.9972118689099981, "全帯域_10ms_modulation_mae_db": 0.6403913415843795, "全帯域_40ms_log_rms_mae_db": 0.5169934063122572, "全帯域_40ms_rms_envelope_nrmse": 0.03217442367030089, "全帯域_40ms_envelope_correlation": 0.9991124322420677, "全帯域_40ms_modulation_mae_db": 0.6940235497634161, "300–1000 Hz_10ms_log_rms_mae_db": 1.0859090582300641, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06433408750719419, "300–1000 Hz_10ms_envelope_correlation": 0.9967467720273225, "300–1000 Hz_10ms_modulation_mae_db": 1.2579391853030606, "300–1000 Hz_40ms_log_rms_mae_db": 0.7005395323666809, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03657326713134055, "300–1000 Hz_40ms_envelope_correlation": 0.9990440937188412, "300–1000 Hz_40ms_modulation_mae_db": 1.539345290572647, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4278458760181292, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13781031981382647, "1000–3000 Hz_10ms_envelope_correlation": 0.9898026130591282, "1000–3000 Hz_10ms_modulation_mae_db": 1.5683772734226482, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0329962030101827, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10215429054571933, "1000–3000 Hz_40ms_envelope_correlation": 0.9961542126011983, "1000–3000 Hz_40ms_modulation_mae_db": 1.8074843380053178, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2279742301879917, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1955307457246155, "3000–6000 Hz_10ms_envelope_correlation": 0.976710774052868, "3000–6000 Hz_10ms_modulation_mae_db": 1.9644931736309268, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8289897608428923, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11892449401253408, "3000–6000 Hz_40ms_envelope_correlation": 0.993860827421923, "3000–6000 Hz_40ms_modulation_mae_db": 2.123299938276812, "mr_stft_db": 5.520103028543623, "band_mae_db": 0.3953546869235191, "rms_gain_error_db": -0.14238729540119, "output_peak": 0.28309913995603314}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9450481557168928, "全帯域_10ms_rms_envelope_nrmse": 0.05657582062703815, "全帯域_10ms_envelope_correlation": 0.9967117312021695, "全帯域_10ms_modulation_mae_db": 0.42853333734307525, "全帯域_40ms_log_rms_mae_db": 0.5674377532151601, "全帯域_40ms_rms_envelope_nrmse": 0.032656571017688665, "全帯域_40ms_envelope_correlation": 0.9989272827996322, "全帯域_40ms_modulation_mae_db": 0.4798962525323381, "300–1000 Hz_10ms_log_rms_mae_db": 1.0306027167199028, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06681203623581271, "300–1000 Hz_10ms_envelope_correlation": 0.9963549878306156, "300–1000 Hz_10ms_modulation_mae_db": 1.067579261826272, "300–1000 Hz_40ms_log_rms_mae_db": 0.6668733614229508, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03598509791345761, "300–1000 Hz_40ms_envelope_correlation": 0.9989743254233026, "300–1000 Hz_40ms_modulation_mae_db": 0.9302818816599207, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4292445738046122, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15262351156696063, "1000–3000 Hz_10ms_envelope_correlation": 0.9863112420517648, "1000–3000 Hz_10ms_modulation_mae_db": 0.6983944432650143, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0697154719444801, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11385929792285975, "1000–3000 Hz_40ms_envelope_correlation": 0.9939684778515997, "1000–3000 Hz_40ms_modulation_mae_db": 0.3638335202871728, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2234066027978423, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17621160659093027, "3000–6000 Hz_10ms_envelope_correlation": 0.9793056449640772, "3000–6000 Hz_10ms_modulation_mae_db": 0.42283099539844443, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7640778799615946, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09323748781590002, "3000–6000 Hz_40ms_envelope_correlation": 0.9939863290085007, "3000–6000 Hz_40ms_modulation_mae_db": 0.511170697771392, "mr_stft_db": 5.523548111267638, "band_mae_db": 0.2780134218701752, "rms_gain_error_db": -0.09927955622354975, "output_peak": 0.27333019167968015}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.941313963137112, "全帯域_10ms_rms_envelope_nrmse": 0.055417835158743114, "全帯域_10ms_envelope_correlation": 0.9968099319638205, "全帯域_10ms_modulation_mae_db": 0.47501259211426533, "全帯域_40ms_log_rms_mae_db": 0.5279794929404555, "全帯域_40ms_rms_envelope_nrmse": 0.02712113776287883, "全帯域_40ms_envelope_correlation": 0.9992560523034041, "全帯域_40ms_modulation_mae_db": 0.44581416921947586, "300–1000 Hz_10ms_log_rms_mae_db": 1.1099052381436656, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07229150390332331, "300–1000 Hz_10ms_envelope_correlation": 0.9956837492749815, "300–1000 Hz_10ms_modulation_mae_db": 0.6836519585625944, "300–1000 Hz_40ms_log_rms_mae_db": 0.7360306534703681, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03830787152921835, "300–1000 Hz_40ms_envelope_correlation": 0.9987702150164022, "300–1000 Hz_40ms_modulation_mae_db": 0.7434913601111025, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3534976064390318, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11283278572535997, "1000–3000 Hz_10ms_envelope_correlation": 0.9920228630110927, "1000–3000 Hz_10ms_modulation_mae_db": 0.6218955293599789, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0017252926126385, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07228373706570608, "1000–3000 Hz_40ms_envelope_correlation": 0.9974330510103618, "1000–3000 Hz_40ms_modulation_mae_db": 0.9994051045626217, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2454896001266358, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1744533179886513, "3000–6000 Hz_10ms_envelope_correlation": 0.9826557511641356, "3000–6000 Hz_10ms_modulation_mae_db": 1.6269216401509092, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8261770823733408, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11695337402370694, "3000–6000 Hz_40ms_envelope_correlation": 0.9945045280967033, "3000–6000 Hz_40ms_modulation_mae_db": 1.7018378660876856, "mr_stft_db": 5.517103148739207, "band_mae_db": 0.28807414372506507, "rms_gain_error_db": -0.08093553496340478, "output_peak": 0.27783802656132456}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.93009911477388, "全帯域_10ms_rms_envelope_nrmse": 0.05407941981808481, "全帯域_10ms_envelope_correlation": 0.9970298072601081, "全帯域_10ms_modulation_mae_db": 0.3737510170839624, "全帯域_40ms_log_rms_mae_db": 0.49733985408448533, "全帯域_40ms_rms_envelope_nrmse": 0.029836929587853084, "全帯域_40ms_envelope_correlation": 0.99915163084508, "全帯域_40ms_modulation_mae_db": 0.35569778914949207, "300–1000 Hz_10ms_log_rms_mae_db": 1.0613422911628814, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06439798584331959, "300–1000 Hz_10ms_envelope_correlation": 0.9966701024163421, "300–1000 Hz_10ms_modulation_mae_db": 0.7404120132217938, "300–1000 Hz_40ms_log_rms_mae_db": 0.6813886914727109, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03468922244451099, "300–1000 Hz_40ms_envelope_correlation": 0.9990856109744981, "300–1000 Hz_40ms_modulation_mae_db": 0.9560453909159973, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3693562556586019, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1349605634275744, "1000–3000 Hz_10ms_envelope_correlation": 0.9886521710182438, "1000–3000 Hz_10ms_modulation_mae_db": 0.7746650692859071, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9979456639640444, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08715776521873929, "1000–3000 Hz_40ms_envelope_correlation": 0.996442361165923, "1000–3000 Hz_40ms_modulation_mae_db": 0.7388945075372093, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2259185102864403, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1693188811756465, "3000–6000 Hz_10ms_envelope_correlation": 0.9834719257418211, "3000–6000 Hz_10ms_modulation_mae_db": 2.154857570118089, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8374479653772107, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12231427440963502, "3000–6000 Hz_40ms_envelope_correlation": 0.9929543552085666, "3000–6000 Hz_40ms_modulation_mae_db": 2.4815088750866408, "mr_stft_db": 5.528288969003228, "band_mae_db": 0.3885788667053144, "rms_gain_error_db": -0.10724333054781184, "output_peak": 0.27291177943282896}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.956155357782583, "全帯域_10ms_rms_envelope_nrmse": 0.05581164667081213, "全帯域_10ms_envelope_correlation": 0.9968195799655907, "全帯域_10ms_modulation_mae_db": 0.46447889025872663, "全帯域_40ms_log_rms_mae_db": 0.5536731972502741, "全帯域_40ms_rms_envelope_nrmse": 0.03055130339195103, "全帯域_40ms_envelope_correlation": 0.9990991129275195, "全帯域_40ms_modulation_mae_db": 0.871433710456024, "300–1000 Hz_10ms_log_rms_mae_db": 1.06486500409621, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06897008346619736, "300–1000 Hz_10ms_envelope_correlation": 0.9961319417955741, "300–1000 Hz_10ms_modulation_mae_db": 0.9179664349746446, "300–1000 Hz_40ms_log_rms_mae_db": 0.7261351867505256, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04003954287610904, "300–1000 Hz_40ms_envelope_correlation": 0.9987046354770261, "300–1000 Hz_40ms_modulation_mae_db": 1.1025871891757812, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3911820446682508, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1294474643082139, "1000–3000 Hz_10ms_envelope_correlation": 0.9892718337010703, "1000–3000 Hz_10ms_modulation_mae_db": 1.4510191755398296, "1000–3000 Hz_40ms_log_rms_mae_db": 1.034416592057911, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08429569865220511, "1000–3000 Hz_40ms_envelope_correlation": 0.9962358941969979, "1000–3000 Hz_40ms_modulation_mae_db": 1.5981982951579587, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2382133341158252, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19175765578803253, "3000–6000 Hz_10ms_envelope_correlation": 0.9772279921360408, "3000–6000 Hz_10ms_modulation_mae_db": 1.8362506207182099, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8464573949352732, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11621386608321062, "3000–6000 Hz_40ms_envelope_correlation": 0.9936296309441695, "3000–6000 Hz_40ms_modulation_mae_db": 2.239260959096439, "mr_stft_db": 5.510587120291916, "band_mae_db": 0.31319638848145276, "rms_gain_error_db": -0.1045503246275848, "output_peak": 0.27121947588485973}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.926325677209258, "全帯域_10ms_rms_envelope_nrmse": 0.048414889189539775, "全帯域_10ms_envelope_correlation": 0.9976264754374086, "全帯域_10ms_modulation_mae_db": 0.4546862776834737, "全帯域_40ms_log_rms_mae_db": 0.5027176908936478, "全帯域_40ms_rms_envelope_nrmse": 0.025875049378126357, "全帯域_40ms_envelope_correlation": 0.9993737108400866, "全帯域_40ms_modulation_mae_db": 0.5558705510052938, "300–1000 Hz_10ms_log_rms_mae_db": 1.026904717549669, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06026405643556357, "300–1000 Hz_10ms_envelope_correlation": 0.9970676284334401, "300–1000 Hz_10ms_modulation_mae_db": 0.6088685882068051, "300–1000 Hz_40ms_log_rms_mae_db": 0.6866275572769746, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03353127466371282, "300–1000 Hz_40ms_envelope_correlation": 0.9991120740826963, "300–1000 Hz_40ms_modulation_mae_db": 0.7350668043109853, "1000–3000 Hz_10ms_log_rms_mae_db": 1.451455268137596, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16059670841320464, "1000–3000 Hz_10ms_envelope_correlation": 0.9831435120743025, "1000–3000 Hz_10ms_modulation_mae_db": 0.44096415800558475, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0495731455783255, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10237155175691066, "1000–3000 Hz_40ms_envelope_correlation": 0.9943815937881226, "1000–3000 Hz_40ms_modulation_mae_db": 0.8884646601640588, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2520490498883852, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14749382531344626, "3000–6000 Hz_10ms_envelope_correlation": 0.9865858306060128, "3000–6000 Hz_10ms_modulation_mae_db": 1.1723833554694656, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8536160120339461, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0816621132498482, "3000–6000 Hz_40ms_envelope_correlation": 0.9970269719200585, "3000–6000 Hz_40ms_modulation_mae_db": 1.3742789932929147, "mr_stft_db": 5.521418406246775, "band_mae_db": 0.3199343517297814, "rms_gain_error_db": -0.09638014548598403, "output_peak": 0.279282061550753}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8946963357749015, "全帯域_10ms_rms_envelope_nrmse": 0.05175136730767562, "全帯域_10ms_envelope_correlation": 0.9972388883711371, "全帯域_10ms_modulation_mae_db": 0.3820926531618962, "全帯域_40ms_log_rms_mae_db": 0.5166281500735899, "全帯域_40ms_rms_envelope_nrmse": 0.025021594940127307, "全帯域_40ms_envelope_correlation": 0.9993925272618368, "全帯域_40ms_modulation_mae_db": 0.6571906310724361, "300–1000 Hz_10ms_log_rms_mae_db": 1.048392724710194, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06485019975147958, "300–1000 Hz_10ms_envelope_correlation": 0.9965865720031465, "300–1000 Hz_10ms_modulation_mae_db": 0.6598321689782504, "300–1000 Hz_40ms_log_rms_mae_db": 0.6897696387582375, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035062205646728024, "300–1000 Hz_40ms_envelope_correlation": 0.9990194440526773, "300–1000 Hz_40ms_modulation_mae_db": 0.8919323565726991, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3929137672011165, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13097187771367527, "1000–3000 Hz_10ms_envelope_correlation": 0.9895719231234364, "1000–3000 Hz_10ms_modulation_mae_db": 1.196518912476822, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0239726719576068, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08361783158975028, "1000–3000 Hz_40ms_envelope_correlation": 0.9970578710172949, "1000–3000 Hz_40ms_modulation_mae_db": 1.3694885451486822, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2556145671841532, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1573143846066066, "3000–6000 Hz_10ms_envelope_correlation": 0.9834947187016403, "3000–6000 Hz_10ms_modulation_mae_db": 1.099439992730481, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8188819653324254, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08878628206238384, "3000–6000 Hz_40ms_envelope_correlation": 0.9947369269997639, "3000–6000 Hz_40ms_modulation_mae_db": 1.2373213546580526, "mr_stft_db": 5.513609724208176, "band_mae_db": 0.2604757311409266, "rms_gain_error_db": -0.08384222872430822, "output_peak": 0.2786109886925278}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.597842552203173, "spectral_convergence": 0.1520179445341063, "spectral_convergence_status": "ok", "amplitude_floor": 9.829298518478812e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.524512548227507, "spectral_convergence": 0.1550444110081665, "spectral_convergence_status": "ok", "amplitude_floor": 9.065329093063253e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.446595602191907, "spectral_convergence": 0.15910866782688127, "spectral_convergence_status": "ok", "amplitude_floor": 8.043941450863317e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.0001149513766055836, "output_power": 0.00012048195618798904, "delta_db": 0.20407833723584165, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0017363654374162414, "output_power": 0.0017143290573215391, "delta_db": -0.055469462116008346, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0004421876194377549, "output_power": 0.0004351461315915852, "delta_db": -0.06971451808008215, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.7408011480563064e-05, "output_power": 2.5266602739534066e-05, "delta_db": -0.35330675433509273, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7412343207141002e-05, "output_power": 2.349128895800029e-05, "delta_db": -0.6703931361648652, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.428426915438781e-05, "output_power": 3.662301078030791e-05, "delta_db": 0.28659148868235707, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.433275239990599e-05, "output_power": 1.4079664823476524e-05, "delta_db": -0.0773728220661046, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.24527521695433596, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.05015860173432095, "pitch": null, "output_rms_dbfs": -26.253583693322113, "output_peak": 0.2818607089367985, "reference_rms_dbfs": -26.20342509158779, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.522983567540862}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014020226421084518, "log_rms_mae_db": 0.9411538770896221, "rms_envelope_nrmse": 0.0521933003431814, "envelope_correlation": 0.997137104488685, "rms_gain_error_db": -0.050158625065049894, "reference_mean_power": 0.002398940884341968, "output_mean_power": 0.002371393818917273}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.599888913877476e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003971876344997112, "output_power": 0.0003849189066512814, "reference_active": true, "delta_db": -0.13626475773822566}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.277425400163653e-05, "output_power": 4.9456097960941146e-05, "reference_active": true, "delta_db": -0.2820225503277227}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.46569016072901e-05, "output_power": 1.2434463930370408e-05, "reference_active": true, "delta_db": -0.7141510553487047}], "active_band_count": 3, "active_band_mae_db": 0.377479454471551}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001294702248118231, "log_rms_mae_db": 0.5325382425161125, "rms_envelope_nrmse": 0.027199101553551017, "envelope_correlation": 0.9991964400722844, "rms_gain_error_db": -0.0501586099784055, "reference_mean_power": 0.0024110057038516162, "output_mean_power": 0.002383320106246691}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 8.923189531660561e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00035367674920645624, "output_power": 0.00034196556650072476, "reference_active": true, "delta_db": -0.1462413223715303}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.2909806376051565e-05, "output_power": 2.1897837771085483e-05, "reference_active": true, "delta_db": -0.19620184734658544}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.181144761591823e-07, "output_power": 7.165989964289629e-07, "reference_active": true, "delta_db": -0.5753788175352174}], "active_band_count": 3, "active_band_mae_db": 0.3059406624177777}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00013300454501172858, "log_rms_mae_db": 1.1121065666118484, "rms_envelope_nrmse": 0.06539946498101191, "envelope_correlation": 0.9964496604578903, "rms_gain_error_db": -0.057122949867258244, "reference_mean_power": 0.0013111812883454625, "output_mean_power": 0.0012940481847344078}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.210472671322603e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002971533743381409, "output_power": 0.0002845159181025249, "reference_active": true, "delta_db": -0.1887409694465194}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.9363200025831e-05, "output_power": 4.1574175922748515e-05, "reference_active": true, "delta_db": -0.7457965611867339}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.44718666084695e-06, "output_power": 6.711808243760369e-06, "reference_active": true, "delta_db": -1.484629561721449}], "active_band_count": 3, "active_band_mae_db": 0.8063890307849008}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00012063998479701045, "log_rms_mae_db": 0.7195616629362839, "rms_envelope_nrmse": 0.03617520674453919, "envelope_correlation": 0.9988630259636206, "rms_gain_error_db": -0.057122926440303756, "reference_mean_power": 0.0013177756236779122, "output_mean_power": 0.0013005563594170183}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.775720236374225e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00027184637186405784, "output_power": 0.0002574213086908748, "reference_active": true, "delta_db": -0.23679047298308037}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0948015125222398e-05, "output_power": 1.821878948581146e-05, "reference_active": true, "delta_db": -0.6062336111382223}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.00249959518115e-07, "output_power": 4.408267459355237e-07, "reference_active": true, "delta_db": -2.009851561370776}], "active_band_count": 3, "active_band_mae_db": 0.9509585484973595}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.4324234792903394e-05, "log_rms_mae_db": 1.433448563802321, "rms_envelope_nrmse": 0.15652110514769135, "envelope_correlation": 0.9839104904812761, "rms_gain_error_db": -0.4772169121415331, "reference_mean_power": 3.621970358575803e-05, "output_mean_power": 3.245063507712235e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.144567073932934e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6016299479105344e-05, "output_power": 1.3675429141431042e-05, "reference_active": true, "delta_db": -0.6862121723579452}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.217328435986187e-06, "output_power": 4.265201993033138e-06, "reference_active": true, "delta_db": -0.8750857337890245}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.162268250073546e-07, "output_power": 5.808718971174421e-07, "reference_active": true, "delta_db": -0.2566023409887249}], "active_band_count": 3, "active_band_mae_db": 0.6059667490452315}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9150097924886824e-05, "log_rms_mae_db": 1.0276375184082776, "rms_envelope_nrmse": 0.09046005436370384, "envelope_correlation": 0.9959499247119342, "rms_gain_error_db": -0.4772168760826012, "reference_mean_power": 3.640185858193717e-05, "output_mean_power": 3.261383506307397e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.976051267531115e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.575058419062026e-05, "output_power": 1.3349254749163517e-05, "reference_active": true, "delta_db": -0.7183964549222741}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5755236704985135e-06, "output_power": 2.081894111892962e-06, "reference_active": true, "delta_db": -0.9240690874456646}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.671987913674402e-08, "output_power": 4.053077527829257e-08, "reference_active": true, "delta_db": -2.164703398384252}], "active_band_count": 3, "active_band_mae_db": 1.2690563135840636}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.268273320274525e-05, "log_rms_mae_db": 1.247193040967928, "rms_envelope_nrmse": 0.151548645887612, "envelope_correlation": 0.9850541014246249, "rms_gain_error_db": 0.06641583592766652, "reference_mean_power": 3.4234790780271314e-05, "output_mean_power": 3.476236070997134e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.011440004206466e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3904345626991894e-05, "output_power": 1.5807836187447446e-05, "reference_active": true, "delta_db": 0.5572187207940802}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.336600248325665e-06, "output_power": 4.920016597164114e-06, "reference_active": true, "delta_db": -0.3529810426728439}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.037307900027025e-06, "output_power": 1.7763472653019713e-06, "reference_active": true, "delta_db": -0.59528797519408}], "active_band_count": 3, "active_band_mae_db": 0.5018292462203348}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.282155756745637e-05, "log_rms_mae_db": 0.8364085922765053, "rms_envelope_nrmse": 0.1097124882831333, "envelope_correlation": 0.9919334369214893, "rms_gain_error_db": 0.06641590535604991, "reference_mean_power": 3.440696652445238e-05, "output_mean_power": 3.4937190300257073e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.8610527191429872e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5067699650347801e-05, "output_power": 1.6795753334369557e-05, "reference_active": true, "delta_db": 0.47152533205444963}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.7890585183930857e-06, "output_power": 2.6329844230325286e-06, "reference_active": true, "delta_db": -0.2500933668491369}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4153621023540917e-07, "output_power": 1.3028089359890135e-07, "reference_active": true, "delta_db": -0.35986834046999727}], "active_band_count": 3, "active_band_mae_db": 0.3604956797911946}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9015767345892843, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "efeac22cdaafed622b52119b6418a67a75841b75e0f57a10314e59e111e22b07", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9878358310650392, "standard_deviation": 0.0030912902050628842, "minimum": 0.9831435120743025, "maximum": 0.9920228630110927, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4061179944662074, "standard_deviation": 0.034490439261471474, "minimum": 1.3534976064390318, "maximum": 1.451455268137596, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.9197251638001271, "standard_deviation": 0.42527744205693657, "minimum": 0.44096415800558475, "maximum": 1.5683772734226482, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.13947054201456333, "standard_deviation": 0.016104093996988002, "minimum": 0.11283278572535997, "maximum": 0.16059670841320464, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.995952923292929, "standard_deviation": 0.0012058746675554651, "minimum": 0.9939684778515997, "maximum": 0.9974330510103618, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.0297478199416834, "standard_deviation": 0.02347415307579674, "minimum": 0.9979456639640444, "maximum": 1.0697154719444801, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.1293531605558855, "standard_deviation": 0.4736260843143014, "minimum": 0.3638335202871728, "maximum": 1.8074843380053178, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09202502838944929, "standard_deviation": 0.01327010225765589, "minimum": 0.07228373706570608, "maximum": 0.11385929792285975, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9818133423489026, "standard_deviation": 0.003643329078860095, "minimum": 0.976710774052868, "maximum": 0.9865858306060128, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2394823669444002, "standard_deviation": 0.0124795078053734, "minimum": 1.2234066027978423, "maximum": 1.2556145671841532, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.3473758243046077, "standard_deviation": 0.6559433468003671, "minimum": 0.42283099539844443, "maximum": 2.154857570118089, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17045363288444262, "standard_deviation": 0.017689195759024483, "minimum": 0.14749382531344626, "maximum": 0.1955307457246155, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9940791258151469, "standard_deviation": 0.0014847254185065023, "minimum": 0.9919334369214893, "maximum": 0.9970269719200585, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8265070816416485, "standard_deviation": 0.0275485861031194, "minimum": 0.7640778799615946, "maximum": 0.8536160120339461, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.5036467955076414, "standard_deviation": 0.783769345515404, "minimum": 0.3604956797911946, "maximum": 2.4815088750866408, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10597554749254401, "standard_deviation": 0.015688038562919917, "minimum": 0.0816621132498482, "maximum": 0.12231427440963502, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9964614267799141, "standard_deviation": 0.00041968007474031633, "minimum": 0.9956837492749815, "maximum": 0.9970676284334401, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0675035396530543, "standard_deviation": 0.032833298326139744, "minimum": 1.026904717549669, "maximum": 1.1121065666118484, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8428298302322903, "standard_deviation": 0.22483471254956164, "minimum": 0.6088685882068051, "maximum": 1.2579391853030606, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06591492726548778, "standard_deviation": 0.003564334566939218, "minimum": 0.06026405643556357, "maximum": 0.07229150390332331, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.998946678088633, "standard_deviation": 0.00015067882920170118, "minimum": 0.9987046354770261, "maximum": 0.9991120740826963, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7008657855568415, "standard_deviation": 0.024158543460649197, "minimum": 0.6668733614229508, "maximum": 0.7360306534703681, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.9812136027270615, "standard_deviation": 0.2550788751368536, "minimum": 0.7350668043109853, "maximum": 1.539345290572647, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03629546111870208, "standard_deviation": 0.0020701123149792773, "minimum": 0.03353127466371282, "maximum": 0.04003954287610904, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.3111128509413213, "standard_deviation": 0.05568392524977366, "minimum": 0.24527521695433596, "maximum": 0.3953546869235191, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.519705259480178, "standard_deviation": 0.005724071573701135, "minimum": 5.510587120291916, "maximum": 5.528288969003228, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.2772690465868507, "standard_deviation": 0.004348198126156807, "minimum": 0.27121947588485973, "maximum": 0.28309913995603314, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.0955971272135193, "standard_deviation": 0.026287114061082112, "minimum": -0.14238729540119, "maximum": -0.05015860173432095, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9970731734498647, "standard_deviation": 0.0002983418444413152, "minimum": 0.9967117312021695, "maximum": 0.9976264754374086, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9275801634969887, "standard_deviation": 0.024857608490858607, "minimum": 0.8858488264916603, "maximum": 0.956155357782583, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.44955319546266626, "standard_deviation": 0.0872188195464713, "minimum": 0.3737510170839624, "maximum": 0.6403913415843795, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05346170688030241, "standard_deviation": 0.0026574038355171433, "minimum": 0.048414889189539775, "maximum": 0.05657582062703815, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9991886486614889, "standard_deviation": 0.0001530296298925708, "minimum": 0.9989272827996322, "maximum": 0.9993925272618368, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5269134734107478, "standard_deviation": 0.02406926005693427, "minimum": 0.49733985408448533, "maximum": 0.5674377532151601, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5457334144520317, "standard_deviation": 0.1884252826498747, "minimum": 0.3059406624177777, "maximum": 0.871433710456024, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.028804513912809648, "standard_deviation": 0.002893715699399587, "minimum": 0.025021594940127307, "maximum": 0.032656571017688665, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 2.1953234672546387, "predicted_mos": 2.1953234672546387, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "ab375f8d04d17a7a4f5322d32edf0a560fe0194097b90644d8c689ff6ffff2db", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.921957199927419}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8889832756369812, "全帯域_10ms_rms_envelope_nrmse": 0.05290988278719844, "全帯域_10ms_envelope_correlation": 0.9970802186593903, "全帯域_10ms_modulation_mae_db": 0.472553363087024, "全帯域_40ms_log_rms_mae_db": 0.4879446409146699, "全帯域_40ms_rms_envelope_nrmse": 0.02641975940852697, "全帯域_40ms_envelope_correlation": 0.999270698944042, "全帯域_40ms_modulation_mae_db": 0.5077619519746384, "300–1000 Hz_10ms_log_rms_mae_db": 1.2564417431086368, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0672457405350692, "300–1000 Hz_10ms_envelope_correlation": 0.9962947933421253, "300–1000 Hz_10ms_modulation_mae_db": 0.6764720921201769, "300–1000 Hz_40ms_log_rms_mae_db": 0.817971407431107, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03664884256764427, "300–1000 Hz_40ms_envelope_correlation": 0.9988680691428592, "300–1000 Hz_40ms_modulation_mae_db": 0.7439636469280932, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7757881087406673, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12357897351968881, "1000–3000 Hz_10ms_envelope_correlation": 0.9900155500649884, "1000–3000 Hz_10ms_modulation_mae_db": 0.4928646418632736, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3076498779615768, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08405006967024256, "1000–3000 Hz_40ms_envelope_correlation": 0.9958071340322256, "1000–3000 Hz_40ms_modulation_mae_db": 0.6151441113822361, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5967404899284945, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18427547718842316, "3000–6000 Hz_10ms_envelope_correlation": 0.9784223810785052, "3000–6000 Hz_10ms_modulation_mae_db": 1.2554653055497973, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0492453035587108, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11017475024818854, "3000–6000 Hz_40ms_envelope_correlation": 0.9935021059239841, "3000–6000 Hz_40ms_modulation_mae_db": 1.5637884168363332, "mr_stft_db": 5.82609485574119, "band_mae_db": 0.24205150862379562, "rms_gain_error_db": -0.06115056629389726, "output_peak": 0.2667097078936699}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8801651434935296, "全帯域_10ms_rms_envelope_nrmse": 0.050692432719744024, "全帯域_10ms_envelope_correlation": 0.9973854160136829, "全帯域_10ms_modulation_mae_db": 0.5199821357245549, "全帯域_40ms_log_rms_mae_db": 0.5122682431124557, "全帯域_40ms_rms_envelope_nrmse": 0.029115344766836984, "全帯域_40ms_envelope_correlation": 0.9991727535624565, "全帯域_40ms_modulation_mae_db": 0.5074268581103726, "300–1000 Hz_10ms_log_rms_mae_db": 1.23553425357502, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06482302768416168, "300–1000 Hz_10ms_envelope_correlation": 0.9966100563894421, "300–1000 Hz_10ms_modulation_mae_db": 0.8963587546036758, "300–1000 Hz_40ms_log_rms_mae_db": 0.8097624437469271, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03887687335914555, "300–1000 Hz_40ms_envelope_correlation": 0.9987828040408946, "300–1000 Hz_40ms_modulation_mae_db": 1.147666057643475, "1000–3000 Hz_10ms_log_rms_mae_db": 1.710303269217339, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1305742504830325, "1000–3000 Hz_10ms_envelope_correlation": 0.9883226296508005, "1000–3000 Hz_10ms_modulation_mae_db": 0.8865501916483313, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2478241932493777, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07583739112001478, "1000–3000 Hz_40ms_envelope_correlation": 0.9963604441996803, "1000–3000 Hz_40ms_modulation_mae_db": 0.7919859359897545, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5789992381593685, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1869418340842389, "3000–6000 Hz_10ms_envelope_correlation": 0.977815669296321, "3000–6000 Hz_10ms_modulation_mae_db": 0.7487679916340579, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0270438383269114, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11230563813288269, "3000–6000 Hz_40ms_envelope_correlation": 0.9919004095978131, "3000–6000 Hz_40ms_modulation_mae_db": 0.8465069476881112, "mr_stft_db": 5.804930065722988, "band_mae_db": 0.13646653989941945, "rms_gain_error_db": -0.0981712025109125, "output_peak": 0.26814029720304583}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9062542875623589, "全帯域_10ms_rms_envelope_nrmse": 0.0523101127988638, "全帯域_10ms_envelope_correlation": 0.9971440180961982, "全帯域_10ms_modulation_mae_db": 0.6445446361092073, "全帯域_40ms_log_rms_mae_db": 0.5108084076993002, "全帯域_40ms_rms_envelope_nrmse": 0.027488214670943072, "全帯域_40ms_envelope_correlation": 0.9992031728596924, "全帯域_40ms_modulation_mae_db": 0.5899739511318877, "300–1000 Hz_10ms_log_rms_mae_db": 1.2274020917482218, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06464596166544254, "300–1000 Hz_10ms_envelope_correlation": 0.9965877431311512, "300–1000 Hz_10ms_modulation_mae_db": 0.9949199681178662, "300–1000 Hz_40ms_log_rms_mae_db": 0.8067008556164288, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03441780694998966, "300–1000 Hz_40ms_envelope_correlation": 0.9990015557046034, "300–1000 Hz_40ms_modulation_mae_db": 1.0534251572125692, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7886074152624984, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.14899088397718785, "1000–3000 Hz_10ms_envelope_correlation": 0.9878656632186336, "1000–3000 Hz_10ms_modulation_mae_db": 1.3811037257025605, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3187198613754016, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10859853659535265, "1000–3000 Hz_40ms_envelope_correlation": 0.9956610675675888, "1000–3000 Hz_40ms_modulation_mae_db": 1.6579250137368267, "3000–6000 Hz_10ms_log_rms_mae_db": 1.575254379177695, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.20281505291414106, "3000–6000 Hz_10ms_envelope_correlation": 0.9743937960052331, "3000–6000 Hz_10ms_modulation_mae_db": 2.4406164248097997, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0239670502190457, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13714445539855433, "3000–6000 Hz_40ms_envelope_correlation": 0.9898322499228612, "3000–6000 Hz_40ms_modulation_mae_db": 2.6073173574605146, "mr_stft_db": 5.826652632545496, "band_mae_db": 0.32898129701018025, "rms_gain_error_db": -0.06681212157723632, "output_peak": 0.2712425471672639}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8949348141422543, "全帯域_10ms_rms_envelope_nrmse": 0.05073143040975627, "全帯域_10ms_envelope_correlation": 0.9973217605343988, "全帯域_10ms_modulation_mae_db": 0.42537329937977236, "全帯域_40ms_log_rms_mae_db": 0.48666664867036974, "全帯域_40ms_rms_envelope_nrmse": 0.025824609334498923, "全帯域_40ms_envelope_correlation": 0.9993083186970083, "全帯域_40ms_modulation_mae_db": 0.5653981699949778, "300–1000 Hz_10ms_log_rms_mae_db": 1.2290941578814871, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06627305251426382, "300–1000 Hz_10ms_envelope_correlation": 0.9964058951210358, "300–1000 Hz_10ms_modulation_mae_db": 0.6125610504253721, "300–1000 Hz_40ms_log_rms_mae_db": 0.7889756358486439, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03405843388357271, "300–1000 Hz_40ms_envelope_correlation": 0.9990515552542732, "300–1000 Hz_40ms_modulation_mae_db": 0.7987327147970542, "1000–3000 Hz_10ms_log_rms_mae_db": 1.744027830787834, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13293684658063537, "1000–3000 Hz_10ms_envelope_correlation": 0.9887907385769742, "1000–3000 Hz_10ms_modulation_mae_db": 0.9972674244218457, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2636537329198316, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07850735501037678, "1000–3000 Hz_40ms_envelope_correlation": 0.9972156730731986, "1000–3000 Hz_40ms_modulation_mae_db": 1.2277360049782757, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6209199991962537, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.21391236439963024, "3000–6000 Hz_10ms_envelope_correlation": 0.9693964625465847, "3000–6000 Hz_10ms_modulation_mae_db": 1.7638164552582571, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0645232310072799, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11779588195250784, "3000–6000 Hz_40ms_envelope_correlation": 0.9911985612396405, "3000–6000 Hz_40ms_modulation_mae_db": 2.2063249910175284, "mr_stft_db": 5.821835029619133, "band_mae_db": 0.2102764761871807, "rms_gain_error_db": -0.06776428540558979, "output_peak": 0.2885082675490968}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9141712979038487, "全帯域_10ms_rms_envelope_nrmse": 0.0516934754033443, "全帯域_10ms_envelope_correlation": 0.9971949108919651, "全帯域_10ms_modulation_mae_db": 0.31408660099740876, "全帯域_40ms_log_rms_mae_db": 0.5016593738941981, "全帯域_40ms_rms_envelope_nrmse": 0.027168518445810554, "全帯域_40ms_envelope_correlation": 0.9991904203448364, "全帯域_40ms_modulation_mae_db": 0.4144370556844097, "300–1000 Hz_10ms_log_rms_mae_db": 1.2762753266302915, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06933656573370822, "300–1000 Hz_10ms_envelope_correlation": 0.9960443581729168, "300–1000 Hz_10ms_modulation_mae_db": 0.8489333640966058, "300–1000 Hz_40ms_log_rms_mae_db": 0.8513532159046274, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03958912231115822, "300–1000 Hz_40ms_envelope_correlation": 0.9986471974865391, "300–1000 Hz_40ms_modulation_mae_db": 1.0480663800040553, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7503954065931664, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1308553054527924, "1000–3000 Hz_10ms_envelope_correlation": 0.9883511595770051, "1000–3000 Hz_10ms_modulation_mae_db": 0.44781797776259236, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3061304582327242, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0785531392335722, "1000–3000 Hz_40ms_envelope_correlation": 0.9961626342504271, "1000–3000 Hz_40ms_modulation_mae_db": 0.6284455619957808, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5566280000539787, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16870367503999809, "3000–6000 Hz_10ms_envelope_correlation": 0.9809229718493615, "3000–6000 Hz_10ms_modulation_mae_db": 1.1239109279563297, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0268298671626268, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08632714896298768, "3000–6000 Hz_40ms_envelope_correlation": 0.9948064666187693, "3000–6000 Hz_40ms_modulation_mae_db": 1.2061102169280775, "mr_stft_db": 5.812732599814502, "band_mae_db": 0.15571790204263314, "rms_gain_error_db": -0.03227706653676396, "output_peak": 0.2709828896085711}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8789949144620928, "全帯域_10ms_rms_envelope_nrmse": 0.04861259158798705, "全帯域_10ms_envelope_correlation": 0.9975581331856033, "全帯域_10ms_modulation_mae_db": 0.3906125580953837, "全帯域_40ms_log_rms_mae_db": 0.4727421795490694, "全帯域_40ms_rms_envelope_nrmse": 0.022788807930244043, "全帯域_40ms_envelope_correlation": 0.9994922560563747, "全帯域_40ms_modulation_mae_db": 0.3943941420069866, "300–1000 Hz_10ms_log_rms_mae_db": 1.2145156685393566, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06443575885175555, "300–1000 Hz_10ms_envelope_correlation": 0.996568265422093, "300–1000 Hz_10ms_modulation_mae_db": 0.9010200911364888, "300–1000 Hz_40ms_log_rms_mae_db": 0.7807905437409991, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.030868995638216597, "300–1000 Hz_40ms_envelope_correlation": 0.9991982998887953, "300–1000 Hz_40ms_modulation_mae_db": 1.0182095640207693, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7701910815261093, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1445306822188089, "1000–3000 Hz_10ms_envelope_correlation": 0.98614982199162, "1000–3000 Hz_10ms_modulation_mae_db": 0.7370216529277623, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3100227567101566, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08913738296573452, "1000–3000 Hz_40ms_envelope_correlation": 0.9955440381934748, "1000–3000 Hz_40ms_modulation_mae_db": 1.1326242023130773, "3000–6000 Hz_10ms_log_rms_mae_db": 1.633659019609673, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19836627008377186, "3000–6000 Hz_10ms_envelope_correlation": 0.9748264077680544, "3000–6000 Hz_10ms_modulation_mae_db": 1.2291461300921958, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0427973275038198, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12947413991957593, "3000–6000 Hz_40ms_envelope_correlation": 0.9903512186546282, "3000–6000 Hz_40ms_modulation_mae_db": 1.33709492737082, "mr_stft_db": 5.821892547861876, "band_mae_db": 0.26427920699957574, "rms_gain_error_db": -0.07508243213882626, "output_peak": 0.30079457412268074}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8951636644564013, "全帯域_10ms_rms_envelope_nrmse": 0.0529037615253049, "全帯域_10ms_envelope_correlation": 0.997166206648881, "全帯域_10ms_modulation_mae_db": 0.4497934523223428, "全帯域_40ms_log_rms_mae_db": 0.5303822917971858, "全帯域_40ms_rms_envelope_nrmse": 0.027793743996254016, "全帯域_40ms_envelope_correlation": 0.9992915192481723, "全帯域_40ms_modulation_mae_db": 0.5237297125286724, "300–1000 Hz_10ms_log_rms_mae_db": 1.2105902626988978, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06650669610415799, "300–1000 Hz_10ms_envelope_correlation": 0.9964448654647692, "300–1000 Hz_10ms_modulation_mae_db": 0.997942796740122, "300–1000 Hz_40ms_log_rms_mae_db": 0.805882646376223, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03580199392721175, "300–1000 Hz_40ms_envelope_correlation": 0.9990057292377083, "300–1000 Hz_40ms_modulation_mae_db": 1.186101244247789, "1000–3000 Hz_10ms_log_rms_mae_db": 1.800508089062963, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15653414457720244, "1000–3000 Hz_10ms_envelope_correlation": 0.983313985119048, "1000–3000 Hz_10ms_modulation_mae_db": 0.33611272865659086, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3036678478222588, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09219547280990416, "1000–3000 Hz_40ms_envelope_correlation": 0.9949424969369586, "1000–3000 Hz_40ms_modulation_mae_db": 0.7532747655444361, "3000–6000 Hz_10ms_log_rms_mae_db": 1.585592627104948, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1807620910841736, "3000–6000 Hz_10ms_envelope_correlation": 0.9798505715004414, "3000–6000 Hz_10ms_modulation_mae_db": 2.2958037881285756, "3000–6000 Hz_40ms_log_rms_mae_db": 1.054258458032675, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1154398168312699, "3000–6000 Hz_40ms_envelope_correlation": 0.9931969943380151, "3000–6000 Hz_40ms_modulation_mae_db": 2.6713698076786727, "mr_stft_db": 5.817959873036183, "band_mae_db": 0.23586135824269114, "rms_gain_error_db": -0.10761787526631247, "output_peak": 0.27104871240056055}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9360212774412419, "全帯域_10ms_rms_envelope_nrmse": 0.05817269442797186, "全帯域_10ms_envelope_correlation": 0.9964292524753051, "全帯域_10ms_modulation_mae_db": 0.6210262684585638, "全帯域_40ms_log_rms_mae_db": 0.5459870246120531, "全帯域_40ms_rms_envelope_nrmse": 0.032352330579626824, "全帯域_40ms_envelope_correlation": 0.9988416924930312, "全帯域_40ms_modulation_mae_db": 0.6488898546138341, "300–1000 Hz_10ms_log_rms_mae_db": 1.2011302001174078, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0732519137967732, "300–1000 Hz_10ms_envelope_correlation": 0.9955255370790278, "300–1000 Hz_10ms_modulation_mae_db": 0.9785376987676265, "300–1000 Hz_40ms_log_rms_mae_db": 0.7958937270679727, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.041678652243185815, "300–1000 Hz_40ms_envelope_correlation": 0.9984840708694319, "300–1000 Hz_40ms_modulation_mae_db": 1.2897650252790116, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7545001546650292, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13882840193351353, "1000–3000 Hz_10ms_envelope_correlation": 0.9867442192298296, "1000–3000 Hz_10ms_modulation_mae_db": 0.5721711986941621, "1000–3000 Hz_40ms_log_rms_mae_db": 1.287349762698301, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07814952464381543, "1000–3000 Hz_40ms_envelope_correlation": 0.9961642089297041, "1000–3000 Hz_40ms_modulation_mae_db": 1.0691835734106123, "3000–6000 Hz_10ms_log_rms_mae_db": 1.589416305700835, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15813887715798797, "3000–6000 Hz_10ms_envelope_correlation": 0.9836118921791995, "3000–6000 Hz_10ms_modulation_mae_db": 0.4181944698861341, "3000–6000 Hz_40ms_log_rms_mae_db": 1.021505467021587, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10624137033303635, "3000–6000 Hz_40ms_envelope_correlation": 0.9926803596159973, "3000–6000 Hz_40ms_modulation_mae_db": 0.3980211128571363, "mr_stft_db": 5.823627652784367, "band_mae_db": 0.1644855280782818, "rms_gain_error_db": -0.04783922841245826, "output_peak": 0.2747076722075878}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.958791760028439, "spectral_convergence": 0.15318930382378151, "spectral_convergence_status": "ok", "amplitude_floor": 9.829298518478812e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.877575500998184, "spectral_convergence": 0.15498233446985893, "spectral_convergence_status": "ok", "amplitude_floor": 9.065329093063253e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.641917306196948, "spectral_convergence": 0.15799238152333225, "spectral_convergence_status": "ok", "amplitude_floor": 8.043941450863317e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.0001149513766055836, "output_power": 0.00012075574384218693, "delta_db": 0.21393620924081633, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0017363654374162414, "output_power": 0.0017130501312924006, "delta_db": -0.05871060067950358, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0004421876194377549, "output_power": 0.0004340735980766674, "delta_db": -0.08043207562464308, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.7408011480563064e-05, "output_power": 2.534713774760992e-05, "delta_db": -0.33948602550203777, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7412343207141002e-05, "output_power": 2.509634405777427e-05, "delta_db": -0.3833570093814743, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.428426915438781e-05, "output_power": 3.163318467759632e-05, "delta_db": -0.34951979139088296, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.433275239990599e-05, "output_power": 1.3472174938774074e-05, "delta_db": -0.2689188485472114, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.24205150862379562, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.06115056629389726, "pitch": null, "output_rms_dbfs": -26.26457565788169, "output_peak": 0.2667097078936699, "reference_rms_dbfs": -26.20342509158779, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.82609485574119}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014020226421084518, "log_rms_mae_db": 0.8889832756369812, "rms_envelope_nrmse": 0.05290988278719844, "envelope_correlation": 0.9970802186593903, "rms_gain_error_db": -0.06115057266077016, "reference_mean_power": 0.002398940884341968, "output_mean_power": 0.0023653994351988373}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.599888913877476e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003971876344997112, "output_power": 0.0003897445401142788, "reference_active": true, "delta_db": -0.08215679376492217}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.277425400163653e-05, "output_power": 4.8301833084034805e-05, "reference_active": true, "delta_db": -0.3845849018363532}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.46569016072901e-05, "output_power": 1.1774713073973378e-05, "reference_active": true, "delta_db": -0.9509183936597967}], "active_band_count": 3, "active_band_mae_db": 0.472553363087024}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001294702248118231, "log_rms_mae_db": 0.4879446409146699, "rms_envelope_nrmse": 0.02641975940852697, "envelope_correlation": 0.999270698944042, "rms_gain_error_db": -0.061150556087258626, "reference_mean_power": 0.0024110057038516162, "output_mean_power": 0.002377295576201677}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 8.923189531660561e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00035367674920645624, "output_power": 0.00034658195518542847, "reference_active": true, "delta_db": -0.08800562737829437}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.2909806376051565e-05, "output_power": 2.103802613997132e-05, "reference_active": true, "delta_db": -0.3701642834260045}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.181144761591823e-07, "output_power": 6.401805612149464e-07, "reference_active": true, "delta_db": -1.0651159451196162}], "active_band_count": 3, "active_band_mae_db": 0.5077619519746384}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00013300454501172858, "log_rms_mae_db": 1.2564417431086368, "rms_envelope_nrmse": 0.0672457405350692, "envelope_correlation": 0.9962947933421253, "rms_gain_error_db": -0.06247981510540576, "reference_mean_power": 0.0013111812883454625, "output_mean_power": 0.001292453007136738}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.210472671322603e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002971533743381409, "output_power": 0.00028893210405871015, "reference_active": true, "delta_db": -0.12184866065560969}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.9363200025831e-05, "output_power": 4.1037948488196316e-05, "reference_active": true, "delta_db": -0.8021766357043012}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.44718666084695e-06, "output_power": 7.324254024709628e-06, "reference_active": true, "delta_db": -1.1053909800006199}], "active_band_count": 3, "active_band_mae_db": 0.6764720921201769}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00012063998479701045, "log_rms_mae_db": 0.817971407431107, "rms_envelope_nrmse": 0.03664884256764427, "envelope_correlation": 0.9988680691428592, "rms_gain_error_db": -0.06247982066584978, "reference_mean_power": 0.0013177756236779122, "output_mean_power": 0.0012989531505003002}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.775720236374225e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00027184637186405784, "output_power": 0.00026193013917745294, "reference_active": true, "delta_db": -0.16138067460164668}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0948015125222398e-05, "output_power": 1.779786771333702e-05, "reference_active": true, "delta_db": -0.7077490435098115}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.00249959518115e-07, "output_power": 5.116547026648908e-07, "reference_active": true, "delta_db": -1.3627612226728214}], "active_band_count": 3, "active_band_mae_db": 0.7439636469280932}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.4324234792903394e-05, "log_rms_mae_db": 1.7757881087406673, "rms_envelope_nrmse": 0.12357897351968881, "envelope_correlation": 0.9900155500649884, "rms_gain_error_db": -0.3064552417759239, "reference_mean_power": 3.621970358575803e-05, "output_mean_power": 3.375198875194848e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.144567073932934e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6016299479105344e-05, "output_power": 1.4534796438767098e-05, "reference_active": true, "delta_db": -0.4215322700851418}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.217328435986187e-06, "output_power": 4.683152067720577e-06, "reference_active": true, "delta_db": -0.4690991676195666}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.162268250073546e-07, "output_power": 5.382008147781631e-07, "reference_active": true, "delta_db": -0.5879624878851123}], "active_band_count": 3, "active_band_mae_db": 0.4928646418632736}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9150097924886824e-05, "log_rms_mae_db": 1.3076498779615768, "rms_envelope_nrmse": 0.08405006967024256, "envelope_correlation": 0.9958071340322256, "rms_gain_error_db": -0.30645543585032253, "reference_mean_power": 3.640185858193717e-05, "output_mean_power": 3.392173167828774e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.976051267531115e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.575058419062026e-05, "output_power": 1.4177968874325236e-05, "reference_active": true, "delta_db": -0.45682647860238434}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5755236704985135e-06, "output_power": 2.365617467128471e-06, "reference_active": true, "delta_db": -0.369210273914965}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.671987913674402e-08, "output_power": 5.276132490927945e-08, "reference_active": true, "delta_db": -1.019395581629359}], "active_band_count": 3, "active_band_mae_db": 0.6151441113822361}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.268273320274525e-05, "log_rms_mae_db": 1.5967404899284945, "rms_envelope_nrmse": 0.18427547718842316, "envelope_correlation": 0.9784223810785052, "rms_gain_error_db": -0.4789556932977604, "reference_mean_power": 3.4234790780271314e-05, "output_mean_power": 3.065999705264785e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.011440004206466e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3904345626991894e-05, "output_power": 1.2316197185238893e-05, "reference_active": true, "delta_db": -0.5267392126060902}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.336600248325665e-06, "output_power": 4.206739985578009e-06, "reference_active": true, "delta_db": -1.0331900254857738}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.037307900027025e-06, "output_power": 1.225772860107505e-06, "reference_active": true, "delta_db": -2.206466678557528}], "active_band_count": 3, "active_band_mae_db": 1.2554653055497973}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.282155756745637e-05, "log_rms_mae_db": 1.0492453035587108, "rms_envelope_nrmse": 0.11017475024818854, "envelope_correlation": 0.9935021059239841, "rms_gain_error_db": -0.4789557951240342, "reference_mean_power": 3.440696652445238e-05, "output_mean_power": 3.081419349886039e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.8610527191429872e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5067699650347801e-05, "output_power": 1.2881323425306288e-05, "reference_active": true, "delta_db": -0.6808647000754311}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.7890585183930857e-06, "output_power": 2.1067146245816853e-06, "reference_active": true, "delta_db": -1.2185191638264412}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4153621023540917e-07, "output_power": 7.441653151936379e-08, "reference_active": true, "delta_db": -2.7919813866071275}], "active_band_count": 3, "active_band_mae_db": 1.5637884168363332}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8935862617104664, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "44495b8d34280920236567ef2da5ad74eadda57c4d56942961cc42b88f422cbe", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9874442209286124, "standard_deviation": 0.0020501189976926738, "minimum": 0.983313985119048, "maximum": 0.9900155500649884, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.7617901694819509, "standard_deviation": 0.028370372137812024, "minimum": 1.710303269217339, "maximum": 1.800508089062963, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7313636927096399, "standard_deviation": 0.3455486964718947, "minimum": 0.33611272865659086, "maximum": 1.3811037257025605, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.13835368609285773, "standard_deviation": 0.010996358477452022, "minimum": 0.12357897351968881, "maximum": 0.15653414457720244, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9959822121479072, "standard_deviation": 0.0006694294612526025, "minimum": 0.9949424969369586, "maximum": 0.9972156730731986, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.2931273113712036, "standard_deviation": 0.025031319733560355, "minimum": 1.2478241932493777, "maximum": 1.3187198613754016, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.9845398961688748, "standard_deviation": 0.357671514620602, "minimum": 0.6151441113822361, "maximum": 1.6579250137368267, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08562860900612664, "standard_deviation": 0.010942210121310731, "minimum": 0.07583739112001478, "maximum": 0.10859853659535265, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9774050190279626, "standard_deviation": 0.004439101091233441, "minimum": 0.9693964625465847, "maximum": 0.9836118921791995, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5921512573664058, "standard_deviation": 0.02490689345707846, "minimum": 1.5566280000539787, "maximum": 1.633659019609673, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.4094651866643935, "standard_deviation": 0.7102659855498917, "minimum": 0.4181944698861341, "maximum": 2.4406164248097997, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.18673945524404562, "standard_deviation": 0.018193790610787967, "minimum": 0.15813887715798797, "maximum": 0.21391236439963024, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9921835457389636, "standard_deviation": 0.0016830496169460965, "minimum": 0.9898322499228612, "maximum": 0.9948064666187693, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.038771317854082, "standard_deviation": 0.016152547954947714, "minimum": 1.021505467021587, "maximum": 1.0645232310072799, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.6045667222296491, "standard_deviation": 0.8253197839764898, "minimum": 0.3980211128571363, "maximum": 2.6713698076786727, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1143629002223754, "standard_deviation": 0.015278507118106903, "minimum": 0.08632714896298768, "maximum": 0.13714445539855433, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9963101892653201, "standard_deviation": 0.0003678973634764766, "minimum": 0.9955255370790278, "maximum": 0.9966100563894421, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.2313729630374148, "standard_deviation": 0.02482411506507674, "minimum": 1.2011302001174078, "maximum": 1.2762753266302915, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8633432270009918, "standard_deviation": 0.14600830981490182, "minimum": 0.6125610504253721, "maximum": 0.997942796740122, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06706483961066653, "standard_deviation": 0.0029809049333434975, "minimum": 0.06443575885175555, "maximum": 0.0732519137967732, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.998879910203138, "standard_deviation": 0.0002335673280200581, "minimum": 0.9984840708694319, "maximum": 0.9991982998887953, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.8071663094666162, "standard_deviation": 0.021485842289496904, "minimum": 0.7807905437409991, "maximum": 0.8513532159046274, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.0357412237666022, "standard_deviation": 0.18583501656571133, "minimum": 0.7439636469280932, "maximum": 1.2897650252790116, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03649259011001557, "standard_deviation": 0.0034749008851481, "minimum": 0.030868995638216597, "maximum": 0.041678652243185815, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.21726497713546972, "standard_deviation": 0.06414493719040408, "minimum": 0.13646653989941945, "maximum": 0.32898129701018025, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.819465657140717, "standard_deviation": 0.007399900447166636, "minimum": 5.804930065722988, "maximum": 5.826652632545496, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.2765168335190596, "standard_deviation": 0.011899371517268074, "minimum": 0.2667097078936699, "maximum": 0.30079457412268074, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06958934726774961, "standard_deviation": 0.024613574052624012, "minimum": -0.10761787526631247, "maximum": -0.03227706653676396, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9971599895631782, "standard_deviation": 0.00033324349818870225, "minimum": 0.9964292524753051, "maximum": 0.9975581331856033, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.8993360843873386, "standard_deviation": 0.01904505023886756, "minimum": 0.8789949144620928, "maximum": 0.9360212774412419, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.47974653927178224, "standard_deviation": 0.11214196231909518, "minimum": 0.31408660099740876, "maximum": 0.6445446361092073, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05225329770752133, "standard_deviation": 0.002783040841467403, "minimum": 0.04861259158798705, "maximum": 0.05817269442797186, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9992213540257018, "standard_deviation": 0.0001836538574583219, "minimum": 0.9988416924930312, "maximum": 0.9994922560563747, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5060573512811628, "standard_deviation": 0.024144037285318106, "minimum": 0.4727421795490694, "maximum": 0.5459870246120531, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5190014620057224, "standard_deviation": 0.08519230089291238, "minimum": 0.3943941420069866, "maximum": 0.6488898546138341, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.027368916141592675, "standard_deviation": 0.002735545799078163, "minimum": 0.022788807930244043, "maximum": 0.032352330579626824, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 2.218665361404419, "predicted_mos": 2.218665361404419, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "767e5bf2e3bcf159b6edb35fd4b409c091ea3c8effc1d2b5000e011f97a295ab", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.790998800192028}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9110678708342417, "全帯域_10ms_rms_envelope_nrmse": 0.054201574356627966, "全帯域_10ms_envelope_correlation": 0.997019815156962, "全帯域_10ms_modulation_mae_db": 0.3020152235705113, "全帯域_40ms_log_rms_mae_db": 0.5299218522134138, "全帯域_40ms_rms_envelope_nrmse": 0.030788163628344068, "全帯域_40ms_envelope_correlation": 0.9990924116563942, "全帯域_40ms_modulation_mae_db": 0.10971124277168261, "300–1000 Hz_10ms_log_rms_mae_db": 1.0657600558672742, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06480361468462721, "300–1000 Hz_10ms_envelope_correlation": 0.9965317122151677, "300–1000 Hz_10ms_modulation_mae_db": 0.5766918798814246, "300–1000 Hz_40ms_log_rms_mae_db": 0.7181669785788547, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035675548998067935, "300–1000 Hz_40ms_envelope_correlation": 0.9989429815621681, "300–1000 Hz_40ms_modulation_mae_db": 0.5012594929316919, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3187779142098337, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11691534921620851, "1000–3000 Hz_10ms_envelope_correlation": 0.9905296087219855, "1000–3000 Hz_10ms_modulation_mae_db": 0.3695820523282687, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9882451209499094, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07382429653617555, "1000–3000 Hz_40ms_envelope_correlation": 0.9962769854634198, "1000–3000 Hz_40ms_modulation_mae_db": 0.4570680553708934, "3000–6000 Hz_10ms_log_rms_mae_db": 1.211062850429493, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.20163599544475586, "3000–6000 Hz_10ms_envelope_correlation": 0.9727788561125185, "3000–6000 Hz_10ms_modulation_mae_db": 0.573135791445219, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8283729317255484, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1458400094635626, "3000–6000 Hz_40ms_envelope_correlation": 0.9851620252824809, "3000–6000 Hz_40ms_modulation_mae_db": 0.7127432604423795, "mr_stft_db": 5.509866260778954, "band_mae_db": 0.20466110762734632, "rms_gain_error_db": -0.10994442996962257, "output_peak": 0.28892077073250455}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9146855584044142, "全帯域_10ms_rms_envelope_nrmse": 0.052495201647193304, "全帯域_10ms_envelope_correlation": 0.9972105193668892, "全帯域_10ms_modulation_mae_db": 0.2948495577306308, "全帯域_40ms_log_rms_mae_db": 0.4800934878697351, "全帯域_40ms_rms_envelope_nrmse": 0.02560354218202803, "全帯域_40ms_envelope_correlation": 0.9994233512465152, "全帯域_40ms_modulation_mae_db": 0.4639929815260448, "300–1000 Hz_10ms_log_rms_mae_db": 1.0692186856393144, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05922456467172771, "300–1000 Hz_10ms_envelope_correlation": 0.9971690599661035, "300–1000 Hz_10ms_modulation_mae_db": 0.7938234282738758, "300–1000 Hz_40ms_log_rms_mae_db": 0.7169363843657353, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.033223498439604655, "300–1000 Hz_40ms_envelope_correlation": 0.9991293424477236, "300–1000 Hz_40ms_modulation_mae_db": 1.0249024058448384, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4206471662783686, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1330310093335989, "1000–3000 Hz_10ms_envelope_correlation": 0.9895648659108554, "1000–3000 Hz_10ms_modulation_mae_db": 0.8315018945716476, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0576181252557895, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08918616814091797, "1000–3000 Hz_40ms_envelope_correlation": 0.9967608381171089, "1000–3000 Hz_40ms_modulation_mae_db": 1.105485079150078, "3000–6000 Hz_10ms_log_rms_mae_db": 1.170749225685272, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13779135155541156, "3000–6000 Hz_10ms_envelope_correlation": 0.9881024323793997, "3000–6000 Hz_10ms_modulation_mae_db": 0.2704368978288125, "3000–6000 Hz_40ms_log_rms_mae_db": 0.737146682609614, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07863679137967977, "3000–6000 Hz_40ms_envelope_correlation": 0.996868590099944, "3000–6000 Hz_40ms_modulation_mae_db": 0.27961798221214196, "mr_stft_db": 5.507249595151245, "band_mae_db": 0.3130089249614083, "rms_gain_error_db": -0.10785964547363297, "output_peak": 0.2797160576242317}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9104937151302315, "全帯域_10ms_rms_envelope_nrmse": 0.05870462891741837, "全帯域_10ms_envelope_correlation": 0.9963735703228755, "全帯域_10ms_modulation_mae_db": 0.6973024918713255, "全帯域_40ms_log_rms_mae_db": 0.5085928716418221, "全帯域_40ms_rms_envelope_nrmse": 0.03150229913480581, "全帯域_40ms_envelope_correlation": 0.9989138094125132, "全帯域_40ms_modulation_mae_db": 1.0061513258021901, "300–1000 Hz_10ms_log_rms_mae_db": 1.0544344410271482, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07147553286021806, "300–1000 Hz_10ms_envelope_correlation": 0.99573873503912, "300–1000 Hz_10ms_modulation_mae_db": 0.605233960436936, "300–1000 Hz_40ms_log_rms_mae_db": 0.6691485837605876, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037792564981644634, "300–1000 Hz_40ms_envelope_correlation": 0.9987492047957319, "300–1000 Hz_40ms_modulation_mae_db": 0.8617784238847174, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3307199113856774, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15663780800372026, "1000–3000 Hz_10ms_envelope_correlation": 0.983399220941956, "1000–3000 Hz_10ms_modulation_mae_db": 0.3953578435531482, "1000–3000 Hz_40ms_log_rms_mae_db": 1.002292632797317, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08208446146328983, "1000–3000 Hz_40ms_envelope_correlation": 0.9964833777087099, "1000–3000 Hz_40ms_modulation_mae_db": 0.814047440437012, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1815892050421202, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2189723570964106, "3000–6000 Hz_10ms_envelope_correlation": 0.9721398289459082, "3000–6000 Hz_10ms_modulation_mae_db": 3.3892403325406515, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7842984268141766, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.15484372736740176, "3000–6000 Hz_40ms_envelope_correlation": 0.9894196275785504, "3000–6000 Hz_40ms_modulation_mae_db": 3.720364732172399, "mr_stft_db": 5.514584927660079, "band_mae_db": 0.3073747772485665, "rms_gain_error_db": -0.055676688439787285, "output_peak": 0.2703503547433864}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9072440486626239, "全帯域_10ms_rms_envelope_nrmse": 0.04963372955578415, "全帯域_10ms_envelope_correlation": 0.9975059316904481, "全帯域_10ms_modulation_mae_db": 0.3964928303806037, "全帯域_40ms_log_rms_mae_db": 0.47823370667823606, "全帯域_40ms_rms_envelope_nrmse": 0.028987315776373705, "全帯域_40ms_envelope_correlation": 0.9991900511624513, "全帯域_40ms_modulation_mae_db": 0.41005989740975174, "300–1000 Hz_10ms_log_rms_mae_db": 1.0017158696125146, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0607156847447138, "300–1000 Hz_10ms_envelope_correlation": 0.9969857240026648, "300–1000 Hz_10ms_modulation_mae_db": 0.6078805315244713, "300–1000 Hz_40ms_log_rms_mae_db": 0.6546321547933529, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035879521822368705, "300–1000 Hz_40ms_envelope_correlation": 0.9989349447051538, "300–1000 Hz_40ms_modulation_mae_db": 0.7411707654678082, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3418694629700771, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12112934422337743, "1000–3000 Hz_10ms_envelope_correlation": 0.9903673649066356, "1000–3000 Hz_10ms_modulation_mae_db": 0.7800496366132453, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0379750006702855, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07067758828135545, "1000–3000 Hz_40ms_envelope_correlation": 0.9973577313401163, "1000–3000 Hz_40ms_modulation_mae_db": 1.0224956081774248, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1772445451462132, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1557435019263073, "3000–6000 Hz_10ms_envelope_correlation": 0.9870050454880291, "3000–6000 Hz_10ms_modulation_mae_db": 1.726957567056332, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7495653155943052, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1113938464775733, "3000–6000 Hz_40ms_envelope_correlation": 0.9952902085545333, "3000–6000 Hz_40ms_modulation_mae_db": 2.0470291658209603, "mr_stft_db": 5.511728956403938, "band_mae_db": 0.28379605229498706, "rms_gain_error_db": -0.1013518726942354, "output_peak": 0.2828728789041666}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9339777664299628, "全帯域_10ms_rms_envelope_nrmse": 0.04942544097797467, "全帯域_10ms_envelope_correlation": 0.9974306270182576, "全帯域_10ms_modulation_mae_db": 0.3311432723685184, "全帯域_40ms_log_rms_mae_db": 0.5514453462807519, "全帯域_40ms_rms_envelope_nrmse": 0.026239534302877426, "全帯域_40ms_envelope_correlation": 0.999247460922674, "全帯域_40ms_modulation_mae_db": 0.5486192851526849, "300–1000 Hz_10ms_log_rms_mae_db": 1.0311818213438637, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06463005909946089, "300–1000 Hz_10ms_envelope_correlation": 0.9964957852998108, "300–1000 Hz_10ms_modulation_mae_db": 0.6839920054903149, "300–1000 Hz_40ms_log_rms_mae_db": 0.6733075619561527, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03595927725255673, "300–1000 Hz_40ms_envelope_correlation": 0.9988376488671805, "300–1000 Hz_40ms_modulation_mae_db": 0.9613920117475434, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4144054080796917, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11689754057679035, "1000–3000 Hz_10ms_envelope_correlation": 0.9921087404655115, "1000–3000 Hz_10ms_modulation_mae_db": 0.8907511401024107, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0880151925447177, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08290605390151368, "1000–3000 Hz_40ms_envelope_correlation": 0.997033128943484, "1000–3000 Hz_40ms_modulation_mae_db": 1.1098760800425809, "3000–6000 Hz_10ms_log_rms_mae_db": 1.212279936849819, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16525569094115078, "3000–6000 Hz_10ms_envelope_correlation": 0.9816703401707203, "3000–6000 Hz_10ms_modulation_mae_db": 0.7723976911849332, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8111968305393501, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09348117940824173, "3000–6000 Hz_40ms_envelope_correlation": 0.9939365543438148, "3000–6000 Hz_40ms_modulation_mae_db": 0.8433259313028881, "mr_stft_db": 5.524352404922659, "band_mae_db": 0.22970327737668214, "rms_gain_error_db": -0.04624413730969188, "output_peak": 0.2767539344953911}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9071955822644687, "全帯域_10ms_rms_envelope_nrmse": 0.04614316467365023, "全帯域_10ms_envelope_correlation": 0.9977972461346672, "全帯域_10ms_modulation_mae_db": 0.11123908570624141, "全帯域_40ms_log_rms_mae_db": 0.5576502232485312, "全帯域_40ms_rms_envelope_nrmse": 0.024678617799577737, "全帯域_40ms_envelope_correlation": 0.9993758118577671, "全帯域_40ms_modulation_mae_db": 0.17198127158736765, "300–1000 Hz_10ms_log_rms_mae_db": 1.0700892662903, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07209115481075268, "300–1000 Hz_10ms_envelope_correlation": 0.9956956332006405, "300–1000 Hz_10ms_modulation_mae_db": 0.5944511710230662, "300–1000 Hz_40ms_log_rms_mae_db": 0.6893703145478165, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03856646279246839, "300–1000 Hz_40ms_envelope_correlation": 0.9987347828458701, "300–1000 Hz_40ms_modulation_mae_db": 0.8685728767603712, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3416602820792516, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10076109460484034, "1000–3000 Hz_10ms_envelope_correlation": 0.9932044319899606, "1000–3000 Hz_10ms_modulation_mae_db": 1.014787083710208, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0106082655793907, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.061544343721295386, "1000–3000 Hz_40ms_envelope_correlation": 0.9976932320951649, "1000–3000 Hz_40ms_modulation_mae_db": 1.129251812052954, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1853926535394768, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1477391802469034, "3000–6000 Hz_10ms_envelope_correlation": 0.9857612135515562, "3000–6000 Hz_10ms_modulation_mae_db": 0.26828473839915395, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7654823393556738, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09128019920709078, "3000–6000 Hz_40ms_envelope_correlation": 0.994794841371918, "3000–6000 Hz_40ms_modulation_mae_db": 0.36198793779306326, "mr_stft_db": 5.519309076798009, "band_mae_db": 0.18948686462729938, "rms_gain_error_db": -0.06827670782088276, "output_peak": 0.27782747664221247}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8648822846199347, "全帯域_10ms_rms_envelope_nrmse": 0.04776040624567849, "全帯域_10ms_envelope_correlation": 0.9976536418612771, "全帯域_10ms_modulation_mae_db": 0.3275871338716948, "全帯域_40ms_log_rms_mae_db": 0.47881087853788495, "全帯域_40ms_rms_envelope_nrmse": 0.026278904442932627, "全帯域_40ms_envelope_correlation": 0.9993064884518505, "全帯域_40ms_modulation_mae_db": 0.4766649359172588, "300–1000 Hz_10ms_log_rms_mae_db": 1.0430607156009948, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06363654625736291, "300–1000 Hz_10ms_envelope_correlation": 0.9966412155580114, "300–1000 Hz_10ms_modulation_mae_db": 0.6846532601523775, "300–1000 Hz_40ms_log_rms_mae_db": 0.727674807345198, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03492687029104807, "300–1000 Hz_40ms_envelope_correlation": 0.9989493761462644, "300–1000 Hz_40ms_modulation_mae_db": 0.7195546597770935, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3846651384547055, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11983292652149584, "1000–3000 Hz_10ms_envelope_correlation": 0.9912263121458329, "1000–3000 Hz_10ms_modulation_mae_db": 1.4465766768450534, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0475331783218125, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07977626931485862, "1000–3000 Hz_40ms_envelope_correlation": 0.997008986096499, "1000–3000 Hz_40ms_modulation_mae_db": 1.6542606235311101, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2085473947690304, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1633697975008655, "3000–6000 Hz_10ms_envelope_correlation": 0.982899475394795, "3000–6000 Hz_10ms_modulation_mae_db": 0.7229985869573626, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7919043580474671, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09698071292910396, "3000–6000 Hz_40ms_envelope_correlation": 0.9938889364548105, "3000–6000 Hz_40ms_modulation_mae_db": 0.738150099001102, "mr_stft_db": 5.529743611691096, "band_mae_db": 0.1986841790713943, "rms_gain_error_db": -0.08006730721932136, "output_peak": 0.2932791064183302}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9448493962348496, "全帯域_10ms_rms_envelope_nrmse": 0.05106522183963845, "全帯域_10ms_envelope_correlation": 0.9973259386214335, "全帯域_10ms_modulation_mae_db": 0.5705960631251176, "全帯域_40ms_log_rms_mae_db": 0.507435968558761, "全帯域_40ms_rms_envelope_nrmse": 0.025580150316150206, "全帯域_40ms_envelope_correlation": 0.9993734403055615, "全帯域_40ms_modulation_mae_db": 0.6601533227523498, "300–1000 Hz_10ms_log_rms_mae_db": 1.0677085613835162, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06875340809011236, "300–1000 Hz_10ms_envelope_correlation": 0.9961330670768768, "300–1000 Hz_10ms_modulation_mae_db": 0.8595459142378736, "300–1000 Hz_40ms_log_rms_mae_db": 0.705206150576903, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035557165537676086, "300–1000 Hz_40ms_envelope_correlation": 0.9989799365438312, "300–1000 Hz_40ms_modulation_mae_db": 0.9690585108700982, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3576323632508531, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12188092022972051, "1000–3000 Hz_10ms_envelope_correlation": 0.990550578627475, "1000–3000 Hz_10ms_modulation_mae_db": 0.9355862610752527, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0118282679435775, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07125719048485547, "1000–3000 Hz_40ms_envelope_correlation": 0.9976993898414345, "1000–3000 Hz_40ms_modulation_mae_db": 1.2042759986524816, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1650174999078504, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17497590783289702, "3000–6000 Hz_10ms_envelope_correlation": 0.9796226236659553, "3000–6000 Hz_10ms_modulation_mae_db": 0.37462370562298614, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8042509805196978, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11790146656133631, "3000–6000 Hz_40ms_envelope_correlation": 0.9903979421038644, "3000–6000 Hz_40ms_modulation_mae_db": 0.3760166228555972, "mr_stft_db": 5.5194756680553745, "band_mae_db": 0.24212125863538383, "rms_gain_error_db": -0.09019463545583722, "output_peak": 0.2645062037482876}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.524910770496749, "spectral_convergence": 0.15127257836974692, "spectral_convergence_status": "ok", "amplitude_floor": 9.829298518478812e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.520498529293086, "spectral_convergence": 0.15262083103759058, "spectral_convergence_status": "ok", "amplitude_floor": 9.065329093063253e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.484189482547027, "spectral_convergence": 0.16068702400557902, "spectral_convergence_status": "ok", "amplitude_floor": 8.043941450863317e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.0001149513766055836, "output_power": 0.00012010521701622494, "delta_db": 0.19047695733111547, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0017363654374162414, "output_power": 0.0016782476888504505, "delta_db": -0.14785074782106825, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0004421876194377549, "output_power": 0.00043769868825990527, "delta_db": -0.04431333769143391, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.7408011480563064e-05, "output_power": 2.6560217690677743e-05, "delta_db": -0.1364589729770711, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7412343207141002e-05, "output_power": 2.400594927406872e-05, "delta_db": -0.5762727654449389, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.428426915438781e-05, "output_power": 3.540633826818572e-05, "delta_db": 0.13986118298044622, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.433275239990599e-05, "output_power": 1.4999230437186414e-05, "delta_db": 0.19739378914535047, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.20466110762734632, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.10994442996962257, "pitch": null, "output_rms_dbfs": -26.313369521557416, "output_peak": 0.28892077073250455, "reference_rms_dbfs": -26.20342509158779, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.509866260778954}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014020226421084518, "log_rms_mae_db": 0.9110678708342417, "rms_envelope_nrmse": 0.054201574356627966, "envelope_correlation": 0.997019815156962, "rms_gain_error_db": -0.10994446038749428, "reference_mean_power": 0.002398940884341968, "output_mean_power": 0.002338972415413523}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.599888913877476e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003971876344997112, "output_power": 0.00038157185549857897, "reference_active": true, "delta_db": -0.1741938537532992}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.277425400163653e-05, "output_power": 5.498942566918971e-05, "reference_active": true, "delta_db": 0.17857080777725107}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.46569016072901e-05, "output_power": 1.2903694472817816e-05, "reference_active": true, "delta_db": -0.5532810091809837}], "active_band_count": 3, "active_band_mae_db": 0.3020152235705113}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001294702248118231, "log_rms_mae_db": 0.5299218522134138, "rms_envelope_nrmse": 0.030788163628344068, "envelope_correlation": 0.9990924116563942, "rms_gain_error_db": -0.10994442950237181, "reference_mean_power": 0.0024110057038516162, "output_mean_power": 0.0023507356565664254}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 8.923189531660561e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00035367674920645624, "output_power": 0.00034118571716037626, "reference_active": true, "delta_db": -0.15615667847042577}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.2909806376051565e-05, "output_power": 2.3212746344832013e-05, "reference_active": true, "delta_db": 0.05705106981785345}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.181144761591823e-07, "output_power": 7.965654754019265e-07, "reference_active": true, "delta_db": -0.11592598002676863}], "active_band_count": 3, "active_band_mae_db": 0.10971124277168261}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00013300454501172858, "log_rms_mae_db": 1.0657600558672742, "rms_envelope_nrmse": 0.06480361468462721, "envelope_correlation": 0.9965317122151677, "rms_gain_error_db": -0.09462954745675434, "reference_mean_power": 0.0013111812883454625, "output_mean_power": 0.001282920627794358}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.210472671322603e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002971533743381409, "output_power": 0.00028227990910194577, "reference_active": true, "delta_db": -0.22300697358957028}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.9363200025831e-05, "output_power": 4.377255697873536e-05, "reference_active": true, "delta_db": -0.5220138885957286}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.44718666084695e-06, "output_power": 7.530035412824091e-06, "reference_active": true, "delta_db": -0.9850547774589746}], "active_band_count": 3, "active_band_mae_db": 0.5766918798814246}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00012063998479701045, "log_rms_mae_db": 0.7181669785788547, "rms_envelope_nrmse": 0.035675548998067935, "envelope_correlation": 0.9989429815621681, "rms_gain_error_db": -0.09462961806010362, "reference_mean_power": 0.0013177756236779122, "output_mean_power": 0.0012893728105822335}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.775720236374225e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00027184637186405784, "output_power": 0.000257447272136171, "reference_active": true, "delta_db": -0.23635246680236602}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0948015125222398e-05, "output_power": 1.8693359812760243e-05, "reference_active": true, "delta_db": -0.49455513381762173}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.00249959518115e-07, "output_power": 5.860922849572449e-07, "reference_active": true, "delta_db": -0.772870878175088}], "active_band_count": 3, "active_band_mae_db": 0.5012594929316919}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.4324234792903394e-05, "log_rms_mae_db": 1.3187779142098337, "rms_envelope_nrmse": 0.11691534921620851, "envelope_correlation": 0.9905296087219855, "rms_gain_error_db": -0.202227080957928, "reference_mean_power": 3.621970358575803e-05, "output_mean_power": 3.4571815268908106e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.144567073932934e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6016299479105344e-05, "output_power": 1.5091331212661403e-05, "reference_active": true, "delta_db": -0.25834630057350993}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.217328435986187e-06, "output_power": 4.9646927024912495e-06, "reference_active": true, "delta_db": -0.21555804530876452}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.162268250073546e-07, "output_power": 5.32422522372341e-07, "reference_active": true, "delta_db": -0.6348418111025317}], "active_band_count": 3, "active_band_mae_db": 0.3695820523282687}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9150097924886824e-05, "log_rms_mae_db": 0.9882451209499094, "rms_envelope_nrmse": 0.07382429653617555, "envelope_correlation": 0.9962769854634198, "rms_gain_error_db": -0.2022270914366826, "reference_mean_power": 3.640185858193717e-05, "output_mean_power": 3.474568267306338e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.976051267531115e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.575058419062026e-05, "output_power": 1.4762007697454723e-05, "reference_active": true, "delta_db": -0.28151238998336325}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5755236704985135e-06, "output_power": 2.510967446673348e-06, "reference_active": true, "delta_db": -0.11024463285594187}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.671987913674402e-08, "output_power": 5.324888723636524e-08, "reference_active": true, "delta_db": -0.9794471432733751}], "active_band_count": 3, "active_band_mae_db": 0.4570680553708934}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.268273320274525e-05, "log_rms_mae_db": 1.211062850429493, "rms_envelope_nrmse": 0.20163599544475586, "envelope_correlation": 0.9727788561125185, "rms_gain_error_db": -0.18820785700928044, "reference_mean_power": 3.4234790780271314e-05, "output_mean_power": 3.2782864027287765e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.011440004206466e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3904345626991894e-05, "output_power": 1.4149945882577043e-05, "reference_active": true, "delta_db": 0.07604224169809777}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.336600248325665e-06, "output_power": 5.297772860988014e-06, "reference_active": true, "delta_db": -0.03171337854030175}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.037307900027025e-06, "output_power": 2.952717137230182e-06, "reference_active": true, "delta_db": 1.6116517540972572}], "active_band_count": 3, "active_band_mae_db": 0.573135791445219}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.282155756745637e-05, "log_rms_mae_db": 0.8283729317255484, "rms_envelope_nrmse": 0.1458400094635626, "envelope_correlation": 0.9851620252824809, "rms_gain_error_db": -0.1882079011557147, "reference_mean_power": 3.440696652445238e-05, "output_mean_power": 3.294773731600468e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.8610527191429872e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5067699650347801e-05, "output_power": 1.59294487518241e-05, "reference_active": true, "delta_db": 0.2415379236297725}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.7890585183930857e-06, "output_power": 2.9451272480229158e-06, "reference_active": true, "delta_db": 0.23646437307747759}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4153621023540917e-07, "output_power": 2.0743895275125895e-07, "reference_active": true, "delta_db": 1.6602274846198886}], "active_band_count": 3, "active_band_mae_db": 0.7127432604423795}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9026372261255287, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "4fe74f670ab6e9d9bd26818d63914d55c8be21f4f81eea26a7f25950848f91c2", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9901188904637765, "standard_deviation": 0.0029419172008325334, "minimum": 0.983399220941956, "maximum": 0.9932044319899606, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.3637972058385575, "standard_deviation": 0.038467606705971324, "minimum": 1.3187779142098337, "maximum": 1.4206471662783686, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8330240735999043, "standard_deviation": 0.34485501079785025, "minimum": 0.3695820523282687, "maximum": 1.4465766768450534, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12338574908871902, "standard_deviation": 0.016100340737312254, "minimum": 0.10076109460484034, "maximum": 0.15663780800372026, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9970392087007421, "standard_deviation": 0.0005255494155204986, "minimum": 0.9962769854634198, "maximum": 0.9976993898414345, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.03051447300785, "standard_deviation": 0.03319818897417684, "minimum": 0.9882451209499094, "maximum": 1.0880151925447177, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.0620950871768169, "standard_deviation": 0.33989591629931354, "minimum": 0.4570680553708934, "maximum": 1.6542606235311101, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07640704648053274, "standard_deviation": 0.008750885586854475, "minimum": 0.061544343721295386, "maximum": 0.08918616814091797, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9812474769636104, "standard_deviation": 0.006103028275636899, "minimum": 0.9721398289459082, "maximum": 0.9881024323793997, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.1889854139211593, "standard_deviation": 0.018993225829989926, "minimum": 1.1650174999078504, "maximum": 1.212279936849819, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.0122594138794314, "standard_deviation": 1.0693953582107387, "minimum": 0.26828473839915395, "maximum": 3.3892403325406515, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17068547281808777, "standard_deviation": 0.02731505488580903, "minimum": 0.13779135155541156, "maximum": 0.2189723570964106, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9924698407237396, "standard_deviation": 0.0038521776952884943, "minimum": 0.9851620252824809, "maximum": 0.996868590099944, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7840272331507291, "standard_deviation": 0.031407854957473724, "minimum": 0.737146682609614, "maximum": 0.8283729317255484, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.1349044664500665, "standard_deviation": 1.185751967347811, "minimum": 0.27961798221214196, "maximum": 3.720364732172399, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.11129474159924878, "standard_deviation": 0.0270525582739745, "minimum": 0.07863679137967977, "maximum": 0.15484372736740176, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9964238665447995, "standard_deviation": 0.0005370998765541248, "minimum": 0.9956956332006405, "maximum": 0.9971690599661035, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0503961770956158, "standard_deviation": 0.024162995276347406, "minimum": 1.0017158696125146, "maximum": 1.0700892662903, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6757840188775424, "standard_deviation": 0.10272727370060299, "minimum": 0.5766918798814246, "maximum": 0.8595459142378736, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06566632065237196, "standard_deviation": 0.004728313637448302, "minimum": 0.05922456467172771, "maximum": 0.07209115481075268, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9989072772392404, "standard_deviation": 0.00012983190231841179, "minimum": 0.9987347828458701, "maximum": 0.9991293424477236, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.6943053669905751, "standard_deviation": 0.026688617570589362, "minimum": 0.6546321547933529, "maximum": 0.727674807345198, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8309611434105203, "standard_deviation": 0.17122981622267683, "minimum": 0.5012594929316919, "maximum": 1.0249024058448384, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.035947613764429405, "standard_deviation": 0.0016456079367889447, "minimum": 0.033223498439604655, "maximum": 0.03856646279246839, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.2461045552303835, "standard_deviation": 0.049436202215936066, "minimum": 0.18948686462729938, "maximum": 0.3130089249614083, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.517038812682669, "standard_deviation": 0.007629672513587636, "minimum": 5.507249595151245, "maximum": 5.529743611691096, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.2792783479135639, "standard_deviation": 0.009323647318202373, "minimum": 0.2645062037482876, "maximum": 0.2932791064183302, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.08245192804787643, "standard_deviation": 0.02406268018421748, "minimum": -0.10994442996962257, "maximum": -0.04624413730969188, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9972896612716013, "standard_deviation": 0.00044342619578982437, "minimum": 0.9963735703228755, "maximum": 0.9977972461346672, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9117995278225909, "standard_deviation": 0.02341523962192366, "minimum": 0.8648822846199347, "maximum": 0.9448493962348496, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.37890320732808047, "standard_deviation": 0.18046323766639816, "minimum": 0.11123908570624141, "maximum": 0.6973024918713255, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.051178671026745705, "standard_deviation": 0.003964586600765453, "minimum": 0.04614316467365023, "maximum": 0.05870462891741837, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9992403531269658, "standard_deviation": 0.00017113976843101538, "minimum": 0.9989138094125132, "maximum": 0.9994233512465152, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5115230418786421, "standard_deviation": 0.03218561318196879, "minimum": 0.47823370667823606, "maximum": 0.5576502232485312, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4809167828649163, "standard_deviation": 0.2805964529192952, "minimum": 0.10971124277168261, "maximum": 1.0061513258021901, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.027457315947886203, "standard_deviation": 0.002600834259599368, "minimum": 0.024678617799577737, "maximum": 0.03150229913480581, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 1.7487549781799316, "predicted_mos": 1.7487549781799316, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "4ca380f30611a90415e9bf5ef25ae632a395327927f3f6d1cd98fca9c8952325", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.060441100038588}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.923414032859081, "全帯域_10ms_rms_envelope_nrmse": 0.05170881025294955, "全帯域_10ms_envelope_correlation": 0.9971937125371672, "全帯域_10ms_modulation_mae_db": 0.41593693616088223, "全帯域_40ms_log_rms_mae_db": 0.5002503320658748, "全帯域_40ms_rms_envelope_nrmse": 0.02676387874168994, "全帯域_40ms_envelope_correlation": 0.9992268524844626, "全帯域_40ms_modulation_mae_db": 0.34344101165448365, "300–1000 Hz_10ms_log_rms_mae_db": 1.1397387823386742, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06391769698452392, "300–1000 Hz_10ms_envelope_correlation": 0.9966200202603264, "300–1000 Hz_10ms_modulation_mae_db": 0.8377244694305848, "300–1000 Hz_40ms_log_rms_mae_db": 0.7368255163846329, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03512000663889182, "300–1000 Hz_40ms_envelope_correlation": 0.9989387970839975, "300–1000 Hz_40ms_modulation_mae_db": 0.953929373604189, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4986397316835003, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1577393391611157, "1000–3000 Hz_10ms_envelope_correlation": 0.983563508629434, "1000–3000 Hz_10ms_modulation_mae_db": 0.5828976176614962, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1218636740885537, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09222458967575377, "1000–3000 Hz_40ms_envelope_correlation": 0.9956449297383978, "1000–3000 Hz_40ms_modulation_mae_db": 1.2183953668008418, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2570052938850196, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14468468895476755, "3000–6000 Hz_10ms_envelope_correlation": 0.9861532774317202, "3000–6000 Hz_10ms_modulation_mae_db": 0.5095264595425113, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8197436390865528, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.099778234582049, "3000–6000 Hz_40ms_envelope_correlation": 0.9931141477808274, "3000–6000 Hz_40ms_modulation_mae_db": 0.3304868998946772, "mr_stft_db": 5.581231025457452, "band_mae_db": 0.22106978192709256, "rms_gain_error_db": -0.05339371668320253, "output_peak": 0.2823273570623384}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8776758351963159, "全帯域_10ms_rms_envelope_nrmse": 0.05337397159930329, "全帯域_10ms_envelope_correlation": 0.9972009364939108, "全帯域_10ms_modulation_mae_db": 0.6415492501536103, "全帯域_40ms_log_rms_mae_db": 0.4991581303283921, "全帯域_40ms_rms_envelope_nrmse": 0.03181844545595454, "全帯域_40ms_envelope_correlation": 0.999116074503428, "全帯域_40ms_modulation_mae_db": 0.7016532565006078, "300–1000 Hz_10ms_log_rms_mae_db": 1.1020200760716228, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06279508537914431, "300–1000 Hz_10ms_envelope_correlation": 0.9968886413340424, "300–1000 Hz_10ms_modulation_mae_db": 1.2441595712093863, "300–1000 Hz_40ms_log_rms_mae_db": 0.7098740445896332, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03541040861841297, "300–1000 Hz_40ms_envelope_correlation": 0.9990913107807964, "300–1000 Hz_40ms_modulation_mae_db": 1.5170670549874945, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5130845314480998, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.14009562253027272, "1000–3000 Hz_10ms_envelope_correlation": 0.9892450135490789, "1000–3000 Hz_10ms_modulation_mae_db": 1.5054784583743641, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1347666641291525, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10325724656501231, "1000–3000 Hz_40ms_envelope_correlation": 0.995892552499368, "1000–3000 Hz_40ms_modulation_mae_db": 1.744795395649783, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2581101502945167, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.20455281067910125, "3000–6000 Hz_10ms_envelope_correlation": 0.974485032276279, "3000–6000 Hz_10ms_modulation_mae_db": 2.170443792514561, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8421328512068923, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13243783300455997, "3000–6000 Hz_40ms_envelope_correlation": 0.9917894921966839, "3000–6000 Hz_40ms_modulation_mae_db": 2.3687587896564515, "mr_stft_db": 5.579457381523402, "band_mae_db": 0.37185565979538554, "rms_gain_error_db": -0.136723129942934, "output_peak": 0.28386422995374877}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9209267046283661, "全帯域_10ms_rms_envelope_nrmse": 0.05565910876119314, "全帯域_10ms_envelope_correlation": 0.9968384256496826, "全帯域_10ms_modulation_mae_db": 0.4643537593210447, "全帯域_40ms_log_rms_mae_db": 0.5537392925865301, "全帯域_40ms_rms_envelope_nrmse": 0.03190900028146566, "全帯域_40ms_envelope_correlation": 0.9990015117552244, "全帯域_40ms_modulation_mae_db": 0.5140118768189932, "300–1000 Hz_10ms_log_rms_mae_db": 1.025814352123037, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06563543196576595, "300–1000 Hz_10ms_envelope_correlation": 0.9965036003104265, "300–1000 Hz_10ms_modulation_mae_db": 1.071574391649478, "300–1000 Hz_40ms_log_rms_mae_db": 0.6776374056010589, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.036179461697167695, "300–1000 Hz_40ms_envelope_correlation": 0.9989799602629126, "300–1000 Hz_40ms_modulation_mae_db": 0.9340197283077218, "1000–3000 Hz_10ms_log_rms_mae_db": 1.526129782659417, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1529720620954183, "1000–3000 Hz_10ms_envelope_correlation": 0.9859655713257746, "1000–3000 Hz_10ms_modulation_mae_db": 0.8122670039492017, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1818918397478626, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11241502043852668, "1000–3000 Hz_40ms_envelope_correlation": 0.9939434606961136, "1000–3000 Hz_40ms_modulation_mae_db": 0.3715263367631904, "3000–6000 Hz_10ms_log_rms_mae_db": 1.251122478742229, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16977861613957507, "3000–6000 Hz_10ms_envelope_correlation": 0.9806604051380761, "3000–6000 Hz_10ms_modulation_mae_db": 0.35619406086988015, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7795344569428047, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08331221827431687, "3000–6000 Hz_40ms_envelope_correlation": 0.9953220276374115, "3000–6000 Hz_40ms_modulation_mae_db": 0.44371655509381464, "mr_stft_db": 5.576474813615555, "band_mae_db": 0.2368341865084457, "rms_gain_error_db": -0.10594118479232285, "output_peak": 0.27318697399415043}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9297298372867374, "全帯域_10ms_rms_envelope_nrmse": 0.05496324601712302, "全帯域_10ms_envelope_correlation": 0.9968624713594124, "全帯域_10ms_modulation_mae_db": 0.45869735293653807, "全帯域_40ms_log_rms_mae_db": 0.5225750931970997, "全帯域_40ms_rms_envelope_nrmse": 0.02705404827829908, "全帯域_40ms_envelope_correlation": 0.9992585506679571, "全帯域_40ms_modulation_mae_db": 0.4386841027544792, "300–1000 Hz_10ms_log_rms_mae_db": 1.1034735766624388, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07236445487913422, "300–1000 Hz_10ms_envelope_correlation": 0.9956750027181233, "300–1000 Hz_10ms_modulation_mae_db": 0.6824173913496899, "300–1000 Hz_40ms_log_rms_mae_db": 0.7317341347725246, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038620542872853825, "300–1000 Hz_40ms_envelope_correlation": 0.9987487380517225, "300–1000 Hz_40ms_modulation_mae_db": 0.7230104171293977, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4191423417941473, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11397197249953363, "1000–3000 Hz_10ms_envelope_correlation": 0.9916943856557712, "1000–3000 Hz_10ms_modulation_mae_db": 0.5121350983462055, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0623613833467103, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07237622532971306, "1000–3000 Hz_40ms_envelope_correlation": 0.9972645946458207, "1000–3000 Hz_40ms_modulation_mae_db": 0.8704089604914834, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2753182092327426, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17049082687568945, "3000–6000 Hz_10ms_envelope_correlation": 0.9829051723748149, "3000–6000 Hz_10ms_modulation_mae_db": 1.4421193917434731, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8383072657984522, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11315680933714176, "3000–6000 Hz_40ms_envelope_correlation": 0.9942676134422113, "3000–6000 Hz_40ms_modulation_mae_db": 1.4961176315582858, "mr_stft_db": 5.567840473272947, "band_mae_db": 0.24519667557544636, "rms_gain_error_db": -0.08023180023670942, "output_peak": 0.27831418634964056}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9115895111119579, "全帯域_10ms_rms_envelope_nrmse": 0.053937773488181726, "全帯域_10ms_envelope_correlation": 0.9970457659688324, "全帯域_10ms_modulation_mae_db": 0.31786240989838715, "全帯域_40ms_log_rms_mae_db": 0.481567677022366, "全帯域_40ms_rms_envelope_nrmse": 0.029796165000530752, "全帯域_40ms_envelope_correlation": 0.9991537862060901, "全帯域_40ms_modulation_mae_db": 0.30209650160417945, "300–1000 Hz_10ms_log_rms_mae_db": 1.0576340135937876, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0626442739886428, "300–1000 Hz_10ms_envelope_correlation": 0.9968624586313628, "300–1000 Hz_10ms_modulation_mae_db": 0.6820054905389913, "300–1000 Hz_40ms_log_rms_mae_db": 0.6977367011545732, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0345910860321803, "300–1000 Hz_40ms_envelope_correlation": 0.9990932753625705, "300–1000 Hz_40ms_modulation_mae_db": 0.8471818501364368, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4526586428158013, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13647316980752602, "1000–3000 Hz_10ms_envelope_correlation": 0.988181408712357, "1000–3000 Hz_10ms_modulation_mae_db": 0.6262191306046997, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0977097397797515, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08781487080046148, "1000–3000 Hz_40ms_envelope_correlation": 0.9961727564973484, "1000–3000 Hz_40ms_modulation_mae_db": 0.6101053957615561, "3000–6000 Hz_10ms_log_rms_mae_db": 1.233123033829894, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16764067250092127, "3000–6000 Hz_10ms_envelope_correlation": 0.9837248844963901, "3000–6000 Hz_10ms_modulation_mae_db": 2.1778520382226403, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8096336520396218, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1210382303883769, "3000–6000 Hz_40ms_envelope_correlation": 0.9929857737250352, "3000–6000 Hz_40ms_modulation_mae_db": 2.5122203447756006, "mr_stft_db": 5.585502429524978, "band_mae_db": 0.3611819376630005, "rms_gain_error_db": -0.10694915881088106, "output_peak": 0.2727707834263431}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9396947321776303, "全帯域_10ms_rms_envelope_nrmse": 0.05529194405815985, "全帯域_10ms_envelope_correlation": 0.9968838152173336, "全帯域_10ms_modulation_mae_db": 0.4757763125418975, "全帯域_40ms_log_rms_mae_db": 0.5393478289899566, "全帯域_40ms_rms_envelope_nrmse": 0.03057659201379667, "全帯域_40ms_envelope_correlation": 0.999099408479077, "全帯域_40ms_modulation_mae_db": 0.8626309967483832, "300–1000 Hz_10ms_log_rms_mae_db": 1.0728228777797082, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06848007362984546, "300–1000 Hz_10ms_envelope_correlation": 0.996189943752026, "300–1000 Hz_10ms_modulation_mae_db": 0.8597443619177089, "300–1000 Hz_40ms_log_rms_mae_db": 0.7398972625869409, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.039880237295434794, "300–1000 Hz_40ms_envelope_correlation": 0.9987173500394527, "300–1000 Hz_40ms_modulation_mae_db": 1.0693756171303004, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4711403189989447, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12878219538349275, "1000–3000 Hz_10ms_envelope_correlation": 0.9892035713477292, "1000–3000 Hz_10ms_modulation_mae_db": 1.402183733482705, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1176351844444188, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08411077335098176, "1000–3000 Hz_40ms_envelope_correlation": 0.9960238298010251, "1000–3000 Hz_40ms_modulation_mae_db": 1.5490306371934626, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2700584234665773, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19773680300681273, "3000–6000 Hz_10ms_envelope_correlation": 0.9761710658834819, "3000–6000 Hz_10ms_modulation_mae_db": 2.2120336098226363, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8601244241906376, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12594740507838353, "3000–6000 Hz_40ms_envelope_correlation": 0.9926404294523681, "3000–6000 Hz_40ms_modulation_mae_db": 2.6607908541154983, "mr_stft_db": 5.568631433101408, "band_mae_db": 0.2962701842993781, "rms_gain_error_db": -0.10573320200588295, "output_peak": 0.2717944868145849}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9131084035715188, "全帯域_10ms_rms_envelope_nrmse": 0.04828093994300837, "全帯域_10ms_envelope_correlation": 0.9976409410111127, "全帯域_10ms_modulation_mae_db": 0.4675739903379675, "全帯域_40ms_log_rms_mae_db": 0.5097660947715836, "全帯域_40ms_rms_envelope_nrmse": 0.02536871265071109, "全帯域_40ms_envelope_correlation": 0.9994040007574202, "全帯域_40ms_modulation_mae_db": 0.5728790298980239, "300–1000 Hz_10ms_log_rms_mae_db": 1.044209177048465, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05841291746564046, "300–1000 Hz_10ms_envelope_correlation": 0.9972497896241628, "300–1000 Hz_10ms_modulation_mae_db": 0.6000880386861301, "300–1000 Hz_40ms_log_rms_mae_db": 0.6841768102567741, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03218416118376022, "300–1000 Hz_40ms_envelope_correlation": 0.9991911577771989, "300–1000 Hz_40ms_modulation_mae_db": 0.7187362668193109, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5642312162871288, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1637486350410906, "1000–3000 Hz_10ms_envelope_correlation": 0.9823889691287406, "1000–3000 Hz_10ms_modulation_mae_db": 0.4138895771187787, "1000–3000 Hz_40ms_log_rms_mae_db": 1.178605816790813, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10524222245834434, "1000–3000 Hz_40ms_envelope_correlation": 0.9939475273717089, "1000–3000 Hz_40ms_modulation_mae_db": 0.7247692940143914, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2893313648102949, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14583374766007248, "3000–6000 Hz_10ms_envelope_correlation": 0.9867304904722518, "3000–6000 Hz_10ms_modulation_mae_db": 1.0581013674984525, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8420666516135564, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08163036906233348, "3000–6000 Hz_40ms_envelope_correlation": 0.9967649566947492, "3000–6000 Hz_40ms_modulation_mae_db": 1.228657181632254, "mr_stft_db": 5.574132207281155, "band_mae_db": 0.29141397313317874, "rms_gain_error_db": -0.0967407175637047, "output_peak": 0.27950891448751997}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8766067150405787, "全帯域_10ms_rms_envelope_nrmse": 0.049963080671324954, "全帯域_10ms_envelope_correlation": 0.9974457846777371, "全帯域_10ms_modulation_mae_db": 0.43968637274413364, "全帯域_40ms_log_rms_mae_db": 0.5058435695817224, "全帯域_40ms_rms_envelope_nrmse": 0.02435310662508185, "全帯域_40ms_envelope_correlation": 0.9994442861229859, "全帯域_40ms_modulation_mae_db": 0.7096279476984538, "300–1000 Hz_10ms_log_rms_mae_db": 1.043648744346216, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.062483865480857506, "300–1000 Hz_10ms_envelope_correlation": 0.9968433275969422, "300–1000 Hz_10ms_modulation_mae_db": 0.6972168403875224, "300–1000 Hz_40ms_log_rms_mae_db": 0.6929368692215757, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03325125451010234, "300–1000 Hz_40ms_envelope_correlation": 0.9991357162446379, "300–1000 Hz_40ms_modulation_mae_db": 0.8914118500962059, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4954196875583552, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13250611123494957, "1000–3000 Hz_10ms_envelope_correlation": 0.989194511340477, "1000–3000 Hz_10ms_modulation_mae_db": 1.23600824631128, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1375474489800113, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08530004714636823, "1000–3000 Hz_40ms_envelope_correlation": 0.9967527602832937, "1000–3000 Hz_40ms_modulation_mae_db": 1.4228586919086643, "3000–6000 Hz_10ms_log_rms_mae_db": 1.282509816863292, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15438933610693978, "3000–6000 Hz_10ms_envelope_correlation": 0.9841352687848728, "3000–6000 Hz_10ms_modulation_mae_db": 1.2564330220534061, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8203400117317193, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08394588597513691, "3000–6000 Hz_40ms_envelope_correlation": 0.9953679840623595, "3000–6000 Hz_40ms_modulation_mae_db": 1.5671001053407794, "mr_stft_db": 5.567254923905119, "band_mae_db": 0.23567840153808542, "rms_gain_error_db": -0.090192578367158, "output_peak": 0.2780186054986775}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.642456340211102, "spectral_convergence": 0.15184367311669633, "spectral_convergence_status": "ok", "amplitude_floor": 9.829298518478812e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.5810302969593755, "spectral_convergence": 0.15468265486668725, "spectral_convergence_status": "ok", "amplitude_floor": 9.065329093063253e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.5202064392018775, "spectral_convergence": 0.15929769506539312, "spectral_convergence_status": "ok", "amplitude_floor": 8.043941450863317e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.0001149513766055836, "output_power": 0.00012012382580180185, "delta_db": 0.19114978962585727, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0017363654374162414, "output_power": 0.0017132948545451254, "delta_db": -0.0580902197262029, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0004421876194377549, "output_power": 0.0004343353275070421, "delta_db": -0.07781423862512782, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.7408011480563064e-05, "output_power": 2.5291185648153093e-05, "delta_db": -0.34908338035287767, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7412343207141002e-05, "output_power": 2.3849613316569055e-05, "delta_db": -0.6046481857820029, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.428426915438781e-05, "output_power": 3.640640230982935e-05, "delta_db": 0.26082868015180627, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.433275239990599e-05, "output_power": 1.435215104624745e-05, "delta_db": 0.005873979225773219, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.22106978192709256, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.05339371668320253, "pitch": null, "output_rms_dbfs": -26.256818808270992, "output_peak": 0.2823273570623384, "reference_rms_dbfs": -26.20342509158779, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.581231025457452}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014020226421084518, "log_rms_mae_db": 0.923414032859081, "rms_envelope_nrmse": 0.05170881025294955, "envelope_correlation": 0.9971937125371672, "rms_gain_error_db": -0.05339375382972872, "reference_mean_power": 0.002398940884341968, "output_mean_power": 0.002369627987672537}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.599888913877476e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003971876344997112, "output_power": 0.00038381174353464446, "reference_active": true, "delta_db": -0.14877460535452863}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.277425400163653e-05, "output_power": 4.904445189081331e-05, "reference_active": true, "delta_db": -0.31832217663653123}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.46569016072901e-05, "output_power": 1.2245337791201273e-05, "reference_active": true, "delta_db": -0.7807140264915868}], "active_band_count": 3, "active_band_mae_db": 0.41593693616088223}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001294702248118231, "log_rms_mae_db": 0.5002503320658748, "rms_envelope_nrmse": 0.02676387874168994, "envelope_correlation": 0.9992268524844626, "rms_gain_error_db": -0.05339380451565963, "reference_mean_power": 0.0024110057038516162, "output_mean_power": 0.0023815453581609233}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 8.923189531660561e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00035367674920645624, "output_power": 0.00034077114381731203, "reference_active": true, "delta_db": -0.16143698130830464}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.2909806376051565e-05, "output_power": 2.1847616999314378e-05, "reference_active": true, "delta_db": -0.20617344954087047}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.181144761591823e-07, "output_power": 7.023325830750506e-07, "reference_active": true, "delta_db": -0.6627126041142759}], "active_band_count": 3, "active_band_mae_db": 0.34344101165448365}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00013300454501172858, "log_rms_mae_db": 1.1397387823386742, "rms_envelope_nrmse": 0.06391769698452392, "envelope_correlation": 0.9966200202603264, "rms_gain_error_db": -0.060854982582522206, "reference_mean_power": 0.0013111812883454625, "output_mean_power": 0.0012929366450042646}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.210472671322603e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002971533743381409, "output_power": 0.0002830894845086324, "reference_active": true, "delta_db": -0.21056928679252884}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.9363200025831e-05, "output_power": 4.1580057249639774e-05, "reference_active": true, "delta_db": -0.7451822261800946}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.44718666084695e-06, "output_power": 6.600248800508148e-06, "reference_active": true, "delta_db": -1.557421895319131}], "active_band_count": 3, "active_band_mae_db": 0.8377244694305848}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00012063998479701045, "log_rms_mae_db": 0.7368255163846329, "rms_envelope_nrmse": 0.03512000663889182, "envelope_correlation": 0.9989387970839975, "rms_gain_error_db": -0.06085497098835445, "reference_mean_power": 0.0013177756236779122, "output_mean_power": 0.0012994392258640708}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.775720236374225e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00027184637186405784, "output_power": 0.00025604474836287544, "reference_active": true, "delta_db": -0.26007668551930946}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0948015125222398e-05, "output_power": 1.8322030123155328e-05, "reference_active": true, "delta_db": -0.5816928597856442}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.00249959518115e-07, "output_power": 4.397959592485087e-07, "reference_active": true, "delta_db": -2.0200185755076134}], "active_band_count": 3, "active_band_mae_db": 0.953929373604189}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.4324234792903394e-05, "log_rms_mae_db": 1.4986397316835003, "rms_envelope_nrmse": 0.1577393391611157, "envelope_correlation": 0.983563508629434, "rms_gain_error_db": -0.45882152787198094, "reference_mean_power": 3.621970358575803e-05, "output_mean_power": 3.258837754113328e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.144567073932934e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6016299479105344e-05, "output_power": 1.367933125006281e-05, "reference_active": true, "delta_db": -0.6849731454143313}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.217328435986187e-06, "output_power": 4.1906268669722574e-06, "reference_active": true, "delta_db": -0.9516918383528028}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.162268250073546e-07, "output_power": 6.00534293423305e-07, "reference_active": true, "delta_db": -0.11202786921735444}], "active_band_count": 3, "active_band_mae_db": 0.5828976176614962}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9150097924886824e-05, "log_rms_mae_db": 1.1218636740885537, "rms_envelope_nrmse": 0.09222458967575377, "envelope_correlation": 0.9956449297383978, "rms_gain_error_db": -0.45882169065422784, "reference_mean_power": 3.640185858193717e-05, "output_mean_power": 3.275226875875146e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.976051267531115e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.575058419062026e-05, "output_power": 1.3328553993985945e-05, "reference_active": true, "delta_db": -0.7251363079857391}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5755236704985135e-06, "output_power": 2.037634450995622e-06, "reference_active": true, "delta_db": -1.0173927085761223}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.671987913674402e-08, "output_power": 4.2952608398035004e-08, "reference_active": true, "delta_db": -1.912657083840664}], "active_band_count": 3, "active_band_mae_db": 1.2183953668008418}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.268273320274525e-05, "log_rms_mae_db": 1.2570052938850196, "rms_envelope_nrmse": 0.14468468895476755, "envelope_correlation": 0.9861532774317202, "rms_gain_error_db": 0.030366973836580408, "reference_mean_power": 3.4234790780271314e-05, "output_mean_power": 3.447500798857691e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.011440004206466e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3904345626991894e-05, "output_power": 1.52742590323902e-05, "reference_active": true, "delta_db": 0.40809596716873425}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.336600248325665e-06, "output_power": 4.692255193879608e-06, "reference_active": true, "delta_db": -0.5588304837662038}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.037307900027025e-06, "output_power": 1.790158052818403e-06, "reference_active": true, "delta_db": -0.5616529276925958}], "active_band_count": 3, "active_band_mae_db": 0.5095264595425113}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.282155756745637e-05, "log_rms_mae_db": 0.8197436390865528, "rms_envelope_nrmse": 0.099778234582049, "envelope_correlation": 0.9931141477808274, "rms_gain_error_db": 0.030366976833745528, "reference_mean_power": 3.440696652445238e-05, "output_mean_power": 3.464839187203013e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.8610527191429872e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5067699650347801e-05, "output_power": 1.6219707686600047e-05, "reference_active": true, "delta_db": 0.3199606836570037}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.7890585183930857e-06, "output_power": 2.5245523919234634e-06, "reference_active": true, "delta_db": -0.43273238455133856}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4153621023540917e-07, "output_power": 1.3396483071831778e-07, "reference_active": true, "delta_db": -0.23876763147568938}], "active_band_count": 3, "active_band_mae_db": 0.3304868998946772}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9013104043493011, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "16ebe675ba761affb10101c337b5e939467aa853f2af90dc26e37121f4d0a043", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9874296174611703, "standard_deviation": 0.0031805037289377447, "minimum": 0.9823889691287406, "maximum": 0.9916943856557712, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4925557816556743, "standard_deviation": 0.044993911217788514, "minimum": 1.4191423417941473, "maximum": 1.5642312162871288, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8863848582310914, "standard_deviation": 0.43097244189862155, "minimum": 0.4138895771187787, "maximum": 1.5054784583743641, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14078613846917493, "standard_deviation": 0.016535310724673947, "minimum": 0.11397197249953363, "maximum": 0.1637486350410906, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9957053014416346, "standard_deviation": 0.0012000654780406485, "minimum": 0.9939434606961136, "maximum": 0.9972645946458207, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.1290477189134092, "standard_deviation": 0.039577141036075354, "minimum": 1.0623613833467103, "maximum": 1.1818918397478626, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.0639862598229215, "standard_deviation": 0.49127380011946314, "minimum": 0.3715263367631904, "maximum": 1.744795395649783, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0928426244706452, "standard_deviation": 0.013217750683882479, "minimum": 0.07237622532971306, "maximum": 0.11241502043852668, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9818706996072358, "standard_deviation": 0.004473623784478886, "minimum": 0.974485032276279, "maximum": 0.9867304904722518, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2645723463905707, "standard_deviation": 0.018319821085672348, "minimum": 1.233123033829894, "maximum": 1.2893313648102949, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.3978379677834452, "standard_deviation": 0.7444799507277035, "minimum": 0.35619406086988015, "maximum": 2.2120336098226363, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16938843774048495, "standard_deviation": 0.022150965152870954, "minimum": 0.14468468895476755, "maximum": 0.20455281067910125, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9940315531239557, "standard_deviation": 0.0016850579075993056, "minimum": 0.9917894921966839, "maximum": 0.9967649566947492, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8264853690762797, "standard_deviation": 0.024872670575858995, "minimum": 0.7795344569428047, "maximum": 0.8601244241906376, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.5759810452584202, "standard_deviation": 0.8977927173569888, "minimum": 0.3304868998946772, "maximum": 2.6607908541154983, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1051558732127873, "standard_deviation": 0.020709675234347736, "minimum": 0.08163036906233348, "maximum": 0.13243783300455997, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9966040980284265, "standard_deviation": 0.0004879927818929441, "minimum": 0.9956750027181233, "maximum": 0.9972497896241628, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0736701999954938, "standard_deviation": 0.03849733457257151, "minimum": 1.025814352123037, "maximum": 1.1397387823386742, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8343663193961864, "standard_deviation": 0.22195626734528967, "minimum": 0.6000880386861301, "maximum": 1.2441595712093863, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06459172497169433, "standard_deviation": 0.004254735790105024, "minimum": 0.05841291746564046, "maximum": 0.07236445487913422, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9989870382004111, "standard_deviation": 0.00017640255733700197, "minimum": 0.9987173500394527, "maximum": 0.9991911577771989, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7088523430709641, "standard_deviation": 0.0245851864876716, "minimum": 0.6776374056010589, "maximum": 0.7398972625869409, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.9568415197763822, "standard_deviation": 0.2548734332963436, "minimum": 0.7187362668193109, "maximum": 1.5170670549874945, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.035654644856100495, "standard_deviation": 0.002569736063046837, "minimum": 0.03218416118376022, "maximum": 0.039880237295434794, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.2824376000550016, "standard_deviation": 0.058416197979288986, "minimum": 0.22106978192709256, "maximum": 0.37185565979538554, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.575065585960251, "standard_deviation": 0.006800129751855412, "minimum": 5.567254923905119, "maximum": 5.585502429524978, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.27747319219837546, "standard_deviation": 0.004508550634638219, "minimum": 0.2717944868145849, "maximum": 0.28386422995374877, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.09698818605034944, "standard_deviation": 0.024089754741067858, "minimum": -0.136723129942934, "maximum": -0.05339371668320253, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9971389816143985, "standard_deviation": 0.00029118381343216216, "minimum": 0.9968384256496826, "maximum": 0.9976409410111127, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9115932214840232, "standard_deviation": 0.02305960519250825, "minimum": 0.8766067150405787, "maximum": 0.9396947321776303, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.46017954801180766, "standard_deviation": 0.08931810996589755, "minimum": 0.31786240989838715, "maximum": 0.6415492501536103, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.052897359348905486, "standard_deviation": 0.0026798926613036747, "minimum": 0.04828093994300837, "maximum": 0.05565910876119314, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9992130588720807, "standard_deviation": 0.00015249001070302438, "minimum": 0.9990015117552244, "maximum": 0.9994442861229859, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5140310023179406, "standard_deviation": 0.023424320975051975, "minimum": 0.481567677022366, "maximum": 0.5537392925865301, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5556280904597005, "standard_deviation": 0.19431091175364054, "minimum": 0.30209650160417945, "maximum": 0.8626309967483832, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0284549936309412, "standard_deviation": 0.0029451173929864517, "minimum": 0.02435310662508185, "maximum": 0.03190900028146566, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 2.1899170875549316, "predicted_mos": 2.1899170875549316, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "8dcb87be1c384b0aab9f5191264ecb200517e4029bbff42cadabe0ba313f47d4", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.617753199767321}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9038027385942038, "全帯域_10ms_rms_envelope_nrmse": 0.05488968335143899, "全帯域_10ms_envelope_correlation": 0.9968747638170011, "全帯域_10ms_modulation_mae_db": 0.5150268515984747, "全帯域_40ms_log_rms_mae_db": 0.4790876465927573, "全帯域_40ms_rms_envelope_nrmse": 0.029501648036659348, "全帯域_40ms_envelope_correlation": 0.9991054345630346, "全帯域_40ms_modulation_mae_db": 0.8082286945711948, "300–1000 Hz_10ms_log_rms_mae_db": 1.0553081034234004, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06661222211370095, "300–1000 Hz_10ms_envelope_correlation": 0.9963531811376704, "300–1000 Hz_10ms_modulation_mae_db": 0.9682582128779403, "300–1000 Hz_40ms_log_rms_mae_db": 0.7166661848160184, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03716434719914517, "300–1000 Hz_40ms_envelope_correlation": 0.9988440390981224, "300–1000 Hz_40ms_modulation_mae_db": 1.1486244891825954, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4152446338308824, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13690848415507068, "1000–3000 Hz_10ms_envelope_correlation": 0.9890821281858888, "1000–3000 Hz_10ms_modulation_mae_db": 0.7032322164593202, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0525913624854946, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09405563084371052, "1000–3000 Hz_40ms_envelope_correlation": 0.996477006910076, "1000–3000 Hz_40ms_modulation_mae_db": 1.0805149101959597, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2848999085782347, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2078285927710422, "3000–6000 Hz_10ms_envelope_correlation": 0.9714489658485248, "3000–6000 Hz_10ms_modulation_mae_db": 1.066231931867221, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8094820103964739, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1113744569520444, "3000–6000 Hz_40ms_envelope_correlation": 0.9927811795166194, "3000–6000 Hz_40ms_modulation_mae_db": 1.334337151959571, "mr_stft_db": 5.536190794179189, "band_mae_db": 0.27797174997990015, "rms_gain_error_db": -0.08145727191188536, "output_peak": 0.2935702231849335}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9157253488562405, "全帯域_10ms_rms_envelope_nrmse": 0.04919909021312006, "全帯域_10ms_envelope_correlation": 0.9975588775106773, "全帯域_10ms_modulation_mae_db": 0.2604342114190152, "全帯域_40ms_log_rms_mae_db": 0.5444899689548873, "全帯域_40ms_rms_envelope_nrmse": 0.026360446357142842, "全帯域_40ms_envelope_correlation": 0.9993575719627846, "全帯域_40ms_modulation_mae_db": 0.22270773831875493, "300–1000 Hz_10ms_log_rms_mae_db": 1.0471758605673585, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.061721523916961174, "300–1000 Hz_10ms_envelope_correlation": 0.996979392326402, "300–1000 Hz_10ms_modulation_mae_db": 0.5414677248080745, "300–1000 Hz_40ms_log_rms_mae_db": 0.6643206527345711, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.033166806268799746, "300–1000 Hz_40ms_envelope_correlation": 0.9991925591855977, "300–1000 Hz_40ms_modulation_mae_db": 0.661352717094782, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4074884600227398, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12253705804813751, "1000–3000 Hz_10ms_envelope_correlation": 0.9904769685466734, "1000–3000 Hz_10ms_modulation_mae_db": 0.9305721296993511, "1000–3000 Hz_40ms_log_rms_mae_db": 1.037781799213927, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08069320921551727, "1000–3000 Hz_40ms_envelope_correlation": 0.9966003228126603, "1000–3000 Hz_40ms_modulation_mae_db": 1.2120715825955461, "3000–6000 Hz_10ms_log_rms_mae_db": 1.266108549268063, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1442814965554093, "3000–6000 Hz_10ms_envelope_correlation": 0.9860506835105742, "3000–6000 Hz_10ms_modulation_mae_db": 0.5329678404087795, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7963141065647903, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06636251412136306, "3000–6000 Hz_40ms_envelope_correlation": 0.9969376250655798, "3000–6000 Hz_40ms_modulation_mae_db": 0.677105123743888, "mr_stft_db": 5.545504551860074, "band_mae_db": 0.20149125308424765, "rms_gain_error_db": -0.09763442751388031, "output_peak": 0.2749039575187334}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8986926082764207, "全帯域_10ms_rms_envelope_nrmse": 0.05214105443747066, "全帯域_10ms_envelope_correlation": 0.9972521867045567, "全帯域_10ms_modulation_mae_db": 0.5507481939158086, "全帯域_40ms_log_rms_mae_db": 0.474895238194164, "全帯域_40ms_rms_envelope_nrmse": 0.027676763053028085, "全帯域_40ms_envelope_correlation": 0.9992961509473741, "全帯域_40ms_modulation_mae_db": 0.9219175825083594, "300–1000 Hz_10ms_log_rms_mae_db": 1.0742433837674388, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.070572642475702, "300–1000 Hz_10ms_envelope_correlation": 0.9960200289624327, "300–1000 Hz_10ms_modulation_mae_db": 1.2138878447678951, "300–1000 Hz_40ms_log_rms_mae_db": 0.741048964118641, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04112780460988506, "300–1000 Hz_40ms_envelope_correlation": 0.9987063840994235, "300–1000 Hz_40ms_modulation_mae_db": 1.4526446655612026, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3911327464639653, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12263811896439356, "1000–3000 Hz_10ms_envelope_correlation": 0.9906698954636898, "1000–3000 Hz_10ms_modulation_mae_db": 0.38066854343169015, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0324823317700604, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0815855751723875, "1000–3000 Hz_40ms_envelope_correlation": 0.9967481495587089, "1000–3000 Hz_40ms_modulation_mae_db": 0.5700615142897577, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2745271730205894, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16000820821746523, "3000–6000 Hz_10ms_envelope_correlation": 0.9829311392410424, "3000–6000 Hz_10ms_modulation_mae_db": 0.5422372861951523, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7997135803370293, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0935975136941193, "3000–6000 Hz_40ms_envelope_correlation": 0.994148364439003, "3000–6000 Hz_40ms_modulation_mae_db": 0.9628023613953339, "mr_stft_db": 5.546885709168959, "band_mae_db": 0.22061387317952041, "rms_gain_error_db": -0.10791236023983063, "output_peak": 0.27657970543878857}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.89494195679428, "全帯域_10ms_rms_envelope_nrmse": 0.05328935950195817, "全帯域_10ms_envelope_correlation": 0.997085080039851, "全帯域_10ms_modulation_mae_db": 0.4195241699693994, "全帯域_40ms_log_rms_mae_db": 0.5107835468693355, "全帯域_40ms_rms_envelope_nrmse": 0.03106025297386167, "全帯域_40ms_envelope_correlation": 0.9990263171815398, "全帯域_40ms_modulation_mae_db": 0.5935627342311599, "300–1000 Hz_10ms_log_rms_mae_db": 1.0463918313736418, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06156872274144384, "300–1000 Hz_10ms_envelope_correlation": 0.9970301092336598, "300–1000 Hz_10ms_modulation_mae_db": 0.8995625727263797, "300–1000 Hz_40ms_log_rms_mae_db": 0.7014734469586992, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035873281767761674, "300–1000 Hz_40ms_envelope_correlation": 0.999076713753075, "300–1000 Hz_40ms_modulation_mae_db": 1.0726656768423497, "1000–3000 Hz_10ms_log_rms_mae_db": 1.415800052876895, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10435552512600885, "1000–3000 Hz_10ms_envelope_correlation": 0.992414593092257, "1000–3000 Hz_10ms_modulation_mae_db": 0.6927527630474409, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0524074317164034, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.058166405572215, "1000–3000 Hz_40ms_envelope_correlation": 0.9976852783159701, "1000–3000 Hz_40ms_modulation_mae_db": 0.9030836552563472, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2503130974387104, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16900181251660293, "3000–6000 Hz_10ms_envelope_correlation": 0.9810601450952358, "3000–6000 Hz_10ms_modulation_mae_db": 0.3361581149804565, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7865064873739804, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09863787778712015, "3000–6000 Hz_40ms_envelope_correlation": 0.9932317096439178, "3000–6000 Hz_40ms_modulation_mae_db": 0.448463000840537, "mr_stft_db": 5.539068321777929, "band_mae_db": 0.18455592496169065, "rms_gain_error_db": -0.09043497403298548, "output_peak": 0.2737185990341087}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.886254329897327, "全帯域_10ms_rms_envelope_nrmse": 0.05549638024008066, "全帯域_10ms_envelope_correlation": 0.9967922787556311, "全帯域_10ms_modulation_mae_db": 0.4682889016638285, "全帯域_40ms_log_rms_mae_db": 0.5150772804951058, "全帯域_40ms_rms_envelope_nrmse": 0.02926760932346416, "全帯域_40ms_envelope_correlation": 0.9991059399471136, "全帯域_40ms_modulation_mae_db": 0.5916251161203215, "300–1000 Hz_10ms_log_rms_mae_db": 1.0492034699612538, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06815415009976909, "300–1000 Hz_10ms_envelope_correlation": 0.9961770034743752, "300–1000 Hz_10ms_modulation_mae_db": 0.7271369363830118, "300–1000 Hz_40ms_log_rms_mae_db": 0.701968636646415, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03639289567559509, "300–1000 Hz_40ms_envelope_correlation": 0.9989219605489034, "300–1000 Hz_40ms_modulation_mae_db": 0.966710883780013, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4437589125979933, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1355309269836958, "1000–3000 Hz_10ms_envelope_correlation": 0.9878375114773553, "1000–3000 Hz_10ms_modulation_mae_db": 0.3975343050697022, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0541108588990624, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08231217195425701, "1000–3000 Hz_40ms_envelope_correlation": 0.9962348481642527, "1000–3000 Hz_40ms_modulation_mae_db": 0.5079464730230613, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2765025416811497, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14333751350164112, "3000–6000 Hz_10ms_envelope_correlation": 0.9867721887902948, "3000–6000 Hz_10ms_modulation_mae_db": 0.7667022643926549, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8325137489052541, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08143129469075207, "3000–6000 Hz_40ms_envelope_correlation": 0.9962069985175313, "3000–6000 Hz_40ms_modulation_mae_db": 0.8943365849945377, "mr_stft_db": 5.544579599285073, "band_mae_db": 0.1773677418700013, "rms_gain_error_db": -0.07431164200548274, "output_peak": 0.2789137348177642}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.917009099001579, "全帯域_10ms_rms_envelope_nrmse": 0.054426036603084864, "全帯域_10ms_envelope_correlation": 0.9969216219578585, "全帯域_10ms_modulation_mae_db": 0.1782832960050509, "全帯域_40ms_log_rms_mae_db": 0.5395228196144222, "全帯域_40ms_rms_envelope_nrmse": 0.03019104885338167, "全帯域_40ms_envelope_correlation": 0.9990500221153802, "全帯域_40ms_modulation_mae_db": 0.24033271652989296, "300–1000 Hz_10ms_log_rms_mae_db": 1.0751275006740542, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06778717111150608, "300–1000 Hz_10ms_envelope_correlation": 0.9962474688258676, "300–1000 Hz_10ms_modulation_mae_db": 0.6397741066945759, "300–1000 Hz_40ms_log_rms_mae_db": 0.6953780454618121, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03802707424888346, "300–1000 Hz_40ms_envelope_correlation": 0.9988387893109459, "300–1000 Hz_40ms_modulation_mae_db": 0.6733307984565554, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4747457650654427, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13106063789292727, "1000–3000 Hz_10ms_envelope_correlation": 0.988470656803726, "1000–3000 Hz_10ms_modulation_mae_db": 0.4188740048856026, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0824938663144692, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07807271656351483, "1000–3000 Hz_40ms_envelope_correlation": 0.9964393309213707, "1000–3000 Hz_40ms_modulation_mae_db": 0.2775728105025947, "3000–6000 Hz_10ms_log_rms_mae_db": 1.321283226777343, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16220705124131252, "3000–6000 Hz_10ms_envelope_correlation": 0.982367298736782, "3000–6000 Hz_10ms_modulation_mae_db": 0.3432203174999576, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8310609035475346, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09149639853860267, "3000–6000 Hz_40ms_envelope_correlation": 0.9941567824699338, "3000–6000 Hz_40ms_modulation_mae_db": 0.47323744391051287, "mr_stft_db": 5.547260253147942, "band_mae_db": 0.21735471763610711, "rms_gain_error_db": -0.0780591014531365, "output_peak": 0.2961722595447572}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8960610150400462, "全帯域_10ms_rms_envelope_nrmse": 0.049465126696257904, "全帯域_10ms_envelope_correlation": 0.9975175003404029, "全帯域_10ms_modulation_mae_db": 0.32734356221819966, "全帯域_40ms_log_rms_mae_db": 0.5167214038182439, "全帯域_40ms_rms_envelope_nrmse": 0.0270863737884804, "全帯域_40ms_envelope_correlation": 0.9993035426734369, "全帯域_40ms_modulation_mae_db": 0.426877217497126, "300–1000 Hz_10ms_log_rms_mae_db": 1.0243198892375924, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06206723358801622, "300–1000 Hz_10ms_envelope_correlation": 0.9968941150704794, "300–1000 Hz_10ms_modulation_mae_db": 0.6333689132102215, "300–1000 Hz_40ms_log_rms_mae_db": 0.6994255790664865, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03474145133485064, "300–1000 Hz_40ms_envelope_correlation": 0.9990594322409121, "300–1000 Hz_40ms_modulation_mae_db": 0.637256546225725, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4320247773563433, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11714193507706698, "1000–3000 Hz_10ms_envelope_correlation": 0.991253684819105, "1000–3000 Hz_10ms_modulation_mae_db": 1.248729553460068, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0353338350635781, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07295558047925088, "1000–3000 Hz_40ms_envelope_correlation": 0.9973296888442409, "1000–3000 Hz_40ms_modulation_mae_db": 1.390444736459747, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2762509797941057, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12578239376761977, "3000–6000 Hz_10ms_envelope_correlation": 0.9896480140017309, "3000–6000 Hz_10ms_modulation_mae_db": 0.7325426640504235, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8224493296140171, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06664952412645932, "3000–6000 Hz_40ms_envelope_correlation": 0.9972787807046491, "3000–6000 Hz_40ms_modulation_mae_db": 0.8942267478810358, "mr_stft_db": 5.552794415970271, "band_mae_db": 0.1757793279967422, "rms_gain_error_db": -0.09735885272705144, "output_peak": 0.2787551399521965}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9071470182961068, "全帯域_10ms_rms_envelope_nrmse": 0.051223716356921536, "全帯域_10ms_envelope_correlation": 0.9972916530651265, "全帯域_10ms_modulation_mae_db": 0.5014849435089775, "全帯域_40ms_log_rms_mae_db": 0.5157361519243925, "全帯域_40ms_rms_envelope_nrmse": 0.025978087757058742, "全帯域_40ms_envelope_correlation": 0.9993295816472956, "全帯域_40ms_modulation_mae_db": 0.6616441862102932, "300–1000 Hz_10ms_log_rms_mae_db": 1.0700495197737359, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06222551402722665, "300–1000 Hz_10ms_envelope_correlation": 0.9968084371504728, "300–1000 Hz_10ms_modulation_mae_db": 0.7786756277546494, "300–1000 Hz_40ms_log_rms_mae_db": 0.733529710513662, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03452538776519093, "300–1000 Hz_40ms_envelope_correlation": 0.9989868536707509, "300–1000 Hz_40ms_modulation_mae_db": 1.0685818148308714, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4689532260453897, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.135863011776242, "1000–3000 Hz_10ms_envelope_correlation": 0.9870976669676396, "1000–3000 Hz_10ms_modulation_mae_db": 0.5641443218571162, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0330532712217553, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07964540562842914, "1000–3000 Hz_40ms_envelope_correlation": 0.9956558211458826, "1000–3000 Hz_40ms_modulation_mae_db": 0.8513604386777546, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2200667678365535, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16874009093796224, "3000–6000 Hz_10ms_envelope_correlation": 0.9817090278137731, "3000–6000 Hz_10ms_modulation_mae_db": 1.7620822086517285, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7674219259578966, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08917513821245499, "3000–6000 Hz_40ms_envelope_correlation": 0.9958680113709286, "3000–6000 Hz_40ms_modulation_mae_db": 1.9771610606864998, "mr_stft_db": 5.538662811940841, "band_mae_db": 0.2118189869611168, "rms_gain_error_db": -0.08258075305322787, "output_peak": 0.26429646520371874}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.597602843197271, "spectral_convergence": 0.15318857798912303, "spectral_convergence_status": "ok", "amplitude_floor": 9.829298518478812e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.52755111367597, "spectral_convergence": 0.15182802854990923, "spectral_convergence_status": "ok", "amplitude_floor": 9.065329093063253e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.483418425664326, "spectral_convergence": 0.1559352473193555, "spectral_convergence_status": "ok", "amplitude_floor": 8.043941450863317e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.0001149513766055836, "output_power": 0.00012077236801107256, "delta_db": 0.21453405143560322, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0017363654374162414, "output_power": 0.0017048028111023871, "delta_db": -0.07966979735160201, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0004421876194377549, "output_power": 0.00043189811511286727, "delta_db": -0.10225270139893798, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.7408011480563064e-05, "output_power": 2.4316119698929946e-05, "delta_db": -0.5198325495427515, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7412343207141002e-05, "output_power": 2.3870316070056033e-05, "delta_db": -0.6008799102295217, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.428426915438781e-05, "output_power": 3.342321346906359e-05, "delta_db": -0.11046693212770389, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.433275239990599e-05, "output_power": 1.3320268149158483e-05, "delta_db": -0.31816630777318083, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.27797174997990015, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.08145727191188536, "pitch": null, "output_rms_dbfs": -26.284882363499676, "output_peak": 0.2935702231849335, "reference_rms_dbfs": -26.20342509158779, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.536190794179189}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014020226421084518, "log_rms_mae_db": 0.9038027385942038, "rms_envelope_nrmse": 0.05488968335143899, "envelope_correlation": 0.9968747638170011, "rms_gain_error_db": -0.08145725499870589, "reference_mean_power": 0.002398940884341968, "output_mean_power": 0.002354365149764252}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.599888913877476e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003971876344997112, "output_power": 0.00038445973210259976, "reference_active": true, "delta_db": -0.1414486031520332}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.277425400163653e-05, "output_power": 5.32026478483236e-05, "reference_active": true, "delta_db": 0.035111442934251814}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.46569016072901e-05, "output_power": 1.069522982934456e-05, "reference_active": true, "delta_db": -1.3685205087091392}], "active_band_count": 3, "active_band_mae_db": 0.5150268515984747}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001294702248118231, "log_rms_mae_db": 0.4790876465927573, "rms_envelope_nrmse": 0.029501648036659348, "envelope_correlation": 0.9991054345630346, "rms_gain_error_db": -0.08145715864867996, "reference_mean_power": 0.0024110057038516162, "output_mean_power": 0.0023662058402581796}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 8.923189531660561e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00035367674920645624, "output_power": 0.00034143290439882343, "reference_active": true, "delta_db": -0.15301137727422953}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.2909806376051565e-05, "output_power": 2.2976107897424517e-05, "reference_active": true, "delta_db": 0.012550433120463339}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.181144761591823e-07, "output_power": 4.862970667978931e-07, "reference_active": true, "delta_db": -2.2591242733188914}], "active_band_count": 3, "active_band_mae_db": 0.8082286945711948}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00013300454501172858, "log_rms_mae_db": 1.0553081034234004, "rms_envelope_nrmse": 0.06661222211370095, "envelope_correlation": 0.9963531811376704, "rms_gain_error_db": -0.08274911549335459, "reference_mean_power": 0.0013111812883454625, "output_mean_power": 0.0012864349523363104}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.210472671322603e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002971533743381409, "output_power": 0.0002843455606960191, "reference_active": true, "delta_db": -0.19134213990948673}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.9363200025831e-05, "output_power": 4.342122836287738e-05, "reference_active": true, "delta_db": -0.5570120032736561}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.44718666084695e-06, "output_power": 5.749902054302515e-06, "reference_active": true, "delta_db": -2.156420495450678}], "active_band_count": 3, "active_band_mae_db": 0.9682582128779403}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00012063998479701045, "log_rms_mae_db": 0.7166661848160184, "rms_envelope_nrmse": 0.03716434719914517, "envelope_correlation": 0.9988440390981224, "rms_gain_error_db": -0.08274913104228059, "reference_mean_power": 0.0013177756236779122, "output_mean_power": 0.0012929048260792461}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.775720236374225e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00027184637186405784, "output_power": 0.0002578656493633748, "reference_active": true, "delta_db": -0.22930048135930609}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0948015125222398e-05, "output_power": 1.846086572616145e-05, "reference_active": true, "delta_db": -0.5489081530777844}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.00249959518115e-07, "output_power": 3.7886685168707196e-07, "reference_active": true, "delta_db": -2.6676648331106954}], "active_band_count": 3, "active_band_mae_db": 1.1486244891825954}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.4324234792903394e-05, "log_rms_mae_db": 1.4152446338308824, "rms_envelope_nrmse": 0.13690848415507068, "envelope_correlation": 0.9890821281858888, "rms_gain_error_db": -0.545878588723001, "reference_mean_power": 3.621970358575803e-05, "output_mean_power": 3.194162693151718e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.144567073932934e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6016299479105344e-05, "output_power": 1.3193626057682786e-05, "reference_active": true, "delta_db": -0.8419800995859508}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.217328435986187e-06, "output_power": 4.10617496656749e-06, "reference_active": true, "delta_db": -1.0401072587410078}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.162268250073546e-07, "output_power": 5.847627106421454e-07, "reference_active": true, "delta_db": -0.22760929105100197}], "active_band_count": 3, "active_band_mae_db": 0.7032322164593202}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9150097924886824e-05, "log_rms_mae_db": 1.0525913624854946, "rms_envelope_nrmse": 0.09405563084371052, "envelope_correlation": 0.996477006910076, "rms_gain_error_db": -0.5458788372037832, "reference_mean_power": 3.640185858193717e-05, "output_mean_power": 3.21022649221691e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.976051267531115e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.575058419062026e-05, "output_power": 1.2864869721044756e-05, "reference_active": true, "delta_db": -0.8789127385745414}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5755236704985135e-06, "output_power": 2.040711180824431e-06, "reference_active": true, "delta_db": -1.0108400170630496}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.671987913674402e-08, "output_power": 4.887379393670759e-08, "reference_active": true, "delta_db": -1.3517919749502885}], "active_band_count": 3, "active_band_mae_db": 1.0805149101959597}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.268273320274525e-05, "log_rms_mae_db": 1.2848999085782347, "rms_envelope_nrmse": 0.2078285927710422, "envelope_correlation": 0.9714489658485248, "rms_gain_error_db": -0.45904405887264144, "reference_mean_power": 3.4234790780271314e-05, "output_mean_power": 3.080089045917839e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.011440004206466e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3904345626991894e-05, "output_power": 1.3039644534443107e-05, "reference_active": true, "delta_db": -0.27884802176859425}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.336600248325665e-06, "output_power": 4.935069570952581e-06, "reference_active": true, "delta_db": -0.3397139267388111}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.037307900027025e-06, "output_power": 1.124717064797677e-06, "reference_active": true, "delta_db": -2.580133847094258}], "active_band_count": 3, "active_band_mae_db": 1.066231931867221}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.282155756745637e-05, "log_rms_mae_db": 0.8094820103964739, "rms_envelope_nrmse": 0.1113744569520444, "envelope_correlation": 0.9927811795166194, "rms_gain_error_db": -0.45904409388346556, "reference_mean_power": 3.440696652445238e-05, "output_mean_power": 3.095579596822461e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.8610527191429872e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5067699650347801e-05, "output_power": 1.383541490757916e-05, "reference_active": true, "delta_db": -0.37054767030464364}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.7890585183930857e-06, "output_power": 2.468154282223158e-06, "reference_active": true, "delta_db": -0.5308532288613352}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4153621023540917e-07, "output_power": 6.92957352469105e-08, "reference_active": true, "delta_db": -3.1016105567127346}], "active_band_count": 3, "active_band_mae_db": 1.334337151959571}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9038095288956187, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "3e87f38b5ef25c25b6bad06c718f5e1c06ce6af28449c55da214c7d59d2ead9a", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.989662888169542, "standard_deviation": 0.001830314656171313, "minimum": 0.9870976669676396, "maximum": 0.992414593092257, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4311435717824565, "standard_deviation": 0.029614848633630342, "minimum": 1.3911327464639653, "maximum": 1.4747457650654427, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6670634797387864, "standard_deviation": 0.3015670384466439, "minimum": 0.38066854343169015, "maximum": 1.248729553460068, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12575446225294284, "standard_deviation": 0.01135456585594547, "minimum": 0.10435552512600885, "maximum": 0.13690848415507068, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9966463058341453, "standard_deviation": 0.0006302857414334045, "minimum": 0.9956558211458826, "maximum": 0.9976852783159701, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.0475318445855937, "standard_deviation": 0.016881808500117237, "minimum": 1.0324823317700604, "maximum": 1.0824938663144692, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8491320151250961, "standard_deviation": 0.3783736294712583, "minimum": 0.2775728105025947, "maximum": 1.390444736459747, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07843583692866027, "standard_deviation": 0.010117160011787332, "minimum": 0.058166405572215, "maximum": 0.09405563084371052, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9827484328797448, "standard_deviation": 0.005431218872524635, "minimum": 0.9714489658485248, "maximum": 0.9896480140017309, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2712440305493438, "standard_deviation": 0.028877806644252244, "minimum": 1.2200667678365535, "maximum": 1.321283226777343, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7602678285057967, "standard_deviation": 0.47072230956175776, "minimum": 0.3361581149804565, "maximum": 1.7620822086517285, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16014839493863192, "standard_deviation": 0.024334706144165077, "minimum": 0.12578239376761977, "maximum": 0.2078285927710422, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9950761814660204, "standard_deviation": 0.0017153677940711929, "minimum": 0.9927811795166194, "maximum": 0.9972787807046491, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.805682761587122, "standard_deviation": 0.02272358096217798, "minimum": 0.7674219259578966, "maximum": 0.8325137489052541, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.9577086844264895, "standard_deviation": 0.5017093612588445, "minimum": 0.448463000840537, "maximum": 1.9771610606864998, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08734058976536449, "standard_deviation": 0.015437248660699643, "minimum": 0.06636251412136306, "maximum": 0.1113744569520444, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.99656371702267, "standard_deviation": 0.00040511741149686455, "minimum": 0.9960200289624327, "maximum": 0.9970301092336598, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0552274448473093, "standard_deviation": 0.01736901966112954, "minimum": 1.0243198892375924, "maximum": 1.0751275006740542, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8002664924028435, "standard_deviation": 0.2189478281519758, "minimum": 0.5414677248080745, "maximum": 1.2138878447678951, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06508864750929075, "standard_deviation": 0.0035882483432107485, "minimum": 0.06156872274144384, "maximum": 0.070572642475702, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9989533414884664, "standard_deviation": 0.0001566917199434172, "minimum": 0.9987063840994235, "maximum": 0.9991925591855977, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7067264025395381, "standard_deviation": 0.023981598750198337, "minimum": 0.6643206527345711, "maximum": 0.741048964118641, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.9601459489967618, "standard_deviation": 0.28743674158281435, "minimum": 0.637256546225725, "maximum": 1.4526446655612026, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03637738110876397, "standard_deviation": 0.002466218034161965, "minimum": 0.033166806268799746, "maximum": 0.04112780460988506, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.2083691969586658, "standard_deviation": 0.033219305762601445, "minimum": 0.1757793279967422, "maximum": 0.27797174997990015, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.543868307166284, "standard_deviation": 0.00551037864764048, "minimum": 5.536190794179189, "maximum": 5.552794415970271, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.2796137605868751, "standard_deviation": 0.01049458502978209, "minimum": 0.26429646520371874, "maximum": 0.2961722595447572, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.08871867286718504, "standard_deviation": 0.01157014457274121, "minimum": -0.10791236023983063, "maximum": -0.07431164200548274, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9971617452738881, "standard_deviation": 0.0002907458382394296, "minimum": 0.9967922787556311, "maximum": 0.9975588775106773, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9024542643445255, "standard_deviation": 0.010594483418474463, "minimum": 0.886254329897327, "maximum": 0.917009099001579, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.40264176628734427, "standard_deviation": 0.13371611095944125, "minimum": 0.1782832960050509, "maximum": 0.5507481939158086, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05251630592504161, "standard_deviation": 0.0024167174509134894, "minimum": 0.04919909021312006, "maximum": 0.05549638024008066, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.999196820129745, "standard_deviation": 0.00013729765724621593, "minimum": 0.9990263171815398, "maximum": 0.9993575719627846, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5120392570579135, "standard_deviation": 0.024843158320717342, "minimum": 0.474895238194164, "maximum": 0.5444899689548873, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5583619982483878, "standard_deviation": 0.2503464513032379, "minimum": 0.22270773831875493, "maximum": 0.9219175825083594, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.028390278767884615, "standard_deviation": 0.0018717655407129653, "minimum": 0.025978087757058742, "maximum": 0.03106025297386167, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs004_whisper10_BASIC5000_0074", "language": "ja", "style": "whisper", "speaker": "jvs_jvs004", "source_utterance_id": "BASIC5000_0074", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 109060, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs004_whisper10_BASIC5000_0074.wav", "source_file_sha256": "1dc1b85502f10b17f18e1f869d9eaba17aab672d72df9a9f67b64e4b49f65b04", "decoded_pcm_sha256": "8a2729f6e6b88649d73978b5840454d69e802da2f211934be9b5b14712461b43", "original_source_sha256": "1dc1b85502f10b17f18e1f869d9eaba17aab672d72df9a9f67b64e4b49f65b04", "corpus_entry_id": "jvs_jvs004_whisper10_BASIC5000_0074"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 3.7807705402374268, "predicted_mos": 3.7807705402374268, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 109060, "input_sample_rate": 24000, "input_seconds": 4.5441666666666665, "input_float32_sha256": "b8b6fb8696714c9c069a84cac7c81ea33e27e0c049cc20b8009de11613dfbaf3", "internal_samples": 72707, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.759721299633384}, "waveform_sha256": "6ae74a6e4ad284a82413050c402bf2a42f884a3315674052d13d2caa45fe6de7"}, "rows": [{"case": "jvs_jvs004_whisper10_BASIC5000_0074", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 1.720005750656128, "predicted_mos": 1.720005750656128, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 109060, "input_sample_rate": 24000, "input_seconds": 4.5441666666666665, "input_float32_sha256": "9cc904a28bfadd5732d72e18a2ce9a583aa8a09eebd617539092b86eb66144e7", "internal_samples": 72707, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.48207540018484}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4433431828271832, "全帯域_10ms_rms_envelope_nrmse": 0.13108550889810378, "全帯域_10ms_envelope_correlation": 0.9852155529682795, "全帯域_10ms_modulation_mae_db": 0.4120894170300229, "全帯域_40ms_log_rms_mae_db": 0.7304176165376753, "全帯域_40ms_rms_envelope_nrmse": 0.0680868089188179, "全帯域_40ms_envelope_correlation": 0.9959346247008384, "全帯域_40ms_modulation_mae_db": 0.7486778042127539, "300–1000 Hz_10ms_log_rms_mae_db": 2.1061653263981137, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.28134056152920206, "300–1000 Hz_10ms_envelope_correlation": 0.9343003809336883, "300–1000 Hz_10ms_modulation_mae_db": 0.621522270200428, "300–1000 Hz_40ms_log_rms_mae_db": 1.4748331373943089, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17396766553985069, "300–1000 Hz_40ms_envelope_correlation": 0.9742684915877897, "300–1000 Hz_40ms_modulation_mae_db": 0.8678282373470134, "1000–3000 Hz_10ms_log_rms_mae_db": 1.491508055400155, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18269189303738897, "1000–3000 Hz_10ms_envelope_correlation": 0.9744391544981142, "1000–3000 Hz_10ms_modulation_mae_db": 0.9100684382184108, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8501143252249247, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11166648127850343, "1000–3000 Hz_40ms_envelope_correlation": 0.9898843550249055, "1000–3000 Hz_40ms_modulation_mae_db": 1.1308208496035448, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3630157745365243, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16807540043157834, "3000–6000 Hz_10ms_envelope_correlation": 0.9783623832918343, "3000–6000 Hz_10ms_modulation_mae_db": 0.3656714721387974, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7484888005849957, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08066518889654707, "3000–6000 Hz_40ms_envelope_correlation": 0.9947409176976363, "3000–6000 Hz_40ms_modulation_mae_db": 0.4566225170097133, "mr_stft_db": 6.030840474135385, "band_mae_db": 0.4356785241260326, "rms_gain_error_db": 0.15374172925389046, "output_peak": 0.03252869516708512}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.397025140323527, "全帯域_10ms_rms_envelope_nrmse": 0.12036627781851823, "全帯域_10ms_envelope_correlation": 0.9871831250484681, "全帯域_10ms_modulation_mae_db": 0.41762608617768987, "全帯域_40ms_log_rms_mae_db": 0.7204312639536329, "全帯域_40ms_rms_envelope_nrmse": 0.0553062105041679, "全帯域_40ms_envelope_correlation": 0.9971241713982321, "全帯域_40ms_modulation_mae_db": 0.6378272872869067, "300–1000 Hz_10ms_log_rms_mae_db": 2.224524536977226, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2622392518165255, "300–1000 Hz_10ms_envelope_correlation": 0.9444840645317516, "300–1000 Hz_10ms_modulation_mae_db": 1.1165489064472895, "300–1000 Hz_40ms_log_rms_mae_db": 1.4632425051339715, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15131808239693145, "300–1000 Hz_40ms_envelope_correlation": 0.9821992178203437, "300–1000 Hz_40ms_modulation_mae_db": 0.9387409571276505, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5516622406962681, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1948834804254696, "1000–3000 Hz_10ms_envelope_correlation": 0.9706202864390255, "1000–3000 Hz_10ms_modulation_mae_db": 0.7869344119529548, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8700099641005802, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09944655093074334, "1000–3000 Hz_40ms_envelope_correlation": 0.9919564482887219, "1000–3000 Hz_40ms_modulation_mae_db": 0.9293368045170246, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2982366630028128, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1602060136223132, "3000–6000 Hz_10ms_envelope_correlation": 0.9798245396447237, "3000–6000 Hz_10ms_modulation_mae_db": 0.2297747982779781, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7424148520387805, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08451787220194243, "3000–6000 Hz_40ms_envelope_correlation": 0.9940306714622493, "3000–6000 Hz_40ms_modulation_mae_db": 0.35249011459276147, "mr_stft_db": 6.022319690496168, "band_mae_db": 0.42197975887055467, "rms_gain_error_db": 0.0617484162887187, "output_peak": 0.036884045363715166}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3977611107847807, "全帯域_10ms_rms_envelope_nrmse": 0.11759362966840228, "全帯域_10ms_envelope_correlation": 0.9878638431801119, "全帯域_10ms_modulation_mae_db": 0.24444868493350078, "全帯域_40ms_log_rms_mae_db": 0.755634537561066, "全帯域_40ms_rms_envelope_nrmse": 0.06569309737976711, "全帯域_40ms_envelope_correlation": 0.9959891513315919, "全帯域_40ms_modulation_mae_db": 0.06347526173919059, "300–1000 Hz_10ms_log_rms_mae_db": 2.1113121724855426, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24286414041156268, "300–1000 Hz_10ms_envelope_correlation": 0.9492308863159633, "300–1000 Hz_10ms_modulation_mae_db": 0.2174192337463086, "300–1000 Hz_40ms_log_rms_mae_db": 1.42444987432283, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13263346130703038, "300–1000 Hz_40ms_envelope_correlation": 0.9844342172192101, "300–1000 Hz_40ms_modulation_mae_db": 0.9702309240281665, "1000–3000 Hz_10ms_log_rms_mae_db": 1.495806689667913, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17358048051620897, "1000–3000 Hz_10ms_envelope_correlation": 0.9770184638723357, "1000–3000 Hz_10ms_modulation_mae_db": 0.8266204816247139, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8068760027000301, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0986885723653765, "1000–3000 Hz_40ms_envelope_correlation": 0.9920264168613228, "1000–3000 Hz_40ms_modulation_mae_db": 0.3907900354010772, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3034092148768792, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14905231743275774, "3000–6000 Hz_10ms_envelope_correlation": 0.9831720313527222, "3000–6000 Hz_10ms_modulation_mae_db": 0.37554840209704743, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7755317518391004, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08722542762360905, "3000–6000 Hz_40ms_envelope_correlation": 0.9939670309551901, "3000–6000 Hz_40ms_modulation_mae_db": 0.8079729357349676, "mr_stft_db": 6.0259174361160035, "band_mae_db": 0.4204101741537497, "rms_gain_error_db": 0.09045333659756864, "output_peak": 0.03397905566477762}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4029031124768037, "全帯域_10ms_rms_envelope_nrmse": 0.1183424935580268, "全帯域_10ms_envelope_correlation": 0.9875476924345424, "全帯域_10ms_modulation_mae_db": 0.7670556945300196, "全帯域_40ms_log_rms_mae_db": 0.785505832057594, "全帯域_40ms_rms_envelope_nrmse": 0.06401245439946457, "全帯域_40ms_envelope_correlation": 0.9963358434481541, "全帯域_40ms_modulation_mae_db": 0.8799460196663009, "300–1000 Hz_10ms_log_rms_mae_db": 2.1811409287370522, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2785163523697116, "300–1000 Hz_10ms_envelope_correlation": 0.9416813962693664, "300–1000 Hz_10ms_modulation_mae_db": 0.7841550548555564, "300–1000 Hz_40ms_log_rms_mae_db": 1.4792432394350994, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.18518300337165816, "300–1000 Hz_40ms_envelope_correlation": 0.9757302334776594, "300–1000 Hz_40ms_modulation_mae_db": 0.6269111425633681, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4682467850412304, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19130682693290066, "1000–3000 Hz_10ms_envelope_correlation": 0.9716917323352137, "1000–3000 Hz_10ms_modulation_mae_db": 0.647919142605228, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8246425475557524, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10062259845799676, "1000–3000 Hz_40ms_envelope_correlation": 0.9918418013619047, "1000–3000 Hz_40ms_modulation_mae_db": 0.9820469808902127, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2564447744977465, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14108397904265313, "3000–6000 Hz_10ms_envelope_correlation": 0.9847535035616759, "3000–6000 Hz_10ms_modulation_mae_db": 1.0795795425277228, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6828563720903211, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08436517155579507, "3000–6000 Hz_40ms_envelope_correlation": 0.9946916762527479, "3000–6000 Hz_40ms_modulation_mae_db": 1.5707948440974226, "mr_stft_db": 6.021091542496751, "band_mae_db": 0.45212017390380843, "rms_gain_error_db": -0.14996843989418626, "output_peak": 0.03415179745739628}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4072905279926318, "全帯域_10ms_rms_envelope_nrmse": 0.1322173667597876, "全帯域_10ms_envelope_correlation": 0.9843726093400607, "全帯域_10ms_modulation_mae_db": 0.08276861680379106, "全帯域_40ms_log_rms_mae_db": 0.7690493606729817, "全帯域_40ms_rms_envelope_nrmse": 0.07873024427422293, "全帯域_40ms_envelope_correlation": 0.9940186724664865, "全帯域_40ms_modulation_mae_db": 0.16440027311353347, "300–1000 Hz_10ms_log_rms_mae_db": 2.2282035475096413, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2718758845801726, "300–1000 Hz_10ms_envelope_correlation": 0.9357699945758764, "300–1000 Hz_10ms_modulation_mae_db": 0.6534742827620406, "300–1000 Hz_40ms_log_rms_mae_db": 1.5381761576675204, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17177571499116373, "300–1000 Hz_40ms_envelope_correlation": 0.9724952109791292, "300–1000 Hz_40ms_modulation_mae_db": 0.3458914127843606, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5586533885356917, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19261942306689545, "1000–3000 Hz_10ms_envelope_correlation": 0.9713149124014742, "1000–3000 Hz_10ms_modulation_mae_db": 0.47674364421636817, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9303298748970065, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1187271417309236, "1000–3000 Hz_40ms_envelope_correlation": 0.9883554990499939, "1000–3000 Hz_40ms_modulation_mae_db": 0.1629677120897166, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2931375677976849, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16119205237181747, "3000–6000 Hz_10ms_envelope_correlation": 0.9796683214090603, "3000–6000 Hz_10ms_modulation_mae_db": 0.28770972514467813, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7261779154487221, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08289154892747146, "3000–6000 Hz_40ms_envelope_correlation": 0.9942261642314679, "3000–6000 Hz_40ms_modulation_mae_db": 0.5867834666743477, "mr_stft_db": 6.039541613712944, "band_mae_db": 0.3779385813916164, "rms_gain_error_db": -0.002661515318318061, "output_peak": 0.04473534292732471}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3743995224342165, "全帯域_10ms_rms_envelope_nrmse": 0.12215842985943096, "全帯域_10ms_envelope_correlation": 0.9866074329488916, "全帯域_10ms_modulation_mae_db": 0.2779282219731464, "全帯域_40ms_log_rms_mae_db": 0.7611467986900265, "全帯域_40ms_rms_envelope_nrmse": 0.062390824936881084, "全帯域_40ms_envelope_correlation": 0.9963072893930506, "全帯域_40ms_modulation_mae_db": 0.5681569156878706, "300–1000 Hz_10ms_log_rms_mae_db": 2.160852093305741, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.28110492091763, "300–1000 Hz_10ms_envelope_correlation": 0.9356464424175563, "300–1000 Hz_10ms_modulation_mae_db": 0.4639030349175233, "300–1000 Hz_40ms_log_rms_mae_db": 1.475421768840767, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15281314957178876, "300–1000 Hz_40ms_envelope_correlation": 0.9819736773870896, "300–1000 Hz_40ms_modulation_mae_db": 0.8458153124158209, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5142481325932788, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18669372220138694, "1000–3000 Hz_10ms_envelope_correlation": 0.9736503457425733, "1000–3000 Hz_10ms_modulation_mae_db": 0.3916006283214993, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8877465264062359, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10137186393944364, "1000–3000 Hz_40ms_envelope_correlation": 0.9917714524401281, "1000–3000 Hz_40ms_modulation_mae_db": 0.3890653961027153, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3253633680807075, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1677575255708309, "3000–6000 Hz_10ms_envelope_correlation": 0.9778282528893446, "3000–6000 Hz_10ms_modulation_mae_db": 0.4039740801166047, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7412424342616649, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09157327831495156, "3000–6000 Hz_40ms_envelope_correlation": 0.9930975512862691, "3000–6000 Hz_40ms_modulation_mae_db": 0.7120896179696876, "mr_stft_db": 6.02581931603333, "band_mae_db": 0.46806309877674485, "rms_gain_error_db": -0.04795822402297491, "output_peak": 0.03849887028936363}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4730480830362849, "全帯域_10ms_rms_envelope_nrmse": 0.13065331257043236, "全帯域_10ms_envelope_correlation": 0.9849245465915709, "全帯域_10ms_modulation_mae_db": 1.086251219314675, "全帯域_40ms_log_rms_mae_db": 0.804045532206651, "全帯域_40ms_rms_envelope_nrmse": 0.06977573442078168, "全帯域_40ms_envelope_correlation": 0.9958666985490456, "全帯域_40ms_modulation_mae_db": 1.5840013688997086, "300–1000 Hz_10ms_log_rms_mae_db": 2.052107895113018, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24780254036000227, "300–1000 Hz_10ms_envelope_correlation": 0.9486208787555643, "300–1000 Hz_10ms_modulation_mae_db": 0.7060530951908096, "300–1000 Hz_40ms_log_rms_mae_db": 1.4030393682303786, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14023866959536085, "300–1000 Hz_40ms_envelope_correlation": 0.9836534383857903, "300–1000 Hz_40ms_modulation_mae_db": 0.6784689780500511, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6053206852762634, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20438242563883938, "1000–3000 Hz_10ms_envelope_correlation": 0.9676315001928436, "1000–3000 Hz_10ms_modulation_mae_db": 1.1412246693175385, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9416240107833491, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10690013212827006, "1000–3000 Hz_40ms_envelope_correlation": 0.9907545575437892, "1000–3000 Hz_40ms_modulation_mae_db": 1.7134899711456881, "3000–6000 Hz_10ms_log_rms_mae_db": 1.295237399857095, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15045462780396074, "3000–6000 Hz_10ms_envelope_correlation": 0.982224672585167, "3000–6000 Hz_10ms_modulation_mae_db": 0.5548147473189471, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7513738412098024, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08045249245775957, "3000–6000 Hz_40ms_envelope_correlation": 0.9947295821201111, "3000–6000 Hz_40ms_modulation_mae_db": 0.8682607818393621, "mr_stft_db": 6.025832283901642, "band_mae_db": 0.3923350279479744, "rms_gain_error_db": -0.22789809010759432, "output_peak": 0.034292892043860136}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4169030956098876, "全帯域_10ms_rms_envelope_nrmse": 0.13301891989762799, "全帯域_10ms_envelope_correlation": 0.984328715120554, "全帯域_10ms_modulation_mae_db": 0.5104461614432942, "全帯域_40ms_log_rms_mae_db": 0.7235654536728875, "全帯域_40ms_rms_envelope_nrmse": 0.06460718329033703, "全帯域_40ms_envelope_correlation": 0.9960542117628093, "全帯域_40ms_modulation_mae_db": 0.7652842184824954, "300–1000 Hz_10ms_log_rms_mae_db": 2.210860236535077, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2571538588816252, "300–1000 Hz_10ms_envelope_correlation": 0.944273386320622, "300–1000 Hz_10ms_modulation_mae_db": 0.5663201570361209, "300–1000 Hz_40ms_log_rms_mae_db": 1.554637119440756, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1473588674316399, "300–1000 Hz_40ms_envelope_correlation": 0.9814517679033691, "300–1000 Hz_40ms_modulation_mae_db": 0.6828694689898311, "1000–3000 Hz_10ms_log_rms_mae_db": 1.553989076294654, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19505515272982216, "1000–3000 Hz_10ms_envelope_correlation": 0.9707174639690878, "1000–3000 Hz_10ms_modulation_mae_db": 0.5170391313397474, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8832591231135458, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09865745601408005, "1000–3000 Hz_40ms_envelope_correlation": 0.9919787395737832, "1000–3000 Hz_40ms_modulation_mae_db": 0.8701436092800554, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2769462899926687, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15430062285826612, "3000–6000 Hz_10ms_envelope_correlation": 0.981647469460304, "3000–6000 Hz_10ms_modulation_mae_db": 0.6703953278202662, "3000–6000 Hz_40ms_log_rms_mae_db": 0.69371050199735, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0769494778231428, "3000–6000 Hz_40ms_envelope_correlation": 0.9951603091373145, "3000–6000 Hz_40ms_modulation_mae_db": 0.8275076361313806, "mr_stft_db": 6.009906532709134, "band_mae_db": 0.36584797496939647, "rms_gain_error_db": 0.05841759973500939, "output_peak": 0.035740351298729295}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 109060, "output_samples": 109060, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.13505732528478, "spectral_convergence": 0.625968023494518, "spectral_convergence_status": "ok", "amplitude_floor": 7.347807435362163e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.879902712714506, "spectral_convergence": 0.6165015572603519, "spectral_convergence_status": "ok", "amplitude_floor": 3.5954742817466214e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.077561384406869, "spectral_convergence": 0.6431648927383301, "spectral_convergence_status": "ok", "amplitude_floor": 1.4970646531776498e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.2516812561146785e-07, "output_power": 1.1531414904835812e-07, "delta_db": -0.3561115022924946, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 8.469209703610174e-08, "output_power": 1.154010604871324e-07, "delta_db": 1.343669133837597, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 4.7196494133004234e-07, "output_power": 5.033246810516205e-07, "delta_db": 0.27938487590063743, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.5661034348838578e-06, "output_power": 1.5286849657078663e-06, "delta_db": -0.10502447682956774, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2294550474819316e-06, "output_power": 1.3266251807436708e-06, "delta_db": 0.33035582135010644, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.3429464378207576e-06, "output_power": 3.3692085484003408e-06, "delta_db": 0.03398475730212972, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.563896615059082e-07, "output_power": 1.098390537669942e-06, "delta_db": 0.6012191013696951, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.4356785241260326, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.15374172925389046, "pitch": null, "output_rms_dbfs": -50.93829378769109, "output_peak": 0.03252869516708512, "reference_rms_dbfs": -51.09203551694498, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.030840474135385}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 109060, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 1.1882865623804307e-05, "log_rms_mae_db": 1.4433431828271832, "rms_envelope_nrmse": 0.13108550889810378, "envelope_correlation": 0.9852155529682795, "rms_gain_error_db": 0.1537076399754877, "reference_mean_power": 7.792370026271951e-06, "output_mean_power": 8.073099983269133e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 4.121961515330987e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7941587942139734e-06, "output_power": 1.750781995537769e-06, "reference_active": true, "delta_db": -0.10628806348955691}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1263612266386524e-07, "output_power": 2.8856278557859516e-07, "reference_active": true, "delta_db": -0.3479883422141817}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9590349245364564e-07, "output_power": 1.636224886529332e-07, "reference_active": true, "delta_db": -0.7819918453863299}], "active_band_count": 3, "active_band_mae_db": 0.4120894170300229}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 9.239390922709503e-06, "log_rms_mae_db": 0.7304176165376753, "rms_envelope_nrmse": 0.0680868089188179, "envelope_correlation": 0.9959346247008384, "rms_gain_error_db": 0.15371680811695976, "reference_mean_power": 7.844041250222317e-06, "output_mean_power": 8.126649883909746e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 3.7692280722089195e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6572550629104971e-06, "output_power": 1.6159638627153528e-06, "reference_active": true, "delta_db": -0.10957709902136567}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5392861690297655e-07, "output_power": 1.3019538185320002e-07, "reference_active": true, "delta_db": -0.7272378742895944}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6336932951152273e-08, "output_power": 1.1809966962749591e-08, "reference_active": true, "delta_db": -1.4092184393273013}], "active_band_count": 3, "active_band_mae_db": 0.7486778042127539}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 2.9307310026633354e-06, "log_rms_mae_db": 2.1061653263981137, "rms_envelope_nrmse": 0.28134056152920206, "envelope_correlation": 0.9343003809336883, "rms_gain_error_db": 0.5242152023438369, "reference_mean_power": 4.2741366364654595e-07, "output_mean_power": 4.822474300273801e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 2.4398860779830526e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.615850373422058e-08, "output_power": 1.0523712740421747e-07, "reference_active": true, "delta_db": 0.39181287984317636}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8718875021930722e-08, "output_power": 2.552540323205105e-08, "reference_active": true, "delta_db": 1.3469286678789683}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0143942568188046e-08, "output_power": 2.073609628841757e-08, "reference_active": true, "delta_db": 0.12582526287913956}], "active_band_count": 3, "active_band_mae_db": 0.621522270200428}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 1.736089681183382e-06, "log_rms_mae_db": 1.4748331373943089, "rms_envelope_nrmse": 0.17396766553985069, "envelope_correlation": 0.9742684915877897, "rms_gain_error_db": 0.5241593065627782, "reference_mean_power": 4.3025101883138276e-07, "output_mean_power": 4.85442547349102e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 2.1733905138014183e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.047483464267491e-08, "output_power": 9.936442931542538e-08, "reference_active": true, "delta_db": 0.40703144540726477}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.338915747949155e-09, "output_power": 1.2341783997124417e-08, "reference_active": true, "delta_db": 1.2108148384477309}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.438276742938052e-09, "output_power": 1.1462480638699189e-09, "reference_active": true, "delta_db": -0.9856384281860449}], "active_band_count": 3, "active_band_mae_db": 0.8678282373470134}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 7.246614216836824e-06, "log_rms_mae_db": 1.491508055400155, "rms_envelope_nrmse": 0.18269189303738897, "envelope_correlation": 0.9744391544981142, "rms_gain_error_db": -0.027894061195855475, "reference_mean_power": 1.7870157226185334e-06, "output_mean_power": 1.77557477874556e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.838724239404773e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.063249741710556e-07, "output_power": 6.221071433024483e-07, "reference_active": true, "delta_db": -0.5513937413771576}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.654737664402428e-07, "output_power": 1.162028318295538e-07, "reference_active": true, "delta_db": -1.5351244041599743}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2023841152792083e-07, "output_power": 1.036751120067036e-07, "reference_active": true, "delta_db": -0.6436871691181005}], "active_band_count": 3, "active_band_mae_db": 0.9100684382184108}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.77385839866885e-06, "log_rms_mae_db": 0.8501143252249247, "rms_envelope_nrmse": 0.11166648127850343, "envelope_correlation": 0.9898843550249055, "rms_gain_error_db": -0.027893646004600016, "reference_mean_power": 1.7989086732437154e-06, "output_mean_power": 1.7873917584551097e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 1.713692894624548e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.664518497859096e-07, "output_power": 5.834370482259194e-07, "reference_active": true, "delta_db": -0.5777477437325029}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.184085944051966e-08, "output_power": 5.758603045869953e-08, "reference_active": true, "delta_db": -1.5265303879606882}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1933830695482323e-08, "output_power": 8.870772276686299e-09, "reference_active": true, "delta_db": -1.288184417117443}], "active_band_count": 3, "active_band_mae_db": 1.1308208496035448}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 6.060487704579714e-06, "log_rms_mae_db": 1.3630157745365243, "rms_envelope_nrmse": 0.16807540043157834, "envelope_correlation": 0.9783623832918343, "rms_gain_error_db": 0.10366242570593473, "reference_mean_power": 1.7907615060268857e-06, "output_mean_power": 1.8340196853937097e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.036723230359137e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.741355867444106e-07, "output_power": 4.8666274877198e-07, "reference_active": true, "delta_db": 0.11325551805897983}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0977135221440419e-07, "output_power": 1.3092985046826248e-07, "reference_active": true, "delta_db": 0.7654965780101817}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0575338351673974e-08, "output_power": 3.215122344758199e-08, "reference_active": true, "delta_db": 0.21826232034723062}], "active_band_count": 3, "active_band_mae_db": 0.3656714721387974}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.330101975711502e-06, "log_rms_mae_db": 0.7484888005849957, "rms_envelope_nrmse": 0.08066518889654707, "envelope_correlation": 0.9947409176976363, "rms_gain_error_db": 0.10366266685889637, "reference_mean_power": 1.8026836617488875e-06, "output_mean_power": 1.8462299388504753e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 9.630136220520234e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.5232190822756626e-07, "output_power": 4.7200836767731836e-07, "reference_active": true, "delta_db": 0.1850207447094817}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.528340255264933e-08, "output_power": 6.544057112615604e-08, "reference_active": true, "delta_db": 0.7325231603404475}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3355698674413927e-09, "output_power": 2.104556060945085e-09, "reference_active": true, "delta_db": -0.45232364597921065}], "active_band_count": 3, "active_band_mae_db": 0.4566225170097133}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5440220259974088, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "9f96195dd421060907c341f506c24a9bd8c4148063f63338d6948147dbb43759", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9721354824313335, "standard_deviation": 0.002851263483763349, "minimum": 0.9676315001928436, "maximum": 0.9770184638723357, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.5299293816881818, "standard_deviation": 0.04512095493232793, "minimum": 1.4682467850412304, "maximum": 1.6053206852762634, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7122688184495576, "standard_deviation": 0.2513775682305571, "minimum": 0.3916006283214993, "maximum": 1.1412246693175385, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.190151675568614, "standard_deviation": 0.009247260349443268, "minimum": 0.17358048051620897, "maximum": 0.20438242563883938, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9910711587680686, "standard_deviation": 0.001335654300758552, "minimum": 0.9883554990499939, "maximum": 0.9920264168613228, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.874325296847678, "standard_deviation": 0.0471292272319221, "minimum": 0.8068760027000301, "maximum": 0.9416240107833491, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8210826698787543, "standard_deviation": 0.4981781018280021, "minimum": 0.1629677120897166, "maximum": 1.7134899711456881, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10451009960566716, "standard_deviation": 0.007346473116600463, "minimum": 0.09865745601408005, "maximum": 0.1187271417309236, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.980935146774354, "standard_deviation": 0.0024161355759658065, "minimum": 0.9778282528893446, "maximum": 0.9847535035616759, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.301473881580265, "standard_deviation": 0.031870156928394865, "minimum": 1.2564447744977465, "maximum": 1.3630157745365243, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.4959335119302552, "standard_deviation": 0.2748146209285591, "minimum": 0.2297747982779781, "maximum": 1.0795795425277228, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1565153173917722, "standard_deviation": 0.009494173063802324, "minimum": 0.14108397904265313, "maximum": 0.16807540043157834, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9943304878928733, "standard_deviation": 0.0006436276758391738, "minimum": 0.9930975512862691, "maximum": 0.9951603091373145, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7327245586838422, "standard_deviation": 0.030815140128231475, "minimum": 0.6828563720903211, "maximum": 0.7755317518391004, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7728152392562054, "standard_deviation": 0.3713017819115319, "minimum": 0.35249011459276147, "maximum": 1.5707948440974226, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08358005722515238, "standard_deviation": 0.004494329058537453, "minimum": 0.0769494778231428, "maximum": 0.09157327831495156, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9417509287650486, "standard_deviation": 0.005922482903211715, "minimum": 0.9343003809336883, "maximum": 0.9492308863159633, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.1593958421326764, "standard_deviation": 0.0640937162390351, "minimum": 2.052107895113018, "maximum": 2.2282035475096413, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6411745043945096, "standard_deviation": 0.25850334702135885, "minimum": 0.2174192337463086, "maximum": 1.1165489064472895, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.265362188858304, "standard_deviation": 0.015166858190581932, "minimum": 0.24286414041156268, "maximum": 0.28134056152920206, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9795257818450476, "standard_deviation": 0.004620658210614188, "minimum": 0.9724952109791292, "maximum": 0.9844342172192101, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.4766303963082041, "standard_deviation": 0.0509931779507968, "minimum": 1.4030393682303786, "maximum": 1.554637119440756, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7445945541632828, "standard_deviation": 0.20529871547480846, "minimum": 0.3458914127843606, "maximum": 0.9702309240281665, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15691107677567798, "standard_deviation": 0.018196850566854675, "minimum": 0.13263346130703038, "maximum": 0.18518300337165816, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.4167966642674847, "standard_deviation": 0.03581008515729498, "minimum": 0.36584797496939647, "maximum": 0.46806309877674485, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.02515861120017, "standard_deviation": 0.008433326115849403, "minimum": 6.009906532709134, "maximum": 6.039541613712944, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.036351381276531494, "standard_deviation": 0.003870696051906597, "minimum": 0.03252869516708512, "maximum": 0.04473534292732471, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.0080156484334858, "standard_deviation": 0.1283215551898061, "minimum": -0.22789809010759432, "maximum": 0.15374172925389046, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9860054397040598, "standard_deviation": 0.0014565780300935668, "minimum": 0.984328715120554, "maximum": 0.9878638431801119, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.4140842219356644, "standard_deviation": 0.03080879475750954, "minimum": 1.3743995224342165, "maximum": 1.4730480830362849, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.47482676277576746, "standard_deviation": 0.31921039458271033, "minimum": 0.08276861680379106, "maximum": 1.086251219314675, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.12567949237879125, "standard_deviation": 0.006659212279967631, "minimum": 0.11759362966840228, "maximum": 0.13301891989762799, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.995953832881276, "standard_deviation": 0.0008786910974366744, "minimum": 0.9940186724664865, "maximum": 0.9971241713982321, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.7562245494190645, "standard_deviation": 0.03011185326036698, "minimum": 0.7204312639536329, "maximum": 0.804045532206651, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6764711436360951, "standard_deviation": 0.4674124129270015, "minimum": 0.06347526173919059, "maximum": 1.5840013688997086, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.06607531976555503, "standard_deviation": 0.006697466686967663, "minimum": 0.0553062105041679, "maximum": 0.07873024427422293, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_whisper10_BASIC5000_0074", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 1.752979040145874, "predicted_mos": 1.752979040145874, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 109060, "input_sample_rate": 24000, "input_seconds": 4.5441666666666665, "input_float32_sha256": "4ffde8af22e35e877594465c563e09be957348824108c584032e5ad5ef0db63a", "internal_samples": 72707, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.745377699844539}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4847435548394903, "全帯域_10ms_rms_envelope_nrmse": 0.13254287277501775, "全帯域_10ms_envelope_correlation": 0.9848403848889614, "全帯域_10ms_modulation_mae_db": 0.36495181340879457, "全帯域_40ms_log_rms_mae_db": 0.7567865267736854, "全帯域_40ms_rms_envelope_nrmse": 0.0684403489448031, "全帯域_40ms_envelope_correlation": 0.9958595496722173, "全帯域_40ms_modulation_mae_db": 0.7061646329819963, "300–1000 Hz_10ms_log_rms_mae_db": 2.039254271563288, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.28374908261703824, "300–1000 Hz_10ms_envelope_correlation": 0.932870399807851, "300–1000 Hz_10ms_modulation_mae_db": 0.6437149320994277, "300–1000 Hz_40ms_log_rms_mae_db": 1.3604605570089012, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1742136948995683, "300–1000 Hz_40ms_envelope_correlation": 0.9738705188630303, "300–1000 Hz_40ms_modulation_mae_db": 0.9070626921511672, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5256236761274684, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1879757809134617, "1000–3000 Hz_10ms_envelope_correlation": 0.9729601092928412, "1000–3000 Hz_10ms_modulation_mae_db": 0.7300852859156834, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8434483437360544, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11297760645784621, "1000–3000 Hz_40ms_envelope_correlation": 0.98960569950461, "1000–3000 Hz_40ms_modulation_mae_db": 0.9900820585463762, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3389938246822413, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16724649955845058, "3000–6000 Hz_10ms_envelope_correlation": 0.9784084027610563, "3000–6000 Hz_10ms_modulation_mae_db": 0.2348860676713139, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6676341253132059, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07856085756900785, "3000–6000 Hz_40ms_envelope_correlation": 0.9949256594139558, "3000–6000 Hz_40ms_modulation_mae_db": 0.5017581425988982, "mr_stft_db": 6.036538436859022, "band_mae_db": 0.4475568985689276, "rms_gain_error_db": 0.1495117309261511, "output_peak": 0.03203769818012912}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4067161366975816, "全帯域_10ms_rms_envelope_nrmse": 0.1252316025766672, "全帯域_10ms_envelope_correlation": 0.9861230793499886, "全帯域_10ms_modulation_mae_db": 0.2991968535939897, "全帯域_40ms_log_rms_mae_db": 0.7338223627874703, "全帯域_40ms_rms_envelope_nrmse": 0.05778324202044733, "全帯域_40ms_envelope_correlation": 0.9968546439977671, "全帯域_40ms_modulation_mae_db": 0.47239203990607, "300–1000 Hz_10ms_log_rms_mae_db": 2.1678663967196483, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26642531480708675, "300–1000 Hz_10ms_envelope_correlation": 0.9434225340160862, "300–1000 Hz_10ms_modulation_mae_db": 1.3018102378004177, "300–1000 Hz_40ms_log_rms_mae_db": 1.3687596897437189, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1539394422087579, "300–1000 Hz_40ms_envelope_correlation": 0.9820551380940888, "300–1000 Hz_40ms_modulation_mae_db": 1.0075831097283408, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5426817835111333, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20841572545738768, "1000–3000 Hz_10ms_envelope_correlation": 0.9663959456980585, "1000–3000 Hz_10ms_modulation_mae_db": 0.5268491952564901, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8149918314913082, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10406164570695217, "1000–3000 Hz_40ms_envelope_correlation": 0.991079045671091, "1000–3000 Hz_40ms_modulation_mae_db": 0.6156845373119814, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3294843271315193, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1624468120407792, "3000–6000 Hz_10ms_envelope_correlation": 0.9792575105925435, "3000–6000 Hz_10ms_modulation_mae_db": 0.2920105617738851, "3000–6000 Hz_40ms_log_rms_mae_db": 0.755163932945762, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08641251471438205, "3000–6000 Hz_40ms_envelope_correlation": 0.9937727401121395, "3000–6000 Hz_40ms_modulation_mae_db": 0.4095625379430745, "mr_stft_db": 6.0298822626788775, "band_mae_db": 0.458215122135399, "rms_gain_error_db": 0.061010247071721535, "output_peak": 0.037570442335298916}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4037604908079473, "全帯域_10ms_rms_envelope_nrmse": 0.12081580443964303, "全帯域_10ms_envelope_correlation": 0.9872815793728756, "全帯域_10ms_modulation_mae_db": 0.29947390698257537, "全帯域_40ms_log_rms_mae_db": 0.7640430004427164, "全帯域_40ms_rms_envelope_nrmse": 0.06894362793786517, "全帯域_40ms_envelope_correlation": 0.9956471249481798, "全帯域_40ms_modulation_mae_db": 0.16990516183572477, "300–1000 Hz_10ms_log_rms_mae_db": 2.045409931535377, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24398126365791184, "300–1000 Hz_10ms_envelope_correlation": 0.9488537045249427, "300–1000 Hz_10ms_modulation_mae_db": 0.24195254360008608, "300–1000 Hz_40ms_log_rms_mae_db": 1.3273883676240406, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1301628091112009, "300–1000 Hz_40ms_envelope_correlation": 0.985080653052693, "300–1000 Hz_40ms_modulation_mae_db": 1.011083950063982, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5138189200600045, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18405848857186113, "1000–3000 Hz_10ms_envelope_correlation": 0.9743654879016438, "1000–3000 Hz_10ms_modulation_mae_db": 0.7907910669028567, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8170171816466474, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10840881030673939, "1000–3000 Hz_40ms_envelope_correlation": 0.9904731926812156, "1000–3000 Hz_40ms_modulation_mae_db": 0.43352975190085036, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3204560205249283, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1507654254305979, "3000–6000 Hz_10ms_envelope_correlation": 0.9829591650800922, "3000–6000 Hz_10ms_modulation_mae_db": 0.3567549340325284, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7227226538887296, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08700847585157476, "3000–6000 Hz_40ms_envelope_correlation": 0.9941496379524646, "3000–6000 Hz_40ms_modulation_mae_db": 0.8346236977246413, "mr_stft_db": 6.030653115627783, "band_mae_db": 0.46472825100063664, "rms_gain_error_db": 0.1129243698749762, "output_peak": 0.03724977869307697}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.449452600344338, "全帯域_10ms_rms_envelope_nrmse": 0.12128931273314439, "全帯域_10ms_envelope_correlation": 0.9869121631213182, "全帯域_10ms_modulation_mae_db": 0.7891549300711262, "全帯域_40ms_log_rms_mae_db": 0.8221941157899305, "全帯域_40ms_rms_envelope_nrmse": 0.0664684981801164, "全帯域_40ms_envelope_correlation": 0.9960439361681035, "全帯域_40ms_modulation_mae_db": 0.9038395029248871, "300–1000 Hz_10ms_log_rms_mae_db": 2.126361458782888, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2789407838158529, "300–1000 Hz_10ms_envelope_correlation": 0.9415731405166932, "300–1000 Hz_10ms_modulation_mae_db": 0.7683822756649404, "300–1000 Hz_40ms_log_rms_mae_db": 1.3519993031418793, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.18319378035667444, "300–1000 Hz_40ms_envelope_correlation": 0.9764523020493073, "300–1000 Hz_40ms_modulation_mae_db": 0.6396707703127039, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5247796269347158, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1972842165131551, "1000–3000 Hz_10ms_envelope_correlation": 0.9698652840127899, "1000–3000 Hz_10ms_modulation_mae_db": 0.6939612430307273, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8629446258372805, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10390554066367849, "1000–3000 Hz_40ms_envelope_correlation": 0.9912124164365489, "1000–3000 Hz_40ms_modulation_mae_db": 1.0282479597640377, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2792128704670342, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14380747623372894, "3000–6000 Hz_10ms_envelope_correlation": 0.9841388653885019, "3000–6000 Hz_10ms_modulation_mae_db": 1.1031356173834674, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6544711076497508, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08630791883349319, "3000–6000 Hz_40ms_envelope_correlation": 0.9944347119587946, "3000–6000 Hz_40ms_modulation_mae_db": 1.613646296542095, "mr_stft_db": 6.027294429887751, "band_mae_db": 0.48000070723382343, "rms_gain_error_db": -0.15400338233486074, "output_peak": 0.03327216094536615}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4428881838878875, "全帯域_10ms_rms_envelope_nrmse": 0.1313357702860398, "全帯域_10ms_envelope_correlation": 0.9845882533723289, "全帯域_10ms_modulation_mae_db": 0.10183195688396957, "全帯域_40ms_log_rms_mae_db": 0.7881372427657701, "全帯域_40ms_rms_envelope_nrmse": 0.08000450143309093, "全帯域_40ms_envelope_correlation": 0.9938329748291518, "全帯域_40ms_modulation_mae_db": 0.14243842105985335, "300–1000 Hz_10ms_log_rms_mae_db": 2.1476290812374366, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26667728640833804, "300–1000 Hz_10ms_envelope_correlation": 0.9364415474267083, "300–1000 Hz_10ms_modulation_mae_db": 0.5415429429942096, "300–1000 Hz_40ms_log_rms_mae_db": 1.4036049473913508, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1675200846327572, "300–1000 Hz_40ms_envelope_correlation": 0.9725174415599253, "300–1000 Hz_40ms_modulation_mae_db": 0.23551311152020227, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5725534298261536, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19240250507767967, "1000–3000 Hz_10ms_envelope_correlation": 0.9714001249082928, "1000–3000 Hz_10ms_modulation_mae_db": 0.481635806418544, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9060827197237569, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12038366578769029, "1000–3000 Hz_40ms_envelope_correlation": 0.9880339372063892, "1000–3000 Hz_40ms_modulation_mae_db": 0.1320950649016326, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3166106240718478, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16077482106905755, "3000–6000 Hz_10ms_envelope_correlation": 0.9797052733207273, "3000–6000 Hz_10ms_modulation_mae_db": 0.2871442483369212, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7201636094509514, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08062659656787428, "3000–6000 Hz_40ms_envelope_correlation": 0.994541672619825, "3000–6000 Hz_40ms_modulation_mae_db": 0.6698035190882559, "mr_stft_db": 6.044999492005029, "band_mae_db": 0.34450846041355104, "rms_gain_error_db": -0.007900092506625836, "output_peak": 0.04449795616200481}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3951036838112485, "全帯域_10ms_rms_envelope_nrmse": 0.12264932450181276, "全帯域_10ms_envelope_correlation": 0.98650276899619, "全帯域_10ms_modulation_mae_db": 0.31580475013977877, "全帯域_40ms_log_rms_mae_db": 0.7730030252269328, "全帯域_40ms_rms_envelope_nrmse": 0.06359316777037417, "全帯域_40ms_envelope_correlation": 0.996188061785831, "全帯域_40ms_modulation_mae_db": 0.633811974230717, "300–1000 Hz_10ms_log_rms_mae_db": 2.0956638331103776, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2774708346529549, "300–1000 Hz_10ms_envelope_correlation": 0.93657329259021, "300–1000 Hz_10ms_modulation_mae_db": 0.46265495840801424, "300–1000 Hz_40ms_log_rms_mae_db": 1.330101904627898, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14598630278256947, "300–1000 Hz_40ms_envelope_correlation": 0.9832363769983969, "300–1000 Hz_40ms_modulation_mae_db": 0.8307620823903462, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5126061928207877, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19058619289636397, "1000–3000 Hz_10ms_envelope_correlation": 0.9725729240290855, "1000–3000 Hz_10ms_modulation_mae_db": 0.37102446743842726, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8610109907028568, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10360052354860919, "1000–3000 Hz_40ms_envelope_correlation": 0.9913858067339331, "1000–3000 Hz_40ms_modulation_mae_db": 0.4805888233814284, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3489140341053398, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16715237749381004, "3000–6000 Hz_10ms_envelope_correlation": 0.9780385290333926, "3000–6000 Hz_10ms_modulation_mae_db": 0.4555861808093735, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7131152189729487, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08896671502388927, "3000–6000 Hz_40ms_envelope_correlation": 0.993651902734644, "3000–6000 Hz_40ms_modulation_mae_db": 0.765811483330916, "mr_stft_db": 6.027740927138606, "band_mae_db": 0.41640629430725984, "rms_gain_error_db": -0.06850140723558029, "output_peak": 0.03916535841237616}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4849150058561793, "全帯域_10ms_rms_envelope_nrmse": 0.13229694409110043, "全帯域_10ms_envelope_correlation": 0.9845208618623286, "全帯域_10ms_modulation_mae_db": 1.0581280880448587, "全帯域_40ms_log_rms_mae_db": 0.813541979187367, "全帯域_40ms_rms_envelope_nrmse": 0.07121566343997596, "全帯域_40ms_envelope_correlation": 0.9956604599288499, "全帯域_40ms_modulation_mae_db": 1.577720604245739, "300–1000 Hz_10ms_log_rms_mae_db": 2.0208066938179963, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2495964646000484, "300–1000 Hz_10ms_envelope_correlation": 0.9468242707894722, "300–1000 Hz_10ms_modulation_mae_db": 0.6469960668254909, "300–1000 Hz_40ms_log_rms_mae_db": 1.3119702117585599, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1385987518216355, "300–1000 Hz_40ms_envelope_correlation": 0.983224058891699, "300–1000 Hz_40ms_modulation_mae_db": 0.6415041440314967, "1000–3000 Hz_10ms_log_rms_mae_db": 1.621460480146916, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20484093389053654, "1000–3000 Hz_10ms_envelope_correlation": 0.9674706940846945, "1000–3000 Hz_10ms_modulation_mae_db": 1.1141802631399111, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9202990306121313, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10625373856744555, "1000–3000 Hz_40ms_envelope_correlation": 0.9908070341413728, "1000–3000 Hz_40ms_modulation_mae_db": 1.6906251911313752, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2909220048953953, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15050140728579744, "3000–6000 Hz_10ms_envelope_correlation": 0.9822527143816732, "3000–6000 Hz_10ms_modulation_mae_db": 0.6243634031012555, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7012133662343097, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07950391291252998, "3000–6000 Hz_40ms_envelope_correlation": 0.9949479090933194, "3000–6000 Hz_40ms_modulation_mae_db": 0.9543587943532564, "mr_stft_db": 6.033173448062418, "band_mae_db": 0.4080888956769723, "rms_gain_error_db": -0.22833254826160382, "output_peak": 0.03402803999594344}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4193227473367525, "全帯域_10ms_rms_envelope_nrmse": 0.13462511752707557, "全帯域_10ms_envelope_correlation": 0.9839487549403837, "全帯域_10ms_modulation_mae_db": 0.40195998877413874, "全帯域_40ms_log_rms_mae_db": 0.7404419287076058, "全帯域_40ms_rms_envelope_nrmse": 0.06447314651504286, "全帯域_40ms_envelope_correlation": 0.99606794186492, "全帯域_40ms_modulation_mae_db": 0.6305509217753119, "300–1000 Hz_10ms_log_rms_mae_db": 2.1524116923389633, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2600622347289482, "300–1000 Hz_10ms_envelope_correlation": 0.9420695857914201, "300–1000 Hz_10ms_modulation_mae_db": 0.7073771176915665, "300–1000 Hz_40ms_log_rms_mae_db": 1.4543715053159962, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14518009681312458, "300–1000 Hz_40ms_envelope_correlation": 0.9813450070302652, "300–1000 Hz_40ms_modulation_mae_db": 0.8651793082251448, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5724995138023896, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19806288765098287, "1000–3000 Hz_10ms_envelope_correlation": 0.9701196225568671, "1000–3000 Hz_10ms_modulation_mae_db": 0.33207420702521356, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8441712151452356, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09733307369737085, "1000–3000 Hz_40ms_envelope_correlation": 0.9922607870694395, "1000–3000 Hz_40ms_modulation_mae_db": 0.6396811627245974, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2812914232646715, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15523894587604503, "3000–6000 Hz_10ms_envelope_correlation": 0.9814542288241884, "3000–6000 Hz_10ms_modulation_mae_db": 0.6829274535761581, "3000–6000 Hz_40ms_log_rms_mae_db": 0.673958882869018, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07741177821324617, "3000–6000 Hz_40ms_envelope_correlation": 0.9951293985393185, "3000–6000 Hz_40ms_modulation_mae_db": 0.8287581106059728, "mr_stft_db": 6.02106558549266, "band_mae_db": 0.29543167135032117, "rms_gain_error_db": 0.05941198657922493, "output_peak": 0.036053796959929364}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 109060, "output_samples": 109060, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.1467379653508925, "spectral_convergence": 0.6268586078401417, "spectral_convergence_status": "ok", "amplitude_floor": 7.347807435362163e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.887446169330011, "spectral_convergence": 0.6153627984444223, "spectral_convergence_status": "ok", "amplitude_floor": 3.5954742817466214e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.0754311758961626, "spectral_convergence": 0.6409660421719847, "spectral_convergence_status": "ok", "amplitude_floor": 1.4970646531776498e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.2516812561146785e-07, "output_power": 1.1030808060160466e-07, "delta_db": -0.548864209534195, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 8.469209703610174e-08, "output_power": 1.147902168484666e-07, "delta_db": 1.3206198986670312, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 4.7196494133004234e-07, "output_power": 5.014792460538935e-07, "delta_db": 0.2634322484127321, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.5661034348838578e-06, "output_power": 1.5420821892156738e-06, "delta_db": -0.06712920919732435, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2294550474819316e-06, "output_power": 1.316123484257532e-06, "delta_db": 0.29583984257596485, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.3429464378207576e-06, "output_power": 3.363662291003079e-06, "delta_db": 0.026829683084513188, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.563896615059082e-07, "output_power": 1.10066002262352e-06, "delta_db": 0.6101831985107324, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.4475568985689276, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.1495117309261511, "pitch": null, "output_rms_dbfs": -50.94252378601883, "output_peak": 0.03203769818012912, "reference_rms_dbfs": -51.09203551694498, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.036538436859022}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 109060, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 1.1882865623804307e-05, "log_rms_mae_db": 1.4847435548394903, "rms_envelope_nrmse": 0.13254287277501775, "envelope_correlation": 0.9848403848889614, "rms_gain_error_db": 0.14946685586058317, "reference_mean_power": 7.792370026271951e-06, "output_mean_power": 8.065220637440064e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 4.121961515330987e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7941587942139734e-06, "output_power": 1.73279067825782e-06, "reference_active": true, "delta_db": -0.15114775220811527}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1263612266386524e-07, "output_power": 2.871743580112464e-07, "reference_active": true, "delta_db": -0.36893497060729785}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9590349245364564e-07, "output_power": 1.7161881806612685e-07, "reference_active": true, "delta_db": -0.5747727174109705}], "active_band_count": 3, "active_band_mae_db": 0.36495181340879457}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 9.239390922709503e-06, "log_rms_mae_db": 0.7567865267736854, "rms_envelope_nrmse": 0.0684403489448031, "envelope_correlation": 0.9958595496722173, "rms_gain_error_db": 0.14947814851439928, "reference_mean_power": 7.844041250222317e-06, "output_mean_power": 8.1187222449488e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 3.7692280722089195e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6572550629104971e-06, "output_power": 1.6001621444221378e-06, "reference_active": true, "delta_db": -0.15225362516877158}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5392861690297655e-07, "output_power": 1.2889932116694532e-07, "reference_active": true, "delta_db": -0.7706873692128386}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6336932951152273e-08, "output_power": 1.2405527511368446e-08, "reference_active": true, "delta_db": -1.1955529045643782}], "active_band_count": 3, "active_band_mae_db": 0.7061646329819963}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 2.9307310026633354e-06, "log_rms_mae_db": 2.039254271563288, "rms_envelope_nrmse": 0.28374908261703824, "envelope_correlation": 0.932870399807851, "rms_gain_error_db": 0.49971689229201854, "reference_mean_power": 4.2741366364654595e-07, "output_mean_power": 4.795347573213216e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 2.4398860779830526e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.615850373422058e-08, "output_power": 1.0285999680305907e-07, "reference_active": true, "delta_db": 0.2925880957610083}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8718875021930722e-08, "output_power": 2.646859338702347e-08, "reference_active": true, "delta_db": 1.5045111762706151}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0143942568188046e-08, "output_power": 2.0775382431576546e-08, "reference_active": true, "delta_db": 0.1340455242666597}], "active_band_count": 3, "active_band_mae_db": 0.6437149320994277}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 1.736089681183382e-06, "log_rms_mae_db": 1.3604605570089012, "rms_envelope_nrmse": 0.1742136948995683, "envelope_correlation": 0.9738705188630303, "rms_gain_error_db": 0.4996756308013322, "reference_mean_power": 4.3025101883138276e-07, "output_mean_power": 4.827135284858011e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 2.1733905138014183e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.047483464267491e-08, "output_power": 9.757656838655374e-08, "reference_active": true, "delta_db": 0.3281774255748994}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.338915747949155e-09, "output_power": 1.2816976423691994e-08, "reference_active": true, "delta_db": 1.374891280649766}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.438276742938052e-09, "output_power": 1.1377072376481716e-09, "reference_active": true, "delta_db": -1.018119370228836}], "active_band_count": 3, "active_band_mae_db": 0.9070626921511672}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 7.246614216836824e-06, "log_rms_mae_db": 1.5256236761274684, "rms_envelope_nrmse": 0.1879757809134617, "envelope_correlation": 0.9729601092928412, "rms_gain_error_db": 0.0009382035045874203, "reference_mean_power": 1.7870157226185334e-06, "output_mean_power": 1.7874018121481813e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.838724239404773e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.063249741710556e-07, "output_power": 6.216488941165488e-07, "reference_active": true, "delta_db": -0.554593968685257}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.654737664402428e-07, "output_power": 1.1932410799081926e-07, "reference_active": true, "delta_db": -1.4200095575532656}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2023841152792083e-07, "output_power": 1.1441369120288648e-07, "reference_active": true, "delta_db": -0.21565233150852775}], "active_band_count": 3, "active_band_mae_db": 0.7300852859156834}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.77385839866885e-06, "log_rms_mae_db": 0.8434483437360544, "rms_envelope_nrmse": 0.11297760645784621, "envelope_correlation": 0.98960569950461, "rms_gain_error_db": 0.0009401401845310362, "reference_mean_power": 1.7989086732437154e-06, "output_mean_power": 1.7992981346506758e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 1.713692894624548e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.664518497859096e-07, "output_power": 5.845813141012493e-07, "reference_active": true, "delta_db": -0.5692384851370005}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.184085944051966e-08, "output_power": 5.9400555515164715e-08, "reference_active": true, "delta_db": -1.3917967488103875}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1933830695482323e-08, "output_power": 9.459295182431908e-09, "reference_active": true, "delta_db": -1.0092109416917403}], "active_band_count": 3, "active_band_mae_db": 0.9900820585463762}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 6.060487704579714e-06, "log_rms_mae_db": 1.3389938246822413, "rms_envelope_nrmse": 0.16724649955845058, "envelope_correlation": 0.9784084027610563, "rms_gain_error_db": 0.06658045501799677, "reference_mean_power": 1.7907615060268857e-06, "output_mean_power": 1.818426684329028e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.036723230359137e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.741355867444106e-07, "output_power": 4.791463649023043e-07, "reference_active": true, "delta_db": 0.045656447021722925}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0977135221440419e-07, "output_power": 1.269776245901036e-07, "reference_active": true, "delta_db": 0.6323818425246635}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0575338351673974e-08, "output_power": 3.038850118015681e-08, "reference_active": true, "delta_db": -0.026619913467555368}], "active_band_count": 3, "active_band_mae_db": 0.2348860676713139}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.330101975711502e-06, "log_rms_mae_db": 0.6676341253132059, "rms_envelope_nrmse": 0.07856085756900785, "envelope_correlation": 0.9949256594139558, "rms_gain_error_db": 0.06658175244169415, "reference_mean_power": 1.8026836617488875e-06, "output_mean_power": 1.8305335703214989e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 9.630136220520234e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.5232190822756626e-07, "output_power": 4.6406326835186647e-07, "reference_active": true, "delta_db": 0.11129571073569668}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.528340255264933e-08, "output_power": 6.32406415393607e-08, "reference_active": true, "delta_db": 0.5840150203811464}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3355698674413927e-09, "output_power": 1.9381906486353026e-09, "reference_active": true, "delta_db": -0.8099636966798516}], "active_band_count": 3, "active_band_mae_db": 0.5017581425988982}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5463447124539937, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "76adc6c13839453ff2c82b95d047c73e4801a8aeb482167d0142782509123773", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9706437740605343, "standard_deviation": 0.002738704409882272, "minimum": 0.9663959456980585, "maximum": 0.9743654879016438, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.5482529529036961, "standard_deviation": 0.03796288448564002, "minimum": 1.5126061928207877, "maximum": 1.621460480146916, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6300751918909817, "standard_deviation": 0.2571471177827431, "minimum": 0.33207420702521356, "maximum": 1.1141802631399111, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.19545334137142858, "standard_deviation": 0.008324365674352819, "minimum": 0.18405848857186113, "maximum": 0.20841572545738768, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.990607239930575, "standard_deviation": 0.001287970729191481, "minimum": 0.9880339372063892, "maximum": 0.9922607870694395, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8587457423619088, "standard_deviation": 0.03808723715142941, "minimum": 0.8149918314913082, "maximum": 0.9202990306121313, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.751316818707785, "standard_deviation": 0.4787746857880809, "minimum": 0.1320950649016326, "maximum": 1.6906251911313752, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10711557559204152, "standard_deviation": 0.006974490135664886, "minimum": 0.09733307369737085, "maximum": 0.12038366578769029, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.980776836172772, "standard_deviation": 0.0022445895959196487, "minimum": 0.9780385290333926, "maximum": 0.9841388653885019, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.3132356411428723, "standard_deviation": 0.026564897007347252, "minimum": 1.2792128704670342, "maximum": 1.3489140341053398, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5046010583356129, "standard_deviation": 0.2912721445071182, "minimum": 0.2348860676713139, "maximum": 1.1031356173834674, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1572417206235333, "standard_deviation": 0.00853360373454802, "minimum": 0.14380747623372894, "maximum": 0.16724649955845058, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9944442040530577, "standard_deviation": 0.0005516176377862472, "minimum": 0.993651902734644, "maximum": 0.9951293985393185, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7010553621655845, "standard_deviation": 0.03365601245397739, "minimum": 0.6544711076497508, "maximum": 0.755163932945762, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.8222903227733888, "standard_deviation": 0.36711374070933817, "minimum": 0.4095625379430745, "maximum": 1.613646296542095, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08309984621074969, "standard_deviation": 0.004519280496191433, "minimum": 0.07741177821324617, "maximum": 0.08896671502388927, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.941078559432923, "standard_deviation": 0.005468876024943336, "minimum": 0.932870399807851, "maximum": 0.9488537045249427, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.099425419888247, "standard_deviation": 0.057661759094863756, "minimum": 2.0208066938179963, "maximum": 2.1678663967196483, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6643038843855191, "standard_deviation": 0.3056465335389081, "minimum": 0.24195254360008608, "maximum": 1.3018102378004177, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2658629081610224, "standard_deviation": 0.014160916553619493, "minimum": 0.24398126365791184, "maximum": 0.28374908261703824, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9797226870674256, "standard_deviation": 0.004754614669956194, "minimum": 0.9725174415599253, "maximum": 0.985080653052693, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.363582060826543, "standard_deviation": 0.04646035765419646, "minimum": 1.3119702117585599, "maximum": 1.4543715053159962, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7672948960529229, "standard_deviation": 0.2577981226593668, "minimum": 0.23551311152020227, "maximum": 1.011083950063982, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15484937032828605, "standard_deviation": 0.018459667770312244, "minimum": 0.1301628091112009, "maximum": 0.18319378035667444, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.41436703758586135, "standard_deviation": 0.06429582032486432, "minimum": 0.29543167135032117, "maximum": 0.48000070723382343, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.031418462219018, "standard_deviation": 0.007115356768018992, "minimum": 6.02106558549266, "maximum": 6.044999492005029, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.03673440396051562, "standard_deviation": 0.003945714805652009, "minimum": 0.03203769818012912, "maximum": 0.04449795616200481, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.009484886985824614, "standard_deviation": 0.13215015775637784, "minimum": -0.22833254826160382, "maximum": 0.1495117309261511, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9855897307380468, "standard_deviation": 0.0012608974792227838, "minimum": 0.9839487549403837, "maximum": 0.9872815793728756, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.4358628004476781, "standard_deviation": 0.03554564654260842, "minimum": 1.3951036838112485, "maximum": 1.4849150058561793, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.45381278598740393, "standard_deviation": 0.3114252079583084, "minimum": 0.10183195688396957, "maximum": 1.0581280880448587, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.12759834361631262, "standard_deviation": 0.00567916098481084, "minimum": 0.12081580443964303, "maximum": 0.13462511752707557, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9957693366493775, "standard_deviation": 0.0008703216219388981, "minimum": 0.9938329748291518, "maximum": 0.9968546439977671, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.7739962727101848, "standard_deviation": 0.0321223744384462, "minimum": 0.7338223627874703, "maximum": 0.8221941157899305, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6546029073700375, "standard_deviation": 0.45487513217431413, "minimum": 0.14243842105985335, "maximum": 1.577720604245739, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.06761527453021449, "standard_deviation": 0.00646899511559627, "minimum": 0.05778324202044733, "maximum": 0.08000450143309093, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_whisper10_BASIC5000_0074", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 1.8502953052520752, "predicted_mos": 1.8502953052520752, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 109060, "input_sample_rate": 24000, "input_seconds": 4.5441666666666665, "input_float32_sha256": "85b9bd5718cbfccc345ce62691eeb1fdcd837c02dd45601fc0391ace3084525c", "internal_samples": 72707, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.38669850025326}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4298864058384355, "全帯域_10ms_rms_envelope_nrmse": 0.11817945112796267, "全帯域_10ms_envelope_correlation": 0.9877244319350688, "全帯域_10ms_modulation_mae_db": 0.3094862298928804, "全帯域_40ms_log_rms_mae_db": 0.7367154496735964, "全帯域_40ms_rms_envelope_nrmse": 0.05551569038946593, "全帯域_40ms_envelope_correlation": 0.9971616539208171, "全帯域_40ms_modulation_mae_db": 0.47682146611506043, "300–1000 Hz_10ms_log_rms_mae_db": 2.4132194157963154, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3018900329540525, "300–1000 Hz_10ms_envelope_correlation": 0.9292820458049205, "300–1000 Hz_10ms_modulation_mae_db": 1.1615203282572208, "300–1000 Hz_40ms_log_rms_mae_db": 1.7378544472294457, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20009765684228964, "300–1000 Hz_40ms_envelope_correlation": 0.9698752745321083, "300–1000 Hz_40ms_modulation_mae_db": 0.8578489021337989, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7950213400388895, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18627288087696867, "1000–3000 Hz_10ms_envelope_correlation": 0.9750681568118694, "1000–3000 Hz_10ms_modulation_mae_db": 0.24602124441274761, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0714458753363798, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09414481396624086, "1000–3000 Hz_40ms_envelope_correlation": 0.9937949289113681, "1000–3000 Hz_40ms_modulation_mae_db": 0.5783314446958997, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6379345739331, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17529163751106105, "3000–6000 Hz_10ms_envelope_correlation": 0.9759991172897118, "3000–6000 Hz_10ms_modulation_mae_db": 0.3681048135868555, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9633725349646739, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0880185207397074, "3000–6000 Hz_40ms_envelope_correlation": 0.9935559239754121, "3000–6000 Hz_40ms_modulation_mae_db": 0.7356597200569187, "mr_stft_db": 6.167882821496427, "band_mae_db": 0.3758540937940041, "rms_gain_error_db": 0.09160865412862912, "output_peak": 0.033773989708816794}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.421006127096063, "全帯域_10ms_rms_envelope_nrmse": 0.12734045600860028, "全帯域_10ms_envelope_correlation": 0.9854127537057668, "全帯域_10ms_modulation_mae_db": 0.688277434940003, "全帯域_40ms_log_rms_mae_db": 0.7686474212823583, "全帯域_40ms_rms_envelope_nrmse": 0.06264417442099326, "全帯域_40ms_envelope_correlation": 0.996231909322641, "全帯域_40ms_modulation_mae_db": 0.8418963537109602, "300–1000 Hz_10ms_log_rms_mae_db": 2.3953742176870945, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3082130320333786, "300–1000 Hz_10ms_envelope_correlation": 0.9211620186391, "300–1000 Hz_10ms_modulation_mae_db": 0.6538099698505518, "300–1000 Hz_40ms_log_rms_mae_db": 1.5692183619488882, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17520516264601402, "300–1000 Hz_40ms_envelope_correlation": 0.9744114155832811, "300–1000 Hz_40ms_modulation_mae_db": 0.6858269144450109, "1000–3000 Hz_10ms_log_rms_mae_db": 1.811206573770319, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20180893906566513, "1000–3000 Hz_10ms_envelope_correlation": 0.9684220252989519, "1000–3000 Hz_10ms_modulation_mae_db": 0.6665487884910574, "1000–3000 Hz_40ms_log_rms_mae_db": 1.033050827006536, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1155048028838939, "1000–3000 Hz_40ms_envelope_correlation": 0.9890819028158909, "1000–3000 Hz_40ms_modulation_mae_db": 1.0281862525983354, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5859483483504562, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17472788443534096, "3000–6000 Hz_10ms_envelope_correlation": 0.9759773234445619, "3000–6000 Hz_10ms_modulation_mae_db": 0.30502793734649747, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9026472737971769, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08110470893035544, "3000–6000 Hz_40ms_envelope_correlation": 0.9947974105593219, "3000–6000 Hz_40ms_modulation_mae_db": 0.5768813255574522, "mr_stft_db": 6.1634390692052925, "band_mae_db": 0.4320538863271089, "rms_gain_error_db": -0.06309834236420697, "output_peak": 0.0319720038497945}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4009845441421502, "全帯域_10ms_rms_envelope_nrmse": 0.12442935201588202, "全帯域_10ms_envelope_correlation": 0.9860789636074934, "全帯域_10ms_modulation_mae_db": 0.32987071121866846, "全帯域_40ms_log_rms_mae_db": 0.7098343316104512, "全帯域_40ms_rms_envelope_nrmse": 0.0652594161186385, "全帯域_40ms_envelope_correlation": 0.9959059339170411, "全帯域_40ms_modulation_mae_db": 0.7579261042483592, "300–1000 Hz_10ms_log_rms_mae_db": 2.2205439015524213, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25697881244332227, "300–1000 Hz_10ms_envelope_correlation": 0.9436962931195572, "300–1000 Hz_10ms_modulation_mae_db": 0.5173660472948212, "300–1000 Hz_40ms_log_rms_mae_db": 1.4664952614974267, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14076015571440537, "300–1000 Hz_40ms_envelope_correlation": 0.9831169418912039, "300–1000 Hz_40ms_modulation_mae_db": 0.315810967506902, "1000–3000 Hz_10ms_log_rms_mae_db": 1.863169328973671, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.22624983454464237, "1000–3000 Hz_10ms_envelope_correlation": 0.9613868779804562, "1000–3000 Hz_10ms_modulation_mae_db": 0.6308559506373558, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1049251236199964, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12706865426012187, "1000–3000 Hz_40ms_envelope_correlation": 0.9869896413537217, "1000–3000 Hz_40ms_modulation_mae_db": 1.2938602892185773, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5196450539570372, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15109332677881432, "3000–6000 Hz_10ms_envelope_correlation": 0.9822755406281511, "3000–6000 Hz_10ms_modulation_mae_db": 0.5290783160670326, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8785275450191602, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07309755182702198, "3000–6000 Hz_40ms_envelope_correlation": 0.9955620803412379, "3000–6000 Hz_40ms_modulation_mae_db": 0.6856577264819461, "mr_stft_db": 6.1804787279517805, "band_mae_db": 0.3584938248247324, "rms_gain_error_db": -0.06354108310362397, "output_peak": 0.03502825064335915}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4243880832155662, "全帯域_10ms_rms_envelope_nrmse": 0.12163320282852211, "全帯域_10ms_envelope_correlation": 0.9867654585946191, "全帯域_10ms_modulation_mae_db": 0.8793985159690351, "全帯域_40ms_log_rms_mae_db": 0.7778388505385906, "全帯域_40ms_rms_envelope_nrmse": 0.06958632255953265, "全帯域_40ms_envelope_correlation": 0.995504948935238, "全帯域_40ms_modulation_mae_db": 1.3309230947210269, "300–1000 Hz_10ms_log_rms_mae_db": 2.354028996882097, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2825139948874255, "300–1000 Hz_10ms_envelope_correlation": 0.9285967073110879, "300–1000 Hz_10ms_modulation_mae_db": 0.7242383906669336, "300–1000 Hz_40ms_log_rms_mae_db": 1.649284275620634, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15712351911847658, "300–1000 Hz_40ms_envelope_correlation": 0.976249523283964, "300–1000 Hz_40ms_modulation_mae_db": 1.055568572005616, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8273458364463373, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20621954151354432, "1000–3000 Hz_10ms_envelope_correlation": 0.967309983399864, "1000–3000 Hz_10ms_modulation_mae_db": 0.9341331306478775, "1000–3000 Hz_40ms_log_rms_mae_db": 1.060253918922505, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12696718353555805, "1000–3000 Hz_40ms_envelope_correlation": 0.9875737136693273, "1000–3000 Hz_40ms_modulation_mae_db": 1.5656919250794974, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6378746027709494, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18786419941080418, "3000–6000 Hz_10ms_envelope_correlation": 0.9737132789414128, "3000–6000 Hz_10ms_modulation_mae_db": 0.24933236096346167, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9358259054211624, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12072947116774588, "3000–6000 Hz_40ms_envelope_correlation": 0.988706749800674, "3000–6000 Hz_40ms_modulation_mae_db": 0.7380161683318351, "mr_stft_db": 6.180290020114803, "band_mae_db": 0.4391517405723687, "rms_gain_error_db": -0.1424826941934897, "output_peak": 0.033849067930695184}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.340817281684742, "全帯域_10ms_rms_envelope_nrmse": 0.12309628575704389, "全帯域_10ms_envelope_correlation": 0.986386596826487, "全帯域_10ms_modulation_mae_db": 0.2236533110599633, "全帯域_40ms_log_rms_mae_db": 0.7019212844634277, "全帯域_40ms_rms_envelope_nrmse": 0.05780700375247124, "全帯域_40ms_envelope_correlation": 0.9969026487291398, "全帯域_40ms_modulation_mae_db": 0.651995552928767, "300–1000 Hz_10ms_log_rms_mae_db": 2.4936162409287532, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.32720663822965695, "300–1000 Hz_10ms_envelope_correlation": 0.9152507697619856, "300–1000 Hz_10ms_modulation_mae_db": 1.4012947936772047, "300–1000 Hz_40ms_log_rms_mae_db": 1.687004030534209, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19952792907934377, "300–1000 Hz_40ms_envelope_correlation": 0.9691012958557174, "300–1000 Hz_40ms_modulation_mae_db": 0.9730448040850096, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8067796405655088, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21072924494345432, "1000–3000 Hz_10ms_envelope_correlation": 0.9655450196214165, "1000–3000 Hz_10ms_modulation_mae_db": 0.7267660923198113, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0648214197536165, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11344600008740859, "1000–3000 Hz_40ms_envelope_correlation": 0.989808774009378, "1000–3000 Hz_40ms_modulation_mae_db": 1.1252472834250504, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5378626079175732, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14945009179238028, "3000–6000 Hz_10ms_envelope_correlation": 0.9825169660896309, "3000–6000 Hz_10ms_modulation_mae_db": 0.657347702622009, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8522087101932987, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07676035409851255, "3000–6000 Hz_40ms_envelope_correlation": 0.9952667799509901, "3000–6000 Hz_40ms_modulation_mae_db": 0.9855827787083844, "mr_stft_db": 6.18307614498377, "band_mae_db": 0.4408996350561219, "rms_gain_error_db": -0.10207694468332217, "output_peak": 0.03194945020031132}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3677403062124684, "全帯域_10ms_rms_envelope_nrmse": 0.11711421385403621, "全帯域_10ms_envelope_correlation": 0.9879641191690328, "全帯域_10ms_modulation_mae_db": 0.5170411298211949, "全帯域_40ms_log_rms_mae_db": 0.7213620263059244, "全帯域_40ms_rms_envelope_nrmse": 0.05635626905488956, "全帯域_40ms_envelope_correlation": 0.9970765555733423, "全帯域_40ms_modulation_mae_db": 0.9345560482530422, "300–1000 Hz_10ms_log_rms_mae_db": 2.400019482686684, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26995582423372255, "300–1000 Hz_10ms_envelope_correlation": 0.9383425163426021, "300–1000 Hz_10ms_modulation_mae_db": 0.7936835401445488, "300–1000 Hz_40ms_log_rms_mae_db": 1.7344806501295984, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1608268229846638, "300–1000 Hz_40ms_envelope_correlation": 0.9776414558049077, "300–1000 Hz_40ms_modulation_mae_db": 0.797958984838643, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7837496818315461, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19030781816356404, "1000–3000 Hz_10ms_envelope_correlation": 0.9726517995354906, "1000–3000 Hz_10ms_modulation_mae_db": 0.708869674687619, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0093452445667244, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09088180816130324, "1000–3000 Hz_40ms_envelope_correlation": 0.99340561885074, "1000–3000 Hz_40ms_modulation_mae_db": 0.9261377722920113, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5977015330793414, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16933416543173907, "3000–6000 Hz_10ms_envelope_correlation": 0.9774058250216825, "3000–6000 Hz_10ms_modulation_mae_db": 0.5095968767807871, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8944842818502495, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07521050268127312, "3000–6000 Hz_40ms_envelope_correlation": 0.9953151916766456, "3000–6000 Hz_40ms_modulation_mae_db": 0.7459477233105322, "mr_stft_db": 6.1774305683444934, "band_mae_db": 0.42020609918147717, "rms_gain_error_db": 0.08873560083194126, "output_peak": 0.04131731655175884}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3801668963931593, "全帯域_10ms_rms_envelope_nrmse": 0.1269971179029852, "全帯域_10ms_envelope_correlation": 0.9862370124853986, "全帯域_10ms_modulation_mae_db": 0.525736690034746, "全帯域_40ms_log_rms_mae_db": 0.7046001996749428, "全帯域_40ms_rms_envelope_nrmse": 0.0651420539320477, "全帯域_40ms_envelope_correlation": 0.9963863738793999, "全帯域_40ms_modulation_mae_db": 0.5581391140349075, "300–1000 Hz_10ms_log_rms_mae_db": 2.371069538462555, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27198856547902883, "300–1000 Hz_10ms_envelope_correlation": 0.9432937251818784, "300–1000 Hz_10ms_modulation_mae_db": 1.175848098726157, "300–1000 Hz_40ms_log_rms_mae_db": 1.6717498160087014, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16027546478331828, "300–1000 Hz_40ms_envelope_correlation": 0.9828146735050756, "300–1000 Hz_40ms_modulation_mae_db": 1.2458412858334555, "1000–3000 Hz_10ms_log_rms_mae_db": 1.807657554979058, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1940976979677843, "1000–3000 Hz_10ms_envelope_correlation": 0.970902599600188, "1000–3000 Hz_10ms_modulation_mae_db": 0.33081415608464676, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0286542585162555, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10575857510585067, "1000–3000 Hz_40ms_envelope_correlation": 0.9907589420722474, "1000–3000 Hz_40ms_modulation_mae_db": 0.5022622771456604, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5571961616052994, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16674546224904113, "3000–6000 Hz_10ms_envelope_correlation": 0.979157168053758, "3000–6000 Hz_10ms_modulation_mae_db": 0.5070974578944415, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8821538039127302, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07666797411915546, "3000–6000 Hz_40ms_envelope_correlation": 0.9956140484918788, "3000–6000 Hz_40ms_modulation_mae_db": 0.790900665521124, "mr_stft_db": 6.187010973928551, "band_mae_db": 0.5141897842968753, "rms_gain_error_db": 0.16970731709602915, "output_peak": 0.0337602274841479}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4309387321130551, "全帯域_10ms_rms_envelope_nrmse": 0.1238906389685549, "全帯域_10ms_envelope_correlation": 0.9863502349426192, "全帯域_10ms_modulation_mae_db": 0.10880553336437519, "全帯域_40ms_log_rms_mae_db": 0.7645855688562816, "全帯域_40ms_rms_envelope_nrmse": 0.06229143600322454, "全帯域_40ms_envelope_correlation": 0.9962939411111366, "全帯域_40ms_modulation_mae_db": 0.2426012514750188, "300–1000 Hz_10ms_log_rms_mae_db": 2.4070996198663988, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2870184823189224, "300–1000 Hz_10ms_envelope_correlation": 0.9270366749348486, "300–1000 Hz_10ms_modulation_mae_db": 0.17492109148533228, "300–1000 Hz_40ms_log_rms_mae_db": 1.6153259517635803, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15317097670583107, "300–1000 Hz_40ms_envelope_correlation": 0.9778657074294278, "300–1000 Hz_40ms_modulation_mae_db": 0.6759808528568191, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8144701442755697, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1989708499300992, "1000–3000 Hz_10ms_envelope_correlation": 0.9706103214104934, "1000–3000 Hz_10ms_modulation_mae_db": 0.3692753853745339, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0747247000461952, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10527017239702957, "1000–3000 Hz_40ms_envelope_correlation": 0.991418315693718, "1000–3000 Hz_40ms_modulation_mae_db": 0.24344387502006848, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5288019929772076, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15665363333154106, "3000–6000 Hz_10ms_envelope_correlation": 0.9807315914769813, "3000–6000 Hz_10ms_modulation_mae_db": 0.6590628039854022, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8146949374409477, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07274654503698062, "3000–6000 Hz_40ms_envelope_correlation": 0.9958026179377197, "3000–6000 Hz_40ms_modulation_mae_db": 0.8731784277871437, "mr_stft_db": 6.175020473434665, "band_mae_db": 0.42853268943765654, "rms_gain_error_db": 0.04372196798750069, "output_peak": 0.0404035107661564}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 109060, "output_samples": 109060, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.345153765495652, "spectral_convergence": 0.6245175000023608, "spectral_convergence_status": "ok", "amplitude_floor": 7.347807435362163e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.077287384714118, "spectral_convergence": 0.6186136951028646, "spectral_convergence_status": "ok", "amplitude_floor": 3.5954742817466214e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.081207314279512, "spectral_convergence": 0.6494644915295379, "spectral_convergence_status": "ok", "amplitude_floor": 1.4970646531776498e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.2516812561146785e-07, "output_power": 1.2959947578859633e-07, "delta_db": 0.1510949614395155, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 8.469209703610174e-08, "output_power": 1.2075606870999044e-07, "delta_db": 1.5406607941269035, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 4.7196494133004234e-07, "output_power": 5.294003388427371e-07, "delta_db": 0.49874475522731165, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.5661034348838578e-06, "output_power": 1.6368575452845633e-06, "delta_db": 0.19190442585160572, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2294550474819316e-06, "output_power": 1.2424405410228472e-06, "delta_db": 0.04562959773943562, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.3429464378207576e-06, "output_power": 3.364764582192262e-06, "delta_db": 0.028252657560471402, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.563896615059082e-07, "output_power": 9.18683098112989e-07, "delta_db": -0.17469146461278534, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.3758540937940041, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.09160865412862912, "pitch": null, "output_rms_dbfs": -51.000426862816354, "output_peak": 0.033773989708816794, "reference_rms_dbfs": -51.09203551694498, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.167882821496427}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 109060, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 1.1882865623804307e-05, "log_rms_mae_db": 1.4298864058384355, "rms_envelope_nrmse": 0.11817945112796267, "envelope_correlation": 0.9877244319350688, "rms_gain_error_db": 0.09162116913973989, "reference_mean_power": 7.792370026271951e-06, "output_mean_power": 7.958508492699547e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 4.121961515330987e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7941587942139734e-06, "output_power": 1.8694345265564733e-06, "reference_active": true, "delta_db": 0.17849381233264294}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1263612266386524e-07, "output_power": 3.2925065664232373e-07, "reference_active": true, "delta_db": 0.22487493851524018}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9590349245364564e-07, "output_power": 1.7359339008691084e-07, "reference_active": true, "delta_db": -0.5250899388307579}], "active_band_count": 3, "active_band_mae_db": 0.3094862298928804}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 9.239390922709503e-06, "log_rms_mae_db": 0.7367154496735964, "rms_envelope_nrmse": 0.05551569038946593, "envelope_correlation": 0.9971616539208171, "rms_gain_error_db": 0.09161120505063841, "reference_mean_power": 7.844041250222317e-06, "output_mean_power": 8.011263000818697e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 3.7692280722089195e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6572550629104971e-06, "output_power": 1.7429481192355641e-06, "reference_active": true, "delta_db": 0.2189510559003768}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5392861690297655e-07, "output_power": 1.5105204102724813e-07, "reference_active": true, "delta_db": -0.08192769249414086}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6336932951152273e-08, "output_power": 1.2595399925781489e-08, "reference_active": true, "delta_db": -1.1295856499506636}], "active_band_count": 3, "active_band_mae_db": 0.47682146611506043}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 2.9307310026633354e-06, "log_rms_mae_db": 2.4132194157963154, "rms_envelope_nrmse": 0.3018900329540525, "envelope_correlation": 0.9292820458049205, "rms_gain_error_db": 0.760798138870752, "reference_mean_power": 4.2741366364654595e-07, "output_mean_power": 5.092466908155178e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 2.4398860779830526e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.615850373422058e-08, "output_power": 1.192354988282869e-07, "reference_active": true, "delta_db": 0.9341787602725339}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8718875021930722e-08, "output_power": 3.181244337642686e-08, "reference_active": true, "delta_db": 2.3031728197388137}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0143942568188046e-08, "output_power": 1.9029331600154002e-08, "reference_active": true, "delta_db": -0.247209404760315}], "active_band_count": 3, "active_band_mae_db": 1.1615203282572208}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 1.736089681183382e-06, "log_rms_mae_db": 1.7378544472294457, "rms_envelope_nrmse": 0.20009765684228964, "envelope_correlation": 0.9698752745321083, "rms_gain_error_db": 0.7607948841956571, "reference_mean_power": 4.3025101883138276e-07, "output_mean_power": 5.126269045554544e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 2.1733905138014183e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.047483464267491e-08, "output_power": 1.1335761790935716e-07, "reference_active": true, "delta_db": 0.9792291305745527}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.338915747949155e-09, "output_power": 1.306451278607751e-08, "reference_active": true, "delta_db": 1.4579676086826217}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.438276742938052e-09, "output_power": 1.3938224688924656e-09, "reference_active": true, "delta_db": -0.1363499671442225}], "active_band_count": 3, "active_band_mae_db": 0.8578489021337989}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 7.246614216836824e-06, "log_rms_mae_db": 1.7950213400388895, "rms_envelope_nrmse": 0.18627288087696867, "envelope_correlation": 0.9750681568118694, "rms_gain_error_db": 0.2818774253272534, "reference_mean_power": 1.7870157226185334e-06, "output_mean_power": 1.9068481775936397e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.838724239404773e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.063249741710556e-07, "output_power": 7.630309067461672e-07, "reference_active": true, "delta_db": 0.335375672456856}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.654737664402428e-07, "output_power": 1.740511993189054e-07, "reference_active": true, "delta_db": 0.21947867953694272}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2023841152792083e-07, "output_power": 1.1527159222212219e-07, "reference_active": true, "delta_db": -0.18320938124444408}], "active_band_count": 3, "active_band_mae_db": 0.24602124441274761}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.77385839866885e-06, "log_rms_mae_db": 1.0714458753363798, "rms_envelope_nrmse": 0.09414481396624086, "envelope_correlation": 0.9937949289113681, "rms_gain_error_db": 0.2818773341088806, "reference_mean_power": 1.7989086732437154e-06, "output_mean_power": 1.9195385970961566e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 1.713692894624548e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.664518497859096e-07, "output_power": 7.34949557045424e-07, "reference_active": true, "delta_db": 0.42488754773102066}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.184085944051966e-08, "output_power": 7.884451680360956e-08, "reference_active": true, "delta_db": -0.16198685455630224}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1933830695482323e-08, "output_power": 9.161527278691025e-09, "reference_active": true, "delta_db": -1.148119931800376}], "active_band_count": 3, "active_band_mae_db": 0.5783314446958997}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 6.060487704579714e-06, "log_rms_mae_db": 1.6379345739331, "rms_envelope_nrmse": 0.17529163751106105, "envelope_correlation": 0.9759991172897118, "rms_gain_error_db": 0.014768301789687889, "reference_mean_power": 1.7907615060268857e-06, "output_mean_power": 1.7968614047137246e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.036723230359137e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.741355867444106e-07, "output_power": 4.724855161113322e-07, "reference_active": true, "delta_db": -0.015140530764383377}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0977135221440419e-07, "output_power": 9.792005610660693e-08, "reference_active": true, "delta_db": -0.4961736043471404}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0575338351673974e-08, "output_power": 2.667296168686054e-08, "reference_active": true, "delta_db": -0.5930003056490427}], "active_band_count": 3, "active_band_mae_db": 0.3681048135868555}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.330101975711502e-06, "log_rms_mae_db": 0.9633725349646739, "rms_envelope_nrmse": 0.0880185207397074, "envelope_correlation": 0.9935559239754121, "rms_gain_error_db": 0.01476669048045205, "reference_mean_power": 1.8026836617488875e-06, "output_mean_power": 1.8088234999540445e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 9.630136220520234e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.5232190822756626e-07, "output_power": 4.505520760203417e-07, "reference_active": true, "delta_db": -0.017026281837340722}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.528340255264933e-08, "output_power": 4.795098821165588e-08, "reference_active": true, "delta_db": -0.6179720302722855}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3355698674413927e-09, "output_power": 1.6262779690682463e-09, "reference_active": true, "delta_db": -1.5719808480611301}], "active_band_count": 3, "active_band_mae_db": 0.7356597200569187}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5050717044169917, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "e740a89e7b076d34be6eb46f6a809760ce3619b079705ae1ef57e65514cad59c", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9689870979573413, "standard_deviation": 0.004300441550212934, "minimum": 0.9613868779804562, "maximum": 0.9750681568118694, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.8136750126101124, "standard_deviation": 0.023816396140667388, "minimum": 1.7837496818315461, "maximum": 1.863169328973671, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5766605528319562, "standard_deviation": 0.23651820092368855, "minimum": 0.24602124441274761, "maximum": 0.9341331306478775, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2018321008757153, "standard_deviation": 0.012747779785536116, "minimum": 0.18627288087696867, "maximum": 0.22624983454464237, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9903539796720489, "standard_deviation": 0.0024903677056590297, "minimum": 0.9869896413537217, "maximum": 0.9937949289113681, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.055902670971026, "standard_deviation": 0.03054227746683295, "minimum": 1.0093452445667244, "maximum": 1.1049251236199964, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.9078951399343876, "standard_deviation": 0.4405120622233896, "minimum": 0.24344387502006848, "maximum": 1.5656919250794974, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10988025129967585, "standard_deviation": 0.013514756307706528, "minimum": 0.09088180816130324, "maximum": 0.12706865426012187, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9784721013682363, "standard_deviation": 0.0032187973799391017, "minimum": 0.9737132789414128, "maximum": 0.9825169660896309, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5753706093238704, "standard_deviation": 0.046969126412842656, "minimum": 1.5196450539570372, "maximum": 1.6379345739331, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.47308103365581083, "standard_deviation": 0.15282808372812753, "minimum": 0.24933236096346167, "maximum": 0.6590628039854022, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16639505011759026, "standard_deviation": 0.013279632657687548, "minimum": 0.14945009179238028, "maximum": 0.18786419941080418, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9943276003417351, "standard_deviation": 0.0023791393541036585, "minimum": 0.988706749800674, "maximum": 0.9958026179377197, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8904893740749249, "standard_deviation": 0.04621982098893958, "minimum": 0.8146949374409477, "maximum": 0.9633725349646739, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7664780669694171, "standard_deviation": 0.1222693174960447, "minimum": 0.5768813255574522, "maximum": 0.9855827787083844, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08304195357509406, "standard_deviation": 0.016014156291672868, "minimum": 0.07274654503698062, "maximum": 0.12072947116774588, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9308325938869975, "standard_deviation": 0.010248896413744888, "minimum": 0.9152507697619856, "maximum": 0.9436962931195572, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.38187142673279, "standard_deviation": 0.07703078328664748, "minimum": 2.2205439015524213, "maximum": 2.4936162409287532, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8253352825128462, "standard_deviation": 0.4010942167127893, "minimum": 0.17492109148533228, "maximum": 1.4012947936772047, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2882206728224387, "standard_deviation": 0.023032903823336382, "minimum": 0.25697881244332227, "maximum": 0.32720663822965695, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9763845359857107, "standard_deviation": 0.00520677001723241, "minimum": 0.9691012958557174, "maximum": 0.9831169418912039, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.6414265993415604, "standard_deviation": 0.09064229169598993, "minimum": 1.4664952614974267, "maximum": 1.7378544472294457, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8259851604631568, "standard_deviation": 0.28153618026511923, "minimum": 0.315810967506902, "maximum": 1.2458412858334555, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.16837346098429282, "standard_deviation": 0.021601581517612524, "minimum": 0.14076015571440537, "maximum": 0.20009765684228964, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.4261727191862931, "standard_deviation": 0.046782926894996184, "minimum": 0.3584938248247324, "maximum": 0.5141897842968753, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.176828599932472, "standard_deviation": 0.007846342149799576, "minimum": 6.1634390692052925, "maximum": 6.187010973928551, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.03525672714188001, "standard_deviation": 0.003613849175251569, "minimum": 0.03194945020031132, "maximum": 0.04131731655175884, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": 0.002821809462432181, "standard_deviation": 0.1106180857657607, "minimum": -0.1424826941934897, "maximum": 0.16970731709602915, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9866149464083107, "standard_deviation": 0.0008511734579881632, "minimum": 0.9854127537057668, "maximum": 0.9879641191690328, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.399491047086955, "standard_deviation": 0.03342789559840025, "minimum": 1.340817281684742, "maximum": 1.4309387321130551, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4477836945376083, "standard_deviation": 0.2544383557152635, "minimum": 0.10880553336437519, "maximum": 0.8793985159690351, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.12283508980794841, "standard_deviation": 0.003726216145055824, "minimum": 0.11711421385403621, "maximum": 0.12734045600860028, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9964329956735944, "standard_deviation": 0.0005814632411623741, "minimum": 0.995504948935238, "maximum": 0.9971616539208171, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.7356881415506966, "standard_deviation": 0.030890199299935413, "minimum": 0.7019212844634277, "maximum": 0.7778388505385906, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7243573731858928, "standard_deviation": 0.32804082019312125, "minimum": 0.2426012514750188, "maximum": 1.3309230947210269, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.06182529577890792, "standard_deviation": 0.004924914750112957, "minimum": 0.05551569038946593, "maximum": 0.06958632255953265, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_whisper10_BASIC5000_0074", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 2.0154237747192383, "predicted_mos": 2.0154237747192383, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 109060, "input_sample_rate": 24000, "input_seconds": 4.5441666666666665, "input_float32_sha256": "345748b8b4c870b13b0242f9aedc44b044489823465be75f13e44835f07347ac", "internal_samples": 72707, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.305398000404239}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4582606080366893, "全帯域_10ms_rms_envelope_nrmse": 0.11942333976800239, "全帯域_10ms_envelope_correlation": 0.987281231549438, "全帯域_10ms_modulation_mae_db": 0.686129448229531, "全帯域_40ms_log_rms_mae_db": 0.7504479404683622, "全帯域_40ms_rms_envelope_nrmse": 0.06474252728061856, "全帯域_40ms_envelope_correlation": 0.9961998320429538, "全帯域_40ms_modulation_mae_db": 1.097485792362266, "300–1000 Hz_10ms_log_rms_mae_db": 2.2697209987579177, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.273991111287992, "300–1000 Hz_10ms_envelope_correlation": 0.942313733942617, "300–1000 Hz_10ms_modulation_mae_db": 0.3950497551195138, "300–1000 Hz_40ms_log_rms_mae_db": 1.6523827727210851, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17646633573805798, "300–1000 Hz_40ms_envelope_correlation": 0.9772819046721807, "300–1000 Hz_40ms_modulation_mae_db": 0.11235495425970654, "1000–3000 Hz_10ms_log_rms_mae_db": 1.523694563106961, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17773216867893357, "1000–3000 Hz_10ms_envelope_correlation": 0.9756908419342093, "1000–3000 Hz_10ms_modulation_mae_db": 0.7811424096636227, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8923172023177722, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09601874867512054, "1000–3000 Hz_40ms_envelope_correlation": 0.9923952062580312, "1000–3000 Hz_40ms_modulation_mae_db": 1.3583334884533904, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2371107358709088, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14661987911200686, "3000–6000 Hz_10ms_envelope_correlation": 0.9832617626696002, "3000–6000 Hz_10ms_modulation_mae_db": 0.4999921463422623, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7135059129845006, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07687710704420807, "3000–6000 Hz_40ms_envelope_correlation": 0.9954833343334895, "3000–6000 Hz_40ms_modulation_mae_db": 0.4952565155065612, "mr_stft_db": 6.001163451545562, "band_mae_db": 0.48765656222816195, "rms_gain_error_db": -0.1430575999887705, "output_peak": 0.034241330206237}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5007834356499914, "全帯域_10ms_rms_envelope_nrmse": 0.13555681563031025, "全帯域_10ms_envelope_correlation": 0.9839146138269057, "全帯域_10ms_modulation_mae_db": 0.37387111882493446, "全帯域_40ms_log_rms_mae_db": 0.8321539957570072, "全帯域_40ms_rms_envelope_nrmse": 0.07492745691158509, "全帯域_40ms_envelope_correlation": 0.9947709663778189, "全帯域_40ms_modulation_mae_db": 0.7219966452052816, "300–1000 Hz_10ms_log_rms_mae_db": 2.1941389566168947, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2669864474939081, "300–1000 Hz_10ms_envelope_correlation": 0.9449570648933097, "300–1000 Hz_10ms_modulation_mae_db": 1.1411932612791051, "300–1000 Hz_40ms_log_rms_mae_db": 1.5117159397360012, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16702895175580942, "300–1000 Hz_40ms_envelope_correlation": 0.9797395413775456, "300–1000 Hz_40ms_modulation_mae_db": 0.9152336054691684, "1000–3000 Hz_10ms_log_rms_mae_db": 1.520190718358695, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20227158574565593, "1000–3000 Hz_10ms_envelope_correlation": 0.9700894574829799, "1000–3000 Hz_10ms_modulation_mae_db": 0.4343928423877778, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8425516054540078, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11751963807889734, "1000–3000 Hz_40ms_envelope_correlation": 0.9895300472772239, "1000–3000 Hz_40ms_modulation_mae_db": 0.9616846236902822, "3000–6000 Hz_10ms_log_rms_mae_db": 1.176575979771031, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16211559950624657, "3000–6000 Hz_10ms_envelope_correlation": 0.9797673992559894, "3000–6000 Hz_10ms_modulation_mae_db": 0.48493334217622525, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6225383880511343, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07826903872709953, "3000–6000 Hz_40ms_envelope_correlation": 0.994988320400273, "3000–6000 Hz_40ms_modulation_mae_db": 0.030474751253246418, "mr_stft_db": 5.998828858274128, "band_mae_db": 0.322924133011575, "rms_gain_error_db": 0.09098613769144039, "output_peak": 0.037262962212636495}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5005710290628096, "全帯域_10ms_rms_envelope_nrmse": 0.1220097132796387, "全帯域_10ms_envelope_correlation": 0.9866883515449707, "全帯域_10ms_modulation_mae_db": 0.9310577361514722, "全帯域_40ms_log_rms_mae_db": 0.7971222476959041, "全帯域_40ms_rms_envelope_nrmse": 0.06555387745620046, "全帯域_40ms_envelope_correlation": 0.9960465064368266, "全帯域_40ms_modulation_mae_db": 1.6323762639993376, "300–1000 Hz_10ms_log_rms_mae_db": 2.161011774789829, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2697512534340375, "300–1000 Hz_10ms_envelope_correlation": 0.9363239710387722, "300–1000 Hz_10ms_modulation_mae_db": 1.0682012477773593, "300–1000 Hz_40ms_log_rms_mae_db": 1.5497074204978498, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1705860248029509, "300–1000 Hz_40ms_envelope_correlation": 0.9724102766059498, "300–1000 Hz_40ms_modulation_mae_db": 0.9253893398766627, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4865444438112316, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19567354277325757, "1000–3000 Hz_10ms_envelope_correlation": 0.9707149551296481, "1000–3000 Hz_10ms_modulation_mae_db": 1.4100337087199903, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8545711097307158, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11410390176606339, "1000–3000 Hz_40ms_envelope_correlation": 0.9902959683010224, "1000–3000 Hz_40ms_modulation_mae_db": 2.022599369151287, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2063424196781718, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1375640998441027, "3000–6000 Hz_10ms_envelope_correlation": 0.9851764190279896, "3000–6000 Hz_10ms_modulation_mae_db": 0.6899530088637994, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6441689831763162, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07030641996032687, "3000–6000 Hz_40ms_envelope_correlation": 0.9960202342268002, "3000–6000 Hz_40ms_modulation_mae_db": 0.9314996153738754, "mr_stft_db": 5.993051877332949, "band_mae_db": 0.3762103616227258, "rms_gain_error_db": -0.14491175937788608, "output_peak": 0.03149346490566639}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4659742247155796, "全帯域_10ms_rms_envelope_nrmse": 0.1324034265724956, "全帯域_10ms_envelope_correlation": 0.9843461574658668, "全帯域_10ms_modulation_mae_db": 0.2086317847043693, "全帯域_40ms_log_rms_mae_db": 0.7825790510463607, "全帯域_40ms_rms_envelope_nrmse": 0.07136764745944182, "全帯域_40ms_envelope_correlation": 0.9951036299313691, "全帯域_40ms_modulation_mae_db": 0.6408338526107761, "300–1000 Hz_10ms_log_rms_mae_db": 2.1898412646552616, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27660004557024653, "300–1000 Hz_10ms_envelope_correlation": 0.9370811567683373, "300–1000 Hz_10ms_modulation_mae_db": 1.320070442803002, "300–1000 Hz_40ms_log_rms_mae_db": 1.5417199570984952, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.182229319249827, "300–1000 Hz_40ms_envelope_correlation": 0.9716408168679702, "300–1000 Hz_40ms_modulation_mae_db": 0.921091479071494, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5261400212981966, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2020429772930745, "1000–3000 Hz_10ms_envelope_correlation": 0.9689872903914496, "1000–3000 Hz_10ms_modulation_mae_db": 0.3425493508986143, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8564674502237992, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1192780369097739, "1000–3000 Hz_40ms_envelope_correlation": 0.9884045937983155, "1000–3000 Hz_40ms_modulation_mae_db": 0.8445750237187056, "3000–6000 Hz_10ms_log_rms_mae_db": 1.219829182474054, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15396066867337074, "3000–6000 Hz_10ms_envelope_correlation": 0.9814136183533033, "3000–6000 Hz_10ms_modulation_mae_db": 0.4807151963191507, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6463463674521348, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08041516981322137, "3000–6000 Hz_40ms_envelope_correlation": 0.9948431200455945, "3000–6000 Hz_40ms_modulation_mae_db": 0.8863083589716024, "mr_stft_db": 6.001510177155107, "band_mae_db": 0.36320730978473276, "rms_gain_error_db": 0.0034498819459188677, "output_peak": 0.0365855550898021}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5135920871593793, "全帯域_10ms_rms_envelope_nrmse": 0.12403122050031366, "全帯域_10ms_envelope_correlation": 0.9862440351231097, "全帯域_10ms_modulation_mae_db": 0.5296685543371807, "全帯域_40ms_log_rms_mae_db": 0.8355126337872161, "全帯域_40ms_rms_envelope_nrmse": 0.062431479630641176, "全帯域_40ms_envelope_correlation": 0.996238032399437, "全帯域_40ms_modulation_mae_db": 0.7354922664522742, "300–1000 Hz_10ms_log_rms_mae_db": 2.09773105722397, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.23291915440188182, "300–1000 Hz_10ms_envelope_correlation": 0.9510528557979624, "300–1000 Hz_10ms_modulation_mae_db": 0.4207943867162996, "300–1000 Hz_40ms_log_rms_mae_db": 1.4418421472018708, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14331944872069374, "300–1000 Hz_40ms_envelope_correlation": 0.979625943367128, "300–1000 Hz_40ms_modulation_mae_db": 1.0607198831364888, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5585324770200186, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17513331514571662, "1000–3000 Hz_10ms_envelope_correlation": 0.9768071678058603, "1000–3000 Hz_10ms_modulation_mae_db": 0.23577476943694756, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8850057254747505, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09731161617507982, "1000–3000 Hz_40ms_envelope_correlation": 0.9923593643283276, "1000–3000 Hz_40ms_modulation_mae_db": 0.6351501260667265, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2500975272048198, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17116822485115524, "3000–6000 Hz_10ms_envelope_correlation": 0.9771964165412735, "3000–6000 Hz_10ms_modulation_mae_db": 0.2267420043265811, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6940237065013299, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0860232861101509, "3000–6000 Hz_40ms_envelope_correlation": 0.9938212109522531, "3000–6000 Hz_40ms_modulation_mae_db": 0.23674824251366355, "mr_stft_db": 6.008002028019134, "band_mae_db": 0.4612598525750042, "rms_gain_error_db": 0.007879307824796091, "output_peak": 0.03643335530753443}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3930797266427353, "全帯域_10ms_rms_envelope_nrmse": 0.12069799667731276, "全帯域_10ms_envelope_correlation": 0.986943303257346, "全帯域_10ms_modulation_mae_db": 0.4719711734323604, "全帯域_40ms_log_rms_mae_db": 0.7442649212811907, "全帯域_40ms_rms_envelope_nrmse": 0.058141603489680636, "全帯域_40ms_envelope_correlation": 0.9967493268073756, "全帯域_40ms_modulation_mae_db": 0.7617009659698403, "300–1000 Hz_10ms_log_rms_mae_db": 2.114934984190665, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2683243635475312, "300–1000 Hz_10ms_envelope_correlation": 0.936350911869295, "300–1000 Hz_10ms_modulation_mae_db": 0.7900734332599214, "300–1000 Hz_40ms_log_rms_mae_db": 1.4220216521069593, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15864149113888143, "300–1000 Hz_40ms_envelope_correlation": 0.9757516578429467, "300–1000 Hz_40ms_modulation_mae_db": 0.4750870932821017, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4455205281504788, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19142289366494378, "1000–3000 Hz_10ms_envelope_correlation": 0.9717168238302473, "1000–3000 Hz_10ms_modulation_mae_db": 0.3080195881373079, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8284045398374366, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09621581053305259, "1000–3000 Hz_40ms_envelope_correlation": 0.9924836186107778, "1000–3000 Hz_40ms_modulation_mae_db": 0.6965544919598319, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2144856786977167, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14606614615920674, "3000–6000 Hz_10ms_envelope_correlation": 0.9840939164213169, "3000–6000 Hz_10ms_modulation_mae_db": 0.3337229712065237, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6848489348774659, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08717299389610768, "3000–6000 Hz_40ms_envelope_correlation": 0.9941713860943128, "3000–6000 Hz_40ms_modulation_mae_db": 0.6234760155314856, "mr_stft_db": 6.009698739249333, "band_mae_db": 0.37986504724888276, "rms_gain_error_db": -0.03309442869868346, "output_peak": 0.031381647582162726}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4050168653371915, "全帯域_10ms_rms_envelope_nrmse": 0.1328278813227605, "全帯域_10ms_envelope_correlation": 0.9841529960725575, "全帯域_10ms_modulation_mae_db": 0.47011779699314554, "全帯域_40ms_log_rms_mae_db": 0.7369433386642508, "全帯域_40ms_rms_envelope_nrmse": 0.0686938112205063, "全帯域_40ms_envelope_correlation": 0.9954582488301211, "全帯域_40ms_modulation_mae_db": 0.8823461711709207, "300–1000 Hz_10ms_log_rms_mae_db": 2.2007699878787528, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.29188231242924145, "300–1000 Hz_10ms_envelope_correlation": 0.9234602374306353, "300–1000 Hz_10ms_modulation_mae_db": 0.342500917731604, "300–1000 Hz_40ms_log_rms_mae_db": 1.5222280306162037, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1823294863419113, "300–1000 Hz_40ms_envelope_correlation": 0.967124592650958, "300–1000 Hz_40ms_modulation_mae_db": 0.35051485920886205, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4447385128215078, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2229642831748499, "1000–3000 Hz_10ms_envelope_correlation": 0.9635921988107413, "1000–3000 Hz_10ms_modulation_mae_db": 0.8498364271105596, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8497696024793729, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12456157266977395, "1000–3000 Hz_40ms_envelope_correlation": 0.9882081132494281, "1000–3000 Hz_40ms_modulation_mae_db": 1.3405927426830264, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2506790357821385, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15504920591752075, "3000–6000 Hz_10ms_envelope_correlation": 0.9811319851194381, "3000–6000 Hz_10ms_modulation_mae_db": 0.7801988981482321, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7081072007859917, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08330827731534808, "3000–6000 Hz_40ms_envelope_correlation": 0.9943925002663181, "3000–6000 Hz_40ms_modulation_mae_db": 1.2735766034322828, "mr_stft_db": 5.994629207466598, "band_mae_db": 0.41612686337363686, "rms_gain_error_db": -0.05302757544983525, "output_peak": 0.03305193580396204}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5026587430639513, "全帯域_10ms_rms_envelope_nrmse": 0.1374700261966929, "全帯域_10ms_envelope_correlation": 0.9830799326913952, "全帯域_10ms_modulation_mae_db": 0.6200014652254304, "全帯域_40ms_log_rms_mae_db": 0.8800614044102574, "全帯域_40ms_rms_envelope_nrmse": 0.0802413337816522, "全帯域_40ms_envelope_correlation": 0.9937928563544416, "全帯域_40ms_modulation_mae_db": 0.7855218795461986, "300–1000 Hz_10ms_log_rms_mae_db": 2.196097385533988, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2811818000816875, "300–1000 Hz_10ms_envelope_correlation": 0.9327189982836271, "300–1000 Hz_10ms_modulation_mae_db": 0.8631689965897271, "300–1000 Hz_40ms_log_rms_mae_db": 1.4865192524275501, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1732188760319859, "300–1000 Hz_40ms_envelope_correlation": 0.9730695406037055, "300–1000 Hz_40ms_modulation_mae_db": 0.4657705603805304, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5213994292157291, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.22076225040864728, "1000–3000 Hz_10ms_envelope_correlation": 0.9622792668394522, "1000–3000 Hz_10ms_modulation_mae_db": 0.8210938721624489, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8833538381390975, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.13145570642511356, "1000–3000 Hz_40ms_envelope_correlation": 0.986595220936898, "1000–3000 Hz_40ms_modulation_mae_db": 1.018235146202308, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2153052318337216, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16466266361550277, "3000–6000 Hz_10ms_envelope_correlation": 0.979486939384188, "3000–6000 Hz_10ms_modulation_mae_db": 0.2653648630725209, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6696588592864023, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0931775165081635, "3000–6000 Hz_40ms_envelope_correlation": 0.9931273431718115, "3000–6000 Hz_40ms_modulation_mae_db": 0.2519260777938878, "mr_stft_db": 5.990377283516558, "band_mae_db": 0.3976442724208263, "rms_gain_error_db": -0.03390169018831707, "output_peak": 0.039811365677186634}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 109060, "output_samples": 109060, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.01890673230094, "spectral_convergence": 0.5998706804261609, "spectral_convergence_status": "ok", "amplitude_floor": 7.347807435362163e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.874056403736891, "spectral_convergence": 0.6043612564818603, "spectral_convergence_status": "ok", "amplitude_floor": 3.5954742817466214e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.110527218598854, "spectral_convergence": 0.6389926766065158, "spectral_convergence_status": "ok", "amplitude_floor": 1.4970646531776498e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.2516812561146785e-07, "output_power": 1.1678133967696902e-07, "delta_db": -0.3012029570816716, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 8.469209703610174e-08, "output_power": 1.2987957242378234e-07, "delta_db": 1.856979637789025, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 4.7196494133004234e-07, "output_power": 5.090472880492843e-07, "delta_db": 0.32848388670297257, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.5661034348838578e-06, "output_power": 1.518992830209184e-06, "delta_db": -0.13264718130767236, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2294550474819316e-06, "output_power": 1.1810170280121947e-06, "delta_db": -0.17456494915960852, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.3429464378207576e-06, "output_power": 3.2037817593874957e-06, "delta_db": -0.18466493773010806, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.563896615059082e-07, "output_power": 8.652261448511031e-07, "delta_db": -0.43505238582607514, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.48765656222816195, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.1430575999887705, "pitch": null, "output_rms_dbfs": -51.235093116933754, "output_peak": 0.034241330206237, "reference_rms_dbfs": -51.09203551694498, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.001163451545562}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 109060, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 1.1882865623804307e-05, "log_rms_mae_db": 1.4582606080366893, "rms_envelope_nrmse": 0.11942333976800239, "envelope_correlation": 0.987281231549438, "rms_gain_error_db": -0.14306442972827968, "reference_mean_power": 7.792370026271951e-06, "output_mean_power": 7.53985726041297e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 4.121961515330987e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7941587942139734e-06, "output_power": 1.701317974055763e-06, "reference_active": true, "delta_db": -0.2307538791537197}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1263612266386524e-07, "output_power": 3.0504545126193764e-07, "reference_active": true, "delta_db": -0.10674602600715842}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9590349245364564e-07, "output_power": 1.318115097666885e-07, "reference_active": true, "delta_db": -1.720888439527715}], "active_band_count": 3, "active_band_mae_db": 0.686129448229531}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 9.239390922709503e-06, "log_rms_mae_db": 0.7504479404683622, "rms_envelope_nrmse": 0.06474252728061856, "envelope_correlation": 0.9961998320429538, "rms_gain_error_db": -0.14306073829149948, "reference_mean_power": 7.844041250222317e-06, "output_mean_power": 7.589860522882517e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 3.7692280722089195e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6572550629104971e-06, "output_power": 1.5700523339441847e-06, "reference_active": true, "delta_db": -0.23475225640598874}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5392861690297655e-07, "output_power": 1.4547123121075504e-07, "reference_active": true, "delta_db": -0.245422525732613}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6336932951152273e-08, "output_power": 8.54953052328996e-09, "reference_active": true, "delta_db": -2.8122825949481967}], "active_band_count": 3, "active_band_mae_db": 1.097485792362266}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 2.9307310026633354e-06, "log_rms_mae_db": 2.2697209987579177, "rms_envelope_nrmse": 0.273991111287992, "envelope_correlation": 0.942313733942617, "rms_gain_error_db": 0.7160525438975365, "reference_mean_power": 4.2741366364654595e-07, "output_mean_power": 5.040268310861558e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 2.4398860779830526e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.615850373422058e-08, "output_power": 1.0139342150571448e-07, "reference_active": true, "delta_db": 0.2302208159287067}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8718875021930722e-08, "output_power": 2.1415779048331475e-08, "reference_active": true, "delta_db": 0.5845413278425118}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0143942568188046e-08, "output_power": 2.1937300621702377e-08, "reference_active": true, "delta_db": 0.3703871215873228}], "active_band_count": 3, "active_band_mae_db": 0.3950497551195138}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 1.736089681183382e-06, "log_rms_mae_db": 1.6523827727210851, "rms_envelope_nrmse": 0.17646633573805798, "envelope_correlation": 0.9772819046721807, "rms_gain_error_db": 0.7160311404396037, "reference_mean_power": 4.3025101883138276e-07, "output_mean_power": 5.073702768366136e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 2.1733905138014183e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.047483464267491e-08, "output_power": 9.534119534071978e-08, "reference_active": true, "delta_db": 0.22752794556541375}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.338915747949155e-09, "output_power": 9.254672257676487e-09, "reference_active": true, "delta_db": -0.03935414004291545}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.438276742938052e-09, "output_power": 1.4617083761597054e-09, "reference_active": true, "delta_db": 0.07018277717079043}], "active_band_count": 3, "active_band_mae_db": 0.11235495425970654}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 7.246614216836824e-06, "log_rms_mae_db": 1.523694563106961, "rms_envelope_nrmse": 0.17773216867893357, "envelope_correlation": 0.9756908419342093, "rms_gain_error_db": -0.042621864214809756, "reference_mean_power": 1.7870157226185334e-06, "output_mean_power": 1.7695636443071024e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.838724239404773e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.063249741710556e-07, "output_power": 6.645698555610432e-07, "reference_active": true, "delta_db": -0.2646392417988287}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.654737664402428e-07, "output_power": 1.4038567942784134e-07, "reference_active": true, "delta_db": -0.7140634402862599}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2023841152792083e-07, "output_power": 8.781541851528217e-08, "reference_active": true, "delta_db": -1.3647245469057798}], "active_band_count": 3, "active_band_mae_db": 0.7811424096636227}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.77385839866885e-06, "log_rms_mae_db": 0.8923172023177722, "rms_envelope_nrmse": 0.09601874867512054, "envelope_correlation": 0.9923952062580312, "rms_gain_error_db": -0.042620106507912474, "reference_mean_power": 1.7989086732437154e-06, "output_mean_power": 1.7813411687823332e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 1.713692894624548e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.664518497859096e-07, "output_power": 6.205941690258447e-07, "reference_active": true, "delta_db": -0.3096108698796101}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.184085944051966e-08, "output_power": 7.03757820517728e-08, "reference_active": true, "delta_db": -0.6554694742260015}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1933830695482323e-08, "output_power": 5.8316017836159535e-09, "reference_active": true, "delta_db": -3.109920121254559}], "active_band_count": 3, "active_band_mae_db": 1.3583334884533904}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 6.060487704579714e-06, "log_rms_mae_db": 1.2371107358709088, "rms_envelope_nrmse": 0.14661987911200686, "envelope_correlation": 0.9832617626696002, "rms_gain_error_db": -0.21600284578334483, "reference_mean_power": 1.7907615060268857e-06, "output_mean_power": 1.7038739598940937e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.036723230359137e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.741355867444106e-07, "output_power": 4.3273965244249e-07, "reference_active": true, "delta_db": -0.3967586103533998}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0977135221440419e-07, "output_power": 9.952809829477099e-08, "reference_active": true, "delta_db": -0.4254330809132967}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0575338351673974e-08, "output_power": 3.5739604850421477e-08, "reference_active": true, "delta_db": 0.6777847477600905}], "active_band_count": 3, "active_band_mae_db": 0.4999921463422623}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.330101975711502e-06, "log_rms_mae_db": 0.7135059129845006, "rms_envelope_nrmse": 0.07687710704420807, "envelope_correlation": 0.9954833343334895, "rms_gain_error_db": -0.21600344853286169, "reference_mean_power": 1.8026836617488875e-06, "output_mean_power": 1.7152174159142635e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 9.630136220520234e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.5232190822756626e-07, "output_power": 4.1540516667662757e-07, "reference_active": true, "delta_db": -0.369757294753267}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.528340255264933e-08, "output_power": 5.0303504275394226e-08, "reference_active": true, "delta_db": -0.4099652469408783}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3355698674413927e-09, "output_power": 1.9851263908744077e-09, "reference_active": true, "delta_db": -0.7060470048255383}], "active_band_count": 3, "active_band_mae_db": 0.4952565155065612}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5333948804489911, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "05cabb9e13115a4c8c6be17f87e209e80edf699681e2445a798f6342875516ea", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9699847502780735, "standard_deviation": 0.005125332322836932, "minimum": 0.9622792668394522, "maximum": 0.9768071678058603, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.5033450867228524, "standard_deviation": 0.04079524578053775, "minimum": 1.4447385128215078, "maximum": 1.5585324770200186, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6478553710646586, "standard_deviation": 0.39525145287670305, "minimum": 0.23577476943694756, "maximum": 1.4100337087199903, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1985003771106349, "standard_deviation": 0.017551009592071492, "minimum": 0.17513331514571662, "maximum": 0.2229642831748499, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9900340165950031, "standard_deviation": 0.0022398938038237074, "minimum": 0.986595220936898, "maximum": 0.9924836186107778, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.861555134207119, "standard_deviation": 0.022819397934966342, "minimum": 0.8284045398374366, "maximum": 0.8923172023177722, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.1097156264906949, "standard_deviation": 0.4543390402180582, "minimum": 0.6351501260667265, "maximum": 2.022599369151287, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.11205812890410938, "standard_deviation": 0.013858689216162208, "minimum": 0.09601874867512054, "maximum": 0.13145570642511356, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9814410570966374, "standard_deviation": 0.002646791010039687, "minimum": 0.9771964165412735, "maximum": 0.9851764190279896, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2213032239140702, "standard_deviation": 0.024642899067419465, "minimum": 1.176575979771031, "maximum": 1.2506790357821385, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.47020280380691193, "standard_deviation": 0.19473833094313436, "minimum": 0.2267420043265811, "maximum": 0.7801988981482321, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15465081095988906, "standard_deviation": 0.011081311623324519, "minimum": 0.1375640998441027, "maximum": 0.17116822485115524, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9946059311863565, "standard_deviation": 0.0009265111205784358, "minimum": 0.9931273431718115, "maximum": 0.9960202342268002, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.6728997941394095, "standard_deviation": 0.03285191635557204, "minimum": 0.6225383880511343, "maximum": 0.7135059129845006, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.5911582725470756, "standard_deviation": 0.41985254680194706, "minimum": 0.030474751253246418, "maximum": 1.2735766034322828, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08194372617182824, "standard_deviation": 0.0070608116992825565, "minimum": 0.07030641996032687, "maximum": 0.0931775165081635, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9380323662530694, "standard_deviation": 0.00830700417610702, "minimum": 0.9234602374306353, "maximum": 0.9510528557979624, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.1780308012059097, "standard_deviation": 0.05394216796469915, "minimum": 2.09773105722397, "maximum": 2.2697209987579177, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7926315551595666, "standard_deviation": 0.37408164341919464, "minimum": 0.342500917731604, "maximum": 1.320070442803002, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2702045610308158, "standard_deviation": 0.017112916177934038, "minimum": 0.23291915440188182, "maximum": 0.29188231242924145, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9745805342485481, "standard_deviation": 0.004341931166531585, "minimum": 0.967124592650958, "maximum": 0.9797395413775456, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.516017146550752, "standard_deviation": 0.07136979928742537, "minimum": 1.4220216521069593, "maximum": 1.6523827727210851, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6532702218356268, "standard_deviation": 0.3446680738111139, "minimum": 0.11235495425970654, "maximum": 1.0607198831364888, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.16922749172251472, "standard_deviation": 0.013087677323676106, "minimum": 0.14331944872069374, "maximum": 0.1823294863419113, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.4006118002831932, "standard_deviation": 0.05340522681600581, "minimum": 0.322924133011575, "maximum": 0.48765656222816195, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.999657702819921, "standard_deviation": 0.00688564736664327, "minimum": 5.990377283516558, "maximum": 6.009698739249333, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.035032702098148474, "standard_deviation": 0.002990197584809255, "minimum": 0.031381647582162726, "maximum": 0.039811365677186634, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.038209715780167124, "standard_deviation": 0.07855297382420301, "minimum": -0.14491175937788608, "maximum": 0.09098613769144039, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9853313276914487, "standard_deviation": 0.0016261269618766297, "minimum": 0.9830799326913952, "maximum": 0.987281231549438, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.467492089958541, "standard_deviation": 0.04643322520699704, "minimum": 1.3930797266427353, "maximum": 1.5135920871593793, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.536431134737303, "standard_deviation": 0.21633313935004655, "minimum": 0.2086317847043693, "maximum": 0.9310577361514722, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.12805255249344083, "standard_deviation": 0.007250383902495572, "minimum": 0.11942333976800239, "maximum": 0.1374700261966929, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.995544924897543, "standard_deviation": 0.0009623245173658155, "minimum": 0.9937928563544416, "maximum": 0.9967493268073756, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.7948856916388187, "standard_deviation": 0.05119336583816668, "minimum": 0.7369433386642508, "maximum": 0.8800614044102574, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.9072192296646119, "standard_deviation": 0.323687965541633, "minimum": 0.6408338526107761, "maximum": 1.6323762639993376, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.06826246715379078, "standard_deviation": 0.0071103774086829314, "minimum": 0.058141603489680636, "maximum": 0.0802413337816522, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_whisper10_BASIC5000_0074", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 1.839550495147705, "predicted_mos": 1.839550495147705, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 109060, "input_sample_rate": 24000, "input_seconds": 4.5441666666666665, "input_float32_sha256": "f005b57c3366c8f4ffcbcce212c259b3ed021e39af945b29af4001d871af35ac", "internal_samples": 72707, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.8970747999846935}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4026299435635385, "全帯域_10ms_rms_envelope_nrmse": 0.13087807758126258, "全帯域_10ms_envelope_correlation": 0.9852474151122443, "全帯域_10ms_modulation_mae_db": 0.402830907117544, "全帯域_40ms_log_rms_mae_db": 0.6979695325753604, "全帯域_40ms_rms_envelope_nrmse": 0.06782763453992004, "全帯域_40ms_envelope_correlation": 0.9959554373023489, "全帯域_40ms_modulation_mae_db": 0.7292284459963212, "300–1000 Hz_10ms_log_rms_mae_db": 2.215120573212329, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.28164253365482766, "300–1000 Hz_10ms_envelope_correlation": 0.9343765587115044, "300–1000 Hz_10ms_modulation_mae_db": 0.6327291459972076, "300–1000 Hz_40ms_log_rms_mae_db": 1.6100863550079083, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17428509171206763, "300–1000 Hz_40ms_envelope_correlation": 0.974400422780811, "300–1000 Hz_40ms_modulation_mae_db": 0.8759758973499965, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5609040383212778, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18297488540963375, "1000–3000 Hz_10ms_envelope_correlation": 0.9744006495295309, "1000–3000 Hz_10ms_modulation_mae_db": 0.9164362425164438, "1000–3000 Hz_40ms_log_rms_mae_db": 0.938999056235128, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11178880486691684, "1000–3000 Hz_40ms_envelope_correlation": 0.9898969531148976, "1000–3000 Hz_40ms_modulation_mae_db": 1.135117886048823, "3000–6000 Hz_10ms_log_rms_mae_db": 1.446335196323993, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16832657589806962, "3000–6000 Hz_10ms_envelope_correlation": 0.9783088426193637, "3000–6000 Hz_10ms_modulation_mae_db": 0.36293848561248027, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8699108791695346, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08082191391162304, "3000–6000 Hz_40ms_envelope_correlation": 0.9947305271401391, "3000–6000 Hz_40ms_modulation_mae_db": 0.4534018290703701, "mr_stft_db": 6.04259551978483, "band_mae_db": 0.49084886613613693, "rms_gain_error_db": 0.1513309440558212, "output_peak": 0.032558573096669895}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.373740192681556, "全帯域_10ms_rms_envelope_nrmse": 0.11993139197874571, "全帯域_10ms_envelope_correlation": 0.9872714378493064, "全帯域_10ms_modulation_mae_db": 0.4203479353457971, "全帯域_40ms_log_rms_mae_db": 0.6873255882267612, "全帯域_40ms_rms_envelope_nrmse": 0.054882152783664796, "全帯域_40ms_envelope_correlation": 0.9971669843256913, "全帯域_40ms_modulation_mae_db": 0.6537726377904213, "300–1000 Hz_10ms_log_rms_mae_db": 2.323544451445332, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2633488827145187, "300–1000 Hz_10ms_envelope_correlation": 0.9442621610743879, "300–1000 Hz_10ms_modulation_mae_db": 1.1414371697480354, "300–1000 Hz_40ms_log_rms_mae_db": 1.596932613317351, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15239227017519286, "300–1000 Hz_40ms_envelope_correlation": 0.9821690055273922, "300–1000 Hz_40ms_modulation_mae_db": 0.9421983465642079, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6160856336012095, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19502967769978483, "1000–3000 Hz_10ms_envelope_correlation": 0.9705932553941323, "1000–3000 Hz_10ms_modulation_mae_db": 0.7951107369092845, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9573038984694207, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09936543370941997, "1000–3000 Hz_40ms_envelope_correlation": 0.9919776333835527, "1000–3000 Hz_40ms_modulation_mae_db": 0.9386504657806766, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3605489796302492, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1603237627106619, "3000–6000 Hz_10ms_envelope_correlation": 0.9797893634791738, "3000–6000 Hz_10ms_modulation_mae_db": 0.23500197373516488, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8262147064541857, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08456274399346793, "3000–6000 Hz_40ms_envelope_correlation": 0.9940155872231993, "3000–6000 Hz_40ms_modulation_mae_db": 0.35804743016640517, "mr_stft_db": 6.034381097018681, "band_mae_db": 0.4752219146816633, "rms_gain_error_db": 0.06103821098356589, "output_peak": 0.036936445093326165}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3691132401902673, "全帯域_10ms_rms_envelope_nrmse": 0.11772215323676151, "全帯域_10ms_envelope_correlation": 0.9878285905717158, "全帯域_10ms_modulation_mae_db": 0.2542855776633108, "全帯域_40ms_log_rms_mae_db": 0.7344221504771506, "全帯域_40ms_rms_envelope_nrmse": 0.06608705136209996, "全帯域_40ms_envelope_correlation": 0.9959336534803699, "全帯域_40ms_modulation_mae_db": 0.057361323034871105, "300–1000 Hz_10ms_log_rms_mae_db": 2.2176444160496795, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2436470401823534, "300–1000 Hz_10ms_envelope_correlation": 0.9491098927261004, "300–1000 Hz_10ms_modulation_mae_db": 0.20390267767868928, "300–1000 Hz_40ms_log_rms_mae_db": 1.5635569243443905, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13353901277247063, "300–1000 Hz_40ms_envelope_correlation": 0.9844195877852082, "300–1000 Hz_40ms_modulation_mae_db": 0.9552157294830548, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5565548470343715, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17390225933617146, "1000–3000 Hz_10ms_envelope_correlation": 0.97695830680117, "1000–3000 Hz_10ms_modulation_mae_db": 0.8297369094065941, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8911834411641602, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09900106974099901, "1000–3000 Hz_40ms_envelope_correlation": 0.9919964365929933, "1000–3000 Hz_40ms_modulation_mae_db": 0.3905784829221333, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3695282000688627, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14913825983652215, "3000–6000 Hz_10ms_envelope_correlation": 0.9831622429410606, "3000–6000 Hz_10ms_modulation_mae_db": 0.3718503717363512, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8677985719586196, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08719200752260717, "3000–6000 Hz_40ms_envelope_correlation": 0.9939796837854405, "3000–6000 Hz_40ms_modulation_mae_db": 0.8064660408273573, "mr_stft_db": 6.038502621725769, "band_mae_db": 0.46279727748095567, "rms_gain_error_db": 0.08911089067816927, "output_peak": 0.03399135858243083}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3888313853214815, "全帯域_10ms_rms_envelope_nrmse": 0.11828657713827656, "全帯域_10ms_envelope_correlation": 0.9875563030818151, "全帯域_10ms_modulation_mae_db": 0.753891683326181, "全帯域_40ms_log_rms_mae_db": 0.7607139745288304, "全帯域_40ms_rms_envelope_nrmse": 0.063926113245979, "全帯域_40ms_envelope_correlation": 0.9963396933973749, "全帯域_40ms_modulation_mae_db": 0.8778280812785777, "300–1000 Hz_10ms_log_rms_mae_db": 2.2784940374059373, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27895461841736013, "300–1000 Hz_10ms_envelope_correlation": 0.9417711744311839, "300–1000 Hz_10ms_modulation_mae_db": 0.7912030733916032, "300–1000 Hz_40ms_log_rms_mae_db": 1.6153526989753697, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1856200584901531, "300–1000 Hz_40ms_envelope_correlation": 0.9758865595248833, "300–1000 Hz_40ms_modulation_mae_db": 0.631514572332784, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5067943071845356, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19151507619665106, "1000–3000 Hz_10ms_envelope_correlation": 0.9716431536549601, "1000–3000 Hz_10ms_modulation_mae_db": 0.6512507229569219, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8811418112056113, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1006069966922805, "1000–3000 Hz_40ms_envelope_correlation": 0.9918475065639519, "1000–3000 Hz_40ms_modulation_mae_db": 0.9832358321958358, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3326420630791735, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14122581845293067, "3000–6000 Hz_10ms_envelope_correlation": 0.9847194550210991, "3000–6000 Hz_10ms_modulation_mae_db": 1.0840172088872995, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7806984548303985, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08440863380603304, "3000–6000 Hz_40ms_envelope_correlation": 0.9946756756377367, "3000–6000 Hz_40ms_modulation_mae_db": 1.5750994535810763, "mr_stft_db": 6.031815793432206, "band_mae_db": 0.49256546421714775, "rms_gain_error_db": -0.1472118573054526, "output_peak": 0.03409571140405021}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.388522302933217, "全帯域_10ms_rms_envelope_nrmse": 0.13210399829601188, "全帯域_10ms_envelope_correlation": 0.9843944759065337, "全帯域_10ms_modulation_mae_db": 0.0844348107556681, "全帯域_40ms_log_rms_mae_db": 0.7646829917076542, "全帯域_40ms_rms_envelope_nrmse": 0.07857112322211267, "全帯域_40ms_envelope_correlation": 0.9940416754670559, "全帯域_40ms_modulation_mae_db": 0.16275679718022731, "300–1000 Hz_10ms_log_rms_mae_db": 2.3282182619179563, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27223002887429837, "300–1000 Hz_10ms_envelope_correlation": 0.9358033860518312, "300–1000 Hz_10ms_modulation_mae_db": 0.6618644331621643, "300–1000 Hz_40ms_log_rms_mae_db": 1.669335767799093, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17208589959242915, "300–1000 Hz_40ms_envelope_correlation": 0.9726088398252245, "300–1000 Hz_40ms_modulation_mae_db": 0.3552977216741799, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6123096777071801, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1930028635971775, "1000–3000 Hz_10ms_envelope_correlation": 0.9712000410176034, "1000–3000 Hz_10ms_modulation_mae_db": 0.4795431025398029, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9973322068982404, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1188166150089085, "1000–3000 Hz_40ms_envelope_correlation": 0.9883297455322191, "1000–3000 Hz_40ms_modulation_mae_db": 0.1630967726967187, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3449283262328031, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16137161395186894, "3000–6000 Hz_10ms_envelope_correlation": 0.9796293107323871, "3000–6000 Hz_10ms_modulation_mae_db": 0.2906616646483862, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8007155661676653, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0829647272245663, "3000–6000 Hz_40ms_envelope_correlation": 0.9942176829503783, "3000–6000 Hz_40ms_modulation_mae_db": 0.5877727640757223, "mr_stft_db": 6.051213599174528, "band_mae_db": 0.38531188247395337, "rms_gain_error_db": -0.0035451003787285926, "output_peak": 0.04474485563132298}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.353743819281465, "全帯域_10ms_rms_envelope_nrmse": 0.12189568822220935, "全帯域_10ms_envelope_correlation": 0.9866684181207349, "全帯域_10ms_modulation_mae_db": 0.27154218708406935, "全帯域_40ms_log_rms_mae_db": 0.7476848733844538, "全帯域_40ms_rms_envelope_nrmse": 0.06225546228023154, "全帯域_40ms_envelope_correlation": 0.9963304807290806, "全帯域_40ms_modulation_mae_db": 0.5706923677334507, "300–1000 Hz_10ms_log_rms_mae_db": 2.256826107119716, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2818327574484712, "300–1000 Hz_10ms_envelope_correlation": 0.9355789375413195, "300–1000 Hz_10ms_modulation_mae_db": 0.46609044664798543, "300–1000 Hz_40ms_log_rms_mae_db": 1.611668619992481, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15356369964446986, "300–1000 Hz_40ms_envelope_correlation": 0.9820485184438421, "300–1000 Hz_40ms_modulation_mae_db": 0.8271158191309403, "1000–3000 Hz_10ms_log_rms_mae_db": 1.581481729187844, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18705150009708366, "1000–3000 Hz_10ms_envelope_correlation": 0.973593662456821, "1000–3000 Hz_10ms_modulation_mae_db": 0.39728041338078635, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9820080216055003, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1017227182318833, "1000–3000 Hz_40ms_envelope_correlation": 0.9917534036588957, "1000–3000 Hz_40ms_modulation_mae_db": 0.3948388480319371, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3972356911510035, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16789882679857482, "3000–6000 Hz_10ms_envelope_correlation": 0.977784920834097, "3000–6000 Hz_10ms_modulation_mae_db": 0.4013453247411302, "3000–6000 Hz_40ms_log_rms_mae_db": 0.840158496495249, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09154388177725774, "3000–6000 Hz_40ms_envelope_correlation": 0.9930902441011705, "3000–6000 Hz_40ms_modulation_mae_db": 0.7103965529345277, "mr_stft_db": 6.037600831401666, "band_mae_db": 0.4278020202053932, "rms_gain_error_db": -0.050311698025241394, "output_peak": 0.038495176673617466}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.45398555340664, "全帯域_10ms_rms_envelope_nrmse": 0.1306325462094762, "全帯域_10ms_envelope_correlation": 0.9849351089709444, "全帯域_10ms_modulation_mae_db": 1.0698482136343417, "全帯域_40ms_log_rms_mae_db": 0.8067263214931286, "全帯域_40ms_rms_envelope_nrmse": 0.06982730569425272, "全帯域_40ms_envelope_correlation": 0.9958666634599511, "全帯域_40ms_modulation_mae_db": 1.5866127663869822, "300–1000 Hz_10ms_log_rms_mae_db": 2.1479464462411695, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24884712890187488, "300–1000 Hz_10ms_envelope_correlation": 0.948462996877966, "300–1000 Hz_10ms_modulation_mae_db": 0.7051307592806925, "300–1000 Hz_40ms_log_rms_mae_db": 1.5294538544591199, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14165951614638764, "300–1000 Hz_40ms_envelope_correlation": 0.9835584923811147, "300–1000 Hz_40ms_modulation_mae_db": 0.6846575683561523, "1000–3000 Hz_10ms_log_rms_mae_db": 1.665991568359824, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20474643246033414, "1000–3000 Hz_10ms_envelope_correlation": 0.9675324077069292, "1000–3000 Hz_10ms_modulation_mae_db": 1.1452983460422113, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0218539444451662, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10711721121318711, "1000–3000 Hz_40ms_envelope_correlation": 0.9907191457791299, "1000–3000 Hz_40ms_modulation_mae_db": 1.7176482468091772, "3000–6000 Hz_10ms_log_rms_mae_db": 1.367025402890585, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15057363627368045, "3000–6000 Hz_10ms_envelope_correlation": 0.9821895016185448, "3000–6000 Hz_10ms_modulation_mae_db": 0.5560229499438657, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8486643555353416, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08034152788447674, "3000–6000 Hz_40ms_envelope_correlation": 0.9947328770322794, "3000–6000 Hz_40ms_modulation_mae_db": 0.8734870443128403, "mr_stft_db": 6.036577267234056, "band_mae_db": 0.44924201275548886, "rms_gain_error_db": -0.2290183088974942, "output_peak": 0.034134690253150114}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3851149355622248, "全帯域_10ms_rms_envelope_nrmse": 0.13284034725466962, "全帯域_10ms_envelope_correlation": 0.9843703551459447, "全帯域_10ms_modulation_mae_db": 0.5281662518457885, "全帯域_40ms_log_rms_mae_db": 0.6960574509451765, "全帯域_40ms_rms_envelope_nrmse": 0.0643691065200735, "全帯域_40ms_envelope_correlation": 0.9960853743874258, "全帯域_40ms_modulation_mae_db": 0.7695478088126356, "300–1000 Hz_10ms_log_rms_mae_db": 2.3168179278387595, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25799512483272374, "300–1000 Hz_10ms_envelope_correlation": 0.9441335413088396, "300–1000 Hz_10ms_modulation_mae_db": 0.5823887972555047, "300–1000 Hz_40ms_log_rms_mae_db": 1.6892792293352497, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14826406146335977, "300–1000 Hz_40ms_envelope_correlation": 0.9814248600592589, "300–1000 Hz_40ms_modulation_mae_db": 0.6830770546647265, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6210897962102448, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19528214772936525, "1000–3000 Hz_10ms_envelope_correlation": 0.970668365379992, "1000–3000 Hz_10ms_modulation_mae_db": 0.5226280495909905, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9789576856371451, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09876915333007424, "1000–3000 Hz_40ms_envelope_correlation": 0.9919739475843187, "1000–3000 Hz_40ms_modulation_mae_db": 0.876452593656326, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3394056172998816, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15434350478700753, "3000–6000 Hz_10ms_envelope_correlation": 0.9816397016187721, "3000–6000 Hz_10ms_modulation_mae_db": 0.6709379126276911, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7844572873508511, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07685953465427815, "3000–6000 Hz_40ms_envelope_correlation": 0.9951714044992327, "3000–6000 Hz_40ms_modulation_mae_db": 0.8278262266891385, "mr_stft_db": 6.020194634893701, "band_mae_db": 0.34405560019979947, "rms_gain_error_db": 0.059881170845644476, "output_peak": 0.03577619406924306}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 109060, "output_samples": 109060, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.148501113493451, "spectral_convergence": 0.6254789538981459, "spectral_convergence_status": "ok", "amplitude_floor": 7.347807435362163e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.89348160856993, "spectral_convergence": 0.6157455409360384, "spectral_convergence_status": "ok", "amplitude_floor": 3.5954742817466214e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.085803837291109, "spectral_convergence": 0.6423547535372304, "spectral_convergence_status": "ok", "amplitude_floor": 1.4970646531776498e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.2516812561146785e-07, "output_power": 1.0640717423788058e-07, "delta_db": -0.705228385683072, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 8.469209703610174e-08, "output_power": 1.1654253953888175e-07, "delta_db": 1.3864159098310747, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 4.7196494133004234e-07, "output_power": 5.048271957526745e-07, "delta_db": 0.2923300350932988, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.5661034348838578e-06, "output_power": 1.5310327971990764e-06, "delta_db": -0.09835947998863456, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2294550474819316e-06, "output_power": 1.3289241379013154e-06, "delta_db": 0.33787535525682816, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.3429464378207576e-06, "output_power": 3.372254738942509e-06, "delta_db": 0.03790955456628304, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.563896615059082e-07, "output_power": 1.092489337519463e-06, "delta_db": 0.5778233425337674, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.49084886613613693, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.1513309440558212, "pitch": null, "output_rms_dbfs": -50.94070457288915, "output_peak": 0.032558573096669895, "reference_rms_dbfs": -51.09203551694498, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.04259551978483}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 109060, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 1.1882865623804307e-05, "log_rms_mae_db": 1.4026299435635385, "rms_envelope_nrmse": 0.13087807758126258, "envelope_correlation": 0.9852474151122443, "rms_gain_error_db": 0.15129208906184832, "reference_mean_power": 7.792370026271951e-06, "output_mean_power": 8.068610964268597e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 4.121961515330987e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7941587942139734e-06, "output_power": 1.7472358315834812e-06, "reference_active": true, "delta_db": -0.115093507263569}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1263612266386524e-07, "output_power": 2.904295183376173e-07, "reference_active": true, "delta_db": -0.31998401331225557}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9590349245364564e-07, "output_power": 1.6394593704757452e-07, "reference_active": true, "delta_db": -0.7734152007768075}], "active_band_count": 3, "active_band_mae_db": 0.402830907117544}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 9.239390922709503e-06, "log_rms_mae_db": 0.6979695325753604, "rms_envelope_nrmse": 0.06782763453992004, "envelope_correlation": 0.9959554373023489, "rms_gain_error_db": 0.1512894443955467, "reference_mean_power": 7.844041250222317e-06, "output_mean_power": 8.122108996511787e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 3.7692280722089195e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6572550629104971e-06, "output_power": 1.6124094375786534e-06, "reference_active": true, "delta_db": -0.11914023006824191}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5392861690297655e-07, "output_power": 1.3116235537619908e-07, "reference_active": true, "delta_db": -0.695101601162069}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6336932951152273e-08, "output_power": 1.1907653152388703e-08, "reference_active": true, "delta_db": -1.3734435067586528}], "active_band_count": 3, "active_band_mae_db": 0.7292284459963212}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 2.9307310026633354e-06, "log_rms_mae_db": 2.215120573212329, "rms_envelope_nrmse": 0.28164253365482766, "envelope_correlation": 0.9343765587115044, "rms_gain_error_db": 0.5402455027927164, "reference_mean_power": 4.2741366364654595e-07, "output_mean_power": 4.840307490178747e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 2.4398860779830526e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.615850373422058e-08, "output_power": 1.0522268416253408e-07, "reference_active": true, "delta_db": 0.39121679262566555}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8718875021930722e-08, "output_power": 2.5639036480549796e-08, "reference_active": true, "delta_db": 1.3662195559264745}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0143942568188046e-08, "output_power": 2.0807484678059107e-08, "reference_active": true, "delta_db": 0.14075108943948295}], "active_band_count": 3, "active_band_mae_db": 0.6327291459972076}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 1.736089681183382e-06, "log_rms_mae_db": 1.6100863550079083, "rms_envelope_nrmse": 0.17428509171206763, "envelope_correlation": 0.974400422780811, "rms_gain_error_db": 0.5401748077586117, "reference_mean_power": 4.3025101883138276e-07, "output_mean_power": 4.872360213368199e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 2.1733905138014183e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.047483464267491e-08, "output_power": 9.941836967410482e-08, "reference_active": true, "delta_db": 0.4093883898532039}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.338915747949155e-09, "output_power": 1.2428317696569938e-08, "reference_active": true, "delta_db": 1.241158889124755}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.438276742938052e-09, "output_power": 1.14842970314487e-09, "reference_active": true, "delta_db": -0.9773804130720305}], "active_band_count": 3, "active_band_mae_db": 0.8759758973499965}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 7.246614216836824e-06, "log_rms_mae_db": 1.5609040383212778, "rms_envelope_nrmse": 0.18297488540963375, "envelope_correlation": 0.9744006495295309, "rms_gain_error_db": -0.020354581025167576, "reference_mean_power": 1.7870157226185334e-06, "output_mean_power": 1.7786599060398781e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.838724239404773e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.063249741710556e-07, "output_power": 6.221741117119653e-07, "reference_active": true, "delta_db": -0.5509262584728546}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.654737664402428e-07, "output_power": 1.1569314540005582e-07, "reference_active": true, "delta_db": -1.5542152364302826}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2023841152792083e-07, "output_power": 1.036636525266896e-07, "reference_active": true, "delta_db": -0.6441672326461942}], "active_band_count": 3, "active_band_mae_db": 0.9164362425164438}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.77385839866885e-06, "log_rms_mae_db": 0.938999056235128, "rms_envelope_nrmse": 0.11178880486691684, "envelope_correlation": 0.9898969531148976, "rms_gain_error_db": -0.0203559195757472, "reference_mean_power": 1.7989086732437154e-06, "output_mean_power": 1.7904966951639528e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 1.713692894624548e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.664518497859096e-07, "output_power": 5.835669615895112e-07, "reference_active": true, "delta_db": -0.576780812056314}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.184085944051966e-08, "output_power": 5.745055782600867e-08, "reference_active": true, "delta_db": -1.5367593151050694}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1933830695482323e-08, "output_power": 8.863362650967656e-09, "reference_active": true, "delta_db": -1.2918135309850853}], "active_band_count": 3, "active_band_mae_db": 1.135117886048823}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 6.060487704579714e-06, "log_rms_mae_db": 1.446335196323993, "rms_envelope_nrmse": 0.16832657589806962, "envelope_correlation": 0.9783088426193637, "rms_gain_error_db": 0.10932576950441918, "reference_mean_power": 1.7907615060268857e-06, "output_mean_power": 1.8364128678261981e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.036723230359137e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.741355867444106e-07, "output_power": 4.864373431576503e-07, "reference_active": true, "delta_db": 0.11124354792237995}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0977135221440419e-07, "output_power": 1.3068581389926584e-07, "reference_active": true, "delta_db": 0.7573943287588738}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0575338351673974e-08, "output_power": 3.2165405420581336e-08, "reference_active": true, "delta_db": 0.22017758015618724}], "active_band_count": 3, "active_band_mae_db": 0.36293848561248027}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.330101975711502e-06, "log_rms_mae_db": 0.8699108791695346, "rms_envelope_nrmse": 0.08082191391162304, "envelope_correlation": 0.9947305271401391, "rms_gain_error_db": 0.10932530010474897, "reference_mean_power": 1.8026836617488875e-06, "output_mean_power": 1.8486387517866643e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 9.630136220520234e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.5232190822756626e-07, "output_power": 4.7177593891843697e-07, "reference_active": true, "delta_db": 0.18288164303650156}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.528340255264933e-08, "output_power": 6.535847149097059e-08, "reference_active": true, "delta_db": 0.7270712208619321}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3355698674413927e-09, "output_power": 2.105559901171518e-09, "reference_active": true, "delta_db": -0.4502526233126767}], "active_band_count": 3, "active_band_mae_db": 0.4534018290703701}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5434845239485123, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "e273d538d45c5e69c51a8da0ac3fa0fa001a22847dfc2ce4606fffb388baf583", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9720737302426423, "standard_deviation": 0.002861643660229915, "minimum": 0.9675324077069292, "maximum": 0.97695830680117, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.590151449700811, "standard_deviation": 0.0491065807217828, "minimum": 1.5067943071845356, "maximum": 1.665991568359824, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7171605654178794, "standard_deviation": 0.25149120817392956, "minimum": 0.39728041338078635, "maximum": 1.1452983460422113, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1904381053157752, "standard_deviation": 0.009239792123466614, "minimum": 0.17390225933617146, "maximum": 0.20474643246033414, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9910618465262448, "standard_deviation": 0.0013404882781510388, "minimum": 0.9883297455322191, "maximum": 0.9919964365929933, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.9560975082075466, "standard_deviation": 0.04977686891076869, "minimum": 0.8811418112056113, "maximum": 1.0218539444451662, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8249523910177035, "standard_deviation": 0.4993528536988118, "minimum": 0.1630967726967187, "maximum": 1.7176482468091772, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10464850034920868, "standard_deviation": 0.007339510442211789, "minimum": 0.09876915333007424, "maximum": 0.1188166150089085, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9809029173580623, "standard_deviation": 0.0024255150875958542, "minimum": 0.977784920834097, "maximum": 0.9847194550210991, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.369706184584569, "standard_deviation": 0.037084397159427254, "minimum": 1.3326420630791735, "maximum": 1.446335196323993, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.49659698649154616, "standard_deviation": 0.27576626247492236, "minimum": 0.23500197373516488, "maximum": 1.0840172088872995, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15665024983866452, "standard_deviation": 0.009526222698393729, "minimum": 0.14122581845293067, "maximum": 0.16832657589806962, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.994326710296197, "standard_deviation": 0.0006460080877963543, "minimum": 0.9930902441011705, "maximum": 0.9951714044992327, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8273272897452306, "standard_deviation": 0.0354415092382682, "minimum": 0.7806984548303985, "maximum": 0.8699108791695346, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7740621677071797, "standard_deviation": 0.37227773647318946, "minimum": 0.35804743016640517, "maximum": 1.5750994535810763, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08358687134678877, "standard_deviation": 0.00450015886844345, "minimum": 0.07685953465427815, "maximum": 0.09154388177725774, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9416873310903915, "standard_deviation": 0.005843255763564007, "minimum": 0.9343765587115044, "maximum": 0.9491098927261004, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.2605765276538596, "standard_deviation": 0.0639570243942129, "minimum": 2.1479464462411695, "maximum": 2.3282182619179563, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6480933128952353, "standard_deviation": 0.2678738998173579, "minimum": 0.20390267767868928, "maximum": 1.1414371697480354, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2660622643783035, "standard_deviation": 0.014961625674081599, "minimum": 0.2436470401823534, "maximum": 0.2818327574484712, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9795645357909668, "standard_deviation": 0.004543672788852156, "minimum": 0.9726088398252245, "maximum": 0.9844195877852082, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.6107082579038703, "standard_deviation": 0.05161499931356975, "minimum": 1.5294538544591199, "maximum": 1.6892792293352497, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7443815886945053, "standard_deviation": 0.19971227268548977, "minimum": 0.3552977216741799, "maximum": 0.9552157294830548, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15767620124956633, "standard_deviation": 0.017876212637744263, "minimum": 0.13353901277247063, "maximum": 0.1856200584901531, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.44098062976881736, "standard_deviation": 0.05282270187623447, "minimum": 0.34405560019979947, "maximum": 0.49256546421714775, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.036610170583179, "standard_deviation": 0.008872695094641569, "minimum": 6.020194634893701, "maximum": 6.051213599174528, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.03634162560047634, "standard_deviation": 0.003885421759220928, "minimum": 0.032558573096669895, "maximum": 0.04474485563132298, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.008590718505464494, "standard_deviation": 0.1277426940427786, "minimum": -0.2290183088974942, "maximum": 0.1513309440558212, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9860340130949049, "standard_deviation": 0.0014517837062091865, "minimum": 0.9843703551459447, "maximum": 0.9878285905717158, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.3894601716175488, "standard_deviation": 0.029985465562118216, "minimum": 1.353743819281465, "maximum": 1.45398555340664, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.47316844584658757, "standard_deviation": 0.31288316234538266, "minimum": 0.0844348107556681, "maximum": 1.0698482136343417, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.12553634748967668, "standard_deviation": 0.006647002542453218, "minimum": 0.11772215323676151, "maximum": 0.13284034725466962, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9959649953186622, "standard_deviation": 0.0008818121764022329, "minimum": 0.9940416754670559, "maximum": 0.9971669843256913, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.7369478604173144, "standard_deviation": 0.041366769792446016, "minimum": 0.6873255882267612, "maximum": 0.8067263214931286, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6759750285266859, "standard_deviation": 0.46892746783484907, "minimum": 0.057361323034871105, "maximum": 1.5866127663869822, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.06596824370604176, "standard_deviation": 0.006767676067351501, "minimum": 0.054882152783664796, "maximum": 0.07857112322211267, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs004_whisper10_BASIC5000_0074", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 1.8526911735534668, "predicted_mos": 1.8526911735534668, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 109060, "input_sample_rate": 24000, "input_seconds": 4.5441666666666665, "input_float32_sha256": "81b95562be840d0bac784b2f3f385a02896cda7abe5ad4f7c2125c2f7ed36616", "internal_samples": 72707, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.265349700115621}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3878734105554997, "全帯域_10ms_rms_envelope_nrmse": 0.12036259171805015, "全帯域_10ms_envelope_correlation": 0.9871894361117485, "全帯域_10ms_modulation_mae_db": 0.8359106699553163, "全帯域_40ms_log_rms_mae_db": 0.7211349653354004, "全帯域_40ms_rms_envelope_nrmse": 0.058867691270828276, "全帯域_40ms_envelope_correlation": 0.9970819571505088, "全帯域_40ms_modulation_mae_db": 1.073729502282197, "300–1000 Hz_10ms_log_rms_mae_db": 2.1060406505886977, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2551491715008558, "300–1000 Hz_10ms_envelope_correlation": 0.9418647121765679, "300–1000 Hz_10ms_modulation_mae_db": 0.8665223468984387, "300–1000 Hz_40ms_log_rms_mae_db": 1.3782915116767647, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1441792865396848, "300–1000 Hz_40ms_envelope_correlation": 0.980003574462822, "300–1000 Hz_40ms_modulation_mae_db": 1.3074195030614666, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4845891276127365, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18187898607693423, "1000–3000 Hz_10ms_envelope_correlation": 0.9745311713136731, "1000–3000 Hz_10ms_modulation_mae_db": 0.8625206552257, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8473008016692817, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08790011610959708, "1000–3000 Hz_40ms_envelope_correlation": 0.9939994934678911, "1000–3000 Hz_40ms_modulation_mae_db": 1.0957603618198168, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2797427605899698, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.140389697346466, "3000–6000 Hz_10ms_envelope_correlation": 0.9845274631990382, "3000–6000 Hz_10ms_modulation_mae_db": 0.33201307133453434, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7038999607637624, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06947787197955722, "3000–6000 Hz_40ms_envelope_correlation": 0.9960499194507464, "3000–6000 Hz_40ms_modulation_mae_db": 0.6260643626259025, "mr_stft_db": 5.9688577170874035, "band_mae_db": 0.30677150705814243, "rms_gain_error_db": -0.17923687337048702, "output_peak": 0.03188374978043131}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3647603609565546, "全帯域_10ms_rms_envelope_nrmse": 0.12070871114130236, "全帯域_10ms_envelope_correlation": 0.9869648955835421, "全帯域_10ms_modulation_mae_db": 0.3767816829936324, "全帯域_40ms_log_rms_mae_db": 0.7125567020554553, "全帯域_40ms_rms_envelope_nrmse": 0.05832877790229367, "全帯域_40ms_envelope_correlation": 0.9967195725452758, "全帯域_40ms_modulation_mae_db": 0.7217207777640021, "300–1000 Hz_10ms_log_rms_mae_db": 2.054200940182124, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25135071486308813, "300–1000 Hz_10ms_envelope_correlation": 0.9502859575040614, "300–1000 Hz_10ms_modulation_mae_db": 0.7532764813745364, "300–1000 Hz_40ms_log_rms_mae_db": 1.4005389445267784, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1443041135303442, "300–1000 Hz_40ms_envelope_correlation": 0.9851309811982131, "300–1000 Hz_40ms_modulation_mae_db": 0.5296325518466451, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4361100747105033, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19054199104161923, "1000–3000 Hz_10ms_envelope_correlation": 0.9719998709498006, "1000–3000 Hz_10ms_modulation_mae_db": 0.6284934687531266, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7822810247140924, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09277076414221616, "1000–3000 Hz_40ms_envelope_correlation": 0.9929332557546844, "1000–3000 Hz_40ms_modulation_mae_db": 1.1960029827693723, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2237348660261065, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15056402339616845, "3000–6000 Hz_10ms_envelope_correlation": 0.9821842474552154, "3000–6000 Hz_10ms_modulation_mae_db": 0.20250968293441707, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6683332691175674, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07574958004808044, "3000–6000 Hz_40ms_envelope_correlation": 0.9952656247865457, "3000–6000 Hz_40ms_modulation_mae_db": 0.42964419488967476, "mr_stft_db": 5.965125253580549, "band_mae_db": 0.36038879521151956, "rms_gain_error_db": 0.012164225696741998, "output_peak": 0.03611620753742255}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3402336330842755, "全帯域_10ms_rms_envelope_nrmse": 0.11960808587148881, "全帯域_10ms_envelope_correlation": 0.9872119652729013, "全帯域_10ms_modulation_mae_db": 0.9148407464326302, "全帯域_40ms_log_rms_mae_db": 0.657347294007683, "全帯域_40ms_rms_envelope_nrmse": 0.06161860155856395, "全帯域_40ms_envelope_correlation": 0.9963451942353972, "全帯域_40ms_modulation_mae_db": 1.3834985554171153, "300–1000 Hz_10ms_log_rms_mae_db": 2.0337163506657285, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24964979629374545, "300–1000 Hz_10ms_envelope_correlation": 0.9491736471211363, "300–1000 Hz_10ms_modulation_mae_db": 0.45886070596613, "300–1000 Hz_40ms_log_rms_mae_db": 1.3370878563983786, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14396435233086402, "300–1000 Hz_40ms_envelope_correlation": 0.9838391791892983, "300–1000 Hz_40ms_modulation_mae_db": 0.697755230491682, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5117447919722462, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2058310415374911, "1000–3000 Hz_10ms_envelope_correlation": 0.9680590329314102, "1000–3000 Hz_10ms_modulation_mae_db": 1.3970418904198556, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8491783106056014, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11841576274123647, "1000–3000 Hz_40ms_envelope_correlation": 0.9904867561768039, "1000–3000 Hz_40ms_modulation_mae_db": 1.9230881624900782, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3139037605161854, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1400416530968896, "3000–6000 Hz_10ms_envelope_correlation": 0.9846041417998116, "3000–6000 Hz_10ms_modulation_mae_db": 0.5860496782891124, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7221900800605132, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06920133046930427, "3000–6000 Hz_40ms_envelope_correlation": 0.9960357582154522, "3000–6000 Hz_40ms_modulation_mae_db": 1.0586030030876243, "mr_stft_db": 5.984619182685079, "band_mae_db": 0.41651462294778935, "rms_gain_error_db": 0.01380781442125905, "output_peak": 0.03774937347494016}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3350201804897666, "全帯域_10ms_rms_envelope_nrmse": 0.11908036310728377, "全帯域_10ms_envelope_correlation": 0.9873289574393994, "全帯域_10ms_modulation_mae_db": 1.180938171895504, "全帯域_40ms_log_rms_mae_db": 0.7372580159467235, "全帯域_40ms_rms_envelope_nrmse": 0.06103792465987277, "全帯域_40ms_envelope_correlation": 0.99658566407923, "全帯域_40ms_modulation_mae_db": 1.4580477516973014, "300–1000 Hz_10ms_log_rms_mae_db": 2.1000345131561535, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.257232090242254, "300–1000 Hz_10ms_envelope_correlation": 0.9444217251994383, "300–1000 Hz_10ms_modulation_mae_db": 1.0495728639886248, "300–1000 Hz_40ms_log_rms_mae_db": 1.382954036532089, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14638269026974124, "300–1000 Hz_40ms_envelope_correlation": 0.9819750981969424, "300–1000 Hz_40ms_modulation_mae_db": 1.0840438537680912, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5047064201598153, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1791968146033592, "1000–3000 Hz_10ms_envelope_correlation": 0.9754407707394114, "1000–3000 Hz_10ms_modulation_mae_db": 1.3351642910766002, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8502113184245177, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0994006957800435, "1000–3000 Hz_40ms_envelope_correlation": 0.992548360023112, "1000–3000 Hz_40ms_modulation_mae_db": 1.7257520901604197, "3000–6000 Hz_10ms_log_rms_mae_db": 1.29035129928501, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1493314679488199, "3000–6000 Hz_10ms_envelope_correlation": 0.9826135458304753, "3000–6000 Hz_10ms_modulation_mae_db": 0.1615036869361091, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6991428557239349, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07200801278386118, "3000–6000 Hz_40ms_envelope_correlation": 0.9956900594338893, "3000–6000 Hz_40ms_modulation_mae_db": 0.4537405674519575, "mr_stft_db": 5.975816751857464, "band_mae_db": 0.3927165268531496, "rms_gain_error_db": -0.1311108571219583, "output_peak": 0.02865774707683794}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4019357914092667, "全帯域_10ms_rms_envelope_nrmse": 0.11048469512928069, "全帯域_10ms_envelope_correlation": 0.9890809663863886, "全帯域_10ms_modulation_mae_db": 0.3187960521202115, "全帯域_40ms_log_rms_mae_db": 0.7073409666509378, "全帯域_40ms_rms_envelope_nrmse": 0.05366027828450248, "全帯域_40ms_envelope_correlation": 0.9972207973540884, "全帯域_40ms_modulation_mae_db": 0.4990104877118715, "300–1000 Hz_10ms_log_rms_mae_db": 2.1413923816075027, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25969874297812906, "300–1000 Hz_10ms_envelope_correlation": 0.9383904455606991, "300–1000 Hz_10ms_modulation_mae_db": 0.4558898927896602, "300–1000 Hz_40ms_log_rms_mae_db": 1.4662877630319748, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1586517542022228, "300–1000 Hz_40ms_envelope_correlation": 0.9746199281648722, "300–1000 Hz_40ms_modulation_mae_db": 0.6271320499295848, "1000–3000 Hz_10ms_log_rms_mae_db": 1.448318545377412, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1676968802101635, "1000–3000 Hz_10ms_envelope_correlation": 0.9784838963669353, "1000–3000 Hz_10ms_modulation_mae_db": 0.15322087675214252, "1000–3000 Hz_40ms_log_rms_mae_db": 0.760171363287833, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08563993123023872, "1000–3000 Hz_40ms_envelope_correlation": 0.9940166167938934, "1000–3000 Hz_40ms_modulation_mae_db": 0.14788859374997726, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2316630069615826, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14168020691856772, "3000–6000 Hz_10ms_envelope_correlation": 0.9853566507094095, "3000–6000 Hz_10ms_modulation_mae_db": 0.7106976984616539, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6832176567850834, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07314600794685396, "3000–6000 Hz_40ms_envelope_correlation": 0.9962770505830281, "3000–6000 Hz_40ms_modulation_mae_db": 0.9691201935506181, "mr_stft_db": 5.9746933303181615, "band_mae_db": 0.3813174759402677, "rms_gain_error_db": 0.0059040200800394, "output_peak": 0.03165408334859786}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3270863690340402, "全帯域_10ms_rms_envelope_nrmse": 0.11981750548046248, "全帯域_10ms_envelope_correlation": 0.987126987219468, "全帯域_10ms_modulation_mae_db": 1.2232244815352258, "全帯域_40ms_log_rms_mae_db": 0.6865121607796116, "全帯域_40ms_rms_envelope_nrmse": 0.05898148379203703, "全帯域_40ms_envelope_correlation": 0.9967622723426842, "全帯域_40ms_modulation_mae_db": 1.525044692951159, "300–1000 Hz_10ms_log_rms_mae_db": 2.0400909543472716, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24526398048965348, "300–1000 Hz_10ms_envelope_correlation": 0.9494030689272727, "300–1000 Hz_10ms_modulation_mae_db": 0.873697030913025, "300–1000 Hz_40ms_log_rms_mae_db": 1.3429152876488104, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14778881782849146, "300–1000 Hz_40ms_envelope_correlation": 0.9813962556051585, "300–1000 Hz_40ms_modulation_mae_db": 1.0911313909046296, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4945679436400388, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1995177787463761, "1000–3000 Hz_10ms_envelope_correlation": 0.9699605343304186, "1000–3000 Hz_10ms_modulation_mae_db": 1.697376145840628, "1000–3000 Hz_40ms_log_rms_mae_db": 0.835209745507766, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10679428342423898, "1000–3000 Hz_40ms_envelope_correlation": 0.9924380766758346, "1000–3000 Hz_40ms_modulation_mae_db": 2.163812072292051, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2486055024662175, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13501582357292333, "3000–6000 Hz_10ms_envelope_correlation": 0.9857368425413869, "3000–6000 Hz_10ms_modulation_mae_db": 0.3179673758391939, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6831678904585873, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07004883043613358, "3000–6000 Hz_40ms_envelope_correlation": 0.9958810414301731, "3000–6000 Hz_40ms_modulation_mae_db": 0.6388443480942251, "mr_stft_db": 5.973666382982401, "band_mae_db": 0.40872012172618305, "rms_gain_error_db": -0.11171565796165411, "output_peak": 0.03750972854802572}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4064478333747246, "全帯域_10ms_rms_envelope_nrmse": 0.12025618572034778, "全帯域_10ms_envelope_correlation": 0.9870052527354795, "全帯域_10ms_modulation_mae_db": 0.44195484653772144, "全帯域_40ms_log_rms_mae_db": 0.7435027457201556, "全帯域_40ms_rms_envelope_nrmse": 0.058992803993767, "全帯域_40ms_envelope_correlation": 0.9966404355463953, "全帯域_40ms_modulation_mae_db": 0.7676144964101718, "300–1000 Hz_10ms_log_rms_mae_db": 2.104466520176037, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2688366330308524, "300–1000 Hz_10ms_envelope_correlation": 0.9416458126114887, "300–1000 Hz_10ms_modulation_mae_db": 1.3166261533081949, "300–1000 Hz_40ms_log_rms_mae_db": 1.5052036405186255, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17252999826915813, "300–1000 Hz_40ms_envelope_correlation": 0.9758196542144084, "300–1000 Hz_40ms_modulation_mae_db": 1.1697329768928797, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4646446879024404, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19629987135953997, "1000–3000 Hz_10ms_envelope_correlation": 0.9701524548407976, "1000–3000 Hz_10ms_modulation_mae_db": 0.6072382131162464, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7929605128530123, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.091317334914959, "1000–3000 Hz_40ms_envelope_correlation": 0.9934282972888903, "1000–3000 Hz_40ms_modulation_mae_db": 0.9218860203261757, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2790306148776225, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1438108294972382, "3000–6000 Hz_10ms_envelope_correlation": 0.983816408466553, "3000–6000 Hz_10ms_modulation_mae_db": 0.5242471741450393, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7025250126254261, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06973761927293869, "3000–6000 Hz_40ms_envelope_correlation": 0.9959189445328906, "3000–6000 Hz_40ms_modulation_mae_db": 0.766000610051916, "mr_stft_db": 5.9762752473589815, "band_mae_db": 0.3333261288216698, "rms_gain_error_db": -0.03665911190078649, "output_peak": 0.03359046317047855}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.379737932121978, "全帯域_10ms_rms_envelope_nrmse": 0.1205878125263955, "全帯域_10ms_envelope_correlation": 0.9869951782491283, "全帯域_10ms_modulation_mae_db": 0.8003957103135381, "全帯域_40ms_log_rms_mae_db": 0.7055367314076042, "全帯域_40ms_rms_envelope_nrmse": 0.06533376409704438, "全帯域_40ms_envelope_correlation": 0.9960637663060192, "全帯域_40ms_modulation_mae_db": 1.2766997930168207, "300–1000 Hz_10ms_log_rms_mae_db": 1.992344339346764, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2390026808817912, "300–1000 Hz_10ms_envelope_correlation": 0.955484559896085, "300–1000 Hz_10ms_modulation_mae_db": 0.900732840686973, "300–1000 Hz_40ms_log_rms_mae_db": 1.4358164564352007, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1509333207465042, "300–1000 Hz_40ms_envelope_correlation": 0.9834676063493698, "300–1000 Hz_40ms_modulation_mae_db": 1.0724358050565514, "1000–3000 Hz_10ms_log_rms_mae_db": 1.487677141794461, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18725535841740357, "1000–3000 Hz_10ms_envelope_correlation": 0.9729679577736573, "1000–3000 Hz_10ms_modulation_mae_db": 1.0057338681914925, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8108787941096829, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09762599537185963, "1000–3000 Hz_40ms_envelope_correlation": 0.9926053557257769, "1000–3000 Hz_40ms_modulation_mae_db": 1.5356935941759062, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2700069074742164, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1500024557046837, "3000–6000 Hz_10ms_envelope_correlation": 0.9826135022616596, "3000–6000 Hz_10ms_modulation_mae_db": 0.15688301920379452, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6985191973620606, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08674870236427215, "3000–6000 Hz_40ms_envelope_correlation": 0.9938233353205871, "3000–6000 Hz_40ms_modulation_mae_db": 0.618347295736891, "mr_stft_db": 5.970082536221919, "band_mae_db": 0.42266264933530684, "rms_gain_error_db": -0.13289209199856844, "output_peak": 0.02891027661186187}, "full_scale": {"sample_count": 109060, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 109060, "output_samples": 109060, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.0938201625984885, "spectral_convergence": 0.6084672102767873, "spectral_convergence_status": "ok", "amplitude_floor": 7.347807435362163e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.794519441174402, "spectral_convergence": 0.6037081315709607, "spectral_convergence_status": "ok", "amplitude_floor": 3.5954742817466214e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.018233547489321, "spectral_convergence": 0.6410697954772346, "spectral_convergence_status": "ok", "amplitude_floor": 1.4970646531776498e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.2516812561146785e-07, "output_power": 1.221701224448334e-07, "delta_db": -0.10528739586607211, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 8.469209703610174e-08, "output_power": 1.0884203439151454e-07, "delta_db": 1.0895376424406713, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 4.7196494133004234e-07, "output_power": 4.780716349331881e-07, "delta_db": 0.055832373775466335, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.5661034348838578e-06, "output_power": 1.4447768356926064e-06, "delta_db": -0.35019672165491633, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2294550474819316e-06, "output_power": 1.2118345481827253e-06, "delta_db": -0.06269324637049066, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.3429464378207576e-06, "output_power": 3.203923739751868e-06, "delta_db": -0.1844724779211984, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.563896615059082e-07, "output_power": 8.926820531871546e-07, "delta_db": -0.2993806913781821, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.30677150705814243, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.17923687337048702, "pitch": null, "output_rms_dbfs": -51.27127239031546, "output_peak": 0.03188374978043131, "reference_rms_dbfs": -51.09203551694498, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.9688577170874035}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 109060, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 1.1882865623804307e-05, "log_rms_mae_db": 1.3878734105554997, "rms_envelope_nrmse": 0.12036259171805015, "envelope_correlation": 0.9871894361117485, "rms_gain_error_db": -0.17922162497406316, "reference_mean_power": 7.792370026271951e-06, "output_mean_power": 7.477344749728209e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 4.121961515330987e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7941587942139734e-06, "output_power": 1.6760685957071034e-06, "reference_active": true, "delta_db": -0.2956908933906}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1263612266386524e-07, "output_power": 2.9947524469836436e-07, "reference_active": true, "delta_db": -0.18678227475986048}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9590349245364564e-07, "output_power": 1.228899292636839e-07, "reference_active": true, "delta_db": -2.0252588417154884}], "active_band_count": 3, "active_band_mae_db": 0.8359106699553163}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 9.239390922709503e-06, "log_rms_mae_db": 0.7211349653354004, "rms_envelope_nrmse": 0.058867691270828276, "envelope_correlation": 0.9970819571505088, "rms_gain_error_db": -0.1791948003656854, "reference_mean_power": 7.844041250222317e-06, "output_mean_power": 7.526973531248257e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 3.7692280722089195e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6572550629104971e-06, "output_power": 1.540260837323311e-06, "reference_active": true, "delta_db": -0.31795081274538917}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5392861690297655e-07, "output_power": 1.4269492322556078e-07, "reference_active": true, "delta_db": -0.3291084498194777}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6336932951152273e-08, "output_power": 9.031452501687187e-09, "reference_active": true, "delta_db": -2.5741292442817243}], "active_band_count": 3, "active_band_mae_db": 1.073729502282197}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 2.9307310026633354e-06, "log_rms_mae_db": 2.1060406505886977, "rms_envelope_nrmse": 0.2551491715008558, "envelope_correlation": 0.9418647121765679, "rms_gain_error_db": 0.26530351871472546, "reference_mean_power": 4.2741366364654595e-07, "output_mean_power": 4.543376773719669e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 2.4398860779830526e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.615850373422058e-08, "output_power": 1.0929916965586809e-07, "reference_active": true, "delta_db": 0.5562916572277434}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8718875021930722e-08, "output_power": 1.7790645120476778e-08, "reference_active": true, "delta_db": -0.22088048037786295}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0143942568188046e-08, "output_power": 1.324051825003527e-08, "reference_active": true, "delta_db": -1.8223949030897098}], "active_band_count": 3, "active_band_mae_db": 0.8665223468984387}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 1.736089681183382e-06, "log_rms_mae_db": 1.3782915116767647, "rms_envelope_nrmse": 0.1441792865396848, "envelope_correlation": 0.980003574462822, "rms_gain_error_db": 0.26528912931532955, "reference_mean_power": 4.3025101883138276e-07, "output_mean_power": 4.5735225036626495e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 2.1733905138014183e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.047483464267491e-08, "output_power": 1.0160866162603949e-07, "reference_active": true, "delta_db": 0.5040293290269325}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.338915747949155e-09, "output_power": 7.88952816356965e-09, "reference_active": true, "delta_db": -0.732454265561385}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.438276742938052e-09, "output_power": 7.749344471890004e-10, "reference_active": true, "delta_db": -2.6857749145960823}], "active_band_count": 3, "active_band_mae_db": 1.3074195030614666}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 7.246614216836824e-06, "log_rms_mae_db": 1.4845891276127365, "rms_envelope_nrmse": 0.18187898607693423, "envelope_correlation": 0.9745311713136731, "rms_gain_error_db": -0.15900922301119075, "reference_mean_power": 1.7870157226185334e-06, "output_mean_power": 1.7227705982861452e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.838724239404773e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.063249741710556e-07, "output_power": 6.320020776329589e-07, "reference_active": true, "delta_db": -0.4828605628842944}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.654737664402428e-07, "output_power": 1.6500398482690483e-07, "reference_active": true, "delta_db": -0.012347197293339888}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2023841152792083e-07, "output_power": 7.426903988419497e-08, "reference_active": true, "delta_db": -2.0923542054994657}], "active_band_count": 3, "active_band_mae_db": 0.8625206552257}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.77385839866885e-06, "log_rms_mae_db": 0.8473008016692817, "rms_envelope_nrmse": 0.08790011610959708, "envelope_correlation": 0.9939994934678911, "rms_gain_error_db": -0.15901625528166036, "reference_mean_power": 1.7989086732437154e-06, "output_mean_power": 1.7342331764886752e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 1.713692894624548e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.664518497859096e-07, "output_power": 5.796031812705977e-07, "reference_active": true, "delta_db": -0.6063801719459825}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.184085944051966e-08, "output_power": 7.824175440345492e-08, "reference_active": true, "delta_db": -0.19531601401177406}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1933830695482323e-08, "output_power": 6.733197946396119e-09, "reference_active": true, "delta_db": -2.485584899501694}], "active_band_count": 3, "active_band_mae_db": 1.0957603618198168}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 907, "rms_floor": 6.060487704579714e-06, "log_rms_mae_db": 1.2797427605899698, "rms_envelope_nrmse": 0.140389697346466, "envelope_correlation": 0.9845274631990382, "rms_gain_error_db": -0.10904758059182806, "reference_mean_power": 1.7907615060268857e-06, "output_mean_power": 1.7463568507337625e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.036723230359137e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.741355867444106e-07, "output_power": 4.5200520781484984e-07, "reference_active": true, "delta_db": -0.207591143712568}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0977135221440419e-07, "output_power": 1.0380727085060187e-07, "reference_active": true, "delta_db": -0.24261240724501498}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0575338351673974e-08, "output_power": 2.696421028525568e-08, "reference_active": true, "delta_db": -0.54583566304602}], "active_band_count": 3, "active_band_mae_db": 0.33201307133453434}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 108960, "uncovered_tail_samples": 100, "metrics": {"frame_count": 901, "rms_floor": 5.330101975711502e-06, "log_rms_mae_db": 0.7038999607637624, "rms_envelope_nrmse": 0.06947787197955722, "envelope_correlation": 0.9960499194507464, "rms_gain_error_db": -0.10904823957066366, "reference_mean_power": 1.8026836617488875e-06, "output_mean_power": 1.7579831117225799e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 9.630136220520234e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.5232190822756626e-07, "output_power": 4.301668100728742e-07, "reference_active": true, "delta_db": -0.21810724381375884}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.528340255264933e-08, "output_power": 5.148941061524752e-08, "reference_active": true, "delta_db": -0.3087684429887541}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3355698674413927e-09, "output_power": 1.7110437861643995e-09, "reference_active": true, "delta_db": -1.3513174010751943}], "active_band_count": 3, "active_band_mae_db": 0.6260643626259025}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5419264308243893, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "c115e6754222431bfdc00bbb43e3523e359542d9e2358dad396548fab27fd718", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9726994611557631, "standard_deviation": 0.003389346404898276, "minimum": 0.9680590329314102, "maximum": 0.9784838963669353, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4790448416462065, "standard_deviation": 0.026909609790236908, "minimum": 1.4361100747105033, "maximum": 1.5117447919722462, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.9608486761719739, "standard_deviation": 0.5031749907673851, "minimum": 0.15322087675214252, "maximum": 1.697376145840628, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1885273402491109, "standard_deviation": 0.012255985124228135, "minimum": 0.1676968802101635, "maximum": 0.2058310415374911, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9928070264883608, "standard_deviation": 0.0011284854046373371, "minimum": 0.9904867561768039, "maximum": 0.9940166167938934, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8160239838964733, "standard_deviation": 0.03470449785179773, "minimum": 0.760171363287833, "maximum": 0.8502113184245177, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.3387354847229747, "standard_deviation": 0.6416589045261069, "minimum": 0.14788859374997726, "maximum": 2.163812072292051, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0974831104642987, "standard_deviation": 0.010829121412281083, "minimum": 0.08563993123023872, "maximum": 0.11841576274123647, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9839316002829437, "standard_deviation": 0.001343672687016847, "minimum": 0.9821842474552154, "maximum": 0.9857368425413869, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2671298397746138, "standard_deviation": 0.030519779606401176, "minimum": 1.2237348660261065, "maximum": 1.3139037605161854, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.3739839233929818, "standard_deviation": 0.20959504148134547, "minimum": 0.15688301920379452, "maximum": 0.7106976984616539, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14385451968521962, "standard_deviation": 0.005634163125758742, "minimum": 0.13501582357292333, "maximum": 0.15056402339616845, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9956177167191641, "standard_deviation": 0.0007842525047077096, "minimum": 0.9938233353205871, "maximum": 0.9962770505830281, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.695124490362117, "standard_deviation": 0.01645121165714381, "minimum": 0.6683332691175674, "maximum": 0.7221900800605132, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6950455719361012, "standard_deviation": 0.2251320653340537, "minimum": 0.42964419488967476, "maximum": 1.0586030030876243, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07326474441262518, "standard_deviation": 0.005894542912926921, "minimum": 0.06920133046930427, "maximum": 0.08674870236427215, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9463337411245937, "standard_deviation": 0.005676316468123364, "minimum": 0.9383904455606991, "maximum": 0.955484559896085, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.071535831258785, "standard_deviation": 0.049219638302300875, "minimum": 1.992344339346764, "maximum": 2.1413923816075027, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8343972894906978, "standard_deviation": 0.2870286844135402, "minimum": 0.4558898927896602, "maximum": 1.3166261533081949, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2532729762850462, "standard_deviation": 0.009159853768948864, "minimum": 0.2390026808817912, "maximum": 0.2688366330308524, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9807815346726356, "standard_deviation": 0.0037886146423844504, "minimum": 0.9746199281648722, "maximum": 0.9851309811982131, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.4061369370960777, "standard_deviation": 0.05906668395751871, "minimum": 1.3370878563983786, "maximum": 1.5052036405186255, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.9474104202439413, "standard_deviation": 0.2862151822622451, "minimum": 0.5296325518466451, "maximum": 1.3074195030614666, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15109179171462636, "standard_deviation": 0.009960750216605608, "minimum": 0.14396435233086402, "maximum": 0.17252999826915813, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.37780222848675354, "standard_deviation": 0.04145312449523244, "minimum": 0.30677150705814243, "maximum": 0.42266264933530684, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.973642050261494, "standard_deviation": 0.005871992627144753, "minimum": 5.965125253580549, "maximum": 5.984619182685079, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.0332589536935745, "standard_deviation": 0.0036066534558744784, "minimum": 0.02865774707683794, "maximum": 0.03774937347494016, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06996731651942674, "standard_deviation": 0.07746942161483529, "minimum": -0.17923687337048702, "maximum": 0.01380781442125905, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9873629548747569, "standard_deviation": 0.0007053842317855655, "minimum": 0.9869648955835421, "maximum": 0.9890809663863886, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.3678869388782633, "standard_deviation": 0.03095056692633374, "minimum": 1.3270863690340402, "maximum": 1.4064478333747246, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.7616052952229725, "standard_deviation": 0.35168676623333994, "minimum": 0.3187960521202115, "maximum": 1.2232244815352258, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.11886324383682645, "standard_deviation": 0.0034284699223698896, "minimum": 0.11048469512928069, "maximum": 0.12070871114130236, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.99667745744495, "standard_deviation": 0.0003712176517124043, "minimum": 0.9960637663060192, "maximum": 0.9972207973540884, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.7088986977379464, "standard_deviation": 0.0276127090656728, "minimum": 0.657347294007683, "maximum": 0.7435027457201556, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 1.08817075715633, "standard_deviation": 0.38448291979339483, "minimum": 0.4990104877118715, "maximum": 1.525044692951159, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.059602665694863693, "standard_deviation": 0.0033209765882170057, "minimum": 0.05366027828450248, "maximum": 0.06533376409704438, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs018_falset10_VOICEACTRESS100_004", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs018", "source_utterance_id": "VOICEACTRESS100_004", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 144000, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs018_falset10_VOICEACTRESS100_004.wav", "source_file_sha256": "2f25f673cd4637e368b26d3baec4d20af21bfa899b114bdcc40c450476e9d396", "decoded_pcm_sha256": "9d50c2c26a1084d289dce329d8bf9f4b4e0142ff514d2355f35c63a498245d13", "original_source_sha256": "2f25f673cd4637e368b26d3baec4d20af21bfa899b114bdcc40c450476e9d396", "corpus_entry_id": "jvs_jvs018_falset10_VOICEACTRESS100_004"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 3.6278305053710938, "predicted_mos": 3.6278305053710938, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "b4abc10cd0a84c2d34efdedc45c4c137e0d529ef0221d6f00272c99f2ce6c909", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.023868300020695}, "waveform_sha256": "da26239d8279f6d38ae980276159b41ddcadaf21ac04eb3047a5bd07346f8c88"}, "rows": [{"case": "jvs_jvs018_falset10_VOICEACTRESS100_004", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 2.176323175430298, "predicted_mos": 2.176323175430298, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "bfd2586e518cc94fabeb123f0523c2e4db1b49ab39aa7ddf4c6992dd7bdbe7c5", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.977071900386363}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6359773207792045, "全帯域_10ms_rms_envelope_nrmse": 0.05990628093444422, "全帯域_10ms_envelope_correlation": 0.9969465784220098, "全帯域_10ms_modulation_mae_db": 0.41191593388955045, "全帯域_40ms_log_rms_mae_db": 0.4137202360885374, "全帯域_40ms_rms_envelope_nrmse": 0.03386544525459577, "全帯域_40ms_envelope_correlation": 0.9990305096874875, "全帯域_40ms_modulation_mae_db": 0.35267257199547714, "300–1000 Hz_10ms_log_rms_mae_db": 0.8153622316879569, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05326063000849236, "300–1000 Hz_10ms_envelope_correlation": 0.9979510038915698, "300–1000 Hz_10ms_modulation_mae_db": 0.541188769448027, "300–1000 Hz_40ms_log_rms_mae_db": 0.5670326230747781, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02898159762612749, "300–1000 Hz_40ms_envelope_correlation": 0.999387905057288, "300–1000 Hz_40ms_modulation_mae_db": 0.2285130944436247, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8215535214124965, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1166986528484286, "1000–3000 Hz_10ms_envelope_correlation": 0.992203298133501, "1000–3000 Hz_10ms_modulation_mae_db": 1.2621997852040083, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5774061365793035, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07499922250936014, "1000–3000 Hz_40ms_envelope_correlation": 0.9968784971724866, "1000–3000 Hz_40ms_modulation_mae_db": 1.2037620279146939, "3000–6000 Hz_10ms_log_rms_mae_db": 1.068262007176198, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16299283164717907, "3000–6000 Hz_10ms_envelope_correlation": 0.9809267708406443, "3000–6000 Hz_10ms_modulation_mae_db": 1.7204230404785654, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7541305762404539, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1004789082804126, "3000–6000 Hz_40ms_envelope_correlation": 0.9930537564129988, "3000–6000 Hz_40ms_modulation_mae_db": 2.0934884323211134, "mr_stft_db": 5.223902532623515, "band_mae_db": 0.11197726259369394, "rms_gain_error_db": -0.07603983678969509, "output_peak": 0.3637118031190992}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6129964819307565, "全帯域_10ms_rms_envelope_nrmse": 0.05251930744286307, "全帯域_10ms_envelope_correlation": 0.9976228552605128, "全帯域_10ms_modulation_mae_db": 0.33672082752854243, "全帯域_40ms_log_rms_mae_db": 0.3650593252568757, "全帯域_40ms_rms_envelope_nrmse": 0.026096922543707116, "全帯域_40ms_envelope_correlation": 0.9993888126954226, "全帯域_40ms_modulation_mae_db": 0.458312643158643, "300–1000 Hz_10ms_log_rms_mae_db": 0.8196628243891004, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.054043639868314786, "300–1000 Hz_10ms_envelope_correlation": 0.9979006355305914, "300–1000 Hz_10ms_modulation_mae_db": 0.5432690999196588, "300–1000 Hz_40ms_log_rms_mae_db": 0.5274103246875202, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0290240073890285, "300–1000 Hz_40ms_envelope_correlation": 0.9993832124154782, "300–1000 Hz_40ms_modulation_mae_db": 0.13794095618537325, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7833879124734608, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07679575992919359, "1000–3000 Hz_10ms_envelope_correlation": 0.9965870292627872, "1000–3000 Hz_10ms_modulation_mae_db": 0.23210557695633216, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5514759804242826, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03865120252845167, "1000–3000 Hz_40ms_envelope_correlation": 0.9991222669675579, "1000–3000 Hz_40ms_modulation_mae_db": 0.11158550440072611, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0840126552532101, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1467971815454493, "3000–6000 Hz_10ms_envelope_correlation": 0.9843828475140692, "3000–6000 Hz_10ms_modulation_mae_db": 0.4776371193176805, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7807332410368406, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07759380317239074, "3000–6000 Hz_40ms_envelope_correlation": 0.9956932997382757, "3000–6000 Hz_40ms_modulation_mae_db": 0.7035411822558958, "mr_stft_db": 5.21509912519238, "band_mae_db": 0.09836481402583029, "rms_gain_error_db": 0.0021519499430591674, "output_peak": 0.3750478017481764}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6072415547535962, "全帯域_10ms_rms_envelope_nrmse": 0.052976877824597896, "全帯域_10ms_envelope_correlation": 0.9975928111648399, "全帯域_10ms_modulation_mae_db": 0.19002680867427546, "全帯域_40ms_log_rms_mae_db": 0.38252978546841565, "全帯域_40ms_rms_envelope_nrmse": 0.028239819041046686, "全帯域_40ms_envelope_correlation": 0.9993056479604489, "全帯域_40ms_modulation_mae_db": 0.5222441056675203, "300–1000 Hz_10ms_log_rms_mae_db": 0.8616351318533938, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05678923964341549, "300–1000 Hz_10ms_envelope_correlation": 0.9976720744550255, "300–1000 Hz_10ms_modulation_mae_db": 0.8165495205580754, "300–1000 Hz_40ms_log_rms_mae_db": 0.5778017632393233, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.030843642775677912, "300–1000 Hz_40ms_envelope_correlation": 0.9993099523748201, "300–1000 Hz_40ms_modulation_mae_db": 0.7058864886430846, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7814083767156019, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07763539660087132, "1000–3000 Hz_10ms_envelope_correlation": 0.9965479425075978, "1000–3000 Hz_10ms_modulation_mae_db": 0.6870638787018665, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5641338689462931, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04475431695819291, "1000–3000 Hz_40ms_envelope_correlation": 0.9988857586671877, "1000–3000 Hz_40ms_modulation_mae_db": 0.5355506316133803, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0574690110975038, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1490492548581498, "3000–6000 Hz_10ms_envelope_correlation": 0.9842714411579458, "3000–6000 Hz_10ms_modulation_mae_db": 0.7167484901388231, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7035508354052784, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.091862071935805, "3000–6000 Hz_40ms_envelope_correlation": 0.9944204666513173, "3000–6000 Hz_40ms_modulation_mae_db": 0.7531227005394358, "mr_stft_db": 5.224618450662562, "band_mae_db": 0.11089423102425511, "rms_gain_error_db": -0.04729644446804299, "output_peak": 0.38069898045437445}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6054747643334549, "全帯域_10ms_rms_envelope_nrmse": 0.05558689665110574, "全帯域_10ms_envelope_correlation": 0.997394120881029, "全帯域_10ms_modulation_mae_db": 0.6641762618935859, "全帯域_40ms_log_rms_mae_db": 0.3806092907638189, "全帯域_40ms_rms_envelope_nrmse": 0.02844023144767472, "全帯域_40ms_envelope_correlation": 0.9993568845831645, "全帯域_40ms_modulation_mae_db": 0.6835650336119984, "300–1000 Hz_10ms_log_rms_mae_db": 0.8518924218481245, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06682205035000463, "300–1000 Hz_10ms_envelope_correlation": 0.9967701673081601, "300–1000 Hz_10ms_modulation_mae_db": 0.4634694901472722, "300–1000 Hz_40ms_log_rms_mae_db": 0.5687046027276267, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03849123202320259, "300–1000 Hz_40ms_envelope_correlation": 0.9989151312118744, "300–1000 Hz_40ms_modulation_mae_db": 0.7921851744309464, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8353653789162893, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09537459895279746, "1000–3000 Hz_10ms_envelope_correlation": 0.994830194626603, "1000–3000 Hz_10ms_modulation_mae_db": 1.485906259099563, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6060200871550121, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06187632569174431, "1000–3000 Hz_40ms_envelope_correlation": 0.9978985869468856, "1000–3000 Hz_40ms_modulation_mae_db": 1.30354084851655, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0474047313991162, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15530990490196434, "3000–6000 Hz_10ms_envelope_correlation": 0.984425610947211, "3000–6000 Hz_10ms_modulation_mae_db": 1.829197628143526, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7669785172451976, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10432842103646905, "3000–6000 Hz_40ms_envelope_correlation": 0.9944563206574714, "3000–6000 Hz_40ms_modulation_mae_db": 2.3103091814641883, "mr_stft_db": 5.204390585406798, "band_mae_db": 0.19923783747650112, "rms_gain_error_db": -0.0851756472426343, "output_peak": 0.3762278261404141}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6309627207961515, "全帯域_10ms_rms_envelope_nrmse": 0.05283479951683072, "全帯域_10ms_envelope_correlation": 0.9977324911492786, "全帯域_10ms_modulation_mae_db": 0.6135254645996852, "全帯域_40ms_log_rms_mae_db": 0.386413234932513, "全帯域_40ms_rms_envelope_nrmse": 0.02768841557244976, "全帯域_40ms_envelope_correlation": 0.9994789193215493, "全帯域_40ms_modulation_mae_db": 0.43599434366316725, "300–1000 Hz_10ms_log_rms_mae_db": 0.8249083774555229, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.053042265176582414, "300–1000 Hz_10ms_envelope_correlation": 0.9980510857102848, "300–1000 Hz_10ms_modulation_mae_db": 0.3193842152218831, "300–1000 Hz_40ms_log_rms_mae_db": 0.5607771392390608, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02945528261756594, "300–1000 Hz_40ms_envelope_correlation": 0.9994614183368877, "300–1000 Hz_40ms_modulation_mae_db": 0.34861251227129525, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8239451491123433, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08032102580127633, "1000–3000 Hz_10ms_envelope_correlation": 0.996433917831956, "1000–3000 Hz_10ms_modulation_mae_db": 0.34929943987387485, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5720004045436548, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0431640881593632, "1000–3000 Hz_40ms_envelope_correlation": 0.9991301116116226, "1000–3000 Hz_40ms_modulation_mae_db": 0.360058282677751, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0555113747880986, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14859739015405332, "3000–6000 Hz_10ms_envelope_correlation": 0.9843669295648384, "3000–6000 Hz_10ms_modulation_mae_db": 1.2832610360800751, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7375273629306879, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09537256912314111, "3000–6000 Hz_40ms_envelope_correlation": 0.9938927651979338, "3000–6000 Hz_40ms_modulation_mae_db": 1.8503745056117433, "mr_stft_db": 5.206727832632919, "band_mae_db": 0.16484470029564222, "rms_gain_error_db": -0.12163673800408391, "output_peak": 0.3692051123558472}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.631101990390167, "全帯域_10ms_rms_envelope_nrmse": 0.05374356635312126, "全帯域_10ms_envelope_correlation": 0.9976906167685328, "全帯域_10ms_modulation_mae_db": 0.3728571746965752, "全帯域_40ms_log_rms_mae_db": 0.37593495358029794, "全帯域_40ms_rms_envelope_nrmse": 0.03116415579175604, "全帯域_40ms_envelope_correlation": 0.9993352450823396, "全帯域_40ms_modulation_mae_db": 0.29683356706986225, "300–1000 Hz_10ms_log_rms_mae_db": 0.8179666780105636, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.055836743792921036, "300–1000 Hz_10ms_envelope_correlation": 0.9977633697906649, "300–1000 Hz_10ms_modulation_mae_db": 0.3918807801769491, "300–1000 Hz_40ms_log_rms_mae_db": 0.5587507515026153, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029797163433637176, "300–1000 Hz_40ms_envelope_correlation": 0.9993719845918592, "300–1000 Hz_40ms_modulation_mae_db": 0.3331368579332359, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8360556183145899, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09553094780691607, "1000–3000 Hz_10ms_envelope_correlation": 0.9962824471027948, "1000–3000 Hz_10ms_modulation_mae_db": 0.48291300084271405, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5693064845015938, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0701445671461205, "1000–3000 Hz_40ms_envelope_correlation": 0.9988516420077721, "1000–3000 Hz_40ms_modulation_mae_db": 0.3741041608060282, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0552655849844197, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14455706717421257, "3000–6000 Hz_10ms_envelope_correlation": 0.9852192863453249, "3000–6000 Hz_10ms_modulation_mae_db": 0.7485125462656654, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7333040871550259, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07997557420326934, "3000–6000 Hz_40ms_envelope_correlation": 0.9959847491703308, "3000–6000 Hz_40ms_modulation_mae_db": 1.0465056066944571, "mr_stft_db": 5.228050266607134, "band_mae_db": 0.1899779285672383, "rms_gain_error_db": -0.1328728924806132, "output_peak": 0.3739775726907395}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6352853597530979, "全帯域_10ms_rms_envelope_nrmse": 0.044672723696374914, "全帯域_10ms_envelope_correlation": 0.9982792660439228, "全帯域_10ms_modulation_mae_db": 0.2055418946992729, "全帯域_40ms_log_rms_mae_db": 0.3674381602101627, "全帯域_40ms_rms_envelope_nrmse": 0.022149648431059234, "全帯域_40ms_envelope_correlation": 0.999558863138852, "全帯域_40ms_modulation_mae_db": 0.14034368212859957, "300–1000 Hz_10ms_log_rms_mae_db": 0.778563115242314, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.04843322315930836, "300–1000 Hz_10ms_envelope_correlation": 0.998332898371361, "300–1000 Hz_10ms_modulation_mae_db": 0.39477759013224595, "300–1000 Hz_40ms_log_rms_mae_db": 0.5363358027477139, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02688196970950013, "300–1000 Hz_40ms_envelope_correlation": 0.9994890446884552, "300–1000 Hz_40ms_modulation_mae_db": 0.2624718127950992, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8127061789111131, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07037163340685913, "1000–3000 Hz_10ms_envelope_correlation": 0.9973687597518514, "1000–3000 Hz_10ms_modulation_mae_db": 1.5031589747503729, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5880391684021635, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.040559745536525395, "1000–3000 Hz_40ms_envelope_correlation": 0.9993099259735598, "1000–3000 Hz_40ms_modulation_mae_db": 1.4975925531241805, "3000–6000 Hz_10ms_log_rms_mae_db": 1.038660792541261, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13956769878731348, "3000–6000 Hz_10ms_envelope_correlation": 0.9862917880012362, "3000–6000 Hz_10ms_modulation_mae_db": 0.6450446574350052, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7179890128520551, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08335736955537949, "3000–6000 Hz_40ms_envelope_correlation": 0.9955378027574814, "3000–6000 Hz_40ms_modulation_mae_db": 0.6644234984259386, "mr_stft_db": 5.222181873660681, "band_mae_db": 0.11176554073515091, "rms_gain_error_db": -0.003261194089513133, "output_peak": 0.3777086039125588}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6457281540624643, "全帯域_10ms_rms_envelope_nrmse": 0.05386341120115569, "全帯域_10ms_envelope_correlation": 0.9975717718894648, "全帯域_10ms_modulation_mae_db": 0.18798241550751424, "全帯域_40ms_log_rms_mae_db": 0.4067006583365675, "全帯域_40ms_rms_envelope_nrmse": 0.030740902799708952, "全帯域_40ms_envelope_correlation": 0.999245378391849, "全帯域_40ms_modulation_mae_db": 0.09541361388391505, "300–1000 Hz_10ms_log_rms_mae_db": 0.796171890216712, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05980833706171067, "300–1000 Hz_10ms_envelope_correlation": 0.9974227484014104, "300–1000 Hz_10ms_modulation_mae_db": 0.7436913332701605, "300–1000 Hz_40ms_log_rms_mae_db": 0.5688285138057516, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03413282525032108, "300–1000 Hz_40ms_envelope_correlation": 0.9991589964719237, "300–1000 Hz_40ms_modulation_mae_db": 0.3440441737823218, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7987552979002486, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07708782421080734, "1000–3000 Hz_10ms_envelope_correlation": 0.9973373644304985, "1000–3000 Hz_10ms_modulation_mae_db": 0.44306601668564466, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5550226617064337, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04953487186539876, "1000–3000 Hz_40ms_envelope_correlation": 0.9994266525229804, "1000–3000 Hz_40ms_modulation_mae_db": 0.6226808821910301, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0312826486933775, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14415296893888227, "3000–6000 Hz_10ms_envelope_correlation": 0.986098986284563, "3000–6000 Hz_10ms_modulation_mae_db": 0.7107843622839672, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7281390517940425, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09884066791743233, "3000–6000 Hz_40ms_envelope_correlation": 0.9942917173690052, "3000–6000 Hz_40ms_modulation_mae_db": 0.910215486596568, "mr_stft_db": 5.212451462971853, "band_mae_db": 0.19036548230229555, "rms_gain_error_db": -0.09322816526767934, "output_peak": 0.36286196237115625}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.498481882484102, "spectral_convergence": 0.19761794508072994, "spectral_convergence_status": "ok", "amplitude_floor": 9.086732072822267e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.114685704996072, "spectral_convergence": 0.20151221275108971, "spectral_convergence_status": "ok", "amplitude_floor": 8.520258431312163e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.058540010390372, "spectral_convergence": 0.20590763293358547, "spectral_convergence_status": "ok", "amplitude_floor": 5.353418087016012e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 3.131933551513939e-05, "output_power": 3.0923529792822204e-05, "delta_db": -0.055234783082537965, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0004897019472039064, "output_power": 0.00048596005079340704, "delta_db": -0.033312621259418265, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.00038033005135275084, "output_power": 0.00037663948695414043, "delta_db": -0.04234792476940274, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0002067238728943134, "output_power": 0.00019426966177072224, "delta_db": -0.26985648678867136, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.323291799953591e-05, "output_power": 1.2432246525108924e-05, "delta_db": -0.2710600793210495, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.500515826026349e-05, "output_power": 2.4983272082238515e-05, "delta_db": -0.003802898746136529, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.8390290595099542e-05, "output_power": 2.910666465385597e-05, "delta_db": 0.10822604418864122, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.11197726259369394, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.07603983678969509, "pitch": null, "output_rms_dbfs": -29.376756936628702, "output_peak": 0.3637118031190992, "reference_rms_dbfs": -29.30071709983901, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.223902532623515}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00015179812996022924, "log_rms_mae_db": 0.6359773207792045, "rms_envelope_nrmse": 0.05990628093444422, "envelope_correlation": 0.9969465784220098, "rms_gain_error_db": -0.07603989531029946, "reference_mean_power": 0.0011756832947918806, "output_mean_power": 0.0011552776135167545}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.744923761629972e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00015071015783187623, "output_power": 0.00014552463438966361, "reference_active": true, "delta_db": -0.1520600780078264}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2413420104691182e-05, "output_power": 1.2815294079151928e-05, "reference_active": true, "delta_db": 0.138371232407541}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.099936667111779e-06, "output_power": 2.4935677473761196e-06, "reference_active": true, "delta_db": -0.9453164912532841}], "active_band_count": 3, "active_band_mae_db": 0.41191593388955045}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001370105991807196, "log_rms_mae_db": 0.4137202360885374, "rms_envelope_nrmse": 0.03386544525459577, "envelope_correlation": 0.9990305096874875, "rms_gain_error_db": -0.0760400074578536, "reference_mean_power": 0.0011815960953402045, "output_mean_power": 0.0011610877588907546}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.5970704572828427e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000136303861600392, "output_power": 0.0001320275537153355, "reference_active": true, "delta_db": -0.13843583436544993}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.090701624693659e-06, "output_power": 5.473660143927216e-06, "reference_active": true, "delta_db": 0.3150018585170328}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5690836910660882e-07, "output_power": 1.3651743068939607e-07, "reference_active": true, "delta_db": -0.6045800231039488}], "active_band_count": 3, "active_band_mae_db": 0.35267257199547714}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.549209054072936e-05, "log_rms_mae_db": 0.8153622316879569, "rms_envelope_nrmse": 0.05326063000849236, "envelope_correlation": 0.9979510038915698, "rms_gain_error_db": -0.03680902433080496, "reference_mean_power": 0.000689577872249739, "output_mean_power": 0.0006837579905012473}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.482675818010425e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.030686777059284e-05, "output_power": 6.867606944667049e-05, "reference_active": true, "delta_db": -0.10192319062267588}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.045775397952136e-06, "output_power": 6.77772811397188e-06, "reference_active": true, "delta_db": 0.4963213429576637}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0022957436919974e-06, "output_power": 1.2691941555773389e-06, "reference_active": true, "delta_db": 1.0253217747637413}], "active_band_count": 3, "active_band_mae_db": 0.541188769448027}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.872309512115098e-05, "log_rms_mae_db": 0.5670326230747781, "rms_envelope_nrmse": 0.02898159762612749, "envelope_correlation": 0.999387905057288, "rms_gain_error_db": -0.03680904495265571, "reference_mean_power": 0.0006930459912916024, "output_mean_power": 0.0006871968361373698}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.4404474148541786e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.432934367906604e-05, "output_power": 6.283752793004608e-05, "reference_active": true, "delta_db": -0.10190029256548648}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.638974827185174e-06, "output_power": 2.996287098958406e-06, "reference_active": true, "delta_db": 0.5514817678942352}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.490824439966143e-08, "output_power": 7.435563664623126e-08, "reference_active": true, "delta_db": -0.032157222871152455}], "active_band_count": 3, "active_band_mae_db": 0.2285130944436247}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.800802183872533e-05, "log_rms_mae_db": 0.8215535214124965, "rms_envelope_nrmse": 0.1166986528484286, "envelope_correlation": 0.992203298133501, "rms_gain_error_db": -0.18109702639607939, "reference_mean_power": 0.0001528560580614903, "output_mean_power": 0.00014661315952276165}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.6939080235935477e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.743995800608424e-06, "output_power": 7.934591529560339e-06, "reference_active": true, "delta_db": -0.4218536605337141}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.01868229376414e-06, "output_power": 1.5550180949641127e-06, "reference_active": true, "delta_db": -1.1333252670285638}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.212055898483429e-07, "output_power": 2.519718840441873e-07, "reference_active": true, "delta_db": -2.231420428049747}], "active_band_count": 3, "active_band_mae_db": 1.2621997852040083}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.485177873530849e-05, "log_rms_mae_db": 0.5774061365793035, "rms_envelope_nrmse": 0.07499922250936014, "envelope_correlation": 0.9968784971724866, "rms_gain_error_db": -0.1810970347954918, "reference_mean_power": 0.00015362482187073777, "output_mean_power": 0.00014735052543987873}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.6796802400302903e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.417995641253307e-06, "output_power": 7.492821565931498e-06, "reference_active": true, "delta_db": -0.5056330610755614}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.917412489595775e-07, "output_power": 7.749608109697203e-07, "reference_active": true, "delta_db": -1.07118635782349}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9786028250337687e-08, "output_power": 1.23854547890973e-08, "reference_active": true, "delta_db": -2.0344666648450302}], "active_band_count": 3, "active_band_mae_db": 1.2037620279146939}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.5712979141900155e-05, "log_rms_mae_db": 1.068262007176198, "rms_envelope_nrmse": 0.16299283164717907, "envelope_correlation": 0.9809267708406443, "rms_gain_error_db": -0.323937490853073, "reference_mean_power": 1.157751296991392e-05, "output_mean_power": 1.0745373779885691e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.302605621158197e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.645490651287566e-07, "output_power": 7.816590984078856e-07, "reference_active": true, "delta_db": -0.4377225812862631}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.590093915842518e-07, "output_power": 3.0826589387667034e-07, "reference_active": true, "delta_db": -1.728960939039761}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3044874644069055e-07, "output_power": 1.1564205215494742e-07, "reference_active": true, "delta_db": -2.9945856011096716}], "active_band_count": 3, "active_band_mae_db": 1.7204230404785654}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.532870280173584e-05, "log_rms_mae_db": 0.7541305762404539, "rms_envelope_nrmse": 0.1004789082804126, "envelope_correlation": 0.9930537564129988, "rms_gain_error_db": -0.323937500951187, "reference_mean_power": 1.163573961751773e-05, "output_mean_power": 1.0799415334696368e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.177196911262554e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.60049524306651e-07, "output_power": 7.297762834768059e-07, "reference_active": true, "delta_db": -0.713337145755739}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5501826725164134e-07, "output_power": 1.572016381040449e-07, "reference_active": true, "delta_db": -2.101142233117303}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7808109251124296e-08, "output_power": 8.017135421483262e-09, "reference_active": true, "delta_db": -3.465985918090298}], "active_band_count": 3, "active_band_mae_db": 2.0934884323211134}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8939941533641146, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "c78d63e9b08e3c9fd3722914dd37e7ac7e3869ae22d2128846111d39edfc05d7", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9959488692059487, "standard_deviation": 0.001704507766647048, "minimum": 0.992203298133501, "maximum": 0.9973687597518514, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.8116471792195179, "standard_deviation": 0.021672873081460133, "minimum": 0.7814083767156019, "maximum": 0.8360556183145899, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8057141165142971, "standard_deviation": 0.527067770657554, "minimum": 0.23210557695633216, "maximum": 1.5031589747503729, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08622697994464373, "standard_deviation": 0.015265859631837289, "minimum": 0.07037163340685913, "maximum": 0.1166986528484286, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9986879302337566, "standard_deviation": 0.0008684806562497907, "minimum": 0.9968784971724866, "maximum": 0.9994266525229804, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5729255990323421, "standard_deviation": 0.01779080876652247, "minimum": 0.5514759804242826, "maximum": 0.6060200871550121, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7511093614055425, "standard_deviation": 0.5119034802106599, "minimum": 0.11158550440072611, "maximum": 1.4975925531241805, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05296054254939461, "standard_deviation": 0.014112153626544072, "minimum": 0.03865120252845167, "maximum": 0.07499922250936014, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9844979575819791, "standard_deviation": 0.0016536441490060808, "minimum": 0.9809267708406443, "maximum": 0.9862917880012362, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.0547336007416481, "standard_deviation": 0.016521180624203168, "minimum": 1.0312826486933775, "maximum": 1.0840126552532101, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.0164511100179134, "standard_deviation": 0.5224433096819332, "minimum": 0.4776371193176805, "maximum": 1.829197628143526, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1488780372509005, "standard_deviation": 0.007296905766167965, "minimum": 0.13956769878731348, "maximum": 0.16299283164717907, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9946663597443518, "standard_deviation": 0.0009997173973499743, "minimum": 0.9930537564129988, "maximum": 0.9959847491703308, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7402940855824477, "standard_deviation": 0.025608801618897042, "minimum": 0.7035508354052784, "maximum": 0.7807332410368406, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.2914975742386674, "standard_deviation": 0.6790401909486027, "minimum": 0.6644234984259386, "maximum": 2.3103091814641883, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09147617315303747, "standard_deviation": 0.010047708070801447, "minimum": 0.07759380317239074, "maximum": 0.10432842103646905, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9977329979323835, "standard_deviation": 0.0004727761530107277, "minimum": 0.9967701673081601, "maximum": 0.998332898371361, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.820770333837961, "standard_deviation": 0.02694042858431628, "minimum": 0.778563115242314, "maximum": 0.8616351318533938, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.526776349859284, "standard_deviation": 0.17490408490426151, "minimum": 0.3193842152218831, "maximum": 0.8165495205580754, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.05600451613259372, "standard_deviation": 0.0054720770873799215, "minimum": 0.04843322315930836, "maximum": 0.06682205035000463, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9993097056435734, "standard_deviation": 0.00018859578581825195, "minimum": 0.9989151312118744, "maximum": 0.9994890446884552, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5582051901280487, "standard_deviation": 0.01739683190520788, "minimum": 0.5274103246875202, "maximum": 0.5778017632393233, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.39409888381062264, "standard_deviation": 0.23125010617684, "minimum": 0.13794095618537325, "maximum": 0.7921851744309464, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.030950965103132604, "standard_deviation": 0.003678275983957949, "minimum": 0.02688196970950013, "maximum": 0.03849123202320259, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.14717847462757594, "standard_deviation": 0.042947982972348225, "minimum": 0.09836481402583029, "maximum": 0.19923783747650112, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.21717776621973, "standard_deviation": 0.00880917070963809, "minimum": 5.204390585406798, "maximum": 5.228050266607134, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3724299578490457, "standard_deviation": 0.006523203078938544, "minimum": 0.36286196237115625, "maximum": 0.38069898045437445, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06966987104990036, "standard_deviation": 0.05014298487854403, "minimum": -0.1328728924806132, "maximum": 0.0021519499430591674, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9976038139474488, "standard_deviation": 0.0003698973083287133, "minimum": 0.9969465784220098, "maximum": 0.9982792660439228, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.6255960433498616, "standard_deviation": 0.014959824309677813, "minimum": 0.6054747643334549, "maximum": 0.6457281540624643, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3728433476861252, "standard_deviation": 0.18563384824613272, "minimum": 0.18798241550751424, "maximum": 0.6641762618935859, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05326298295256169, "standard_deviation": 0.004221310933687339, "minimum": 0.044672723696374914, "maximum": 0.05990628093444422, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9993375326076392, "standard_deviation": 0.00015845634358750967, "minimum": 0.9990305096874875, "maximum": 0.999558863138852, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.3848007055796486, "standard_deviation": 0.01736603458356674, "minimum": 0.3650593252568757, "maximum": 0.4137202360885374, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.3731724451473979, "standard_deviation": 0.1954366662241258, "minimum": 0.09541361388391505, "maximum": 0.6835650336119984, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.028548192610249785, "standard_deviation": 0.003539985391484707, "minimum": 0.022149648431059234, "maximum": 0.03386544525459577, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_falset10_VOICEACTRESS100_004", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 2.282505750656128, "predicted_mos": 2.282505750656128, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "36f380ac0563e2ce139fc2f9288fcf669bdd609cb06a29121aa7c99c15796da1", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.514878599904478}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6343435231351587, "全帯域_10ms_rms_envelope_nrmse": 0.05958199288419261, "全帯域_10ms_envelope_correlation": 0.9969929256008326, "全帯域_10ms_modulation_mae_db": 0.38588322653410123, "全帯域_40ms_log_rms_mae_db": 0.409052102149466, "全帯域_40ms_rms_envelope_nrmse": 0.033138773329342334, "全帯域_40ms_envelope_correlation": 0.9990901800171998, "全帯域_40ms_modulation_mae_db": 0.3285536878807174, "300–1000 Hz_10ms_log_rms_mae_db": 0.7996225558917561, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05313571351154946, "300–1000 Hz_10ms_envelope_correlation": 0.9979640127711893, "300–1000 Hz_10ms_modulation_mae_db": 0.4638093568447796, "300–1000 Hz_40ms_log_rms_mae_db": 0.5504039301250598, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02828769678830302, "300–1000 Hz_40ms_envelope_correlation": 0.99942221462299, "300–1000 Hz_40ms_modulation_mae_db": 0.2556639091808439, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7987427338700702, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1150366967241754, "1000–3000 Hz_10ms_envelope_correlation": 0.9924576708404349, "1000–3000 Hz_10ms_modulation_mae_db": 1.3748217168327432, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5465973057174152, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07505057275060434, "1000–3000 Hz_40ms_envelope_correlation": 0.9969076304159403, "1000–3000 Hz_40ms_modulation_mae_db": 1.3227497607724616, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0684814772837912, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16424258860006308, "3000–6000 Hz_10ms_envelope_correlation": 0.9808692840174315, "3000–6000 Hz_10ms_modulation_mae_db": 1.7488575027784525, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7478646499658029, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10199057981713615, "3000–6000 Hz_40ms_envelope_correlation": 0.9931531060725575, "3000–6000 Hz_40ms_modulation_mae_db": 2.057373863021922, "mr_stft_db": 5.182703803273289, "band_mae_db": 0.12933728345648113, "rms_gain_error_db": -0.08482164815736852, "output_peak": 0.3651967149834583}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6108595072665274, "全帯域_10ms_rms_envelope_nrmse": 0.052213403322422754, "全帯域_10ms_envelope_correlation": 0.9976501181086683, "全帯域_10ms_modulation_mae_db": 0.2605120228342991, "全帯域_40ms_log_rms_mae_db": 0.3581628739968259, "全帯域_40ms_rms_envelope_nrmse": 0.02547560130788149, "全帯域_40ms_envelope_correlation": 0.9994179715450916, "全帯域_40ms_modulation_mae_db": 0.38564049250847027, "300–1000 Hz_10ms_log_rms_mae_db": 0.7985483588886627, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05446872595222923, "300–1000 Hz_10ms_envelope_correlation": 0.9978624580116129, "300–1000 Hz_10ms_modulation_mae_db": 0.6254183627432441, "300–1000 Hz_40ms_log_rms_mae_db": 0.5139083015094099, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029191938693531094, "300–1000 Hz_40ms_envelope_correlation": 0.9993725613161416, "300–1000 Hz_40ms_modulation_mae_db": 0.16529391090643358, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7700340123447442, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07567736119158913, "1000–3000 Hz_10ms_envelope_correlation": 0.9966831057495303, "1000–3000 Hz_10ms_modulation_mae_db": 0.192729408763188, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5297523153907552, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.037892976077724703, "1000–3000 Hz_40ms_envelope_correlation": 0.9991544302263895, "1000–3000 Hz_40ms_modulation_mae_db": 0.08407176883270794, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0930595478388871, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15072750199810103, "3000–6000 Hz_10ms_envelope_correlation": 0.9836040059386003, "3000–6000 Hz_10ms_modulation_mae_db": 0.4741319093487, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7816831753846505, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07973142806192499, "3000–6000 Hz_40ms_envelope_correlation": 0.9954944484624889, "3000–6000 Hz_40ms_modulation_mae_db": 0.6923858883972555, "mr_stft_db": 5.173811117735469, "band_mae_db": 0.11067937504526405, "rms_gain_error_db": -0.0004503990811352804, "output_peak": 0.3768687071446404}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6126433649632692, "全帯域_10ms_rms_envelope_nrmse": 0.053528177552948586, "全帯域_10ms_envelope_correlation": 0.9975446689802036, "全帯域_10ms_modulation_mae_db": 0.22142035237940075, "全帯域_40ms_log_rms_mae_db": 0.40176056689673956, "全帯域_40ms_rms_envelope_nrmse": 0.0282738828535221, "全帯域_40ms_envelope_correlation": 0.9993074740693038, "全帯域_40ms_modulation_mae_db": 0.5450416298853403, "300–1000 Hz_10ms_log_rms_mae_db": 0.851023043397664, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05791636244271829, "300–1000 Hz_10ms_envelope_correlation": 0.9975794217916031, "300–1000 Hz_10ms_modulation_mae_db": 0.8780376597608521, "300–1000 Hz_40ms_log_rms_mae_db": 0.5633050769304955, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03206773043808301, "300–1000 Hz_40ms_envelope_correlation": 0.999254563243674, "300–1000 Hz_40ms_modulation_mae_db": 0.7516889940381315, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7726577662876545, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07746462809747354, "1000–3000 Hz_10ms_envelope_correlation": 0.9965674086276655, "1000–3000 Hz_10ms_modulation_mae_db": 0.6771460347225576, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5479782994687681, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04404559827699719, "1000–3000 Hz_40ms_envelope_correlation": 0.9989279234407129, "1000–3000 Hz_40ms_modulation_mae_db": 0.5296667878519223, "3000–6000 Hz_10ms_log_rms_mae_db": 1.074250442632402, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15122884234979617, "3000–6000 Hz_10ms_envelope_correlation": 0.9838255225232084, "3000–6000 Hz_10ms_modulation_mae_db": 0.6987656577296271, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7302500557306564, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0958185182564742, "3000–6000 Hz_40ms_envelope_correlation": 0.9938651193737683, "3000–6000 Hz_40ms_modulation_mae_db": 0.554799529513672, "mr_stft_db": 5.18419916367852, "band_mae_db": 0.10808397882506489, "rms_gain_error_db": -0.0505787973778028, "output_peak": 0.38156681981728807}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6128371262709512, "全帯域_10ms_rms_envelope_nrmse": 0.057037953203597135, "全帯域_10ms_envelope_correlation": 0.997273916743179, "全帯域_10ms_modulation_mae_db": 0.6471413261446377, "全帯域_40ms_log_rms_mae_db": 0.3809355232480515, "全帯域_40ms_rms_envelope_nrmse": 0.029555779852132185, "全帯域_40ms_envelope_correlation": 0.9993234018897326, "全帯域_40ms_modulation_mae_db": 0.659475715502889, "300–1000 Hz_10ms_log_rms_mae_db": 0.8440082157016541, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06969012594523415, "300–1000 Hz_10ms_envelope_correlation": 0.9964972158355226, "300–1000 Hz_10ms_modulation_mae_db": 0.509585501798296, "300–1000 Hz_40ms_log_rms_mae_db": 0.5666000800288941, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04148033193339683, "300–1000 Hz_40ms_envelope_correlation": 0.9987535660217518, "300–1000 Hz_40ms_modulation_mae_db": 0.9195303262599138, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8173423671580534, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09457281292665848, "1000–3000 Hz_10ms_envelope_correlation": 0.994951836882445, "1000–3000 Hz_10ms_modulation_mae_db": 1.525549954447742, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5752522717402202, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06138111544793795, "1000–3000 Hz_40ms_envelope_correlation": 0.9979741867568239, "1000–3000 Hz_40ms_modulation_mae_db": 1.3091383922234585, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0685011474816533, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15277172364078406, "3000–6000 Hz_10ms_envelope_correlation": 0.9853857624089786, "3000–6000 Hz_10ms_modulation_mae_db": 1.858358446856121, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7793315545770556, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10553094347637736, "3000–6000 Hz_40ms_envelope_correlation": 0.9946587068287929, "3000–6000 Hz_40ms_modulation_mae_db": 2.360137298059304, "mr_stft_db": 5.16736502101861, "band_mae_db": 0.20917652012897753, "rms_gain_error_db": -0.0978880780639513, "output_peak": 0.375016885941323}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6311854541569797, "全帯域_10ms_rms_envelope_nrmse": 0.0516232889194397, "全帯域_10ms_envelope_correlation": 0.9978374783825628, "全帯域_10ms_modulation_mae_db": 0.5984426744966097, "全帯域_40ms_log_rms_mae_db": 0.38952848476257634, "全帯域_40ms_rms_envelope_nrmse": 0.026737415929188057, "全帯域_40ms_envelope_correlation": 0.9995198738460519, "全帯域_40ms_modulation_mae_db": 0.44915474518471515, "300–1000 Hz_10ms_log_rms_mae_db": 0.7924925478137622, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05178621584485606, "300–1000 Hz_10ms_envelope_correlation": 0.9981443889027163, "300–1000 Hz_10ms_modulation_mae_db": 0.37666071767353576, "300–1000 Hz_40ms_log_rms_mae_db": 0.524435108048435, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02831316188994357, "300–1000 Hz_40ms_envelope_correlation": 0.9995074846034471, "300–1000 Hz_40ms_modulation_mae_db": 0.5630080053378025, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8005771533580576, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08128921232914388, "1000–3000 Hz_10ms_envelope_correlation": 0.9963399889140342, "1000–3000 Hz_10ms_modulation_mae_db": 0.3287296534869268, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5513583441665909, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.044064515635194056, "1000–3000 Hz_40ms_envelope_correlation": 0.9990819819573653, "1000–3000 Hz_40ms_modulation_mae_db": 0.314615556084864, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0570643334620655, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14296693715412623, "3000–6000 Hz_10ms_envelope_correlation": 0.9861816571134298, "3000–6000 Hz_10ms_modulation_mae_db": 1.3876146702143413, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7185180012273842, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09084049028143908, "3000–6000 Hz_40ms_envelope_correlation": 0.9952781099003591, "3000–6000 Hz_40ms_modulation_mae_db": 1.9561890872855094, "mr_stft_db": 5.168018191511115, "band_mae_db": 0.17030248296395906, "rms_gain_error_db": -0.11931481661973264, "output_peak": 0.37134086546879647}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6273488685046936, "全帯域_10ms_rms_envelope_nrmse": 0.05217776283807128, "全帯域_10ms_envelope_correlation": 0.9978240069855496, "全帯域_10ms_modulation_mae_db": 0.3916124777601781, "全帯域_40ms_log_rms_mae_db": 0.37854967446448856, "全帯域_40ms_rms_envelope_nrmse": 0.03080381328626295, "全帯域_40ms_envelope_correlation": 0.9993428615100809, "全帯域_40ms_modulation_mae_db": 0.3925831318780811, "300–1000 Hz_10ms_log_rms_mae_db": 0.8010806990638834, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.054345292859914816, "300–1000 Hz_10ms_envelope_correlation": 0.997876696644704, "300–1000 Hz_10ms_modulation_mae_db": 0.20271311752208562, "300–1000 Hz_40ms_log_rms_mae_db": 0.5399603117570195, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029121381496867722, "300–1000 Hz_40ms_envelope_correlation": 0.9993930912683611, "300–1000 Hz_40ms_modulation_mae_db": 0.28696264411830025, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8048116145882261, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09478758748763533, "1000–3000 Hz_10ms_envelope_correlation": 0.9963641239990005, "1000–3000 Hz_10ms_modulation_mae_db": 0.44046870279637024, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5287940723962735, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06886828152167226, "1000–3000 Hz_40ms_envelope_correlation": 0.9989567557421588, "1000–3000 Hz_40ms_modulation_mae_db": 0.30670224940829477, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0774302452198155, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1464179693188002, "3000–6000 Hz_10ms_envelope_correlation": 0.9849663853529206, "3000–6000 Hz_10ms_modulation_mae_db": 0.6058313230575342, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7351363612116198, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08466891091015359, "3000–6000 Hz_40ms_envelope_correlation": 0.9955484975293293, "3000–6000 Hz_40ms_modulation_mae_db": 0.8358153118033506, "mr_stft_db": 5.185290348686437, "band_mae_db": 0.19975852451763149, "rms_gain_error_db": -0.1298839117836651, "output_peak": 0.3742180778242726}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6307969495056901, "全帯域_10ms_rms_envelope_nrmse": 0.04404008450269134, "全帯域_10ms_envelope_correlation": 0.9983274474236762, "全帯域_10ms_modulation_mae_db": 0.22162890094396337, "全帯域_40ms_log_rms_mae_db": 0.3640050270170817, "全帯域_40ms_rms_envelope_nrmse": 0.021714317209967943, "全帯域_40ms_envelope_correlation": 0.9995762012602478, "全帯域_40ms_modulation_mae_db": 0.1509010531336342, "300–1000 Hz_10ms_log_rms_mae_db": 0.8044267938020699, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.04962763519793712, "300–1000 Hz_10ms_envelope_correlation": 0.9982499695029071, "300–1000 Hz_10ms_modulation_mae_db": 0.37931001977042467, "300–1000 Hz_40ms_log_rms_mae_db": 0.5414717129817811, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02716434227025034, "300–1000 Hz_40ms_envelope_correlation": 0.999479426192342, "300–1000 Hz_40ms_modulation_mae_db": 0.3119008160027304, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7880444355546115, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0687953570156849, "1000–3000 Hz_10ms_envelope_correlation": 0.997532226281762, "1000–3000 Hz_10ms_modulation_mae_db": 1.4642019867568734, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5542903076122744, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04063140230668784, "1000–3000 Hz_40ms_envelope_correlation": 0.9993458857762023, "1000–3000 Hz_40ms_modulation_mae_db": 1.412135329975789, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0587805743756835, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14403725513288615, "3000–6000 Hz_10ms_envelope_correlation": 0.9858025957240031, "3000–6000 Hz_10ms_modulation_mae_db": 1.0778239745017029, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7295051410700228, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09333202407451562, "3000–6000 Hz_40ms_envelope_correlation": 0.9947219029956668, "3000–6000 Hz_40ms_modulation_mae_db": 1.1963346133866788, "mr_stft_db": 5.179209016377851, "band_mae_db": 0.10884010219487779, "rms_gain_error_db": -0.006112995333721512, "output_peak": 0.3788698903967981}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.652835887141886, "全帯域_10ms_rms_envelope_nrmse": 0.05564968456938602, "全帯域_10ms_envelope_correlation": 0.9974018521897823, "全帯域_10ms_modulation_mae_db": 0.31712443156835735, "全帯域_40ms_log_rms_mae_db": 0.4105525849428739, "全帯域_40ms_rms_envelope_nrmse": 0.03125882138864392, "全帯域_40ms_envelope_correlation": 0.9992172579426567, "全帯域_40ms_modulation_mae_db": 0.41607509889205635, "300–1000 Hz_10ms_log_rms_mae_db": 0.7971865853484374, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06294788543225079, "300–1000 Hz_10ms_envelope_correlation": 0.997143608534145, "300–1000 Hz_10ms_modulation_mae_db": 0.9657750282729034, "300–1000 Hz_40ms_log_rms_mae_db": 0.5579710317964441, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035642586984152826, "300–1000 Hz_40ms_envelope_correlation": 0.9990825033160461, "300–1000 Hz_40ms_modulation_mae_db": 0.7649567257026989, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7762111169136655, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07639026024698545, "1000–3000 Hz_10ms_envelope_correlation": 0.9974060322838649, "1000–3000 Hz_10ms_modulation_mae_db": 0.39340280913060494, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5304788449937392, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04896552006795737, "1000–3000 Hz_40ms_envelope_correlation": 0.9994665815051995, "1000–3000 Hz_40ms_modulation_mae_db": 0.588032122315692, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0504943746139932, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15381653664372144, "3000–6000 Hz_10ms_envelope_correlation": 0.9846817630506229, "3000–6000 Hz_10ms_modulation_mae_db": 1.0076131972431566, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7419851411201993, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10574411440932363, "3000–6000 Hz_40ms_envelope_correlation": 0.9941135276305606, "3000–6000 Hz_40ms_modulation_mae_db": 1.2631257834131582, "mr_stft_db": 5.173466195579334, "band_mae_db": 0.18469611968986213, "rms_gain_error_db": -0.09384884579613782, "output_peak": 0.36508091591946346}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.481583598387785, "spectral_convergence": 0.19825251053690784, "spectral_convergence_status": "ok", "amplitude_floor": 9.086732072822267e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.072639155629039, "spectral_convergence": 0.2015739079274681, "spectral_convergence_status": "ok", "amplitude_floor": 8.520258431312163e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.993888655803044, "spectral_convergence": 0.2056275441905597, "spectral_convergence_status": "ok", "amplitude_floor": 5.353418087016012e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 3.131933551513939e-05, "output_power": 3.0809472906738017e-05, "delta_db": -0.07128270897185403, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0004897019472039064, "output_power": 0.0004845813552300916, "delta_db": -0.045651307160111544, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.00038033005135275084, "output_power": 0.00037655998085895184, "delta_db": -0.043264788363228425, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0002067238728943134, "output_power": 0.00019375045801058168, "delta_db": -0.2814789491865404, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.323291799953591e-05, "output_power": 1.2287518455009594e-05, "delta_db": -0.3219143819124845, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.500515826026349e-05, "output_power": 2.4847251925918658e-05, "delta_db": -0.027512442729993033, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.8390290595099542e-05, "output_power": 2.9147108555404206e-05, "delta_db": 0.11425640587115608, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.12933728345648113, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.08482164815736852, "pitch": null, "output_rms_dbfs": -29.385538747996378, "output_peak": 0.3651967149834583, "reference_rms_dbfs": -29.30071709983901, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.182703803273289}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00015179812996022924, "log_rms_mae_db": 0.6343435231351587, "rms_envelope_nrmse": 0.05958199288419261, "envelope_correlation": 0.9969929256008326, "rms_gain_error_db": -0.08482174661962319, "reference_mean_power": 0.0011756832947918806, "output_mean_power": 0.00115294389158561}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.744923761629972e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00015071015783187623, "output_power": 0.00014597764157175692, "reference_active": true, "delta_db": -0.1385618178536056}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2413420104691182e-05, "output_power": 1.2543379084719571e-05, "reference_active": true, "delta_db": 0.04523094298865715}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.099936667111779e-06, "output_power": 2.4772345543374096e-06, "reference_active": true, "delta_db": -0.973856918760041}], "active_band_count": 3, "active_band_mae_db": 0.38588322653410123}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001370105991807196, "log_rms_mae_db": 0.409052102149466, "rms_envelope_nrmse": 0.033138773329342334, "envelope_correlation": 0.9990901800171998, "rms_gain_error_db": -0.08482191364826719, "reference_mean_power": 0.0011815960953402045, "output_mean_power": 0.00115874228551557}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.5970704572828427e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000136303861600392, "output_power": 0.00013240889751597315, "reference_active": true, "delta_db": -0.12590990442186697}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.090701624693659e-06, "output_power": 5.332068874564418e-06, "reference_active": true, "delta_db": 0.201181075870111}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5690836910660882e-07, "output_power": 1.3483079649646758e-07, "reference_active": true, "delta_db": -0.6585700833501744}], "active_band_count": 3, "active_band_mae_db": 0.3285536878807174}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.549209054072936e-05, "log_rms_mae_db": 0.7996225558917561, "rms_envelope_nrmse": 0.05313571351154946, "envelope_correlation": 0.9979640127711893, "rms_gain_error_db": -0.04383439982265368, "reference_mean_power": 0.000689577872249739, "output_mean_power": 0.0006826528018333123}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.482675818010425e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.030686777059284e-05, "output_power": 6.894080074384004e-05, "reference_active": true, "delta_db": -0.08521426776919848}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.045775397952136e-06, "output_power": 6.595953220084123e-06, "reference_active": true, "delta_db": 0.3782555787941123}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0022957436919974e-06, "output_power": 1.241056942878696e-06, "reference_active": true, "delta_db": 0.927958223971028}], "active_band_count": 3, "active_band_mae_db": 0.4638093568447796}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.872309512115098e-05, "log_rms_mae_db": 0.5504039301250598, "rms_envelope_nrmse": 0.02828769678830302, "envelope_correlation": 0.99942221462299, "rms_gain_error_db": -0.04383441725137964, "reference_mean_power": 0.0006930459912916024, "output_mean_power": 0.000686086089613636}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.4404474148541786e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.432934367906604e-05, "output_power": 6.304366943958238e-05, "reference_active": true, "delta_db": -0.08767637319057292}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.638974827185174e-06, "output_power": 2.8993213234349733e-06, "reference_active": true, "delta_db": 0.4086110206442462}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.490824439966143e-08, "output_power": 7.038160808337379e-08, "reference_active": true, "delta_db": -0.27070433370771263}], "active_band_count": 3, "active_band_mae_db": 0.2556639091808439}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.800802183872533e-05, "log_rms_mae_db": 0.7987427338700702, "rms_envelope_nrmse": 0.1150366967241754, "envelope_correlation": 0.9924576708404349, "rms_gain_error_db": -0.19612392489090696, "reference_mean_power": 0.0001528560580614903, "output_mean_power": 0.00014610674416693596}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.6939080235935477e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.743995800608424e-06, "output_power": 7.879672263287563e-06, "reference_active": true, "delta_db": -0.45201785975038167}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.01868229376414e-06, "output_power": 1.5413258977764662e-06, "reference_active": true, "delta_db": -1.171734981570299}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.212055898483429e-07, "output_power": 2.3682246389187025e-07, "reference_active": true, "delta_db": -2.5007123091775485}], "active_band_count": 3, "active_band_mae_db": 1.3748217168327432}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.485177873530849e-05, "log_rms_mae_db": 0.5465973057174152, "rms_envelope_nrmse": 0.07505057275060434, "envelope_correlation": 0.9969076304159403, "rms_gain_error_db": -0.19612392654599353, "reference_mean_power": 0.00015362482187073777, "output_mean_power": 0.00014684156338230103}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.6796802400302903e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.417995641253307e-06, "output_power": 7.441478879151313e-06, "reference_active": true, "delta_db": -0.5354944308595293}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.917412489595775e-07, "output_power": 7.629113903509273e-07, "reference_active": true, "delta_db": -1.1392427797739462}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9786028250337687e-08, "output_power": 1.1668295460868245e-08, "reference_active": true, "delta_db": -2.2935120716839092}], "active_band_count": 3, "active_band_mae_db": 1.3227497607724616}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.5712979141900155e-05, "log_rms_mae_db": 1.0684814772837912, "rms_envelope_nrmse": 0.16424258860006308, "envelope_correlation": 0.9808692840174315, "rms_gain_error_db": -0.3824151842710128, "reference_mean_power": 1.157751296991392e-05, "output_mean_power": 1.0601657209080396e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.302605621158197e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.645490651287566e-07, "output_power": 7.733599132633639e-07, "reference_active": true, "delta_db": -0.4840798863418334}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.590093915842518e-07, "output_power": 2.9790978653366386e-07, "reference_active": true, "delta_db": -1.877368012212316}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3044874644069055e-07, "output_power": 1.18593773803586e-07, "reference_active": true, "delta_db": -2.885124609781208}], "active_band_count": 3, "active_band_mae_db": 1.7488575027784525}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.532870280173584e-05, "log_rms_mae_db": 0.7478646499658029, "rms_envelope_nrmse": 0.10199057981713615, "envelope_correlation": 0.9931531060725575, "rms_gain_error_db": -0.3824151538613725, "reference_mean_power": 1.163573961751773e-05, "output_mean_power": 1.0654976071576766e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.177196911262554e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.60049524306651e-07, "output_power": 7.227941735417731e-07, "reference_active": true, "delta_db": -0.7550881693404737}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5501826725164134e-07, "output_power": 1.5314515031189008e-07, "reference_active": true, "delta_db": -2.214680421194277}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7808109251124296e-08, "output_power": 8.518880212693675e-09, "reference_active": true, "delta_db": -3.2023529985310155}], "active_band_count": 3, "active_band_mae_db": 2.057373863021922}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.89412610540104, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "966361689b451fafb715605bed173e714289e4d40627126815c69dbd214a5cb5", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9960377991973421, "standard_deviation": 0.0016473667510409908, "minimum": 0.9924576708404349, "maximum": 0.997532226281762, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.7910526500093854, "standard_deviation": 0.017070388827744667, "minimum": 0.7700340123447442, "maximum": 0.8173423671580534, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7996312833671257, "standard_deviation": 0.5604279449922502, "minimum": 0.192729408763188, "maximum": 1.525549954447742, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08550173950241827, "standard_deviation": 0.015032375860569899, "minimum": 0.0687953570156849, "maximum": 0.1150366967241754, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.998726921977599, "standard_deviation": 0.0008626123561758411, "minimum": 0.9969076304159403, "maximum": 0.9994665815051995, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5455627201857546, "standard_deviation": 0.015842143798347377, "minimum": 0.5287940723962735, "maximum": 0.5752522717402202, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7333889959331488, "standard_deviation": 0.5320052440936525, "minimum": 0.08407176883270794, "maximum": 1.412135329975789, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05261249776059697, "standard_deviation": 0.013962078996890788, "minimum": 0.037892976077724703, "maximum": 0.07505057275060434, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9844146220161494, "standard_deviation": 0.0016878288245266168, "minimum": 0.9808692840174315, "maximum": 0.9861816571134298, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.0685077678635364, "standard_deviation": 0.013445298546703626, "minimum": 1.0504943746139932, "maximum": 1.0930595478388871, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.1073745852162045, "standard_deviation": 0.5188366599986353, "minimum": 0.4741319093487, "maximum": 1.858358446856121, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15077616935478477, "standard_deviation": 0.006763016854388423, "minimum": 0.14296693715412623, "maximum": 0.16424258860006308, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9946041773491905, "standard_deviation": 0.0008491922902378407, "minimum": 0.9931531060725575, "maximum": 0.9955484975293293, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7455342600359239, "standard_deviation": 0.02328568615367229, "minimum": 0.7185180012273842, "maximum": 0.7816831753846505, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.3645201718601063, "standard_deviation": 0.6810579849030687, "minimum": 0.554799529513672, "maximum": 2.360137298059304, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09470712616091809, "standard_deviation": 0.00952540286490804, "minimum": 0.07973142806192499, "maximum": 0.10574411440932363, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9976647214993001, "standard_deviation": 0.0005840876569689234, "minimum": 0.9964972158355226, "maximum": 0.9982499695029071, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8110485999884862, "standard_deviation": 0.022837290286135587, "minimum": 0.7924925478137622, "maximum": 0.851023043397664, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5501637205482652, "standard_deviation": 0.26049875483171003, "minimum": 0.20271311752208562, "maximum": 0.9657750282729034, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.05673974464833624, "standard_deviation": 0.006618559741077012, "minimum": 0.04962763519793712, "maximum": 0.06969012594523415, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9992831763230942, "standard_deviation": 0.00025349169391499724, "minimum": 0.9987535660217518, "maximum": 0.9995074846034471, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5447569441471924, "standard_deviation": 0.018616707469539605, "minimum": 0.5139083015094099, "maximum": 0.5666000800288941, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5023756664433568, "standard_deviation": 0.28434749330694986, "minimum": 0.16529391090643358, "maximum": 0.9195303262599138, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03140864631181606, "standard_deviation": 0.004888489925947147, "minimum": 0.02716434227025034, "maximum": 0.04148033193339683, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.15260929835276477, "standard_deviation": 0.043033981174161656, "minimum": 0.10808397882506489, "maximum": 0.20917652012897753, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.1767578572325785, "standard_deviation": 0.007107986922928833, "minimum": 5.16736502101861, "maximum": 5.185290348686437, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3735198596870051, "standard_deviation": 0.006006642714205476, "minimum": 0.36508091591946346, "maximum": 0.38156681981728807, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07286243652668938, "standard_deviation": 0.049011017344939525, "minimum": -0.1298839117836651, "maximum": -0.0004503990811352804, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9976065518018068, "standard_deviation": 0.0004062224891578396, "minimum": 0.9969929256008326, "maximum": 0.9983274474236762, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.6266063351181446, "standard_deviation": 0.014240047396268869, "minimum": 0.6108595072665274, "maximum": 0.652835887141886, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3804706765826934, "standard_deviation": 0.16375460880171078, "minimum": 0.22142035237940075, "maximum": 0.6471413261446377, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05323154347409367, "standard_deviation": 0.004628619427083171, "minimum": 0.04404008450269134, "maximum": 0.05958199288419261, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9993494027600456, "standard_deviation": 0.0001569054131031586, "minimum": 0.9990901800171998, "maximum": 0.9995762012602478, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.3865683546847629, "standard_deviation": 0.019756846893177755, "minimum": 0.3581628739968259, "maximum": 0.4105525849428739, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4159281943582379, "standard_deviation": 0.14948756581999012, "minimum": 0.1509010531336342, "maximum": 0.659475715502889, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.028369800644617624, "standard_deviation": 0.0036599421380845375, "minimum": 0.021714317209967943, "maximum": 0.033138773329342334, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_falset10_VOICEACTRESS100_004", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 2.1257176399230957, "predicted_mos": 2.1257176399230957, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "7740719872ab3d1c01d70e2bbb850da3cb576e87b5d5882f1c7161cc5617bbb3", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.395015699788928}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6129943546887251, "全帯域_10ms_rms_envelope_nrmse": 0.05450753212505229, "全帯域_10ms_envelope_correlation": 0.997454113325756, "全帯域_10ms_modulation_mae_db": 0.12472431721504747, "全帯域_40ms_log_rms_mae_db": 0.3742563343529029, "全帯域_40ms_rms_envelope_nrmse": 0.0287680170406976, "全帯域_40ms_envelope_correlation": 0.9992833563156432, "全帯域_40ms_modulation_mae_db": 0.11234857475547548, "300–1000 Hz_10ms_log_rms_mae_db": 0.9346733262892888, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06585393674052045, "300–1000 Hz_10ms_envelope_correlation": 0.9968599288483758, "300–1000 Hz_10ms_modulation_mae_db": 0.8163327764851306, "300–1000 Hz_40ms_log_rms_mae_db": 0.6433622542048612, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.036882855294942396, "300–1000 Hz_40ms_envelope_correlation": 0.9989901175922059, "300–1000 Hz_40ms_modulation_mae_db": 0.5303942492848912, "1000–3000 Hz_10ms_log_rms_mae_db": 0.960640617811043, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09295516354993132, "1000–3000 Hz_10ms_envelope_correlation": 0.9954143446958882, "1000–3000 Hz_10ms_modulation_mae_db": 0.19205072496615835, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7333272216749721, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.060947271435277006, "1000–3000 Hz_40ms_envelope_correlation": 0.9983303761508711, "1000–3000 Hz_40ms_modulation_mae_db": 0.481396831020827, "3000–6000 Hz_10ms_log_rms_mae_db": 1.214397206663546, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1882229712367108, "3000–6000 Hz_10ms_envelope_correlation": 0.9740748406593204, "3000–6000 Hz_10ms_modulation_mae_db": 0.4986906932692215, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8299617836514851, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11452833651137388, "3000–6000 Hz_40ms_envelope_correlation": 0.989916325795038, "3000–6000 Hz_40ms_modulation_mae_db": 0.7186500258099334, "mr_stft_db": 5.4372957501882935, "band_mae_db": 0.14772467155897018, "rms_gain_error_db": -0.051012216755324136, "output_peak": 0.37749390507640823}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6223956091487974, "全帯域_10ms_rms_envelope_nrmse": 0.05294417512948523, "全帯域_10ms_envelope_correlation": 0.9975910194109667, "全帯域_10ms_modulation_mae_db": 0.3346354281624368, "全帯域_40ms_log_rms_mae_db": 0.39434402077414593, "全帯域_40ms_rms_envelope_nrmse": 0.029685420587850984, "全帯域_40ms_envelope_correlation": 0.9992245473360836, "全帯域_40ms_modulation_mae_db": 0.30144182999751873, "300–1000 Hz_10ms_log_rms_mae_db": 0.9414707500054036, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.058045716335772844, "300–1000 Hz_10ms_envelope_correlation": 0.9975586929897375, "300–1000 Hz_10ms_modulation_mae_db": 0.5143489173932866, "300–1000 Hz_40ms_log_rms_mae_db": 0.6546507330089195, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03421785120108317, "300–1000 Hz_40ms_envelope_correlation": 0.9991293020631705, "300–1000 Hz_40ms_modulation_mae_db": 0.33408965400121793, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9972172249062828, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08526856158558407, "1000–3000 Hz_10ms_envelope_correlation": 0.9958901926854109, "1000–3000 Hz_10ms_modulation_mae_db": 0.5695020079085819, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7654048160551723, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04623885975315499, "1000–3000 Hz_40ms_envelope_correlation": 0.9988950372174882, "1000–3000 Hz_40ms_modulation_mae_db": 0.33370222962830765, "3000–6000 Hz_10ms_log_rms_mae_db": 1.218109617003444, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15213056985791373, "3000–6000 Hz_10ms_envelope_correlation": 0.9832533057521706, "3000–6000 Hz_10ms_modulation_mae_db": 0.4184295533983018, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8325549707587484, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09026433421123113, "3000–6000 Hz_40ms_envelope_correlation": 0.9942216027469302, "3000–6000 Hz_40ms_modulation_mae_db": 0.6715568851942807, "mr_stft_db": 5.431753693737682, "band_mae_db": 0.16875159276099927, "rms_gain_error_db": -0.04005813986804281, "output_peak": 0.375355737198765}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6209036552849335, "全帯域_10ms_rms_envelope_nrmse": 0.05005763763286576, "全帯域_10ms_envelope_correlation": 0.9978437989077095, "全帯域_10ms_modulation_mae_db": 0.4409364887419878, "全帯域_40ms_log_rms_mae_db": 0.376098188976341, "全帯域_40ms_rms_envelope_nrmse": 0.02444830102547162, "全帯域_40ms_envelope_correlation": 0.999472950609345, "全帯域_40ms_modulation_mae_db": 0.4456706482211921, "300–1000 Hz_10ms_log_rms_mae_db": 0.9168521011498164, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.04869469518101881, "300–1000 Hz_10ms_envelope_correlation": 0.9982868464253681, "300–1000 Hz_10ms_modulation_mae_db": 0.557580524578082, "300–1000 Hz_40ms_log_rms_mae_db": 0.6432550453691076, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.025802631598238854, "300–1000 Hz_40ms_envelope_correlation": 0.9995102756955506, "300–1000 Hz_40ms_modulation_mae_db": 0.24914649784145318, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9098953540867685, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08352915885197341, "1000–3000 Hz_10ms_envelope_correlation": 0.9959729587271962, "1000–3000 Hz_10ms_modulation_mae_db": 1.2097519431551402, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6790512325093845, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.048307244132501884, "1000–3000 Hz_40ms_envelope_correlation": 0.9986560450651853, "1000–3000 Hz_40ms_modulation_mae_db": 1.215136793315368, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2543038129432822, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15700064042159512, "3000–6000 Hz_10ms_envelope_correlation": 0.982011499619522, "3000–6000 Hz_10ms_modulation_mae_db": 0.5440885134768445, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8772499469923093, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08583908776393075, "3000–6000 Hz_40ms_envelope_correlation": 0.9946258138409761, "3000–6000 Hz_40ms_modulation_mae_db": 0.6952660711664859, "mr_stft_db": 5.44400938445501, "band_mae_db": 0.07754059581945534, "rms_gain_error_db": -0.03188337043107027, "output_peak": 0.37343725493251}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6074208114977392, "全帯域_10ms_rms_envelope_nrmse": 0.04762339467849213, "全帯域_10ms_envelope_correlation": 0.998050536750073, "全帯域_10ms_modulation_mae_db": 0.5517557989824019, "全帯域_40ms_log_rms_mae_db": 0.36828863161963404, "全帯域_40ms_rms_envelope_nrmse": 0.026805519771368892, "全帯域_40ms_envelope_correlation": 0.9993673706146274, "全帯域_40ms_modulation_mae_db": 0.7271786620950175, "300–1000 Hz_10ms_log_rms_mae_db": 0.936883231569602, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05877851831898749, "300–1000 Hz_10ms_envelope_correlation": 0.9975026609818911, "300–1000 Hz_10ms_modulation_mae_db": 0.736609987723195, "300–1000 Hz_40ms_log_rms_mae_db": 0.6633819319306279, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0362488157799678, "300–1000 Hz_40ms_envelope_correlation": 0.9990328137669099, "300–1000 Hz_40ms_modulation_mae_db": 1.1342601998873971, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9911828813985845, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08741493088359369, "1000–3000 Hz_10ms_envelope_correlation": 0.9955676459143354, "1000–3000 Hz_10ms_modulation_mae_db": 0.9489878199892546, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6893993494426505, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.049543410577047364, "1000–3000 Hz_40ms_envelope_correlation": 0.9985599122259513, "1000–3000 Hz_40ms_modulation_mae_db": 0.815716935960487, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2353072163376015, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1641038290525685, "3000–6000 Hz_10ms_envelope_correlation": 0.9809585722229756, "3000–6000 Hz_10ms_modulation_mae_db": 0.8164425156789855, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8730697643532991, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10241276282375393, "3000–6000 Hz_40ms_envelope_correlation": 0.993183284342007, "3000–6000 Hz_40ms_modulation_mae_db": 1.2361008306665089, "mr_stft_db": 5.442702686535196, "band_mae_db": 0.11467102683582768, "rms_gain_error_db": -0.03273853092953352, "output_peak": 0.4029954948477796}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6473020537243733, "全帯域_10ms_rms_envelope_nrmse": 0.0539209528315856, "全帯域_10ms_envelope_correlation": 0.9974989158762506, "全帯域_10ms_modulation_mae_db": 0.250155805841835, "全帯域_40ms_log_rms_mae_db": 0.4001816399217689, "全帯域_40ms_rms_envelope_nrmse": 0.029594062829453704, "全帯域_40ms_envelope_correlation": 0.9992262103677978, "全帯域_40ms_modulation_mae_db": 0.15071122308663887, "300–1000 Hz_10ms_log_rms_mae_db": 0.9115586630042415, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05859888729293186, "300–1000 Hz_10ms_envelope_correlation": 0.9975326001266464, "300–1000 Hz_10ms_modulation_mae_db": 0.3385219618307589, "300–1000 Hz_40ms_log_rms_mae_db": 0.6296955704903271, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03403741450703419, "300–1000 Hz_40ms_envelope_correlation": 0.9991519097346172, "300–1000 Hz_40ms_modulation_mae_db": 0.42083440886051243, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9394475149077024, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08726665589557177, "1000–3000 Hz_10ms_envelope_correlation": 0.996067743268431, "1000–3000 Hz_10ms_modulation_mae_db": 1.1982298457911031, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6779670171194975, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05410766434833959, "1000–3000 Hz_40ms_envelope_correlation": 0.9988455100576549, "1000–3000 Hz_40ms_modulation_mae_db": 1.0732181391352185, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2357312032639969, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16223068415643782, "3000–6000 Hz_10ms_envelope_correlation": 0.981490051680935, "3000–6000 Hz_10ms_modulation_mae_db": 0.9936837244023268, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8571382666751395, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11791594721610678, "3000–6000 Hz_40ms_envelope_correlation": 0.9898448027709212, "3000–6000 Hz_40ms_modulation_mae_db": 1.0357752902240975, "mr_stft_db": 5.44165673904206, "band_mae_db": 0.13505244319103737, "rms_gain_error_db": -0.03795503338500378, "output_peak": 0.3644549907173962}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.625737941752091, "全帯域_10ms_rms_envelope_nrmse": 0.05439920499202348, "全帯域_10ms_envelope_correlation": 0.9975298283040682, "全帯域_10ms_modulation_mae_db": 0.43810603265449943, "全帯域_40ms_log_rms_mae_db": 0.38262887989481864, "全帯域_40ms_rms_envelope_nrmse": 0.029339711446557042, "全帯域_40ms_envelope_correlation": 0.9993311760219729, "全帯域_40ms_modulation_mae_db": 0.46089957670834963, "300–1000 Hz_10ms_log_rms_mae_db": 0.9782704826435173, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.061200844884030534, "300–1000 Hz_10ms_envelope_correlation": 0.9973164851583636, "300–1000 Hz_10ms_modulation_mae_db": 0.4656285924324761, "300–1000 Hz_40ms_log_rms_mae_db": 0.7060203421730026, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03416951685073603, "300–1000 Hz_40ms_envelope_correlation": 0.9991761324401001, "300–1000 Hz_40ms_modulation_mae_db": 0.5133000234784938, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9015997426411833, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07850591793462024, "1000–3000 Hz_10ms_envelope_correlation": 0.9964695678200884, "1000–3000 Hz_10ms_modulation_mae_db": 0.6565952703161997, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6513361618288833, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.044705683166917025, "1000–3000 Hz_40ms_envelope_correlation": 0.9988856652931015, "1000–3000 Hz_40ms_modulation_mae_db": 0.8555080221570183, "3000–6000 Hz_10ms_log_rms_mae_db": 1.291402079307929, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14689327170902916, "3000–6000 Hz_10ms_envelope_correlation": 0.984506208144152, "3000–6000 Hz_10ms_modulation_mae_db": 1.3303096842996585, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8928108003260317, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07925395320634676, "3000–6000 Hz_40ms_envelope_correlation": 0.9958052000661921, "3000–6000 Hz_40ms_modulation_mae_db": 1.698690324104095, "mr_stft_db": 5.435361761275128, "band_mae_db": 0.1245303348636477, "rms_gain_error_db": -0.0977730523664057, "output_peak": 0.37663709188682987}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.600736786556278, "全帯域_10ms_rms_envelope_nrmse": 0.04820185026313708, "全帯域_10ms_envelope_correlation": 0.9979960803878285, "全帯域_10ms_modulation_mae_db": 0.3693542059404842, "全帯域_40ms_log_rms_mae_db": 0.3687068462478225, "全帯域_40ms_rms_envelope_nrmse": 0.02455746966168942, "全帯域_40ms_envelope_correlation": 0.999459506284393, "全帯域_40ms_modulation_mae_db": 0.5058779664769834, "300–1000 Hz_10ms_log_rms_mae_db": 0.9263753915856234, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05247541748760769, "300–1000 Hz_10ms_envelope_correlation": 0.9980171295256843, "300–1000 Hz_10ms_modulation_mae_db": 0.3913307962966897, "300–1000 Hz_40ms_log_rms_mae_db": 0.6418569086981879, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029292500208517543, "300–1000 Hz_40ms_envelope_correlation": 0.9993779656544597, "300–1000 Hz_40ms_modulation_mae_db": 0.5045726562643799, "1000–3000 Hz_10ms_log_rms_mae_db": 0.928016813271837, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07292478657090219, "1000–3000 Hz_10ms_envelope_correlation": 0.9969401233862832, "1000–3000 Hz_10ms_modulation_mae_db": 0.17585849305607526, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6813449005043004, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.040156468712975624, "1000–3000 Hz_40ms_envelope_correlation": 0.9990669087414576, "1000–3000 Hz_40ms_modulation_mae_db": 0.08956160763410076, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2188563608954208, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15206043533604083, "3000–6000 Hz_10ms_envelope_correlation": 0.9835526237507409, "3000–6000 Hz_10ms_modulation_mae_db": 0.4800962316662827, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8449341612154111, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09352013552491731, "3000–6000 Hz_40ms_envelope_correlation": 0.9941443400268628, "3000–6000 Hz_40ms_modulation_mae_db": 0.7851547298774507, "mr_stft_db": 5.4484355368846416, "band_mae_db": 0.08465774157279173, "rms_gain_error_db": -0.013110696662817164, "output_peak": 0.3753026156865441}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6028915550174221, "全帯域_10ms_rms_envelope_nrmse": 0.05346539313801814, "全帯域_10ms_envelope_correlation": 0.9975406510643935, "全帯域_10ms_modulation_mae_db": 0.2760543017946249, "全帯域_40ms_log_rms_mae_db": 0.3720779636105801, "全帯域_40ms_rms_envelope_nrmse": 0.026215263944697243, "全帯域_40ms_envelope_correlation": 0.9993955691069194, "全帯域_40ms_modulation_mae_db": 0.3835988946102464, "300–1000 Hz_10ms_log_rms_mae_db": 0.9721248284876001, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05738763369248337, "300–1000 Hz_10ms_envelope_correlation": 0.9976156225970333, "300–1000 Hz_10ms_modulation_mae_db": 0.43999924994416556, "300–1000 Hz_40ms_log_rms_mae_db": 0.6327652602055436, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02873816754946432, "300–1000 Hz_40ms_envelope_correlation": 0.9993876227354827, "300–1000 Hz_40ms_modulation_mae_db": 0.686193220904069, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9070506709736071, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09227415129303666, "1000–3000 Hz_10ms_envelope_correlation": 0.995063034766389, "1000–3000 Hz_10ms_modulation_mae_db": 0.8708608755044089, "1000–3000 Hz_40ms_log_rms_mae_db": 0.658644203886335, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.054219004541048436, "1000–3000 Hz_40ms_envelope_correlation": 0.9982796072339247, "1000–3000 Hz_40ms_modulation_mae_db": 0.895921884038811, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2364761968160816, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1490004604763366, "3000–6000 Hz_10ms_envelope_correlation": 0.9844121252339474, "3000–6000 Hz_10ms_modulation_mae_db": 1.2892017894117955, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8605103222494199, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0914669267340197, "3000–6000 Hz_40ms_envelope_correlation": 0.9946527038000955, "3000–6000 Hz_40ms_modulation_mae_db": 1.6772969920573866, "mr_stft_db": 5.439433541814577, "band_mae_db": 0.14665341931399517, "rms_gain_error_db": -0.022734879418464058, "output_peak": 0.3811088310323184}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.775562846642417, "spectral_convergence": 0.20242956365478657, "spectral_convergence_status": "ok", "amplitude_floor": 9.086732072822267e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.362797843377808, "spectral_convergence": 0.20421701618153595, "spectral_convergence_status": "ok", "amplitude_floor": 8.520258431312163e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.173526560544656, "spectral_convergence": 0.21011632247154843, "spectral_convergence_status": "ok", "amplitude_floor": 5.353418087016012e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 3.131933551513939e-05, "output_power": 3.1663392589014e-05, "delta_db": 0.04744906404833657, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0004897019472039064, "output_power": 0.00048166347025164444, "delta_db": -0.07188120591105499, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.00038033005135275084, "output_power": 0.00038567319621773846, "delta_db": 0.060588149577655986, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0002067238728943134, "output_power": 0.00019494224754278475, "delta_db": -0.2548466387761288, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.323291799953591e-05, "output_power": 1.2180283279327206e-05, "delta_db": -0.35998232422974663, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.500515826026349e-05, "output_power": 2.5888254929609134e-05, "delta_db": 0.15073168996969724, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.8390290595099542e-05, "output_power": 2.8975384032602596e-05, "delta_db": 0.08859362840017095, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.14772467155897018, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.051012216755324136, "pitch": null, "output_rms_dbfs": -29.351729316594334, "output_peak": 0.37749390507640823, "reference_rms_dbfs": -29.30071709983901, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.4372957501882935}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00015179812996022924, "log_rms_mae_db": 0.6129943546887251, "rms_envelope_nrmse": 0.05450753212505229, "envelope_correlation": 0.997454113325756, "rms_gain_error_db": -0.05101225487086425, "reference_mean_power": 0.0011756832947918806, "output_mean_power": 0.001161954499137658}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.744923761629972e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00015071015783187623, "output_power": 0.00014474906285241656, "reference_active": true, "delta_db": -0.1752676399515558}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2413420104691182e-05, "output_power": 1.209224786614714e-05, "reference_active": true, "delta_db": -0.11384412634569686}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.099936667111779e-06, "output_power": 3.1612507082903803e-06, "reference_active": true, "delta_db": 0.08506118534788976}], "active_band_count": 3, "active_band_mae_db": 0.12472431721504747}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001370105991807196, "log_rms_mae_db": 0.3742563343529029, "rms_envelope_nrmse": 0.0287680170406976, "envelope_correlation": 0.9992833563156432, "rms_gain_error_db": -0.051012245236001376, "reference_mean_power": 0.0011815960953402045, "output_mean_power": 0.0011677982567856486}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.5970704572828427e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000136303861600392, "output_power": 0.0001310744143390928, "reference_active": true, "delta_db": -0.16990234033793938}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.090701624693659e-06, "output_power": 5.139368248756036e-06, "reference_active": true, "delta_db": 0.04132094108367562}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5690836910660882e-07, "output_power": 1.5242768861520959e-07, "reference_active": true, "delta_db": -0.12582244284481145}], "active_band_count": 3, "active_band_mae_db": 0.11234857475547548}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.549209054072936e-05, "log_rms_mae_db": 0.9346733262892888, "rms_envelope_nrmse": 0.06585393674052045, "envelope_correlation": 0.9968599288483758, "rms_gain_error_db": 0.001267446111072417, "reference_mean_power": 0.000689577872249739, "output_mean_power": 0.0006897791481986386}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.482675818010425e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.030686777059284e-05, "output_power": 6.757351615125376e-05, "reference_active": true, "delta_db": -0.17221232395423086}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.045775397952136e-06, "output_power": 6.322786385482558e-06, "reference_active": true, "delta_db": 0.19456500484044081}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0022957436919974e-06, "output_power": 1.618892407178389e-06, "reference_active": true, "delta_db": 2.08222100066072}], "active_band_count": 3, "active_band_mae_db": 0.8163327764851306}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.872309512115098e-05, "log_rms_mae_db": 0.6433622542048612, "rms_envelope_nrmse": 0.036882855294942396, "envelope_correlation": 0.9989901175922059, "rms_gain_error_db": 0.001267437621901484, "reference_mean_power": 0.0006930459912916024, "output_mean_power": 0.0006932482781698481}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.4404474148541786e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.432934367906604e-05, "output_power": 6.17694329034119e-05, "reference_active": true, "delta_db": -0.17635506369433393}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.638974827185174e-06, "output_power": 2.8425667638940915e-06, "reference_active": true, "delta_db": 0.3227542626982071}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.490824439966143e-08, "output_power": 9.632454381709661e-08, "reference_active": true, "delta_db": 1.0920734214621326}], "active_band_count": 3, "active_band_mae_db": 0.5303942492848912}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.800802183872533e-05, "log_rms_mae_db": 0.960640617811043, "rms_envelope_nrmse": 0.09295516354993132, "envelope_correlation": 0.9954143446958882, "rms_gain_error_db": -0.2539109988258425, "reference_mean_power": 0.0001528560580614903, "output_mean_power": 0.000144175529699293}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.6939080235935477e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.743995800608424e-06, "output_power": 8.298130778706372e-06, "reference_active": true, "delta_db": -0.22729665330845605}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.01868229376414e-06, "output_power": 1.918776730380848e-06, "reference_active": true, "delta_db": -0.22043530764052716}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.212055898483429e-07, "output_power": 4.3384654925978803e-07, "reference_active": true, "delta_db": 0.12842021394949177}], "active_band_count": 3, "active_band_mae_db": 0.19205072496615835}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.485177873530849e-05, "log_rms_mae_db": 0.7333272216749721, "rms_envelope_nrmse": 0.060947271435277006, "envelope_correlation": 0.9983303761508711, "rms_gain_error_db": -0.25391100934971567, "reference_mean_power": 0.00015362482187073777, "output_mean_power": 0.00014490063590146752}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.6796802400302903e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.417995641253307e-06, "output_power": 7.994845649499082e-06, "reference_active": true, "delta_db": -0.22398612974405405}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.917412489595775e-07, "output_power": 9.570645754736465e-07, "reference_active": true, "delta_db": -0.15457135315555195}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9786028250337687e-08, "output_power": 2.528843339353721e-08, "reference_active": true, "delta_db": 1.065633010162875}], "active_band_count": 3, "active_band_mae_db": 0.481396831020827}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.5712979141900155e-05, "log_rms_mae_db": 1.214397206663546, "rms_envelope_nrmse": 0.1882229712367108, "envelope_correlation": 0.9740748406593204, "rms_gain_error_db": -0.065125188419186, "reference_mean_power": 1.157751296991392e-05, "output_mean_power": 1.1405196111818793e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.302605621158197e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.645490651287566e-07, "output_power": 8.813143418969334e-07, "reference_active": true, "delta_db": 0.08341192075648846}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.590093915842518e-07, "output_power": 4.903345760793448e-07, "reference_active": true, "delta_db": 0.2867094719065877}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3044874644069055e-07, "output_power": 1.7781945766352533e-07, "reference_active": true, "delta_db": -1.1259506871445883}], "active_band_count": 3, "active_band_mae_db": 0.4986906932692215}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.532870280173584e-05, "log_rms_mae_db": 0.8299617836514851, "rms_envelope_nrmse": 0.11452833651137388, "envelope_correlation": 0.989916325795038, "rms_gain_error_db": -0.06512527566809434, "reference_mean_power": 1.163573961751773e-05, "output_mean_power": 1.1462555898027237e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.177196911262554e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.60049524306651e-07, "output_power": 8.838361975932369e-07, "reference_active": true, "delta_db": 0.11848324180608714}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5501826725164134e-07, "output_power": 2.622962632266733e-07, "reference_active": true, "delta_db": 0.12220812947221699}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7808109251124296e-08, "output_power": 1.1457554737860501e-08, "reference_active": true, "delta_db": -1.915258706151496}], "active_band_count": 3, "active_band_mae_db": 0.7186500258099334}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8833965890139551, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "60aa110affb446d878867c3b3ce3146bef027c3d98f796d7ec3405e970fde903", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9959232014080028, "standard_deviation": 0.0005955004853120116, "minimum": 0.995063034766389, "maximum": 0.9969401233862832, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.9418813524996261, "standard_deviation": 0.03761011858159147, "minimum": 0.9015997426411833, "maximum": 0.9972172249062828, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7277296225858653, "standard_deviation": 0.40439856968205357, "minimum": 0.17585849305607526, "maximum": 1.2097519431551402, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08501741582065167, "standard_deviation": 0.006733545850158069, "minimum": 0.07292478657090219, "maximum": 0.09295516354993132, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9986898827482044, "standard_deviation": 0.0002834471320771636, "minimum": 0.9982796072339247, "maximum": 0.9990669087414576, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6920593628776495, "standard_deviation": 0.038447040877539536, "minimum": 0.6513361618288833, "maximum": 0.7654048160551723, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7200203053612673, "standard_deviation": 0.38396543110817194, "minimum": 0.08956160763410076, "maximum": 1.215136793315368, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04977820083340774, "standard_deviation": 0.00650567960481415, "minimum": 0.040156468712975624, "maximum": 0.060947271435277006, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9817824033829705, "standard_deviation": 0.003377551074863751, "minimum": 0.9740748406593204, "maximum": 0.984506208144152, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2380729616539128, "standard_deviation": 0.025217546072698948, "minimum": 1.214397206663546, "maximum": 1.291402079307929, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7963678382004271, "standard_deviation": 0.3707978591828737, "minimum": 0.4184295533983018, "maximum": 1.3303096842996585, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1589553577808291, "standard_deviation": 0.013289954439989635, "minimum": 0.14689327170902916, "maximum": 0.1882229712367108, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9932992591736278, "standard_deviation": 0.002230539209597653, "minimum": 0.9898448027709212, "maximum": 0.9958052000661921, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8585287520277305, "standard_deviation": 0.022099014137393895, "minimum": 0.8299617836514851, "maximum": 0.8928108003260317, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.0648113936375299, "standard_deviation": 0.4303441594871924, "minimum": 0.6715568851942807, "maximum": 1.698690324104095, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09690018549896003, "standard_deviation": 0.013635664453429302, "minimum": 0.07925395320634676, "maximum": 0.11791594721610678, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9975862458316376, "standard_deviation": 0.0004290014273975119, "minimum": 0.9968599288483758, "maximum": 0.9982868464253681, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.9397760968418867, "standard_deviation": 0.024103494161958623, "minimum": 0.9115586630042415, "maximum": 0.9782704826435173, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.532544100835473, "standard_deviation": 0.1663751390797431, "minimum": 0.3385219618307589, "maximum": 0.8163327764851306, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.05762945624166913, "standard_deviation": 0.005200039255785558, "minimum": 0.04869469518101881, "maximum": 0.06585393674052045, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.999219517460312, "standard_deviation": 0.00018515631086765235, "minimum": 0.9989901175922059, "maximum": 0.9995102756955506, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.6518735057600722, "standard_deviation": 0.02442502843364784, "minimum": 0.6296955704903271, "maximum": 0.7060203421730026, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5465988638153019, "standard_deviation": 0.27187833604530776, "minimum": 0.24914649784145318, "maximum": 1.1342601998873971, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03242371912374804, "standard_deviation": 0.0039751480574304505, "minimum": 0.025802631598238854, "maximum": 0.036882855294942396, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.12494772823959055, "standard_deviation": 0.03159410890415917, "minimum": 0.07754059581945534, "maximum": 0.16875159276099927, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.440081136741574, "standard_deviation": 0.005269572319259947, "minimum": 5.431753693737682, "maximum": 5.4484355368846416, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.37834824017231894, "standard_deviation": 0.011046246944045093, "minimum": 0.3644549907173962, "maximum": 0.4029954948477796, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.04090823997708268, "standard_deviation": 0.025624508911601483, "minimum": -0.0977730523664057, "maximum": -0.013110696662817164, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9976881180033808, "standard_deviation": 0.00023821077697634748, "minimum": 0.997454113325756, "maximum": 0.998050536750073, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.6175478459587949, "standard_deviation": 0.015155680241864268, "minimum": 0.600736786556278, "maximum": 0.6473020537243733, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3482152974166647, "standard_deviation": 0.1328310726831617, "minimum": 0.12472431721504747, "maximum": 0.5517557989824019, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05189001759883246, "standard_deviation": 0.0028291700842118512, "minimum": 0.04762339467849213, "maximum": 0.05450753212505229, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9993450858320978, "standard_deviation": 9.647467083300812e-05, "minimum": 0.9992245473360836, "maximum": 0.999472950609345, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.3795728131747518, "standard_deviation": 0.011917361756394157, "minimum": 0.36828863161963404, "maximum": 0.4001816399217689, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.38596592199392776, "standard_deviation": 0.19904984672773812, "minimum": 0.11234857475547548, "maximum": 0.7271786620950175, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.027426720788473316, "standard_deviation": 0.002210843727165506, "minimum": 0.02444830102547162, "maximum": 0.029685420587850984, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_falset10_VOICEACTRESS100_004", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 2.3321328163146973, "predicted_mos": 2.3321328163146973, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "28bde18b486c2d0fb6c77d9cd06651a2858fab886594c4c3a4c4d8be40f29cfa", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.585587800014764}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6007585719976909, "全帯域_10ms_rms_envelope_nrmse": 0.04725635730136167, "全帯域_10ms_envelope_correlation": 0.9980972650091583, "全帯域_10ms_modulation_mae_db": 0.4034972540977649, "全帯域_40ms_log_rms_mae_db": 0.35100957012767225, "全帯域_40ms_rms_envelope_nrmse": 0.021258106810151136, "全帯域_40ms_envelope_correlation": 0.9996282985178596, "全帯域_40ms_modulation_mae_db": 0.15230682462283746, "300–1000 Hz_10ms_log_rms_mae_db": 0.7885481408073156, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05142113703022608, "300–1000 Hz_10ms_envelope_correlation": 0.998125475401032, "300–1000 Hz_10ms_modulation_mae_db": 0.3095605663540654, "300–1000 Hz_40ms_log_rms_mae_db": 0.5071372096195679, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.026747274512007677, "300–1000 Hz_40ms_envelope_correlation": 0.9995220660079687, "300–1000 Hz_40ms_modulation_mae_db": 0.31050140368578455, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7796192791626745, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0819958102291951, "1000–3000 Hz_10ms_envelope_correlation": 0.9961041964246529, "1000–3000 Hz_10ms_modulation_mae_db": 0.9099221267528027, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5519082455820207, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.047139357152763996, "1000–3000 Hz_40ms_envelope_correlation": 0.9987030532117194, "1000–3000 Hz_40ms_modulation_mae_db": 0.9053214719191787, "3000–6000 Hz_10ms_log_rms_mae_db": 1.01398213961664, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12865715524165414, "3000–6000 Hz_10ms_envelope_correlation": 0.9882447928578336, "3000–6000 Hz_10ms_modulation_mae_db": 0.2750771556437536, "3000–6000 Hz_40ms_log_rms_mae_db": 0.709136568190342, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08478469292050335, "3000–6000 Hz_40ms_envelope_correlation": 0.9950047302482272, "3000–6000 Hz_40ms_modulation_mae_db": 0.36906813626804236, "mr_stft_db": 5.162793974023795, "band_mae_db": 0.0789160596853231, "rms_gain_error_db": -0.05474511177738528, "output_peak": 0.372005703323663}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6648415410746181, "全帯域_10ms_rms_envelope_nrmse": 0.046293046287222715, "全帯域_10ms_envelope_correlation": 0.9982101336842609, "全帯域_10ms_modulation_mae_db": 0.4022960944100422, "全帯域_40ms_log_rms_mae_db": 0.4218787515092893, "全帯域_40ms_rms_envelope_nrmse": 0.023806377631667736, "全帯域_40ms_envelope_correlation": 0.9995623072588413, "全帯域_40ms_modulation_mae_db": 0.2676104117123233, "300–1000 Hz_10ms_log_rms_mae_db": 0.8305799494495109, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05218263074773746, "300–1000 Hz_10ms_envelope_correlation": 0.9980444681409938, "300–1000 Hz_10ms_modulation_mae_db": 0.3412083097433618, "300–1000 Hz_40ms_log_rms_mae_db": 0.5594087160932881, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02861021857752746, "300–1000 Hz_40ms_envelope_correlation": 0.999414420651233, "300–1000 Hz_40ms_modulation_mae_db": 0.42410956351145135, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8555191530048493, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08382927338941615, "1000–3000 Hz_10ms_envelope_correlation": 0.9963943696071743, "1000–3000 Hz_10ms_modulation_mae_db": 0.9038934870456853, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6044181550820127, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.052236019844432824, "1000–3000 Hz_40ms_envelope_correlation": 0.9989440778924213, "1000–3000 Hz_40ms_modulation_mae_db": 0.7929221274154465, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0228686524314006, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14569914686104607, "3000–6000 Hz_10ms_envelope_correlation": 0.9846644858510161, "3000–6000 Hz_10ms_modulation_mae_db": 0.5489411538861465, "3000–6000 Hz_40ms_log_rms_mae_db": 0.705941244788414, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08319851551344923, "3000–6000 Hz_40ms_envelope_correlation": 0.9950750226055792, "3000–6000 Hz_40ms_modulation_mae_db": 0.6922915983207535, "mr_stft_db": 5.159900295020184, "band_mae_db": 0.15945757438314792, "rms_gain_error_db": -0.08013290624713773, "output_peak": 0.3701259043289752}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6265919838016181, "全帯域_10ms_rms_envelope_nrmse": 0.049882101161843856, "全帯域_10ms_envelope_correlation": 0.9978902072377749, "全帯域_10ms_modulation_mae_db": 0.5312735704994148, "全帯域_40ms_log_rms_mae_db": 0.36353284352336296, "全帯域_40ms_rms_envelope_nrmse": 0.024097296613958676, "全帯域_40ms_envelope_correlation": 0.9995281838492529, "全帯域_40ms_modulation_mae_db": 0.5224854443515262, "300–1000 Hz_10ms_log_rms_mae_db": 0.8163250038285496, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.051991402368709874, "300–1000 Hz_10ms_envelope_correlation": 0.998054890103444, "300–1000 Hz_10ms_modulation_mae_db": 0.4267292142734686, "300–1000 Hz_40ms_log_rms_mae_db": 0.5625328328453492, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.028896601969734023, "300–1000 Hz_40ms_envelope_correlation": 0.9993989710032719, "300–1000 Hz_40ms_modulation_mae_db": 0.42940355790240803, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7654353286883407, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06994274008938658, "1000–3000 Hz_10ms_envelope_correlation": 0.997240546276346, "1000–3000 Hz_10ms_modulation_mae_db": 0.4639233815048626, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5587697317677658, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.041631155894194784, "1000–3000 Hz_40ms_envelope_correlation": 0.9990779338098773, "1000–3000 Hz_40ms_modulation_mae_db": 0.3618231782652142, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0108486055635506, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1389723559816988, "3000–6000 Hz_10ms_envelope_correlation": 0.9859711639440951, "3000–6000 Hz_10ms_modulation_mae_db": 0.52159093317682, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6943724375997139, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08648950326631663, "3000–6000 Hz_40ms_envelope_correlation": 0.9944284627615213, "3000–6000 Hz_40ms_modulation_mae_db": 0.5485803185724673, "mr_stft_db": 5.163699089328515, "band_mae_db": 0.09063094022402537, "rms_gain_error_db": -0.06736253732476753, "output_peak": 0.37845484118116424}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6073641757057077, "全帯域_10ms_rms_envelope_nrmse": 0.05505644452181532, "全帯域_10ms_envelope_correlation": 0.9973859113668839, "全帯域_10ms_modulation_mae_db": 0.2113252513707852, "全帯域_40ms_log_rms_mae_db": 0.3724071357467595, "全帯域_40ms_rms_envelope_nrmse": 0.03056393956243118, "全帯域_40ms_envelope_correlation": 0.9991637200654262, "全帯域_40ms_modulation_mae_db": 0.2379360345482128, "300–1000 Hz_10ms_log_rms_mae_db": 0.7882335126727767, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06202575760593747, "300–1000 Hz_10ms_envelope_correlation": 0.9972409357814687, "300–1000 Hz_10ms_modulation_mae_db": 0.5511225879931213, "300–1000 Hz_40ms_log_rms_mae_db": 0.5209070597323509, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03763011465889154, "300–1000 Hz_40ms_envelope_correlation": 0.9989664141944066, "300–1000 Hz_40ms_modulation_mae_db": 0.13855711613405788, "1000–3000 Hz_10ms_log_rms_mae_db": 0.781261957049058, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09395981775527307, "1000–3000 Hz_10ms_envelope_correlation": 0.9955831383941651, "1000–3000 Hz_10ms_modulation_mae_db": 1.001917975993109, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5606568751301784, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05627061947894107, "1000–3000 Hz_40ms_envelope_correlation": 0.9989816046502047, "1000–3000 Hz_40ms_modulation_mae_db": 0.8919593501244251, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0236352577651442, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13786853878323696, "3000–6000 Hz_10ms_envelope_correlation": 0.9862307118698708, "3000–6000 Hz_10ms_modulation_mae_db": 0.3609651432680341, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6958131475745198, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07715697779252333, "3000–6000 Hz_40ms_envelope_correlation": 0.9957388484857977, "3000–6000 Hz_40ms_modulation_mae_db": 0.6553714878027416, "mr_stft_db": 5.153194819815237, "band_mae_db": 0.1885200093245178, "rms_gain_error_db": -0.020891545281890397, "output_peak": 0.3934632427628929}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6507400366719679, "全帯域_10ms_rms_envelope_nrmse": 0.05647654484945523, "全帯域_10ms_envelope_correlation": 0.9973696051761793, "全帯域_10ms_modulation_mae_db": 0.5605466676353825, "全帯域_40ms_log_rms_mae_db": 0.4091398452193418, "全帯域_40ms_rms_envelope_nrmse": 0.03235694776864983, "全帯域_40ms_envelope_correlation": 0.9992057988555589, "全帯域_40ms_modulation_mae_db": 0.6207946298093479, "300–1000 Hz_10ms_log_rms_mae_db": 0.8564789205966078, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06653212370313238, "300–1000 Hz_10ms_envelope_correlation": 0.9968290830422092, "300–1000 Hz_10ms_modulation_mae_db": 0.5413024957689273, "300–1000 Hz_40ms_log_rms_mae_db": 0.5644226299564048, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03981416506238554, "300–1000 Hz_40ms_envelope_correlation": 0.9988770852086909, "300–1000 Hz_40ms_modulation_mae_db": 0.6872574945477101, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8076502275366942, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09165147875941841, "1000–3000 Hz_10ms_envelope_correlation": 0.9956417317608186, "1000–3000 Hz_10ms_modulation_mae_db": 0.55764332989252, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5881451853015821, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.053977633754774414, "1000–3000 Hz_40ms_envelope_correlation": 0.9989127692862553, "1000–3000 Hz_40ms_modulation_mae_db": 0.6980942843859855, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0404644851083926, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14069082416990067, "3000–6000 Hz_10ms_envelope_correlation": 0.9857237855410741, "3000–6000 Hz_10ms_modulation_mae_db": 0.27247546216563495, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7386278817099503, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08488518088463365, "3000–6000 Hz_40ms_envelope_correlation": 0.9947942221877866, "3000–6000 Hz_40ms_modulation_mae_db": 0.4708101394533093, "mr_stft_db": 5.159343852476625, "band_mae_db": 0.1785395772164203, "rms_gain_error_db": -0.1136508019284301, "output_peak": 0.3772747680092071}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6445540074056708, "全帯域_10ms_rms_envelope_nrmse": 0.05133502003243767, "全帯域_10ms_envelope_correlation": 0.9977357074184758, "全帯域_10ms_modulation_mae_db": 0.4561384524561203, "全帯域_40ms_log_rms_mae_db": 0.40820489134105137, "全帯域_40ms_rms_envelope_nrmse": 0.0293740454578603, "全帯域_40ms_envelope_correlation": 0.999242026431216, "全帯域_40ms_modulation_mae_db": 0.42558480949476607, "300–1000 Hz_10ms_log_rms_mae_db": 0.8161404256675151, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05360582447267046, "300–1000 Hz_10ms_envelope_correlation": 0.997919497796857, "300–1000 Hz_10ms_modulation_mae_db": 0.24459153563000205, "300–1000 Hz_40ms_log_rms_mae_db": 0.5524398359560022, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.032828277359427734, "300–1000 Hz_40ms_envelope_correlation": 0.9992032028905155, "300–1000 Hz_40ms_modulation_mae_db": 0.35743993158997833, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7991992317461334, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06668226275956265, "1000–3000 Hz_10ms_envelope_correlation": 0.9974970960832864, "1000–3000 Hz_10ms_modulation_mae_db": 0.39532855852363274, "1000–3000 Hz_40ms_log_rms_mae_db": 0.555524717481019, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04116926710536444, "1000–3000 Hz_40ms_envelope_correlation": 0.9990652139922646, "1000–3000 Hz_40ms_modulation_mae_db": 0.39854756066644015, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0167256271877256, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15029462030315677, "3000–6000 Hz_10ms_envelope_correlation": 0.9843254875504117, "3000–6000 Hz_10ms_modulation_mae_db": 0.7615124277443416, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7171314831272625, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08955441792981401, "3000–6000 Hz_40ms_envelope_correlation": 0.9952126023187995, "3000–6000 Hz_40ms_modulation_mae_db": 0.7609875628153233, "mr_stft_db": 5.154842887466033, "band_mae_db": 0.16465579174399267, "rms_gain_error_db": -0.018473013697306147, "output_peak": 0.38872457980649144}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6133310408348123, "全帯域_10ms_rms_envelope_nrmse": 0.05095425430676668, "全帯域_10ms_envelope_correlation": 0.9977960586873064, "全帯域_10ms_modulation_mae_db": 0.18669546070892926, "全帯域_40ms_log_rms_mae_db": 0.39303621191003096, "全帯域_40ms_rms_envelope_nrmse": 0.029944554982223072, "全帯域_40ms_envelope_correlation": 0.9992405098356375, "全帯域_40ms_modulation_mae_db": 0.07664618424784853, "300–1000 Hz_10ms_log_rms_mae_db": 0.8134297278013713, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05592582090154582, "300–1000 Hz_10ms_envelope_correlation": 0.9977332525887809, "300–1000 Hz_10ms_modulation_mae_db": 0.7218494463492403, "300–1000 Hz_40ms_log_rms_mae_db": 0.5586437415469959, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037250079237536655, "300–1000 Hz_40ms_envelope_correlation": 0.998968128354367, "300–1000 Hz_40ms_modulation_mae_db": 0.6592368845732012, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8111254237505587, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07340792277238753, "1000–3000 Hz_10ms_envelope_correlation": 0.9971661100933774, "1000–3000 Hz_10ms_modulation_mae_db": 0.27149238247552027, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5705260600299755, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04438523901464221, "1000–3000 Hz_40ms_envelope_correlation": 0.9991836778181311, "1000–3000 Hz_40ms_modulation_mae_db": 0.38648333278209174, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0431130498355656, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15527432295515217, "3000–6000 Hz_10ms_envelope_correlation": 0.9824878048049968, "3000–6000 Hz_10ms_modulation_mae_db": 0.4443951361974729, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7286939991467046, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09425360739195442, "3000–6000 Hz_40ms_envelope_correlation": 0.9932699888801217, "3000–6000 Hz_40ms_modulation_mae_db": 0.544401603296626, "mr_stft_db": 5.158795258511138, "band_mae_db": 0.1311653334450753, "rms_gain_error_db": -0.06645427315274036, "output_peak": 0.36702266430108066}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6481130131612282, "全帯域_10ms_rms_envelope_nrmse": 0.058385578700064035, "全帯域_10ms_envelope_correlation": 0.9971478685372289, "全帯域_10ms_modulation_mae_db": 0.29574545873490427, "全帯域_40ms_log_rms_mae_db": 0.39113384750417624, "全帯域_40ms_rms_envelope_nrmse": 0.03528098648334872, "全帯域_40ms_envelope_correlation": 0.9989872762840123, "全帯域_40ms_modulation_mae_db": 0.17026717099242314, "300–1000 Hz_10ms_log_rms_mae_db": 0.8513767845719894, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05938902663747168, "300–1000 Hz_10ms_envelope_correlation": 0.997456322364679, "300–1000 Hz_10ms_modulation_mae_db": 0.5108412368417731, "300–1000 Hz_40ms_log_rms_mae_db": 0.5970230599072257, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03414869671810851, "300–1000 Hz_40ms_envelope_correlation": 0.9991430001229944, "300–1000 Hz_40ms_modulation_mae_db": 0.5886235481817993, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8252668931471344, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09533925491862631, "1000–3000 Hz_10ms_envelope_correlation": 0.9965965303837788, "1000–3000 Hz_10ms_modulation_mae_db": 1.40495591299368, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5587828596850902, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07164641028746097, "1000–3000 Hz_40ms_envelope_correlation": 0.999009197300605, "1000–3000 Hz_40ms_modulation_mae_db": 1.2365367735511656, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0694793223743317, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1370771453422535, "3000–6000 Hz_10ms_envelope_correlation": 0.9864644897403165, "3000–6000 Hz_10ms_modulation_mae_db": 1.0556125357051556, "3000–6000 Hz_40ms_log_rms_mae_db": 0.812116973383875, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07550590970906072, "3000–6000 Hz_40ms_envelope_correlation": 0.996038484346604, "3000–6000 Hz_40ms_modulation_mae_db": 1.2449846097230195, "mr_stft_db": 5.164235249807747, "band_mae_db": 0.18651869826853432, "rms_gain_error_db": -0.09107971321548745, "output_peak": 0.34898192761421487}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.390258726411228, "spectral_convergence": 0.1896921026019645, "spectral_convergence_status": "ok", "amplitude_floor": 9.086732072822267e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.061343118817415, "spectral_convergence": 0.1966116289844174, "spectral_convergence_status": "ok", "amplitude_floor": 8.520258431312163e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.036780076842738, "spectral_convergence": 0.20093381184651526, "spectral_convergence_status": "ok", "amplitude_floor": 5.353418087016012e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 3.131933551513939e-05, "output_power": 3.1448356369482116e-05, "delta_db": 0.01785412919489574, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0004897019472039064, "output_power": 0.0004842205066340199, "delta_db": -0.04888653135801117, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.00038033005135275084, "output_power": 0.0003727516465345961, "delta_db": -0.08741071545572784, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0002067238728943134, "output_power": 0.00020599782291403555, "delta_db": -0.015280021791762518, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.323291799953591e-05, "output_power": 1.248454594605824e-05, "delta_db": -0.2528286931528291, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.500515826026349e-05, "output_power": 2.4464460443544198e-05, "delta_db": -0.09493965622674352, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.8390290595099542e-05, "output_power": 2.8621415270378952e-05, "delta_db": 0.03521267061729179, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0789160596853231, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.05474511177738528, "pitch": null, "output_rms_dbfs": -29.35546221161639, "output_peak": 0.372005703323663, "reference_rms_dbfs": -29.30071709983901, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.162793974023795}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00015179812996022924, "log_rms_mae_db": 0.6007585719976909, "rms_envelope_nrmse": 0.04725635730136167, "envelope_correlation": 0.9980972650091583, "rms_gain_error_db": -0.05474517100755524, "reference_mean_power": 0.0011756832947918806, "output_mean_power": 0.0011609561868620795}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.744923761629972e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00015071015783187623, "output_power": 0.00014533624647447435, "reference_active": true, "delta_db": -0.15768584956029924}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2413420104691182e-05, "output_power": 1.1519912305914857e-05, "reference_active": true, "delta_db": -0.32442280292900505}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.099936667111779e-06, "output_power": 2.621286616555032e-06, "reference_active": true, "delta_db": -0.7283831098039905}], "active_band_count": 3, "active_band_mae_db": 0.4034972540977649}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001370105991807196, "log_rms_mae_db": 0.35100957012767225, "rms_envelope_nrmse": 0.021258106810151136, "envelope_correlation": 0.9996282985178596, "rms_gain_error_db": -0.054745090898127666, "reference_mean_power": 0.0011815960953402045, "output_mean_power": 0.001166794942683802}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.5970704572828427e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000136303861600392, "output_power": 0.00013153567524636374, "reference_active": true, "delta_db": -0.15464601312917087}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.090701624693659e-06, "output_power": 5.064376293371292e-06, "reference_active": true, "delta_db": -0.022516758276851394}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5690836910660882e-07, "output_power": 1.4711953317024103e-07, "reference_active": true, "delta_db": -0.2797577024624901}], "active_band_count": 3, "active_band_mae_db": 0.15230682462283746}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.549209054072936e-05, "log_rms_mae_db": 0.7885481408073156, "rms_envelope_nrmse": 0.05142113703022608, "envelope_correlation": 0.998125475401032, "rms_gain_error_db": -0.0734905243473043, "reference_mean_power": 0.000689577872249739, "output_mean_power": 0.000678007135652291}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.482675818010425e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.030686777059284e-05, "output_power": 6.837393677335892e-05, "reference_active": true, "delta_db": -0.12107164147059689}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.045775397952136e-06, "output_power": 5.400640355604605e-06, "reference_active": true, "delta_db": -0.4900675168662469}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0022957436919974e-06, "output_power": 9.3162606784076e-07, "reference_active": true, "delta_db": -0.3175425407253525}], "active_band_count": 3, "active_band_mae_db": 0.3095605663540654}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.872309512115098e-05, "log_rms_mae_db": 0.5071372096195679, "rms_envelope_nrmse": 0.026747274512007677, "envelope_correlation": 0.9995220660079687, "rms_gain_error_db": -0.07349055368614688, "reference_mean_power": 0.0006930459912916024, "output_mean_power": 0.0006814170569649519}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.4404474148541786e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.432934367906604e-05, "output_power": 6.24527211145144e-05, "reference_active": true, "delta_db": -0.12857754851194358}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.638974827185174e-06, "output_power": 2.408967759116235e-06, "reference_active": true, "delta_db": -0.3960425999155288}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.490824439966143e-08, "output_power": 6.820892619014251e-08, "reference_active": true, "delta_db": -0.4068840626298813}], "active_band_count": 3, "active_band_mae_db": 0.31050140368578455}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.800802183872533e-05, "log_rms_mae_db": 0.7796192791626745, "rms_envelope_nrmse": 0.0819958102291951, "envelope_correlation": 0.9961041964246529, "rms_gain_error_db": -0.05009523211215978, "reference_mean_power": 0.0001528560580614903, "output_mean_power": 0.00015110301580985593}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.6939080235935477e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.743995800608424e-06, "output_power": 8.09839872514562e-06, "reference_active": true, "delta_db": -0.33310784893831513}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.01868229376414e-06, "output_power": 1.5796124372972503e-06, "reference_active": true, "delta_db": -1.065174292060446}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.212055898483429e-07, "output_power": 3.0998858534361616e-07, "reference_active": true, "delta_db": -1.3314842392596469}], "active_band_count": 3, "active_band_mae_db": 0.9099221267528027}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.485177873530849e-05, "log_rms_mae_db": 0.5519082455820207, "rms_envelope_nrmse": 0.047139357152763996, "envelope_correlation": 0.9987030532117194, "rms_gain_error_db": -0.05009523585098974, "reference_mean_power": 0.00015362482187073777, "output_mean_power": 0.00015186296285750171}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.6796802400302903e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.417995641253307e-06, "output_power": 7.655892834469325e-06, "reference_active": true, "delta_db": -0.41212850887911684}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.917412489595775e-07, "output_power": 7.97741825609954e-07, "reference_active": true, "delta_db": -0.9453601427438801}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9786028250337687e-08, "output_power": 1.447141667774231e-08, "reference_active": true, "delta_db": -1.358475764134539}], "active_band_count": 3, "active_band_mae_db": 0.9053214719191787}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.5712979141900155e-05, "log_rms_mae_db": 1.01398213961664, "rms_envelope_nrmse": 0.12865715524165414, "envelope_correlation": 0.9882447928578336, "rms_gain_error_db": -0.25882963896836647, "reference_mean_power": 1.157751296991392e-05, "output_mean_power": 1.0907678085960633e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.302605621158197e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.645490651287566e-07, "output_power": 8.462651336215655e-07, "reference_active": true, "delta_db": -0.09283197330327729}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.590093915842518e-07, "output_power": 4.3582379649252197e-07, "reference_active": true, "delta_db": -0.22510631984009966}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3044874644069055e-07, "output_power": 2.0504304025449352e-07, "reference_active": true, "delta_db": -0.5072931737878839}], "active_band_count": 3, "active_band_mae_db": 0.2750771556437536}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.532870280173584e-05, "log_rms_mae_db": 0.709136568190342, "rms_envelope_nrmse": 0.08478469292050335, "envelope_correlation": 0.9950047302482272, "rms_gain_error_db": -0.2588296717293616, "reference_mean_power": 1.163573961751773e-05, "output_mean_power": 1.0962535858292654e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.177196911262554e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.60049524306651e-07, "output_power": 8.508173780004107e-07, "reference_active": true, "delta_db": -0.04687108166196964}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5501826725164134e-07, "output_power": 2.349008744670299e-07, "reference_active": true, "delta_db": -0.35686657029642166}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7808109251124296e-08, "output_power": 1.5145064793606587e-08, "reference_active": true, "delta_db": -0.7034667568457358}], "active_band_count": 3, "active_band_mae_db": 0.36906813626804236}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8889730343672907, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "0974d5e230f7d4cd5a3b95be218c26b77bcdc2a0e86304c99bdadf486d50addf", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9965279648779499, "standard_deviation": 0.0007304061206718571, "minimum": 0.9955831383941651, "maximum": 0.9974970960832864, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.8031346867606804, "standard_deviation": 0.028750972540411233, "minimum": 0.7654353286883407, "maximum": 0.8555191530048493, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7386346443977265, "standard_deviation": 0.3806492813456406, "minimum": 0.27149238247552027, "maximum": 1.40495591299368, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08210107008415823, "standard_deviation": 0.011156182936339323, "minimum": 0.06668226275956265, "maximum": 0.09533925491862631, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9989846909951847, "standard_deviation": 0.00014219002034208405, "minimum": 0.9987030532117194, "maximum": 0.9991836778181311, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5685914787574555, "standard_deviation": 0.01841716961726572, "minimum": 0.5519082455820207, "maximum": 0.6044181550820127, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7089610098887436, "standard_deviation": 0.31131119038116567, "minimum": 0.3618231782652142, "maximum": 1.2365367735511656, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.051056962816571835, "standard_deviation": 0.010053428359061494, "minimum": 0.04116926710536444, "maximum": 0.07164641028746097, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9855140902699518, "standard_deviation": 0.001707941055920915, "minimum": 0.9824878048049968, "maximum": 0.9882447928578336, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.0301396424853437, "standard_deviation": 0.019751460036670564, "minimum": 1.0108486055635506, "maximum": 1.0694793223743317, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5300712434734199, "standard_deviation": 0.2665926535959538, "minimum": 0.27247546216563495, "maximum": 1.0556125357051556, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14181676370476237, "standard_deviation": 0.008354972896763518, "minimum": 0.12865715524165414, "maximum": 0.15527432295515217, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9949452952293046, "standard_deviation": 0.000846268636683352, "minimum": 0.9932699888801217, "maximum": 0.996038484346604, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7252292169400978, "standard_deviation": 0.0382753737086908, "minimum": 0.6943724375997139, "maximum": 0.812116973383875, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6608119320315353, "standard_deviation": 0.26717459926114684, "minimum": 0.36906813626804236, "maximum": 1.2449846097230195, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08447860067603191, "standard_deviation": 0.006110545557902753, "minimum": 0.07550590970906072, "maximum": 0.09425360739195442, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.997675490652433, "standard_deviation": 0.00046271389635574615, "minimum": 0.9968290830422092, "maximum": 0.998125475401032, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8201390581744545, "standard_deviation": 0.02534587721435776, "minimum": 0.7882335126727767, "maximum": 0.8564789205966078, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.45590067411924495, "standard_deviation": 0.1559213128340485, "minimum": 0.24459153563000205, "maximum": 0.7218494463492403, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.056634215433428906, "standard_deviation": 0.005514238456850668, "minimum": 0.05142113703022608, "maximum": 0.06653212370313238, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.999186661054181, "standard_deviation": 0.0002401573189921198, "minimum": 0.9988770852086909, "maximum": 0.9995220660079687, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5528143857071481, "standard_deviation": 0.027686239904431174, "minimum": 0.5071372096195679, "maximum": 0.5970230599072257, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.4493911875157988, "standard_deviation": 0.18723672493527932, "minimum": 0.13855711613405788, "maximum": 0.6872574945477101, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03324067851195239, "standard_deviation": 0.0048110616111486275, "minimum": 0.026747274512007677, "maximum": 0.03981416506238554, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1473004980363796, "standard_deviation": 0.04277884968216276, "minimum": 0.0789160596853231, "maximum": 0.1885200093245178, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.159600678306159, "standard_deviation": 0.004016917632501708, "minimum": 5.153194819815237, "maximum": 5.164235249807747, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3745067039159612, "standard_deviation": 0.013720265458584869, "minimum": 0.34898192761421487, "maximum": 0.3934632427628929, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06409873782814313, "standard_deviation": 0.03271682417928846, "minimum": -0.1136508019284301, "maximum": -0.018473013697306147, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9977040946396585, "standard_deviation": 0.0003736431415158472, "minimum": 0.9971478685372289, "maximum": 0.9982101336842609, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.6320367963316642, "standard_deviation": 0.023322902893734565, "minimum": 0.6007585719976909, "maximum": 0.6648415410746181, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3809397762391679, "standard_deviation": 0.13899469212311055, "minimum": 0.18669546070892926, "maximum": 0.5605466676353825, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.0519549183951209, "standard_deviation": 0.004329853314292171, "minimum": 0.046293046287222715, "maximum": 0.058385578700064035, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9993197651372256, "standard_deviation": 0.00022604355199487216, "minimum": 0.9989872762840123, "maximum": 0.9996282985178596, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.38879288711021054, "standard_deviation": 0.024620336044089596, "minimum": 0.35100957012767225, "maximum": 0.4218787515092893, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.30920393872241064, "standard_deviation": 0.19307091264166293, "minimum": 0.07664618424784853, "maximum": 0.6207946298093479, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.02833528191378633, "standard_deviation": 0.004804911378484552, "minimum": 0.021258106810151136, "maximum": 0.03528098648334872, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_falset10_VOICEACTRESS100_004", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 2.1766576766967773, "predicted_mos": 2.1766576766967773, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "77b8aab6df08db222e17fcec203b5b2885453f8158028592aab8b34330d044b0", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.725258499849588}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6317139430172215, "全帯域_10ms_rms_envelope_nrmse": 0.059911891269186106, "全帯域_10ms_envelope_correlation": 0.9969459936588023, "全帯域_10ms_modulation_mae_db": 0.4080916914104764, "全帯域_40ms_log_rms_mae_db": 0.40675828813799514, "全帯域_40ms_rms_envelope_nrmse": 0.03386891046928724, "全帯域_40ms_envelope_correlation": 0.999030317616977, "全帯域_40ms_modulation_mae_db": 0.34443493081137505, "300–1000 Hz_10ms_log_rms_mae_db": 0.8221216417347924, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.053286824063285616, "300–1000 Hz_10ms_envelope_correlation": 0.9979490913397404, "300–1000 Hz_10ms_modulation_mae_db": 0.542028841956117, "300–1000 Hz_40ms_log_rms_mae_db": 0.5740833201722302, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029010908829369093, "300–1000 Hz_40ms_envelope_correlation": 0.999386771200678, "300–1000 Hz_40ms_modulation_mae_db": 0.22777779643470367, "1000–3000 Hz_10ms_log_rms_mae_db": 0.825993173185491, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11671061438725162, "1000–3000 Hz_10ms_envelope_correlation": 0.9922016969016575, "1000–3000 Hz_10ms_modulation_mae_db": 1.2620369581047592, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5806010559290448, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07500463243337671, "1000–3000 Hz_40ms_envelope_correlation": 0.9968780389324926, "1000–3000 Hz_40ms_modulation_mae_db": 1.2036271456328451, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0759823800240613, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16301875009516326, "3000–6000 Hz_10ms_envelope_correlation": 0.9809155849826385, "3000–6000 Hz_10ms_modulation_mae_db": 1.715606191715657, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7758393204917876, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10047498987786678, "3000–6000 Hz_40ms_envelope_correlation": 0.9930480030212295, "3000–6000 Hz_40ms_modulation_mae_db": 2.0885287535519415, "mr_stft_db": 5.248944010880794, "band_mae_db": 0.11208114889628713, "rms_gain_error_db": -0.07603072878142521, "output_peak": 0.36363384275633354}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6041505918658711, "全帯域_10ms_rms_envelope_nrmse": 0.052470155758840814, "全帯域_10ms_envelope_correlation": 0.9976272212875534, "全帯域_10ms_modulation_mae_db": 0.3406378454845416, "全帯域_40ms_log_rms_mae_db": 0.3551225150622465, "全帯域_40ms_rms_envelope_nrmse": 0.026051185460539028, "全帯域_40ms_envelope_correlation": 0.999390907197269, "全帯域_40ms_modulation_mae_db": 0.4658999511411057, "300–1000 Hz_10ms_log_rms_mae_db": 0.8259800786282946, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05409363413964579, "300–1000 Hz_10ms_envelope_correlation": 0.9978970644284948, "300–1000 Hz_10ms_modulation_mae_db": 0.5442572664014588, "300–1000 Hz_40ms_log_rms_mae_db": 0.5336003591987534, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029073970836691585, "300–1000 Hz_40ms_envelope_correlation": 0.9993813048381314, "300–1000 Hz_40ms_modulation_mae_db": 0.13799819208087694, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7869578732411265, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07681311466477132, "1000–3000 Hz_10ms_envelope_correlation": 0.9965857476774845, "1000–3000 Hz_10ms_modulation_mae_db": 0.2322541034916464, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5542044891944496, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.038652484506861824, "1000–3000 Hz_40ms_envelope_correlation": 0.99912245762778, "1000–3000 Hz_40ms_modulation_mae_db": 0.11168977650280458, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0927851318206265, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1468373319835846, "3000–6000 Hz_10ms_envelope_correlation": 0.9843676434949062, "3000–6000 Hz_10ms_modulation_mae_db": 0.47733901792577743, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7941270418855031, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07760849709091636, "3000–6000 Hz_40ms_envelope_correlation": 0.9956836902775511, "3000–6000 Hz_40ms_modulation_mae_db": 0.7030666942244516, "mr_stft_db": 5.238942443341171, "band_mae_db": 0.10063829492249152, "rms_gain_error_db": 0.0019366433940359836, "output_peak": 0.37512804373075925}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6061818995915808, "全帯域_10ms_rms_envelope_nrmse": 0.052989854284199896, "全帯域_10ms_envelope_correlation": 0.9975917015601753, "全帯域_10ms_modulation_mae_db": 0.19005621553141036, "全帯域_40ms_log_rms_mae_db": 0.38180278923228445, "全帯域_40ms_rms_envelope_nrmse": 0.02823031991631452, "全帯域_40ms_envelope_correlation": 0.999306249352885, "全帯域_40ms_modulation_mae_db": 0.5213981661209264, "300–1000 Hz_10ms_log_rms_mae_db": 0.865800395307058, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05684704208701511, "300–1000 Hz_10ms_envelope_correlation": 0.9976674930968513, "300–1000 Hz_10ms_modulation_mae_db": 0.8168860268678465, "300–1000 Hz_40ms_log_rms_mae_db": 0.5824212208582847, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0309040454716739, "300–1000 Hz_40ms_envelope_correlation": 0.9993073862782694, "300–1000 Hz_40ms_modulation_mae_db": 0.7051725142843589, "1000–3000 Hz_10ms_log_rms_mae_db": 0.785501923286643, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07766062175635935, "1000–3000 Hz_10ms_envelope_correlation": 0.9965454436965419, "1000–3000 Hz_10ms_modulation_mae_db": 0.6869440893848869, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5682403616641997, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.044771393395799934, "1000–3000 Hz_40ms_envelope_correlation": 0.9988845728116774, "1000–3000 Hz_40ms_modulation_mae_db": 0.5356611889485825, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0633554950168134, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14907860543757512, "3000–6000 Hz_10ms_envelope_correlation": 0.9842574505914568, "3000–6000 Hz_10ms_modulation_mae_db": 0.7166223071536973, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7076714463906185, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09186123006684911, "3000–6000 Hz_40ms_envelope_correlation": 0.9944119106292868, "3000–6000 Hz_40ms_modulation_mae_db": 0.7532177232880404, "mr_stft_db": 5.2483529655462435, "band_mae_db": 0.10904051169038645, "rms_gain_error_db": -0.047402086901453186, "output_peak": 0.38068768868399894}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.5994635302014719, "全帯域_10ms_rms_envelope_nrmse": 0.05559290674104472, "全帯域_10ms_envelope_correlation": 0.9973933740337373, "全帯域_10ms_modulation_mae_db": 0.6733248515975759, "全帯域_40ms_log_rms_mae_db": 0.3722242859733366, "全帯域_40ms_rms_envelope_nrmse": 0.02842812162120113, "全帯域_40ms_envelope_correlation": 0.9993572920642452, "全帯域_40ms_modulation_mae_db": 0.6958314830243181, "300–1000 Hz_10ms_log_rms_mae_db": 0.8585095814072407, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06683648191050458, "300–1000 Hz_10ms_envelope_correlation": 0.9967687399686743, "300–1000 Hz_10ms_modulation_mae_db": 0.46230927067394384, "300–1000 Hz_40ms_log_rms_mae_db": 0.5748971304778125, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038487793336244844, "300–1000 Hz_40ms_envelope_correlation": 0.9989152875656809, "300–1000 Hz_40ms_modulation_mae_db": 0.7913983317589359, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8372229930011658, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09538923756600615, "1000–3000 Hz_10ms_envelope_correlation": 0.9948285315142944, "1000–3000 Hz_10ms_modulation_mae_db": 1.4857670283162079, "1000–3000 Hz_40ms_log_rms_mae_db": 0.608225556310537, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06187992458262769, "1000–3000 Hz_40ms_envelope_correlation": 0.997898193292946, "1000–3000 Hz_40ms_modulation_mae_db": 1.303312705797227, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0579140771077642, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15534363798741083, "3000–6000 Hz_10ms_envelope_correlation": 0.9844081720919589, "3000–6000 Hz_10ms_modulation_mae_db": 1.8237259117253835, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7879174374020507, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1043324449807107, "3000–6000 Hz_40ms_envelope_correlation": 0.9944445146975412, "3000–6000 Hz_40ms_modulation_mae_db": 2.3035323485073356, "mr_stft_db": 5.229160255508908, "band_mae_db": 0.19847559502740225, "rms_gain_error_db": -0.08511301931844344, "output_peak": 0.3761793118813789}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6256557340322477, "全帯域_10ms_rms_envelope_nrmse": 0.05284574857849929, "全帯域_10ms_envelope_correlation": 0.9977315657451604, "全帯域_10ms_modulation_mae_db": 0.6060990862184011, "全帯域_40ms_log_rms_mae_db": 0.38069097232014837, "全帯域_40ms_rms_envelope_nrmse": 0.027700023552616183, "全帯域_40ms_envelope_correlation": 0.9994785047741126, "全帯域_40ms_modulation_mae_db": 0.42593039837757907, "300–1000 Hz_10ms_log_rms_mae_db": 0.8324603836161825, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05307128917577169, "300–1000 Hz_10ms_envelope_correlation": 0.9980489936452586, "300–1000 Hz_10ms_modulation_mae_db": 0.3191157508663829, "300–1000 Hz_40ms_log_rms_mae_db": 0.5659298481263307, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02946943952183411, "300–1000 Hz_40ms_envelope_correlation": 0.9994608913177687, "300–1000 Hz_40ms_modulation_mae_db": 0.34894453666871933, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8274176593456085, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08034057654091069, "1000–3000 Hz_10ms_envelope_correlation": 0.996432153887046, "1000–3000 Hz_10ms_modulation_mae_db": 0.34924212773080127, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5740271641862468, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0431797739274231, "1000–3000 Hz_40ms_envelope_correlation": 0.9991293446055494, "1000–3000 Hz_40ms_modulation_mae_db": 0.36072280262935247, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0644207822255773, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14861053249241477, "3000–6000 Hz_10ms_envelope_correlation": 0.9843578796217228, "3000–6000 Hz_10ms_modulation_mae_db": 1.2803417022245622, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7581468513620858, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09533334842091187, "3000–6000 Hz_40ms_envelope_correlation": 0.9938913449011858, "3000–6000 Hz_40ms_modulation_mae_db": 1.8472872368913045, "mr_stft_db": 5.231872484247133, "band_mae_db": 0.1634789064120119, "rms_gain_error_db": -0.12172199443519555, "output_peak": 0.3691838675333696}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6276015434448116, "全帯域_10ms_rms_envelope_nrmse": 0.053788507972849134, "全帯域_10ms_envelope_correlation": 0.9976863424723194, "全帯域_10ms_modulation_mae_db": 0.37498636618883213, "全帯域_40ms_log_rms_mae_db": 0.3785639698757937, "全帯域_40ms_rms_envelope_nrmse": 0.03119216501255156, "全帯域_40ms_envelope_correlation": 0.9993334833664086, "全帯域_40ms_modulation_mae_db": 0.2972941731012027, "300–1000 Hz_10ms_log_rms_mae_db": 0.8256283008926016, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05589703177251278, "300–1000 Hz_10ms_envelope_correlation": 0.997758623609426, "300–1000 Hz_10ms_modulation_mae_db": 0.3960948510059732, "300–1000 Hz_40ms_log_rms_mae_db": 0.5664661522148251, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029832725679224795, "300–1000 Hz_40ms_envelope_correlation": 0.9993705253116844, "300–1000 Hz_40ms_modulation_mae_db": 0.3386494580860829, "1000–3000 Hz_10ms_log_rms_mae_db": 0.840390145625168, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09554950816393298, "1000–3000 Hz_10ms_envelope_correlation": 0.9962808910832393, "1000–3000 Hz_10ms_modulation_mae_db": 0.4824675166478219, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5731048432037249, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07015130321491309, "1000–3000 Hz_40ms_envelope_correlation": 0.9988517318232517, "1000–3000 Hz_40ms_modulation_mae_db": 0.373526706269363, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0664060276821776, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14461552807745537, "3000–6000 Hz_10ms_envelope_correlation": 0.9851994500422069, "3000–6000 Hz_10ms_modulation_mae_db": 0.7439717871461397, "3000–6000 Hz_40ms_log_rms_mae_db": 0.745347382648268, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08000280039778408, "3000–6000 Hz_40ms_envelope_correlation": 0.9959727773231775, "3000–6000 Hz_40ms_modulation_mae_db": 1.0412331702359554, "mr_stft_db": 5.252238784430524, "band_mae_db": 0.19025636450358924, "rms_gain_error_db": -0.13276736882346135, "output_peak": 0.37395975587430746}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6280022583579915, "全帯域_10ms_rms_envelope_nrmse": 0.04471171885738086, "全帯域_10ms_envelope_correlation": 0.9982762676363807, "全帯域_10ms_modulation_mae_db": 0.20957182232176316, "全帯域_40ms_log_rms_mae_db": 0.3683212373424441, "全帯域_40ms_rms_envelope_nrmse": 0.02217820263227842, "全帯域_40ms_envelope_correlation": 0.9995577165057512, "全帯域_40ms_modulation_mae_db": 0.143448946615841, "300–1000 Hz_10ms_log_rms_mae_db": 0.785744621296184, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.048481487011782655, "300–1000 Hz_10ms_envelope_correlation": 0.9983298396819701, "300–1000 Hz_10ms_modulation_mae_db": 0.3954782784583329, "300–1000 Hz_40ms_log_rms_mae_db": 0.5421226175201259, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.026928488716335755, "300–1000 Hz_40ms_envelope_correlation": 0.999487524595716, "300–1000 Hz_40ms_modulation_mae_db": 0.26218050314065544, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8173031810671565, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07038825272934028, "1000–3000 Hz_10ms_envelope_correlation": 0.997367534422594, "1000–3000 Hz_10ms_modulation_mae_db": 1.5032632875505179, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5921723704112869, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0405697716259439, "1000–3000 Hz_40ms_envelope_correlation": 0.9993094394598624, "1000–3000 Hz_40ms_modulation_mae_db": 1.4975484585057057, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0462620343703595, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13955866764515468, "3000–6000 Hz_10ms_envelope_correlation": 0.986286526502836, "3000–6000 Hz_10ms_modulation_mae_db": 0.6415729158583907, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7319382915240282, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08330605122579557, "3000–6000 Hz_40ms_envelope_correlation": 0.9955365425562199, "3000–6000 Hz_40ms_modulation_mae_db": 0.661194326741966, "mr_stft_db": 5.246498045408944, "band_mae_db": 0.11069794267865761, "rms_gain_error_db": -0.003219770406850761, "output_peak": 0.3777918299612059}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6418294492978286, "全帯域_10ms_rms_envelope_nrmse": 0.053889015812422864, "全帯域_10ms_envelope_correlation": 0.9975691924542931, "全帯域_10ms_modulation_mae_db": 0.1884148758430966, "全帯域_40ms_log_rms_mae_db": 0.3995258965058098, "全帯域_40ms_rms_envelope_nrmse": 0.030753463882252172, "全帯域_40ms_envelope_correlation": 0.9992444648426149, "全帯域_40ms_modulation_mae_db": 0.09585834864050154, "300–1000 Hz_10ms_log_rms_mae_db": 0.7992698995293248, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05984590417226819, "300–1000 Hz_10ms_envelope_correlation": 0.997419354932753, "300–1000 Hz_10ms_modulation_mae_db": 0.7445065322405754, "300–1000 Hz_40ms_log_rms_mae_db": 0.5716652800160257, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03417085916717136, "300–1000 Hz_40ms_envelope_correlation": 0.9991569384701707, "300–1000 Hz_40ms_modulation_mae_db": 0.34401377678392553, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8020103419909089, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07710388130089135, "1000–3000 Hz_10ms_envelope_correlation": 0.9973360104945708, "1000–3000 Hz_10ms_modulation_mae_db": 0.4436412086599377, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5571377727677405, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04953353569083652, "1000–3000 Hz_40ms_envelope_correlation": 0.999426804120773, "1000–3000 Hz_40ms_modulation_mae_db": 0.6234178781189427, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0383708233770714, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1441877410133347, "3000–6000 Hz_10ms_envelope_correlation": 0.9860832368921484, "3000–6000 Hz_10ms_modulation_mae_db": 0.7075780960157294, "3000–6000 Hz_40ms_log_rms_mae_db": 0.731789311327747, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09885322911195439, "3000–6000 Hz_40ms_envelope_correlation": 0.9942806641860223, "3000–6000 Hz_40ms_modulation_mae_db": 0.9070397240576645, "mr_stft_db": 5.236414783555458, "band_mae_db": 0.18944889490599634, "rms_gain_error_db": -0.0931204091065524, "output_peak": 0.3629193553946384}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.523630750491446, "spectral_convergence": 0.19754611820424478, "spectral_convergence_status": "ok", "amplitude_floor": 9.086732072822267e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.141751377229098, "spectral_convergence": 0.20140948018771146, "spectral_convergence_status": "ok", "amplitude_floor": 8.520258431312163e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.081449904921838, "spectral_convergence": 0.2058257641987578, "spectral_convergence_status": "ok", "amplitude_floor": 5.353418087016012e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 3.131933551513939e-05, "output_power": 3.0889580198077776e-05, "delta_db": -0.060005331966120824, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0004897019472039064, "output_power": 0.00048597382882758735, "delta_db": -0.033189490986014765, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.00038033005135275084, "output_power": 0.0003766502387106508, "delta_db": -0.04222395046404706, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0002067238728943134, "output_power": 0.00019427398055238968, "delta_db": -0.26975994046324053, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.323291799953591e-05, "output_power": 1.243524363649007e-05, "delta_db": -0.27001322744148676, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.500515826026349e-05, "output_power": 2.4993574928778602e-05, "delta_db": -0.0020122817979900858, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.8390290595099542e-05, "output_power": 2.9100886545946304e-05, "delta_db": 0.10736381915510984, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.11208114889628713, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.07603072878142521, "pitch": null, "output_rms_dbfs": -29.376747828620434, "output_peak": 0.36363384275633354, "reference_rms_dbfs": -29.30071709983901, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.248944010880794}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00015179812996022924, "log_rms_mae_db": 0.6317139430172215, "rms_envelope_nrmse": 0.059911891269186106, "envelope_correlation": 0.9969459936588023, "rms_gain_error_db": -0.07603080874349702, "reference_mean_power": 0.0011756832947918806, "output_mean_power": 0.0011552800306596448}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.744923761629972e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00015071015783187623, "output_power": 0.0001454845517643849, "reference_active": true, "delta_db": -0.15325644320295237}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2413420104691182e-05, "output_power": 1.282648018252285e-05, "reference_active": true, "delta_db": 0.1421604111333139}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.099936667111779e-06, "output_power": 2.5030354422435123e-06, "reference_active": true, "delta_db": -0.9288582198951629}], "active_band_count": 3, "active_band_mae_db": 0.4080916914104764}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001370105991807196, "log_rms_mae_db": 0.40675828813799514, "rms_envelope_nrmse": 0.03386891046928724, "envelope_correlation": 0.999030317616977, "rms_gain_error_db": -0.07603097510140722, "reference_mean_power": 0.0011815960953402045, "output_mean_power": 0.0011610901736968013}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.5970704572828427e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000136303861600392, "output_power": 0.00013198332657998708, "reference_active": true, "delta_db": -0.1398908956864374}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.090701624693659e-06, "output_power": 5.478298573034704e-06, "reference_active": true, "delta_db": 0.31868055077398494}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5690836910660882e-07, "output_power": 1.374588713921494e-07, "reference_active": true, "delta_db": -0.5747333459737027}], "active_band_count": 3, "active_band_mae_db": 0.34443493081137505}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.549209054072936e-05, "log_rms_mae_db": 0.8221216417347924, "rms_envelope_nrmse": 0.053286824063285616, "envelope_correlation": 0.9979490913397404, "rms_gain_error_db": -0.03667856281047107, "reference_mean_power": 0.000689577872249739, "output_mean_power": 0.0006837785308144569}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.482675818010425e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.030686777059284e-05, "output_power": 6.866457053878916e-05, "reference_active": true, "delta_db": -0.1026504207059155}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.045775397952136e-06, "output_power": 6.7753693700969675e-06, "reference_active": true, "delta_db": 0.4948096745576631}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0022957436919974e-06, "output_power": 1.2701602848316486e-06, "reference_active": true, "delta_db": 1.0286264306047723}], "active_band_count": 3, "active_band_mae_db": 0.542028841956117}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.872309512115098e-05, "log_rms_mae_db": 0.5740833201722302, "rms_envelope_nrmse": 0.029010908829369093, "envelope_correlation": 0.999386771200678, "rms_gain_error_db": -0.036678586357078914, "reference_mean_power": 0.0006930459912916024, "output_mean_power": 0.0006872174792918179}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.4404474148541786e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.432934367906604e-05, "output_power": 6.282717121418424e-05, "reference_active": true, "delta_db": -0.10261614428681351}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.638974827185174e-06, "output_power": 2.995245684758072e-06, "reference_active": true, "delta_db": 0.5499720358725237}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.490824439966143e-08, "output_power": 7.437981568916157e-08, "reference_active": true, "delta_db": -0.030745209144773696}], "active_band_count": 3, "active_band_mae_db": 0.22777779643470367}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.800802183872533e-05, "log_rms_mae_db": 0.825993173185491, "rms_envelope_nrmse": 0.11671061438725162, "envelope_correlation": 0.9922016969016575, "rms_gain_error_db": -0.180948875872376, "reference_mean_power": 0.0001528560580614903, "output_mean_power": 0.00014661816101086583}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.6939080235935477e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.743995800608424e-06, "output_power": 7.934092151119477e-06, "reference_active": true, "delta_db": -0.42212700053554825}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.01868229376414e-06, "output_power": 1.5548800708722487e-06, "reference_active": true, "delta_db": -1.1337107658346928}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.212055898483429e-07, "output_power": 2.5203845882473273e-07, "reference_active": true, "delta_db": -2.2302731079440368}], "active_band_count": 3, "active_band_mae_db": 1.2620369581047592}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.485177873530849e-05, "log_rms_mae_db": 0.5806010559290448, "rms_envelope_nrmse": 0.07500463243337671, "envelope_correlation": 0.9968780389324926, "rms_gain_error_db": -0.180948887711147, "reference_mean_power": 0.00015362482187073777, "output_mean_power": 0.00014735555196541858}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.6796802400302903e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.417995641253307e-06, "output_power": 7.492231314884901e-06, "reference_active": true, "delta_db": -0.5059751923641808}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.917412489595775e-07, "output_power": 7.748625221643108e-07, "reference_active": true, "delta_db": -1.0717372113945625}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9786028250337687e-08, "output_power": 1.2389156001241009e-08, "reference_active": true, "delta_db": -2.033169033139792}], "active_band_count": 3, "active_band_mae_db": 1.2036271456328451}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.5712979141900155e-05, "log_rms_mae_db": 1.0759823800240613, "rms_envelope_nrmse": 0.16301875009516326, "envelope_correlation": 0.9809155849826385, "rms_gain_error_db": -0.3223792289680062, "reference_mean_power": 1.157751296991392e-05, "output_mean_power": 1.0749229944625847e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.302605621158197e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.645490651287566e-07, "output_power": 7.825131638876701e-07, "reference_active": true, "delta_db": -0.4329799327831988}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.590093915842518e-07, "output_power": 3.087624819412641e-07, "reference_active": true, "delta_db": -1.7219704824822557}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3044874644069055e-07, "output_power": 1.1571443364476578e-07, "reference_active": true, "delta_db": -2.9918681598815167}], "active_band_count": 3, "active_band_mae_db": 1.715606191715657}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.532870280173584e-05, "log_rms_mae_db": 0.7758393204917876, "rms_envelope_nrmse": 0.10047498987786678, "envelope_correlation": 0.9930480030212295, "rms_gain_error_db": -0.3223792616402724, "reference_mean_power": 1.163573961751773e-05, "output_mean_power": 1.0803290837036425e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.177196911262554e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.60049524306651e-07, "output_power": 7.306746209054906e-07, "reference_active": true, "delta_db": -0.7079943706415728}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5501826725164134e-07, "output_power": 1.5742586159421325e-07, "reference_active": true, "delta_db": -2.0949521168005467}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7808109251124296e-08, "output_power": 8.023314830848496e-09, "reference_active": true, "delta_db": -3.4626397732137053}], "active_band_count": 3, "active_band_mae_db": 2.0885287535519415}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8939470603485198, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "a43391e8b5cb5108d917b9315b796108371a20e12905da53ffbc58147825c945", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9959472512096785, "standard_deviation": 0.0017045538062968391, "minimum": 0.9922016969016575, "maximum": 0.997367534422594, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.8153496613429085, "standard_deviation": 0.021524485027316326, "minimum": 0.785501923286643, "maximum": 0.840390145625168, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8057020399858223, "standard_deviation": 0.5270120465966054, "minimum": 0.2322541034916464, "maximum": 1.5032632875505179, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08624447588868298, "standard_deviation": 0.015263660499459073, "minimum": 0.07038825272934028, "maximum": 0.11671061438725162, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9986875728342914, "standard_deviation": 0.0008685585960330749, "minimum": 0.9968780389324926, "maximum": 0.999426804120773, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5759642017084037, "standard_deviation": 0.017826566917007923, "minimum": 0.5542044891944496, "maximum": 0.608225556310537, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7511883328006028, "standard_deviation": 0.5117788189381612, "minimum": 0.11168977650280458, "maximum": 1.4975484585057057, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05296785242222284, "standard_deviation": 0.014110486491481332, "minimum": 0.038652484506861824, "maximum": 0.07500463243337671, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9844844930274843, "standard_deviation": 0.0016535085069241636, "minimum": 0.9809155849826385, "maximum": 0.986286526502836, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.0631870939530563, "standard_deviation": 0.016825935359703937, "minimum": 1.0383708233770714, "maximum": 1.0927851318206265, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.013344741220667, "standard_deviation": 0.5210966213763132, "minimum": 0.47733901792577743, "maximum": 1.8237259117253835, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14890634934151165, "standard_deviation": 0.007300216410801596, "minimum": 0.13955866764515468, "maximum": 0.16301875009516326, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9946586809490268, "standard_deviation": 0.00099863348417463, "minimum": 0.9930480030212295, "maximum": 0.9959727773231775, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7540971353790111, "standard_deviation": 0.030368887280659188, "minimum": 0.7076714463906185, "maximum": 0.7941270418855031, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.2881374971873325, "standard_deviation": 0.6773902975043266, "minimum": 0.661194326741966, "maximum": 2.3035323485073356, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0914715738965986, "standard_deviation": 0.010045687753421495, "minimum": 0.07760849709091636, "maximum": 0.1043324449807107, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9977299000878961, "standard_deviation": 0.0004724894069751906, "minimum": 0.9967687399686743, "maximum": 0.9983298396819701, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8269393628014599, "standard_deviation": 0.02679497738713364, "minimum": 0.785744621296184, "maximum": 0.865800395307058, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5275846023088289, "standard_deviation": 0.17472378943630687, "minimum": 0.3191157508663829, "maximum": 0.8168860268678465, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.056044961791598305, "standard_deviation": 0.00546460256630166, "minimum": 0.048481487011782655, "maximum": 0.06683648191050458, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9993083286972624, "standard_deviation": 0.00018827597739541667, "minimum": 0.9989152875656809, "maximum": 0.999487524595716, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5638982410730485, "standard_deviation": 0.017033580701070448, "minimum": 0.5336003591987534, "maximum": 0.5824212208582847, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.3945168886547823, "standard_deviation": 0.23080203529851673, "minimum": 0.13799819208087694, "maximum": 0.7913983317589359, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03098477894481818, "standard_deviation": 0.003666005447836203, "minimum": 0.026928488716335755, "maximum": 0.038487793336244844, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.14676470737960282, "standard_deviation": 0.042630247588868866, "minimum": 0.10063829492249152, "maximum": 0.19847559502740225, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.241552971614897, "standard_deviation": 0.008619038824591812, "minimum": 5.229160255508908, "maximum": 5.252238784430524, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.372435461976999, "standard_deviation": 0.006535370313224317, "minimum": 0.3629193553946384, "maximum": 0.38068768868399894, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06967984179741823, "standard_deviation": 0.05008358592066779, "minimum": -0.13276736882346135, "maximum": 0.0019366433940359836, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9976027073560527, "standard_deviation": 0.0003692117854024018, "minimum": 0.9969459936588023, "maximum": 0.9982762676363807, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.6205748687261281, "standard_deviation": 0.015254014380947506, "minimum": 0.5994635302014719, "maximum": 0.6418294492978286, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3738978443245121, "standard_deviation": 0.1855706637006185, "minimum": 0.1884148758430966, "maximum": 0.6733248515975759, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.053274974909302955, "standard_deviation": 0.0042140046489972174, "minimum": 0.04471171885738086, "maximum": 0.059911891269186106, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.999337366965033, "standard_deviation": 0.0001583986209844682, "minimum": 0.999030317616977, "maximum": 0.9995577165057512, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.3803762443062573, "standard_deviation": 0.016551513945224125, "minimum": 0.3551225150622465, "maximum": 0.40675828813799514, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.37376204972910615, "standard_deviation": 0.19774373055189928, "minimum": 0.09585834864050154, "maximum": 0.6958314830243181, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.028550299068380032, "standard_deviation": 0.0035418010421022455, "minimum": 0.02217820263227842, "maximum": 0.03386891046928724, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_falset10_VOICEACTRESS100_004", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 1.8979606628417969, "predicted_mos": 1.8979606628417969, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "3831842f3c43833951a41d956a2417b3b27260e2e2f58720fa7a97af4ef37855", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.066965099889785}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6041193571214112, "全帯域_10ms_rms_envelope_nrmse": 0.052158378911711656, "全帯域_10ms_envelope_correlation": 0.9977533000771929, "全帯域_10ms_modulation_mae_db": 0.4819053096465782, "全帯域_40ms_log_rms_mae_db": 0.34484369276637983, "全帯域_40ms_rms_envelope_nrmse": 0.026002874763297327, "全帯域_40ms_envelope_correlation": 0.9995186872270521, "全帯域_40ms_modulation_mae_db": 0.46505788266946807, "300–1000 Hz_10ms_log_rms_mae_db": 0.8346639995429717, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06832301157105862, "300–1000 Hz_10ms_envelope_correlation": 0.9967288824687791, "300–1000 Hz_10ms_modulation_mae_db": 0.9035190856384304, "300–1000 Hz_40ms_log_rms_mae_db": 0.5818021079980471, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04472082526605332, "300–1000 Hz_40ms_envelope_correlation": 0.9986536598616114, "300–1000 Hz_40ms_modulation_mae_db": 1.4867359479821616, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8126389876087086, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08482818039532813, "1000–3000 Hz_10ms_envelope_correlation": 0.9958772794614466, "1000–3000 Hz_10ms_modulation_mae_db": 0.9070779893098572, "1000–3000 Hz_40ms_log_rms_mae_db": 0.575164575865987, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03958173784481636, "1000–3000 Hz_40ms_envelope_correlation": 0.9991645778268206, "1000–3000 Hz_40ms_modulation_mae_db": 0.6591240483468676, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1070759508454047, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15709162183054592, "3000–6000 Hz_10ms_envelope_correlation": 0.984087744722823, "3000–6000 Hz_10ms_modulation_mae_db": 1.2133881060061107, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7892270969043584, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11152562788717416, "3000–6000 Hz_40ms_envelope_correlation": 0.9933149438795336, "3000–6000 Hz_40ms_modulation_mae_db": 1.5081608574222383, "mr_stft_db": 5.192989040127994, "band_mae_db": 0.1283758993304265, "rms_gain_error_db": -0.10524866616870981, "output_peak": 0.3670864578898764}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6284192895195667, "全帯域_10ms_rms_envelope_nrmse": 0.05478199199954279, "全帯域_10ms_envelope_correlation": 0.9974165157788348, "全帯域_10ms_modulation_mae_db": 0.1220698435682097, "全帯域_40ms_log_rms_mae_db": 0.3716333164487185, "全帯域_40ms_rms_envelope_nrmse": 0.025858958039103267, "全帯域_40ms_envelope_correlation": 0.9994122720242902, "全帯域_40ms_modulation_mae_db": 0.29541300350386784, "300–1000 Hz_10ms_log_rms_mae_db": 0.8351280280002675, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0600569454497742, "300–1000 Hz_10ms_envelope_correlation": 0.9973961249106761, "300–1000 Hz_10ms_modulation_mae_db": 0.5663153963855775, "300–1000 Hz_40ms_log_rms_mae_db": 0.5572417742471462, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.030770711952105616, "300–1000 Hz_40ms_envelope_correlation": 0.9993003637526606, "300–1000 Hz_40ms_modulation_mae_db": 0.09188424406130886, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8244015262014123, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0907966264821741, "1000–3000 Hz_10ms_envelope_correlation": 0.9953631021183609, "1000–3000 Hz_10ms_modulation_mae_db": 0.8746795870763279, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5868644966243931, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04804372220902115, "1000–3000 Hz_40ms_envelope_correlation": 0.9988496698677304, "1000–3000 Hz_40ms_modulation_mae_db": 0.661557547774993, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0447660244042625, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.140828514048513, "3000–6000 Hz_10ms_envelope_correlation": 0.9862102870456116, "3000–6000 Hz_10ms_modulation_mae_db": 1.6099246209940479, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7050086101182718, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08219687393389268, "3000–6000 Hz_40ms_envelope_correlation": 0.9959272369192914, "3000–6000 Hz_40ms_modulation_mae_db": 2.0929336218249435, "mr_stft_db": 5.192326584830667, "band_mae_db": 0.1325776624566575, "rms_gain_error_db": -0.033498477223970924, "output_peak": 0.36786218424028444}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6141279994957837, "全帯域_10ms_rms_envelope_nrmse": 0.055506418244800695, "全帯域_10ms_envelope_correlation": 0.9973807444866024, "全帯域_10ms_modulation_mae_db": 0.6279891413411757, "全帯域_40ms_log_rms_mae_db": 0.3807383797636907, "全帯域_40ms_rms_envelope_nrmse": 0.03183464339398556, "全帯域_40ms_envelope_correlation": 0.9991360813047022, "全帯域_40ms_modulation_mae_db": 0.5587514485755565, "300–1000 Hz_10ms_log_rms_mae_db": 0.854531735342739, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0545039212305353, "300–1000 Hz_10ms_envelope_correlation": 0.9978624943716345, "300–1000 Hz_10ms_modulation_mae_db": 0.19592942478011288, "300–1000 Hz_40ms_log_rms_mae_db": 0.6225854560009256, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03142501548559058, "300–1000 Hz_40ms_envelope_correlation": 0.9992759005182307, "300–1000 Hz_40ms_modulation_mae_db": 0.4654575013362164, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8329180564867035, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09374256476870765, "1000–3000 Hz_10ms_envelope_correlation": 0.9954877343636743, "1000–3000 Hz_10ms_modulation_mae_db": 0.8883245055025434, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6020373283172122, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05421382613399076, "1000–3000 Hz_40ms_envelope_correlation": 0.9989830551937448, "1000–3000 Hz_40ms_modulation_mae_db": 0.8807096211908396, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0423379063221496, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1350034379413606, "3000–6000 Hz_10ms_envelope_correlation": 0.9871499038841421, "3000–6000 Hz_10ms_modulation_mae_db": 0.3051498341100138, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6763160707151527, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0826871468538049, "3000–6000 Hz_40ms_envelope_correlation": 0.9950435332733376, "3000–6000 Hz_40ms_modulation_mae_db": 0.3803961396166154, "mr_stft_db": 5.201936560435359, "band_mae_db": 0.16116176170107252, "rms_gain_error_db": -0.05977878970331981, "output_peak": 0.38478586775785506}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6064664954120037, "全帯域_10ms_rms_envelope_nrmse": 0.05053627752277662, "全帯域_10ms_envelope_correlation": 0.9977997554737889, "全帯域_10ms_modulation_mae_db": 0.4194077512723415, "全帯域_40ms_log_rms_mae_db": 0.37126125048287734, "全帯域_40ms_rms_envelope_nrmse": 0.02832312842824795, "全帯域_40ms_envelope_correlation": 0.9992827051988987, "全帯域_40ms_modulation_mae_db": 0.5650603384711138, "300–1000 Hz_10ms_log_rms_mae_db": 0.7908310316295462, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05193160602021131, "300–1000 Hz_10ms_envelope_correlation": 0.9980540445971626, "300–1000 Hz_10ms_modulation_mae_db": 0.15898296705462725, "300–1000 Hz_40ms_log_rms_mae_db": 0.5151288346902837, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.030936258400166138, "300–1000 Hz_40ms_envelope_correlation": 0.9992924489920918, "300–1000 Hz_40ms_modulation_mae_db": 0.19918657513673932, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7800187152631224, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08732022848194627, "1000–3000 Hz_10ms_envelope_correlation": 0.9958100216128196, "1000–3000 Hz_10ms_modulation_mae_db": 0.7504970278747304, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5309060198192737, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05078598394525035, "1000–3000 Hz_40ms_envelope_correlation": 0.9987983344168523, "1000–3000 Hz_40ms_modulation_mae_db": 0.9168290952164213, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0110929923501555, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13381554848863644, "3000–6000 Hz_10ms_envelope_correlation": 0.9875310785780251, "3000–6000 Hz_10ms_modulation_mae_db": 0.8742259712971364, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7122172224937997, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07769654732668528, "3000–6000 Hz_40ms_envelope_correlation": 0.9963272543392113, "3000–6000 Hz_40ms_modulation_mae_db": 1.1301836652015014, "mr_stft_db": 5.200578245723951, "band_mae_db": 0.16061815181591074, "rms_gain_error_db": -0.021514015405626655, "output_peak": 0.3968871685948282}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6080210464719324, "全帯域_10ms_rms_envelope_nrmse": 0.04662722698939633, "全帯域_10ms_envelope_correlation": 0.9981287213391791, "全帯域_10ms_modulation_mae_db": 0.15919107455361708, "全帯域_40ms_log_rms_mae_db": 0.35445065476931065, "全帯域_40ms_rms_envelope_nrmse": 0.023564021260087088, "全帯域_40ms_envelope_correlation": 0.9995087388671857, "全帯域_40ms_modulation_mae_db": 0.36117764467954117, "300–1000 Hz_10ms_log_rms_mae_db": 0.8101848120987272, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.052621440080519756, "300–1000 Hz_10ms_envelope_correlation": 0.9979933877669083, "300–1000 Hz_10ms_modulation_mae_db": 0.6247198067478278, "300–1000 Hz_40ms_log_rms_mae_db": 0.5476867518373479, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029539398876516625, "300–1000 Hz_40ms_envelope_correlation": 0.999350325576526, "300–1000 Hz_40ms_modulation_mae_db": 0.24127991941349125, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7360123098393648, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07442873031538848, "1000–3000 Hz_10ms_envelope_correlation": 0.996898503376048, "1000–3000 Hz_10ms_modulation_mae_db": 0.9147879987770997, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4942813733386062, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.043809397912784966, "1000–3000 Hz_40ms_envelope_correlation": 0.9990073639643242, "1000–3000 Hz_40ms_modulation_mae_db": 0.8645302888469374, "3000–6000 Hz_10ms_log_rms_mae_db": 1.047330364435951, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14419360911018847, "3000–6000 Hz_10ms_envelope_correlation": 0.9863077537609102, "3000–6000 Hz_10ms_modulation_mae_db": 0.9337950529363842, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7647845419612135, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0924173837849782, "3000–6000 Hz_40ms_envelope_correlation": 0.9955285530999401, "3000–6000 Hz_40ms_modulation_mae_db": 1.3755414244956528, "mr_stft_db": 5.197645048968753, "band_mae_db": 0.10104910172471183, "rms_gain_error_db": -0.02622707156016161, "output_peak": 0.36776350972970423}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6085808997520575, "全帯域_10ms_rms_envelope_nrmse": 0.05314870583817257, "全帯域_10ms_envelope_correlation": 0.9975659968703985, "全帯域_10ms_modulation_mae_db": 0.851829975398725, "全帯域_40ms_log_rms_mae_db": 0.37993200734498855, "全帯域_40ms_rms_envelope_nrmse": 0.02863676714335333, "全帯域_40ms_envelope_correlation": 0.9992694805853989, "全帯域_40ms_modulation_mae_db": 0.8709920805923227, "300–1000 Hz_10ms_log_rms_mae_db": 0.8550186670119867, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06838475749661822, "300–1000 Hz_10ms_envelope_correlation": 0.996617235948368, "300–1000 Hz_10ms_modulation_mae_db": 0.8123184355032658, "300–1000 Hz_40ms_log_rms_mae_db": 0.5974980626996645, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.044134285705397576, "300–1000 Hz_40ms_envelope_correlation": 0.9985649558714332, "300–1000 Hz_40ms_modulation_mae_db": 0.8933826630761992, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7603599055641416, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07482693401133493, "1000–3000 Hz_10ms_envelope_correlation": 0.9969369646227146, "1000–3000 Hz_10ms_modulation_mae_db": 0.179501694889819, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5466761129063636, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.043795060773020034, "1000–3000 Hz_40ms_envelope_correlation": 0.9990201428534535, "1000–3000 Hz_40ms_modulation_mae_db": 0.35293430094831396, "3000–6000 Hz_10ms_log_rms_mae_db": 1.050023849397384, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1405213771668149, "3000–6000 Hz_10ms_envelope_correlation": 0.9862662541074179, "3000–6000 Hz_10ms_modulation_mae_db": 0.9066915245849687, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7401297003903236, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09239721897713822, "3000–6000 Hz_40ms_envelope_correlation": 0.9944919859782799, "3000–6000 Hz_40ms_modulation_mae_db": 1.4244636048244363, "mr_stft_db": 5.179591805283176, "band_mae_db": 0.11123664556836195, "rms_gain_error_db": -0.003625420278602328, "output_peak": 0.3845362680620118}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6149718177018271, "全帯域_10ms_rms_envelope_nrmse": 0.04953755696105609, "全帯域_10ms_envelope_correlation": 0.9979707130905181, "全帯域_10ms_modulation_mae_db": 0.5876104777606906, "全帯域_40ms_log_rms_mae_db": 0.3641537686562259, "全帯域_40ms_rms_envelope_nrmse": 0.024696754843197777, "全帯域_40ms_envelope_correlation": 0.9995603978996813, "全帯域_40ms_modulation_mae_db": 0.5230776804651688, "300–1000 Hz_10ms_log_rms_mae_db": 0.8266336756037173, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.055152842453081365, "300–1000 Hz_10ms_envelope_correlation": 0.9978122479553843, "300–1000 Hz_10ms_modulation_mae_db": 0.5419651870516836, "300–1000 Hz_40ms_log_rms_mae_db": 0.5933863902216677, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02808155876171544, "300–1000 Hz_40ms_envelope_correlation": 0.9994399958485797, "300–1000 Hz_40ms_modulation_mae_db": 0.8837683909228228, "1000–3000 Hz_10ms_log_rms_mae_db": 0.814463905844542, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08486865050329707, "1000–3000 Hz_10ms_envelope_correlation": 0.9961528198176649, "1000–3000 Hz_10ms_modulation_mae_db": 1.0240706890543712, "1000–3000 Hz_40ms_log_rms_mae_db": 0.56273545937697, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05353225207832564, "1000–3000 Hz_40ms_envelope_correlation": 0.9987070619123566, "1000–3000 Hz_40ms_modulation_mae_db": 0.9099453238183951, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0573775471894598, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.138939413953326, "3000–6000 Hz_10ms_envelope_correlation": 0.9862733593668519, "3000–6000 Hz_10ms_modulation_mae_db": 0.6043542163215253, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7133797583244255, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08393777459941143, "3000–6000 Hz_40ms_envelope_correlation": 0.9952662500270334, "3000–6000 Hz_40ms_modulation_mae_db": 0.7288045990728369, "mr_stft_db": 5.193278031659694, "band_mae_db": 0.0875040925636306, "rms_gain_error_db": -0.0981693354738436, "output_peak": 0.37773810533759855}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6190471618067084, "全帯域_10ms_rms_envelope_nrmse": 0.05388138660351826, "全帯域_10ms_envelope_correlation": 0.9975473169625336, "全帯域_10ms_modulation_mae_db": 0.46835011282846084, "全帯域_40ms_log_rms_mae_db": 0.3833551583112886, "全帯域_40ms_rms_envelope_nrmse": 0.02608374730191647, "全帯域_40ms_envelope_correlation": 0.9994565364581764, "全帯域_40ms_modulation_mae_db": 0.4771969292484383, "300–1000 Hz_10ms_log_rms_mae_db": 0.8126030295822941, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0576876281290789, "300–1000 Hz_10ms_envelope_correlation": 0.9975975433172842, "300–1000 Hz_10ms_modulation_mae_db": 0.36468339908862935, "300–1000 Hz_40ms_log_rms_mae_db": 0.5382144833575085, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03161859735106843, "300–1000 Hz_40ms_envelope_correlation": 0.999270681585609, "300–1000 Hz_40ms_modulation_mae_db": 0.6478263344030665, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8246255034259403, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08622149387724502, "1000–3000 Hz_10ms_envelope_correlation": 0.9958520405143357, "1000–3000 Hz_10ms_modulation_mae_db": 0.5378154414278605, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5730461869174229, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.048107638525995235, "1000–3000 Hz_40ms_envelope_correlation": 0.9988566645364724, "1000–3000 Hz_40ms_modulation_mae_db": 0.5186441395887028, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0289371516737607, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15583898242809646, "3000–6000 Hz_10ms_envelope_correlation": 0.9823751820196979, "3000–6000 Hz_10ms_modulation_mae_db": 0.7275376777495041, "3000–6000 Hz_40ms_log_rms_mae_db": 0.703693258948309, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09303696565461514, "3000–6000 Hz_40ms_envelope_correlation": 0.9937707275630254, "3000–6000 Hz_40ms_modulation_mae_db": 1.0901829567087618, "mr_stft_db": 5.1840208755346895, "band_mae_db": 0.14842523371852426, "rms_gain_error_db": -0.07816360423681924, "output_peak": 0.37378358831632874}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.486501493673734, "spectral_convergence": 0.19587818318710729, "spectral_convergence_status": "ok", "amplitude_floor": 9.086732072822267e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.065920033907327, "spectral_convergence": 0.1941590498659176, "spectral_convergence_status": "ok", "amplitude_floor": 8.520258431312163e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.026545592802923, "spectral_convergence": 0.20099884976034743, "spectral_convergence_status": "ok", "amplitude_floor": 5.353418087016012e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 3.131933551513939e-05, "output_power": 3.124930641388621e-05, "delta_db": -0.009721567868091956, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0004897019472039064, "output_power": 0.00048449487359468165, "delta_db": -0.04642644736120309, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.00038033005135275084, "output_power": 0.00036549829269774106, "delta_db": -0.17275289420980738, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0002067238728943134, "output_power": 0.0002006969264038156, "delta_db": -0.12849911250051338, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.323291799953591e-05, "output_power": 1.2079042336194077e-05, "delta_db": -0.39623117871140245, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.500515826026349e-05, "output_power": 2.427426391484352e-05, "delta_db": -0.12883538217394583, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.8390290595099542e-05, "output_power": 2.8284816568483677e-05, "delta_db": -0.01616471248802146, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.1283758993304265, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.10524866616870981, "pitch": null, "output_rms_dbfs": -29.405965766007718, "output_peak": 0.3670864578898764, "reference_rms_dbfs": -29.30071709983901, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.192989040127994}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00015179812996022924, "log_rms_mae_db": 0.6041193571214112, "rms_envelope_nrmse": 0.052158378911711656, "envelope_correlation": 0.9977533000771929, "rms_gain_error_db": -0.10524866877354222, "reference_mean_power": 0.0011756832947918806, "output_mean_power": 0.0011475337846494347}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.744923761629972e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00015071015783187623, "output_power": 0.00014705718327224555, "reference_active": true, "delta_db": -0.10656281399567209}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2413420104691182e-05, "output_power": 1.1223859707349566e-05, "reference_active": true, "delta_db": -0.43749223783222274}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.099936667111779e-06, "output_power": 2.5187596849857543e-06, "reference_active": true, "delta_db": -0.9016608771118397}], "active_band_count": 3, "active_band_mae_db": 0.4819053096465782}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.0001370105991807196, "log_rms_mae_db": 0.34484369276637983, "rms_envelope_nrmse": 0.026002874763297327, "envelope_correlation": 0.9995186872270521, "rms_gain_error_db": -0.10524861061662354, "reference_mean_power": 0.0011815960953402045, "output_mean_power": 0.0011533050298295497}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.5970704572828427e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000136303861600392, "output_power": 0.00013333720019879946, "reference_active": true, "delta_db": -0.09556828315303044}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.090701624693659e-06, "output_power": 4.7439871131325945e-06, "reference_active": true, "delta_db": -0.3063414237892057}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5690836910660882e-07, "output_power": 1.2483021378766382e-07, "reference_active": true, "delta_db": -0.9932639410661681}], "active_band_count": 3, "active_band_mae_db": 0.46505788266946807}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.549209054072936e-05, "log_rms_mae_db": 0.8346639995429717, "rms_envelope_nrmse": 0.06832301157105862, "envelope_correlation": 0.9967288824687791, "rms_gain_error_db": -0.12938363600091898, "reference_mean_power": 0.000689577872249739, "output_mean_power": 0.0006693371858483331}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.482675818010425e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.030686777059284e-05, "output_power": 6.9295343114081e-05, "reference_active": true, "delta_db": -0.06293700679856384}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.045775397952136e-06, "output_power": 4.7921432606363674e-06, "reference_active": true, "delta_db": -1.009222162295379}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0022957436919974e-06, "output_power": 6.873154039488399e-07, "reference_active": true, "delta_db": -1.6383980878213484}], "active_band_count": 3, "active_band_mae_db": 0.9035190856384304}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.872309512115098e-05, "log_rms_mae_db": 0.5818021079980471, "rms_envelope_nrmse": 0.04472082526605332, "envelope_correlation": 0.9986536598616114, "rms_gain_error_db": -0.1293836452705474, "reference_mean_power": 0.0006930459912916024, "output_mean_power": 0.0006727035062350081}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.4404474148541786e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.432934367906604e-05, "output_power": 6.342198283598849e-05, "reference_active": true, "delta_db": -0.061693047659509614}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.638974827185174e-06, "output_power": 2.0606598265642643e-06, "reference_active": true, "delta_db": -1.0742894314114997}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.490824439966143e-08, "output_power": 3.4842321378788245e-08, "reference_active": true, "delta_db": -3.3242253648754754}], "active_band_count": 3, "active_band_mae_db": 1.4867359479821616}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 9.800802183872533e-05, "log_rms_mae_db": 0.8126389876087086, "rms_envelope_nrmse": 0.08482818039532813, "envelope_correlation": 0.9958772794614466, "rms_gain_error_db": -0.11301757846228228, "reference_mean_power": 0.0001528560580614903, "output_mean_power": 0.00014892955701467918}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.6939080235935477e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.743995800608424e-06, "output_power": 8.244960391710961e-06, "reference_active": true, "delta_db": -0.2552136670619025}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.01868229376414e-06, "output_power": 1.6058504582654479e-06, "reference_active": true, "delta_db": -0.9936287377424718}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.212055898483429e-07, "output_power": 3.0009238131999014e-07, "reference_active": true, "delta_db": -1.4723915631251971}], "active_band_count": 3, "active_band_mae_db": 0.9070779893098572}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.485177873530849e-05, "log_rms_mae_db": 0.575164575865987, "rms_envelope_nrmse": 0.03958173784481636, "envelope_correlation": 0.9991645778268206, "rms_gain_error_db": -0.11301758886974056, "reference_mean_power": 0.00015362482187073777, "output_mean_power": 0.00014967857278928493}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.6796802400302903e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.417995641253307e-06, "output_power": 7.836545631899167e-06, "reference_active": true, "delta_db": -0.3108402972262109}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.917412489595775e-07, "output_power": 7.989112644546614e-07, "reference_active": true, "delta_db": -0.9389983233711101}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9786028250337687e-08, "output_power": 1.6734212222222125e-08, "reference_active": true, "delta_db": -0.7275335244432817}], "active_band_count": 3, "active_band_mae_db": 0.6591240483468676}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.5712979141900155e-05, "log_rms_mae_db": 1.1070759508454047, "rms_envelope_nrmse": 0.15709162183054592, "envelope_correlation": 0.984087744722823, "rms_gain_error_db": -0.5753992669744141, "reference_mean_power": 1.157751296991392e-05, "output_mean_power": 1.0140873132277013e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.302605621158197e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.645490651287566e-07, "output_power": 7.593062459558698e-07, "reference_active": true, "delta_db": -0.5637267316710382}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.590093915842518e-07, "output_power": 3.9441672076642063e-07, "reference_active": true, "delta_db": -0.6586625354187507}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3044874644069055e-07, "output_power": 1.3206777007403155e-07, "reference_active": true, "delta_db": -2.4177750509285434}], "active_band_count": 3, "active_band_mae_db": 1.2133881060061107}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.532870280173584e-05, "log_rms_mae_db": 0.7892270969043584, "rms_envelope_nrmse": 0.11152562788717416, "envelope_correlation": 0.9933149438795336, "rms_gain_error_db": -0.5753993424950536, "reference_mean_power": 1.163573961751773e-05, "output_mean_power": 1.0191874327087028e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.177196911262554e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.60049524306651e-07, "output_power": 7.242806467402322e-07, "reference_active": true, "delta_db": -0.7461657926173633}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5501826725164134e-07, "output_power": 2.0340807727187146e-07, "reference_active": true, "delta_db": -0.9820309593240683}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.7808109251124296e-08, "output_power": 9.353824760006353e-09, "reference_active": true, "delta_db": -2.7962858203252834}], "active_band_count": 3, "active_band_mae_db": 1.5081608574222383}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8785924198257576, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "0b7a23e4cd6e6ef02456e85383235f843c7533790890c050eda8303771adeee7", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.996047308235883, "standard_deviation": 0.0005894015712778685, "minimum": 0.9953631021183609, "maximum": 0.9969369646227146, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.7981798637792419, "standard_deviation": 0.03523980516135198, "minimum": 0.7360123098393648, "maximum": 0.8329180564867035, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7595943667390761, "standard_deviation": 0.27551936027466734, "minimum": 0.179501694889819, "maximum": 1.0240706890543712, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.0846291761044277, "standard_deviation": 0.006877484288174473, "minimum": 0.07442873031538848, "maximum": 0.09374256476870765, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9989233588214694, "standard_deviation": 0.00014661315594576338, "minimum": 0.9987070619123566, "maximum": 0.9991645778268206, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5589639441457785, "standard_deviation": 0.03429040784169695, "minimum": 0.4942813733386062, "maximum": 0.6020373283172122, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7205342957164339, "standard_deviation": 0.20837398843027924, "minimum": 0.35293430094831396, "maximum": 0.9168290952164213, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.047733702427900565, "standard_deviation": 0.005106510337692915, "minimum": 0.03958173784481636, "maximum": 0.05421382613399076, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.985775195435685, "standard_deviation": 0.0017047311922679666, "minimum": 0.9823751820196979, "maximum": 0.9875310785780251, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.048617723327316, "standard_deviation": 0.027639090805347537, "minimum": 1.0110929923501555, "maximum": 1.1070759508454047, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.8968833754999613, "standard_deviation": 0.3918773405426579, "minimum": 0.3051498341100138, "maximum": 1.6099246209940479, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14327906312093522, "standard_deviation": 0.008781973454263155, "minimum": 0.13381554848863644, "maximum": 0.15709162183054592, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9949588106349566, "standard_deviation": 0.0010398183616822571, "minimum": 0.9933149438795336, "maximum": 0.9963272543392113, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7255945324819817, "standard_deviation": 0.03675439159451403, "minimum": 0.6763160707151527, "maximum": 0.7892270969043584, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.216333358645873, "standard_deviation": 0.5185236924208558, "minimum": 0.3803961396166154, "maximum": 2.0929336218249435, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0894869423772125, "standard_deviation": 0.010586733723672697, "minimum": 0.07769654732668528, "maximum": 0.11152562788717416, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9975077451670247, "standard_deviation": 0.0005571633909018862, "minimum": 0.996617235948368, "maximum": 0.9980540445971626, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8274493723515312, "standard_deviation": 0.02224724754758942, "minimum": 0.7908310316295462, "maximum": 0.8550186670119867, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5210542127812693, "standard_deviation": 0.2687537830951996, "minimum": 0.15898296705462725, "maximum": 0.9035190856384304, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.058582769053859715, "standard_deviation": 0.006569437722497676, "minimum": 0.05193160602021131, "maximum": 0.06838475749661822, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9991435415008427, "standard_deviation": 0.0003350565742244444, "minimum": 0.9985649558714332, "maximum": 0.9994399958485797, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5691929826315739, "standard_deviation": 0.03562541957286622, "minimum": 0.5151288346902837, "maximum": 0.6225854560009256, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6136901970415007, "standard_deviation": 0.46587878827821366, "minimum": 0.09188424406130886, "maximum": 1.4867359479821616, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.033903331474826714, "standard_deviation": 0.006596605506949989, "minimum": 0.02808155876171544, "maximum": 0.04472082526605332, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.12886856860991197, "standard_deviation": 0.027368326141817455, "minimum": 0.0875040925636306, "maximum": 0.16116176170107252, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.192795774070536, "standard_deviation": 0.00774107787057428, "minimum": 5.179591805283176, "maximum": 5.201936560435359, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.37755539374106095, "standard_deviation": 0.010612847337427313, "minimum": 0.3670864578898764, "maximum": 0.3968871685948282, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.05327817250638174, "standard_deviation": 0.037749261768393785, "minimum": -0.10524866616870981, "maximum": -0.003625420278602328, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.997695383009881, "standard_deviation": 0.0002654552475600658, "minimum": 0.9973807444866024, "maximum": 0.9981287213391791, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.6129692584101614, "standard_deviation": 0.007976272564193245, "minimum": 0.6041193571214112, "maximum": 0.6284192895195667, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.46479421079622485, "standard_deviation": 0.24045544211305817, "minimum": 0.1220698435682097, "maximum": 0.851829975398725, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.052022242883871875, "standard_deviation": 0.002975795547748437, "minimum": 0.04662722698939633, "maximum": 0.055506418244800695, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9993931124456732, "standard_deviation": 0.0001488298248968011, "minimum": 0.9991360813047022, "maximum": 0.9995603978996813, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.368796028567935, "standard_deviation": 0.013595063561867337, "minimum": 0.34484369276637983, "maximum": 0.3833551583112886, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5145908760256845, "standard_deviation": 0.17197074141312918, "minimum": 0.29541300350386784, "maximum": 0.8709920805923227, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.026875111896648596, "standard_deviation": 0.0026165767880339287, "minimum": 0.023564021260087088, "maximum": 0.03183464339398556, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "language": "ja", "style": "normal", "speaker": "jvs_jvs018", "source_utterance_id": "VOICEACTRESS100_053", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 144000, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs018_parallel100_VOICEACTRESS100_053.wav", "source_file_sha256": "b763eeb5b4ce7a395fdff6d175bf1627c2328491c0da8fa95e8068f5bbf80e1e", "decoded_pcm_sha256": "c3579c72685e0999adafebb721bd42bc335d6cd615b07c9e95509516943c2f54", "original_source_sha256": "b763eeb5b4ce7a395fdff6d175bf1627c2328491c0da8fa95e8068f5bbf80e1e", "corpus_entry_id": "jvs_jvs018_parallel100_VOICEACTRESS100_053"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 4.155930519104004, "predicted_mos": 4.155930519104004, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "e6ba2b5c967e2a13acb5dfbb72e089fbb1379051aac3311456204dcd9b10ff87", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.733545700088143}, "waveform_sha256": "b37f127400e0cd559f6fdd8c6112e251e88f3dae16b7241d2e5f421b213770de"}, "rows": [{"case": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 2.2190752029418945, "predicted_mos": 2.2190752029418945, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "0d3d0cca7e9d657ef40f99f9f51fa00067f1ec840044015fbf0a486688db517e", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.7140729003585875}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.805400694129144, "全帯域_10ms_rms_envelope_nrmse": 0.05007961389846943, "全帯域_10ms_envelope_correlation": 0.9977966536590509, "全帯域_10ms_modulation_mae_db": 0.23826583550870217, "全帯域_40ms_log_rms_mae_db": 0.4957294267665039, "全帯域_40ms_rms_envelope_nrmse": 0.02553462054562689, "全帯域_40ms_envelope_correlation": 0.9995036219833191, "全帯域_40ms_modulation_mae_db": 0.2902244852851718, "300–1000 Hz_10ms_log_rms_mae_db": 1.0714909391756284, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0646087781406035, "300–1000 Hz_10ms_envelope_correlation": 0.997062384767062, "300–1000 Hz_10ms_modulation_mae_db": 1.0408652940853782, "300–1000 Hz_40ms_log_rms_mae_db": 0.7259206821132661, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03580876154827954, "300–1000 Hz_40ms_envelope_correlation": 0.9991020084282259, "300–1000 Hz_40ms_modulation_mae_db": 0.9510099086607181, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2010882444539424, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10074382388840485, "1000–3000 Hz_10ms_envelope_correlation": 0.993470164101706, "1000–3000 Hz_10ms_modulation_mae_db": 0.502261378429039, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8248372754968615, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06644680202182149, "1000–3000 Hz_40ms_envelope_correlation": 0.9974929353211757, "1000–3000 Hz_40ms_modulation_mae_db": 0.8094665772555348, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1155237142757308, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11985644343841162, "3000–6000 Hz_10ms_envelope_correlation": 0.9901932849199201, "3000–6000 Hz_10ms_modulation_mae_db": 0.18256794268045562, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7463025905205868, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06295863554603912, "3000–6000 Hz_40ms_envelope_correlation": 0.9973632253286389, "3000–6000 Hz_40ms_modulation_mae_db": 0.34912059063341605, "mr_stft_db": 5.064201768301378, "band_mae_db": 0.16131237765097728, "rms_gain_error_db": -0.10184515498814611, "output_peak": 0.33627799876877545}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7943167855795302, "全帯域_10ms_rms_envelope_nrmse": 0.050055842068324856, "全帯域_10ms_envelope_correlation": 0.9977669694538995, "全帯域_10ms_modulation_mae_db": 0.25750495403891566, "全帯域_40ms_log_rms_mae_db": 0.45526994569985824, "全帯域_40ms_rms_envelope_nrmse": 0.027121421264067764, "全帯域_40ms_envelope_correlation": 0.9993761846842026, "全帯域_40ms_modulation_mae_db": 0.3598514781664179, "300–1000 Hz_10ms_log_rms_mae_db": 1.017468353491543, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.059717052173793764, "300–1000 Hz_10ms_envelope_correlation": 0.9974664895296799, "300–1000 Hz_10ms_modulation_mae_db": 0.8178383048043409, "300–1000 Hz_40ms_log_rms_mae_db": 0.7009089735950633, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035452301477561565, "300–1000 Hz_40ms_envelope_correlation": 0.9990744321590709, "300–1000 Hz_40ms_modulation_mae_db": 0.7094963717687354, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1453879173755876, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09860079010571408, "1000–3000 Hz_10ms_envelope_correlation": 0.9935498853319812, "1000–3000 Hz_10ms_modulation_mae_db": 0.6924926748644816, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7428102205713556, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.054069030911786276, "1000–3000 Hz_40ms_envelope_correlation": 0.9983438925692206, "1000–3000 Hz_40ms_modulation_mae_db": 0.5889692863642711, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1231010334762095, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11971388164360122, "3000–6000 Hz_10ms_envelope_correlation": 0.9906685423712606, "3000–6000 Hz_10ms_modulation_mae_db": 0.44845379907196675, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8036038606378191, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07574034487810904, "3000–6000 Hz_40ms_envelope_correlation": 0.9966537717571514, "3000–6000 Hz_40ms_modulation_mae_db": 0.5462955983204849, "mr_stft_db": 5.060666031214148, "band_mae_db": 0.15270927233258386, "rms_gain_error_db": -0.09264401728815577, "output_peak": 0.3137143532524691}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.796334172725361, "全帯域_10ms_rms_envelope_nrmse": 0.05082776679238331, "全帯域_10ms_envelope_correlation": 0.9976757635400622, "全帯域_10ms_modulation_mae_db": 0.584144059467195, "全帯域_40ms_log_rms_mae_db": 0.47515968715502616, "全帯域_40ms_rms_envelope_nrmse": 0.029449453554351832, "全帯域_40ms_envelope_correlation": 0.9992197181510706, "全帯域_40ms_modulation_mae_db": 0.6086687142011322, "300–1000 Hz_10ms_log_rms_mae_db": 1.1039307448604487, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06048457036861608, "300–1000 Hz_10ms_envelope_correlation": 0.9974404501889128, "300–1000 Hz_10ms_modulation_mae_db": 0.7994283261569901, "300–1000 Hz_40ms_log_rms_mae_db": 0.7597803180443263, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03459709115082898, "300–1000 Hz_40ms_envelope_correlation": 0.9991582740168011, "300–1000 Hz_40ms_modulation_mae_db": 0.864621407112002, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2103487202538448, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1118764348968344, "1000–3000 Hz_10ms_envelope_correlation": 0.9914666004103369, "1000–3000 Hz_10ms_modulation_mae_db": 0.7042120468958725, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7951978086184072, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06391758211344149, "1000–3000 Hz_40ms_envelope_correlation": 0.9973746127409001, "1000–3000 Hz_40ms_modulation_mae_db": 0.27090872891958573, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1571802806691542, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13715160788341776, "3000–6000 Hz_10ms_envelope_correlation": 0.9878530819216841, "3000–6000 Hz_10ms_modulation_mae_db": 0.6143269392978511, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8021910856894611, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07670634785209411, "3000–6000 Hz_40ms_envelope_correlation": 0.9970368492564912, "3000–6000 Hz_40ms_modulation_mae_db": 0.47216902044217735, "mr_stft_db": 5.0629664919081, "band_mae_db": 0.15266899576614518, "rms_gain_error_db": -0.08134726815964645, "output_peak": 0.31469479559009667}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7748821251031395, "全帯域_10ms_rms_envelope_nrmse": 0.04765430774892808, "全帯域_10ms_envelope_correlation": 0.9979716666601904, "全帯域_10ms_modulation_mae_db": 0.3966405151646654, "全帯域_40ms_log_rms_mae_db": 0.4680759498677053, "全帯域_40ms_rms_envelope_nrmse": 0.025908214271375633, "全帯域_40ms_envelope_correlation": 0.9994260951643359, "全帯域_40ms_modulation_mae_db": 0.33349070980812523, "300–1000 Hz_10ms_log_rms_mae_db": 1.0674780592408566, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.060942974837414, "300–1000 Hz_10ms_envelope_correlation": 0.9974659895695422, "300–1000 Hz_10ms_modulation_mae_db": 1.2048864328495557, "300–1000 Hz_40ms_log_rms_mae_db": 0.7130593092427178, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0340287729991676, "300–1000 Hz_40ms_envelope_correlation": 0.9992719877994206, "300–1000 Hz_40ms_modulation_mae_db": 1.1518033770751135, "1000–3000 Hz_10ms_log_rms_mae_db": 1.15704836810128, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11218655853214958, "1000–3000 Hz_10ms_envelope_correlation": 0.9912467098057474, "1000–3000 Hz_10ms_modulation_mae_db": 0.17193622870267078, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7856177766863726, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0656081935023699, "1000–3000 Hz_40ms_envelope_correlation": 0.9969610889692179, "1000–3000 Hz_40ms_modulation_mae_db": 0.21229383786465394, "3000–6000 Hz_10ms_log_rms_mae_db": 1.153685459368373, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11715775493531423, "3000–6000 Hz_10ms_envelope_correlation": 0.9907501919536023, "3000–6000 Hz_10ms_modulation_mae_db": 0.4681468686719381, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7944759125478957, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06780603926625117, "3000–6000 Hz_40ms_envelope_correlation": 0.9970646846193767, "3000–6000 Hz_40ms_modulation_mae_db": 0.5793330413362557, "mr_stft_db": 5.054149328293197, "band_mae_db": 0.09285792987809094, "rms_gain_error_db": -0.08044470192226914, "output_peak": 0.303519481356541}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8032621533724257, "全帯域_10ms_rms_envelope_nrmse": 0.04712991017064167, "全帯域_10ms_envelope_correlation": 0.9980208051626133, "全帯域_10ms_modulation_mae_db": 0.5550707309000825, "全帯域_40ms_log_rms_mae_db": 0.48754620244226476, "全帯域_40ms_rms_envelope_nrmse": 0.025901893415360182, "全帯域_40ms_envelope_correlation": 0.9994274156116008, "全帯域_40ms_modulation_mae_db": 0.25820025428768506, "300–1000 Hz_10ms_log_rms_mae_db": 1.0430842332832608, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.055617855714537555, "300–1000 Hz_10ms_envelope_correlation": 0.9978285521117964, "300–1000 Hz_10ms_modulation_mae_db": 0.6202416320254306, "300–1000 Hz_40ms_log_rms_mae_db": 0.7295188141335899, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02972813105925368, "300–1000 Hz_40ms_envelope_correlation": 0.99937451180654, "300–1000 Hz_40ms_modulation_mae_db": 0.6334914779418086, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1905477939562885, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1068458262810083, "1000–3000 Hz_10ms_envelope_correlation": 0.9924649483798865, "1000–3000 Hz_10ms_modulation_mae_db": 0.357655205423103, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7861385819857815, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06308553737447711, "1000–3000 Hz_40ms_envelope_correlation": 0.9977119765525566, "1000–3000 Hz_40ms_modulation_mae_db": 0.27152390843323726, "3000–6000 Hz_10ms_log_rms_mae_db": 1.161619754488032, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1305090413623984, "3000–6000 Hz_10ms_envelope_correlation": 0.988283407286188, "3000–6000 Hz_10ms_modulation_mae_db": 0.23929446207413907, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8012220452687652, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07746097602432186, "3000–6000 Hz_40ms_envelope_correlation": 0.9957844332837643, "3000–6000 Hz_40ms_modulation_mae_db": 0.2287204505901648, "mr_stft_db": 5.05342207395579, "band_mae_db": 0.19079089304467514, "rms_gain_error_db": -0.08403167792769742, "output_peak": 0.3030136071340809}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8121409975944787, "全帯域_10ms_rms_envelope_nrmse": 0.051000101829806375, "全帯域_10ms_envelope_correlation": 0.9976478084023318, "全帯域_10ms_modulation_mae_db": 0.35494100884005525, "全帯域_40ms_log_rms_mae_db": 0.4839785141885804, "全帯域_40ms_rms_envelope_nrmse": 0.029139988977402182, "全帯域_40ms_envelope_correlation": 0.9992345508815909, "全帯域_40ms_modulation_mae_db": 0.28197472755487435, "300–1000 Hz_10ms_log_rms_mae_db": 1.046394985074911, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0606043780348249, "300–1000 Hz_10ms_envelope_correlation": 0.9973948064844252, "300–1000 Hz_10ms_modulation_mae_db": 0.23399553001386172, "300–1000 Hz_40ms_log_rms_mae_db": 0.6963128471346222, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035538750281555564, "300–1000 Hz_40ms_envelope_correlation": 0.9990774737951524, "300–1000 Hz_40ms_modulation_mae_db": 0.22387093488492268, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1786983723112432, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10357361508579851, "1000–3000 Hz_10ms_envelope_correlation": 0.9929402702093388, "1000–3000 Hz_10ms_modulation_mae_db": 0.5618827066029605, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7767597902953292, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06142461791387606, "1000–3000 Hz_40ms_envelope_correlation": 0.9978393170079205, "1000–3000 Hz_40ms_modulation_mae_db": 0.6419357919338552, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1368531892854916, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13143074171756, "3000–6000 Hz_10ms_envelope_correlation": 0.9885889037122583, "3000–6000 Hz_10ms_modulation_mae_db": 0.4751145691703567, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7763119610765021, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07695741111924499, "3000–6000 Hz_40ms_envelope_correlation": 0.9965498128443251, "3000–6000 Hz_40ms_modulation_mae_db": 0.3387980069367664, "mr_stft_db": 5.053509560390146, "band_mae_db": 0.1338434914133284, "rms_gain_error_db": -0.07102099642938096, "output_peak": 0.31518044488678637}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8284165722766246, "全帯域_10ms_rms_envelope_nrmse": 0.05197455813011978, "全帯域_10ms_envelope_correlation": 0.9975367215660634, "全帯域_10ms_modulation_mae_db": 0.29152629521974366, "全帯域_40ms_log_rms_mae_db": 0.4820051836069124, "全帯域_40ms_rms_envelope_nrmse": 0.027101584717180056, "全帯域_40ms_envelope_correlation": 0.9993218401373678, "全帯域_40ms_modulation_mae_db": 0.10872710450245937, "300–1000 Hz_10ms_log_rms_mae_db": 1.1128194968010587, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0650470828234014, "300–1000 Hz_10ms_envelope_correlation": 0.9970197488190524, "300–1000 Hz_10ms_modulation_mae_db": 0.6687072167054326, "300–1000 Hz_40ms_log_rms_mae_db": 0.7768137228516618, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03714849824755803, "300–1000 Hz_40ms_envelope_correlation": 0.99900680876321, "300–1000 Hz_40ms_modulation_mae_db": 0.5601271342521739, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1440299600777424, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0987366130100674, "1000–3000 Hz_10ms_envelope_correlation": 0.9932362145085832, "1000–3000 Hz_10ms_modulation_mae_db": 0.22200249438957784, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7748234984502915, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05617615772967222, "1000–3000 Hz_40ms_envelope_correlation": 0.9977842988898822, "1000–3000 Hz_40ms_modulation_mae_db": 0.4638910268672802, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1003489631565786, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11884193822838156, "3000–6000 Hz_10ms_envelope_correlation": 0.9906713128411373, "3000–6000 Hz_10ms_modulation_mae_db": 0.5416043979826294, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7497633872687504, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07393124318394619, "3000–6000 Hz_40ms_envelope_correlation": 0.996683677550579, "3000–6000 Hz_40ms_modulation_mae_db": 0.6792981146493021, "mr_stft_db": 5.059744503856016, "band_mae_db": 0.1729296425955526, "rms_gain_error_db": -0.06152759467313456, "output_peak": 0.31054619352095}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7740060811404205, "全帯域_10ms_rms_envelope_nrmse": 0.04990864460847152, "全帯域_10ms_envelope_correlation": 0.9977150815997888, "全帯域_10ms_modulation_mae_db": 0.6792090300671448, "全帯域_40ms_log_rms_mae_db": 0.4579023890727179, "全帯域_40ms_rms_envelope_nrmse": 0.027688863541027287, "全帯域_40ms_envelope_correlation": 0.9992768255364484, "全帯域_40ms_modulation_mae_db": 0.6614035551958825, "300–1000 Hz_10ms_log_rms_mae_db": 1.1103538278043685, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06679826053320465, "300–1000 Hz_10ms_envelope_correlation": 0.9967978634973376, "300–1000 Hz_10ms_modulation_mae_db": 0.7111148912988184, "300–1000 Hz_40ms_log_rms_mae_db": 0.7891679515493553, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.040052506419399156, "300–1000 Hz_40ms_envelope_correlation": 0.9987969312217638, "300–1000 Hz_40ms_modulation_mae_db": 0.6477560376202484, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1513778431982107, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10004878977640576, "1000–3000 Hz_10ms_envelope_correlation": 0.9930231172162186, "1000–3000 Hz_10ms_modulation_mae_db": 0.47854902837691177, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7780358214406103, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05943384608519857, "1000–3000 Hz_40ms_envelope_correlation": 0.9974826573364282, "1000–3000 Hz_40ms_modulation_mae_db": 0.8103660554231621, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1127221345359064, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11267201393048426, "3000–6000 Hz_10ms_envelope_correlation": 0.9913618067771116, "3000–6000 Hz_10ms_modulation_mae_db": 0.6437905340400837, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7458886524598275, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06663035217571829, "3000–6000 Hz_40ms_envelope_correlation": 0.9970256646130057, "3000–6000 Hz_40ms_modulation_mae_db": 0.6420948970463672, "mr_stft_db": 5.050578077398521, "band_mae_db": 0.0836237980942529, "rms_gain_error_db": -0.04369199175174741, "output_peak": 0.3238341286628957}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.545778423439428, "spectral_convergence": 0.19269614845793206, "spectral_convergence_status": "ok", "amplitude_floor": 8.606911899432486e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.034811284077628, "spectral_convergence": 0.19426690360552767, "spectral_convergence_status": "ok", "amplitude_floor": 7.696353352907002e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.612015597387078, "spectral_convergence": 0.19818487726631998, "spectral_convergence_status": "ok", "amplitude_floor": 7.358558224304984e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00011977037496359504, "output_power": 0.0001207555217198172, "delta_db": 0.03557589419367338, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0009579981539513103, "output_power": 0.0009398781518747317, "delta_db": -0.08293117960520321, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0008712676276581917, "output_power": 0.0008505088259725379, "delta_db": -0.10472753156809828, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00010621716934048885, "output_power": 0.00010172574351048505, "delta_db": -0.1876385062149569, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.322826988453831e-05, "output_power": 4.784498470958181e-05, "delta_db": -0.4630593010146736, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 7.685697629736477e-05, "output_power": 7.296701533807865e-05, "delta_db": -0.22556712355833303, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.3518932532436965e-05, "output_power": 3.374884311009263e-05, "delta_db": 0.02968710740190282, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.16131237765097728, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.10184515498814611, "pitch": null, "output_rms_dbfs": -26.640551028300674, "output_peak": 0.33627799876877545, "reference_rms_dbfs": -26.53870587331253, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.064201768301378}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014088342118781798, "log_rms_mae_db": 0.805400694129144, "rms_envelope_nrmse": 0.05007961389846943, "envelope_correlation": 0.9977966536590509, "rms_gain_error_db": -0.1049020775485223, "reference_mean_power": 0.002217082801939853, "output_mean_power": 0.0021641716587417897}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1112299552930035e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003498826441717729, "output_power": 0.000342343753724673, "reference_active": true, "delta_db": -0.09459991662068774}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.422870023578459e-05, "output_power": 7.987261035805457e-05, "reference_active": true, "delta_db": -0.23062220917723808}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2432690798089743e-05, "output_power": 1.1365998510000615e-05, "reference_active": true, "delta_db": -0.38957538072818065}], "active_band_count": 3, "active_band_mae_db": 0.23826583550870217}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00013937350370136096, "log_rms_mae_db": 0.4957294267665039, "rms_envelope_nrmse": 0.02553462054562689, "envelope_correlation": 0.9995036219833191, "rms_gain_error_db": -0.1051569864723994, "reference_mean_power": 0.002205255256660357, "output_mean_power": 0.002152500035708441}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.0212502799160329e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00029633227983582455, "output_power": 0.00029075238200612055, "reference_active": true, "delta_db": -0.08255680884938676}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2550897730277734e-05, "output_power": 4.181217026365061e-05, "reference_active": true, "delta_db": -0.07606016953634055}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.293923839625812e-07, "output_power": 7.88848241103346e-07, "reference_active": true, "delta_db": -0.7120564774697881}], "active_band_count": 3, "active_band_mae_db": 0.2902244852851718}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.0001225394829970322, "log_rms_mae_db": 1.0714909391756284, "rms_envelope_nrmse": 0.0646087781406035, "envelope_correlation": 0.997062384767062, "rms_gain_error_db": -0.06747448509212235, "reference_mean_power": 0.0009458112547504951, "output_mean_power": 0.0009312301513694835}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 7.572635748614283e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021454762051170055, "output_power": 0.00020199830246256598, "reference_active": true, "delta_db": -0.2617598248328201}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.152647446601531e-05, "output_power": 5.009911733231117e-05, "reference_active": true, "delta_db": -0.8923195590564525}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.926247906815959e-06, "output_power": 4.401962941653005e-06, "reference_active": true, "delta_db": -1.9685164983668615}], "active_band_count": 3, "active_band_mae_db": 1.0408652940853782}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00011593520090475466, "log_rms_mae_db": 0.7259206821132661, "rms_envelope_nrmse": 0.03580876154827954, "envelope_correlation": 0.9991020084282259, "rms_gain_error_db": -0.06806139853980378, "reference_mean_power": 0.000949032375443528, "output_mean_power": 0.0009342753454428711}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 7.167599035150202e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00018822421406971632, "output_power": 0.00017814588783910166, "reference_active": true, "delta_db": -0.2389969048370963}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6896254802287544e-05, "output_power": 2.26522373544366e-05, "reference_active": true, "delta_db": -0.7458070681540006}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.519942395248337e-07, "output_power": 4.89093553337843e-07, "reference_active": true, "delta_db": -1.8682257529910573}], "active_band_count": 3, "active_band_mae_db": 0.9510099086607181}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.911272017593447e-05, "log_rms_mae_db": 1.2010882444539424, "rms_envelope_nrmse": 0.10074382388840485, "envelope_correlation": 0.993470164101706, "rms_gain_error_db": -0.2923565348136381, "reference_mean_power": 0.00014098678071692043, "output_mean_power": 0.00013180829446711218}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1608995504129325e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.7499181258859675e-05, "output_power": 3.436202481180365e-05, "reference_active": true, "delta_db": -0.37943038542314245}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.267009960974534e-06, "output_power": 7.228076520401888e-06, "reference_active": true, "delta_db": -0.5832571931837376}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.898653312592319e-07, "output_power": 6.968565661333989e-07, "reference_active": true, "delta_db": -0.5440965566802367}], "active_band_count": 3, "active_band_mae_db": 0.502261378429039}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.617115763934814e-05, "log_rms_mae_db": 0.8248372754968615, "rms_envelope_nrmse": 0.06644680202182149, "envelope_correlation": 0.9974929353211757, "rms_gain_error_db": -0.29237463003554187, "reference_mean_power": 0.00014167955800585476, "output_mean_power": 0.0001324554188546011}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.105176097335646e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.391055546581272e-05, "output_power": 3.110583580276777e-05, "reference_active": true, "delta_db": -0.37493028545689766}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.965549503856847e-06, "output_power": 3.4974304008640574e-06, "reference_active": true, "delta_db": -0.5455429499785401}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.243578010746913e-08, "output_power": 4.4120547472570044e-08, "reference_active": true, "delta_db": -1.5079264963311665}], "active_band_count": 3, "active_band_mae_db": 0.8094665772555348}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.0412813835527566e-05, "log_rms_mae_db": 1.1155237142757308, "rms_envelope_nrmse": 0.11985644343841162, "envelope_correlation": 0.9901932849199201, "rms_gain_error_db": -0.1656058721031573, "reference_mean_power": 5.063950126149281e-05, "output_mean_power": 4.874486057769277e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.808534933602357e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3975319757086038e-05, "output_power": 1.3538644554064459e-05, "reference_active": true, "delta_db": -0.13786567038485778}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.037166885946856e-06, "output_power": 3.732599343398187e-06, "reference_active": true, "delta_db": -0.3406532705272361}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.22277075461544e-07, "output_power": 8.092816513957468e-07, "reference_active": true, "delta_db": -0.06918488712927295}], "active_band_count": 3, "active_band_mae_db": 0.18256794268045562}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6032760748614375e-05, "log_rms_mae_db": 0.7463025905205868, "rms_envelope_nrmse": 0.06295863554603912, "envelope_correlation": 0.9973632253286389, "rms_gain_error_db": -0.1645434399094002, "reference_mean_power": 5.0785427984468614e-05, "output_mean_power": 4.889728803553738e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.5120507652027295e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2965326164159397e-05, "output_power": 1.2616852126945854e-05, "reference_active": true, "delta_db": -0.11832433600745292}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9046258858040845e-06, "output_power": 1.756887467875422e-06, "reference_active": true, "delta_db": -0.3506573757442287}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.694645968158745e-08, "output_power": 4.984581754682364e-08, "reference_active": true, "delta_db": -0.5783800601485666}], "active_band_count": 3, "active_band_mae_db": 0.34912059063341605}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9404104532266409, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "a7076982d9885410d33c1045ed08223a8d27e269ff8a82d0fda38177998a942d", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9926747387454748, "standard_deviation": 0.0008822527562981405, "minimum": 0.9912467098057474, "maximum": 0.9935498853319812, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1723159024660175, "standard_deviation": 0.026306412934313374, "minimum": 1.1440299600777424, "maximum": 1.2103487202538448, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.46137397046057715, "standard_deviation": 0.1986689449486637, "minimum": 0.17193622870267078, "maximum": 0.7042120468958725, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10407655644704786, "standard_deviation": 0.00561071763519919, "minimum": 0.09860079010571408, "maximum": 0.11218655853214958, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9976238474234127, "standard_deviation": 0.0004029964347758087, "minimum": 0.9969610889692179, "maximum": 0.9983438925692206, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7830275966931262, "standard_deviation": 0.022870749719662936, "minimum": 0.7428102205713556, "maximum": 0.8248372754968615, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5086694016326976, "standard_deviation": 0.24151885880879204, "minimum": 0.21229383786465394, "maximum": 0.8103660554231621, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06127022095658039, "standard_deviation": 0.004425923978344978, "minimum": 0.054069030911786276, "maximum": 0.06644680202182149, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9897963164728953, "standard_deviation": 0.001339910404159905, "minimum": 0.9878530819216841, "maximum": 0.9913618067771116, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.1326293161569345, "standard_deviation": 0.0230716415315996, "minimum": 1.1003489631565786, "maximum": 1.161619754488032, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.45166243912367754, "standard_deviation": 0.16466699743980728, "minimum": 0.18256794268045562, "maximum": 0.6437905340400837, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12341667789244615, "standard_deviation": 0.00849463085131442, "minimum": 0.11267201393048426, "maximum": 0.13715160788341776, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9967702649066665, "standard_deviation": 0.00048049266078091757, "minimum": 0.9957844332837643, "maximum": 0.9973632253286389, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.777469936933701, "standard_deviation": 0.02641768302483696, "minimum": 0.7458886524598275, "maximum": 0.8036038606378191, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.47947871499436684, "standard_deviation": 0.1605902676904281, "minimum": 0.2287204505901648, "maximum": 0.6792981146493021, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0722739187557156, "standard_deviation": 0.0056294660746012345, "minimum": 0.06295863554603912, "maximum": 0.07746097602432186, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9973095356209761, "standard_deviation": 0.0003272763198501491, "minimum": 0.9967978634973376, "maximum": 0.9978285521117964, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0716275799665094, "standard_deviation": 0.03513617638445645, "minimum": 1.017468353491543, "maximum": 1.1128194968010587, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.762134703492476, "standard_deviation": 0.2899778041476752, "minimum": 0.23399553001386172, "maximum": 1.2048864328495557, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06172761907829948, "standard_deviation": 0.003582206355652751, "minimum": 0.055617855714537555, "maximum": 0.06679826053320465, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.999107803498773, "standard_deviation": 0.00017301763267007405, "minimum": 0.9987969312217638, "maximum": 0.99937451180654, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7364353273330753, "standard_deviation": 0.03491398090939392, "minimum": 0.6963128471346222, "maximum": 0.7891679515493553, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7177720811644652, "standard_deviation": 0.2790831929009911, "minimum": 0.22387093488492268, "maximum": 1.1518033770751135, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.035294351647950514, "standard_deviation": 0.002915423664075703, "minimum": 0.02972813105925368, "maximum": 0.040052506419399156, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1425920500969508, "standard_deviation": 0.03746450968366923, "minimum": 0.0836237980942529, "maximum": 0.19079089304467514, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.057404729414662, "standard_deviation": 0.0050917057760557285, "minimum": 5.050578077398521, "maximum": 5.064201768301378, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3150976253965744, "standard_deviation": 0.010874673900873518, "minimum": 0.3030136071340809, "maximum": 0.33627799876877545, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07706917539252223, "standard_deviation": 0.018231664571930314, "minimum": -0.10184515498814611, "maximum": -0.04369199175174741, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9977664337555001, "standard_deviation": 0.00016276042153230187, "minimum": 0.9975367215660634, "maximum": 0.9980208051626133, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7985949477401406, "standard_deviation": 0.018249265512379775, "minimum": 0.7740060811404205, "maximum": 0.8284165722766246, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.41966280365081304, "standard_deviation": 0.1660858484765853, "minimum": 0.23826583550870217, "maximum": 0.6792090300671448, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.04982884315589313, "standard_deviation": 0.0016521593792804415, "minimum": 0.04712991017064167, "maximum": 0.05197455813011978, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.999348281518742, "standard_deviation": 0.00010176634025290486, "minimum": 0.9992197181510706, "maximum": 0.9995036219833191, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.47570841234994615, "standard_deviation": 0.014354487461915633, "minimum": 0.45526994569985824, "maximum": 0.4957294267665039, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.36281762862521855, "standard_deviation": 0.18430460292542183, "minimum": 0.10872710450245937, "maximum": 0.6614035551958825, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.027230755035798977, "standard_deviation": 0.0014734875585301495, "minimum": 0.02553462054562689, "maximum": 0.029449453554351832, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 2.1757185459136963, "predicted_mos": 2.1757185459136963, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "14d9bf1af11e890a27674f170947e3b74430d64b5f46ad463bcd1602ec118622", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.689223499968648}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8247736355450885, "全帯域_10ms_rms_envelope_nrmse": 0.04961404983498139, "全帯域_10ms_envelope_correlation": 0.997834920819783, "全帯域_10ms_modulation_mae_db": 0.2443864495300703, "全帯域_40ms_log_rms_mae_db": 0.5041752253363069, "全帯域_40ms_rms_envelope_nrmse": 0.02500276473330833, "全帯域_40ms_envelope_correlation": 0.999521613084723, "全帯域_40ms_modulation_mae_db": 0.3309272025813692, "300–1000 Hz_10ms_log_rms_mae_db": 1.0601662096440543, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06587980708680993, "300–1000 Hz_10ms_envelope_correlation": 0.9969473649359561, "300–1000 Hz_10ms_modulation_mae_db": 1.0653895613606505, "300–1000 Hz_40ms_log_rms_mae_db": 0.739659461423063, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0365690614928767, "300–1000 Hz_40ms_envelope_correlation": 0.9990636047504128, "300–1000 Hz_40ms_modulation_mae_db": 0.958943159701982, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1759349145174627, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09850921659538188, "1000–3000 Hz_10ms_envelope_correlation": 0.9938312573533331, "1000–3000 Hz_10ms_modulation_mae_db": 0.38891617349132207, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7951812072507982, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0647160345193018, "1000–3000 Hz_40ms_envelope_correlation": 0.9977099059732996, "1000–3000 Hz_40ms_modulation_mae_db": 0.7065087974277885, "3000–6000 Hz_10ms_log_rms_mae_db": 1.154405612714809, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12157014722497442, "3000–6000 Hz_10ms_envelope_correlation": 0.9899425304608284, "3000–6000 Hz_10ms_modulation_mae_db": 0.14867297315140002, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7899656309803106, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0645173068176863, "3000–6000 Hz_40ms_envelope_correlation": 0.997259264361805, "3000–6000 Hz_40ms_modulation_mae_db": 0.29292213354500113, "mr_stft_db": 5.030223865933167, "band_mae_db": 0.1716072743522033, "rms_gain_error_db": -0.10070810702193875, "output_peak": 0.3365930555791749}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8017824804952879, "全帯域_10ms_rms_envelope_nrmse": 0.05008254785303489, "全帯域_10ms_envelope_correlation": 0.9977666013754095, "全帯域_10ms_modulation_mae_db": 0.2621359134428616, "全帯域_40ms_log_rms_mae_db": 0.47206927946458416, "全帯域_40ms_rms_envelope_nrmse": 0.027141764264500268, "全帯域_40ms_envelope_correlation": 0.9993779565172812, "全帯域_40ms_modulation_mae_db": 0.34298667274420547, "300–1000 Hz_10ms_log_rms_mae_db": 1.0249278634770684, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.059684199088109124, "300–1000 Hz_10ms_envelope_correlation": 0.9974710182794635, "300–1000 Hz_10ms_modulation_mae_db": 0.7811375941383288, "300–1000 Hz_40ms_log_rms_mae_db": 0.7143542350545119, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03544220334700971, "300–1000 Hz_40ms_envelope_correlation": 0.9990778219652202, "300–1000 Hz_40ms_modulation_mae_db": 0.6983735048693136, "1000–3000 Hz_10ms_log_rms_mae_db": 1.161415718338218, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09988578741533051, "1000–3000 Hz_10ms_envelope_correlation": 0.99334616100542, "1000–3000 Hz_10ms_modulation_mae_db": 0.7227769144824038, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7423687149268742, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.056195072687303005, "1000–3000 Hz_40ms_envelope_correlation": 0.9981462295236456, "1000–3000 Hz_40ms_modulation_mae_db": 0.4983859245236477, "3000–6000 Hz_10ms_log_rms_mae_db": 1.149036932658297, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12348514728253651, "3000–6000 Hz_10ms_envelope_correlation": 0.9903178901124651, "3000–6000 Hz_10ms_modulation_mae_db": 0.47311303522872566, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8275980493544961, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07982595977076219, "3000–6000 Hz_40ms_envelope_correlation": 0.9965290245213184, "3000–6000 Hz_40ms_modulation_mae_db": 0.6012999339284543, "mr_stft_db": 5.025819749967462, "band_mae_db": 0.15669157678129084, "rms_gain_error_db": -0.09366348830535115, "output_peak": 0.3137520236695457}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8080345978427397, "全帯域_10ms_rms_envelope_nrmse": 0.0527090089491051, "全帯域_10ms_envelope_correlation": 0.9975021096340165, "全帯域_10ms_modulation_mae_db": 0.6280799905046316, "全帯域_40ms_log_rms_mae_db": 0.48264247633453794, "全帯域_40ms_rms_envelope_nrmse": 0.030502084258368697, "全帯域_40ms_envelope_correlation": 0.9991642236423174, "全帯域_40ms_modulation_mae_db": 0.6538630562806086, "300–1000 Hz_10ms_log_rms_mae_db": 1.0947439199300781, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.062102129151298584, "300–1000 Hz_10ms_envelope_correlation": 0.9973024423855662, "300–1000 Hz_10ms_modulation_mae_db": 0.8708086737760121, "300–1000 Hz_40ms_log_rms_mae_db": 0.75940191764842, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03529474129638483, "300–1000 Hz_40ms_envelope_correlation": 0.999129101929814, "300–1000 Hz_40ms_modulation_mae_db": 0.8982797472990787, "1000–3000 Hz_10ms_log_rms_mae_db": 1.214032172359525, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11237544701014279, "1000–3000 Hz_10ms_envelope_correlation": 0.9914143887164388, "1000–3000 Hz_10ms_modulation_mae_db": 0.6830499407793841, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8069078808748003, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0638099563615045, "1000–3000 Hz_40ms_envelope_correlation": 0.997418926939398, "1000–3000 Hz_40ms_modulation_mae_db": 0.23779463281036492, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1733071894578242, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13944049906826078, "3000–6000 Hz_10ms_envelope_correlation": 0.9876797802530358, "3000–6000 Hz_10ms_modulation_mae_db": 0.5598744932919556, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8229808258031741, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08350738597043335, "3000–6000 Hz_40ms_envelope_correlation": 0.9965398592707669, "3000–6000 Hz_40ms_modulation_mae_db": 0.4602419791919988, "mr_stft_db": 5.025508287674637, "band_mae_db": 0.17018019681288402, "rms_gain_error_db": -0.08601071685032474, "output_peak": 0.3155137610606189}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7765383142686484, "全帯域_10ms_rms_envelope_nrmse": 0.04771939160263433, "全帯域_10ms_envelope_correlation": 0.9979679031599874, "全帯域_10ms_modulation_mae_db": 0.45782704480890435, "全帯域_40ms_log_rms_mae_db": 0.4613397945156159, "全帯域_40ms_rms_envelope_nrmse": 0.025987969234729038, "全帯域_40ms_envelope_correlation": 0.9994243459220089, "全帯域_40ms_modulation_mae_db": 0.41625636285343015, "300–1000 Hz_10ms_log_rms_mae_db": 1.0487153082660698, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06176132650271568, "300–1000 Hz_10ms_envelope_correlation": 0.9973916382802677, "300–1000 Hz_10ms_modulation_mae_db": 1.2560161933479201, "300–1000 Hz_40ms_log_rms_mae_db": 0.7005729209645017, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03440944738853318, "300–1000 Hz_40ms_envelope_correlation": 0.9992514558535788, "300–1000 Hz_40ms_modulation_mae_db": 1.2117235781464608, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1744854241332727, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11276653068067477, "1000–3000 Hz_10ms_envelope_correlation": 0.9911774366149272, "1000–3000 Hz_10ms_modulation_mae_db": 0.16277023117357658, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7988970150463572, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06702612083887874, "1000–3000 Hz_40ms_envelope_correlation": 0.996849489678693, "1000–3000 Hz_40ms_modulation_mae_db": 0.2560779253530508, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1816051181884497, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12042971226902166, "3000–6000 Hz_10ms_envelope_correlation": 0.9905408670438385, "3000–6000 Hz_10ms_modulation_mae_db": 0.5686122575894214, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8125371239549809, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07003889672491974, "3000–6000 Hz_40ms_envelope_correlation": 0.9972545340673009, "3000–6000 Hz_40ms_modulation_mae_db": 0.7069524420421466, "mr_stft_db": 5.016700566516053, "band_mae_db": 0.08711696016957217, "rms_gain_error_db": -0.08181776801124176, "output_peak": 0.3044444778315289}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8014948643728056, "全帯域_10ms_rms_envelope_nrmse": 0.04775264398861636, "全帯域_10ms_envelope_correlation": 0.9979720493330795, "全帯域_10ms_modulation_mae_db": 0.536609673801146, "全帯域_40ms_log_rms_mae_db": 0.48795198916642707, "全帯域_40ms_rms_envelope_nrmse": 0.026022438202778497, "全帯域_40ms_envelope_correlation": 0.9994282231578351, "全帯域_40ms_modulation_mae_db": 0.2277242117046617, "300–1000 Hz_10ms_log_rms_mae_db": 1.045503855652025, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05648279563714588, "300–1000 Hz_10ms_envelope_correlation": 0.9977630702987417, "300–1000 Hz_10ms_modulation_mae_db": 0.7075229091978935, "300–1000 Hz_40ms_log_rms_mae_db": 0.7296277993712308, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03006004626770539, "300–1000 Hz_40ms_envelope_correlation": 0.999364218049963, "300–1000 Hz_40ms_modulation_mae_db": 0.6461196399262636, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1957508156979733, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10720358900745239, "1000–3000 Hz_10ms_envelope_correlation": 0.9923396660935624, "1000–3000 Hz_10ms_modulation_mae_db": 0.36106760771537405, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7903471980079774, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06365352691552258, "1000–3000 Hz_40ms_envelope_correlation": 0.997574872008989, "1000–3000 Hz_40ms_modulation_mae_db": 0.21184389706934018, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1857715768523585, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13104121259808915, "3000–6000 Hz_10ms_envelope_correlation": 0.9883073315987271, "3000–6000 Hz_10ms_modulation_mae_db": 0.2611098885181671, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8156726291562992, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08013621205570172, "3000–6000 Hz_40ms_envelope_correlation": 0.9956723951850195, "3000–6000 Hz_40ms_modulation_mae_db": 0.2139946679407246, "mr_stft_db": 5.022160316975676, "band_mae_db": 0.193605754981697, "rms_gain_error_db": -0.08717581168763944, "output_peak": 0.3010822738553939}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8165129381997366, "全帯域_10ms_rms_envelope_nrmse": 0.051555818959285474, "全帯域_10ms_envelope_correlation": 0.9975957335335934, "全帯域_10ms_modulation_mae_db": 0.3432701597972403, "全帯域_40ms_log_rms_mae_db": 0.4782977935871716, "全帯域_40ms_rms_envelope_nrmse": 0.029396050815049167, "全帯域_40ms_envelope_correlation": 0.9992209117862273, "全帯域_40ms_modulation_mae_db": 0.2363585270120252, "300–1000 Hz_10ms_log_rms_mae_db": 1.0442936807660181, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06144679085713981, "300–1000 Hz_10ms_envelope_correlation": 0.9973234414732328, "300–1000 Hz_10ms_modulation_mae_db": 0.23025555716954624, "300–1000 Hz_40ms_log_rms_mae_db": 0.7063606533669352, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0356419195603458, "300–1000 Hz_40ms_envelope_correlation": 0.9990744159680001, "300–1000 Hz_40ms_modulation_mae_db": 0.22757331412000684, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1691146292390313, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1036759166488361, "1000–3000 Hz_10ms_envelope_correlation": 0.9929971845405609, "1000–3000 Hz_10ms_modulation_mae_db": 0.5168246767238966, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7474304671587241, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.061445649627180285, "1000–3000 Hz_40ms_envelope_correlation": 0.9979264531408034, "1000–3000 Hz_40ms_modulation_mae_db": 0.5844710297069861, "3000–6000 Hz_10ms_log_rms_mae_db": 1.168812908829329, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1302427918842257, "3000–6000 Hz_10ms_envelope_correlation": 0.9889627930361717, "3000–6000 Hz_10ms_modulation_mae_db": 0.47340624447702523, "3000–6000 Hz_40ms_log_rms_mae_db": 0.798676636826336, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07868847260480151, "3000–6000 Hz_40ms_envelope_correlation": 0.9965184388291473, "3000–6000 Hz_40ms_modulation_mae_db": 0.3208619741751197, "mr_stft_db": 5.0213604577167965, "band_mae_db": 0.13776416461950816, "rms_gain_error_db": -0.0711824403308396, "output_peak": 0.31682132814731034}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8260350084839123, "全帯域_10ms_rms_envelope_nrmse": 0.05272253035637401, "全帯域_10ms_envelope_correlation": 0.9974659812573309, "全帯域_10ms_modulation_mae_db": 0.26397269321981787, "全帯域_40ms_log_rms_mae_db": 0.4741107823129091, "全帯域_40ms_rms_envelope_nrmse": 0.027514575469134134, "全帯域_40ms_envelope_correlation": 0.9993003506970374, "全帯域_40ms_modulation_mae_db": 0.10042384869469496, "300–1000 Hz_10ms_log_rms_mae_db": 1.0947836423930142, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.065376659091667, "300–1000 Hz_10ms_envelope_correlation": 0.9969856222632789, "300–1000 Hz_10ms_modulation_mae_db": 0.7338933794665722, "300–1000 Hz_40ms_log_rms_mae_db": 0.7703859335485038, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03691312210240041, "300–1000 Hz_40ms_envelope_correlation": 0.9990179828897091, "300–1000 Hz_40ms_modulation_mae_db": 0.6023521094956289, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1450985893149195, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1015044054437245, "1000–3000 Hz_10ms_envelope_correlation": 0.9928666464391533, "1000–3000 Hz_10ms_modulation_mae_db": 0.2562931886561451, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7672231376919522, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05864681793005675, "1000–3000 Hz_40ms_envelope_correlation": 0.9975883129096162, "1000–3000 Hz_40ms_modulation_mae_db": 0.28713427214094994, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1243199030860063, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12005767507757763, "3000–6000 Hz_10ms_envelope_correlation": 0.990569895390522, "3000–6000 Hz_10ms_modulation_mae_db": 0.574707587529756, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7569156871166439, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07347832141992534, "3000–6000 Hz_40ms_envelope_correlation": 0.9968502444378577, "3000–6000 Hz_40ms_modulation_mae_db": 0.7494690003125027, "mr_stft_db": 5.022861242036231, "band_mae_db": 0.1647618574137631, "rms_gain_error_db": -0.06368803621677044, "output_peak": 0.3097381281877878}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7829201758595902, "全帯域_10ms_rms_envelope_nrmse": 0.05084361859741785, "全帯域_10ms_envelope_correlation": 0.9976257542962463, "全帯域_10ms_modulation_mae_db": 0.6628012427559584, "全帯域_40ms_log_rms_mae_db": 0.46069532842599364, "全帯域_40ms_rms_envelope_nrmse": 0.028250881054619117, "全帯域_40ms_envelope_correlation": 0.9992427863093666, "全帯域_40ms_modulation_mae_db": 0.6327401035010092, "300–1000 Hz_10ms_log_rms_mae_db": 1.1034881687104074, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06851870090471487, "300–1000 Hz_10ms_envelope_correlation": 0.9966335982841567, "300–1000 Hz_10ms_modulation_mae_db": 0.6890353086867066, "300–1000 Hz_40ms_log_rms_mae_db": 0.7865406981944174, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04130659500132369, "300–1000 Hz_40ms_envelope_correlation": 0.9987221307129227, "300–1000 Hz_40ms_modulation_mae_db": 0.5554906414463455, "1000–3000 Hz_10ms_log_rms_mae_db": 1.158423902367017, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09819479164572889, "1000–3000 Hz_10ms_envelope_correlation": 0.9932881881113285, "1000–3000 Hz_10ms_modulation_mae_db": 0.4621493305541102, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7916145118079875, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05820442175348193, "1000–3000 Hz_40ms_envelope_correlation": 0.997597904617367, "1000–3000 Hz_40ms_modulation_mae_db": 0.7610750131416159, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1394611970840844, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1153614893175511, "3000–6000 Hz_10ms_envelope_correlation": 0.9909903729999106, "3000–6000 Hz_10ms_modulation_mae_db": 0.6410882732620796, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7699554366617601, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06821004599104168, "3000–6000 Hz_40ms_envelope_correlation": 0.996937852630892, "3000–6000 Hz_40ms_modulation_mae_db": 0.6667923409456451, "mr_stft_db": 5.012789163325151, "band_mae_db": 0.07847907698750209, "rms_gain_error_db": -0.04119968962439123, "output_peak": 0.3230556120877468}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.520131747511004, "spectral_convergence": 0.19229842753977872, "spectral_convergence_status": "ok", "amplitude_floor": 8.606911899432486e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 4.99994646687073, "spectral_convergence": 0.19391659209721634, "spectral_convergence_status": "ok", "amplitude_floor": 7.696353352907002e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.57059338341777, "spectral_convergence": 0.1980108882494078, "spectral_convergence_status": "ok", "amplitude_floor": 7.358558224304984e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00011977037496359504, "output_power": 0.00012067144925794366, "delta_db": 0.03255119421092352, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0009579981539513103, "output_power": 0.0009405254627199009, "delta_db": -0.07994114558212724, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0008712676276581917, "output_power": 0.0008508248614131599, "delta_db": -0.10311406266961806, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00010621716934048885, "output_power": 0.00010114394024409289, "delta_db": -0.2125485505541283, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.322826988453831e-05, "output_power": 4.800051216200668e-05, "delta_db": -0.4489647893554288, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 7.685697629736477e-05, "output_power": 7.26779068857248e-05, "delta_db": -0.24280883285036828, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.3518932532436965e-05, "output_power": 3.415249322498538e-05, "delta_db": 0.08132234524282884, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.1716072743522033, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.10070810702193875, "pitch": null, "output_rms_dbfs": -26.639413980334467, "output_peak": 0.3365930555791749, "reference_rms_dbfs": -26.53870587331253, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.030223865933167}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014088342118781798, "log_rms_mae_db": 0.8247736355450885, "rms_envelope_nrmse": 0.04961404983498139, "envelope_correlation": 0.997834920819783, "rms_gain_error_db": -0.102897350716251, "reference_mean_power": 0.002217082801939853, "output_mean_power": 0.0021651708826977067}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1112299552930035e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003498826441717729, "output_power": 0.0003407238369383343, "reference_active": true, "delta_db": -0.11519882220415516}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.422870023578459e-05, "output_power": 8.016487263385804e-05, "reference_active": true, "delta_db": -0.2147599208706707}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2432690798089743e-05, "output_power": 1.1330395568860696e-05, "reference_active": true, "delta_db": -0.40320060551538506}], "active_band_count": 3, "active_band_mae_db": 0.2443864495300703}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00013937350370136096, "log_rms_mae_db": 0.5041752253363069, "rms_envelope_nrmse": 0.02500276473330833, "envelope_correlation": 0.999521613084723, "rms_gain_error_db": -0.10228557571397871, "reference_mean_power": 0.002205255256660357, "output_mean_power": 0.0021539236677619515}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.0212502799160329e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00029633227983582455, "output_power": 0.00028937546688264493, "reference_active": true, "delta_db": -0.10317253223565889}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2550897730277734e-05, "output_power": 4.1779993596074436e-05, "reference_active": true, "delta_db": -0.07940358098050093}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.293923839625812e-07, "output_power": 7.712204905552416e-07, "reference_active": true, "delta_db": -0.8102054945279478}], "active_band_count": 3, "active_band_mae_db": 0.3309272025813692}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.0001225394829970322, "log_rms_mae_db": 1.0601662096440543, "rms_envelope_nrmse": 0.06587980708680993, "envelope_correlation": 0.9969473649359561, "rms_gain_error_db": -0.06603903270637408, "reference_mean_power": 0.0009458112547504951, "output_mean_power": 0.0009315379972056668}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 7.572635748614283e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021454762051170055, "output_power": 0.00020150925829034617, "reference_active": true, "delta_db": -0.2722869777317035}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.152647446601531e-05, "output_power": 5.004705220915974e-05, "reference_active": true, "delta_db": -0.896835277995083}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.926247906815959e-06, "output_power": 4.343035597817507e-06, "reference_active": true, "delta_db": -2.027046428355165}], "active_band_count": 3, "active_band_mae_db": 1.0653895613606505}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00011593520090475466, "log_rms_mae_db": 0.739659461423063, "rms_envelope_nrmse": 0.0365690614928767, "envelope_correlation": 0.9990636047504128, "rms_gain_error_db": -0.06629194643781956, "reference_mean_power": 0.000949032375443528, "output_mean_power": 0.0009346560761134634}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 7.167599035150202e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00018822421406971632, "output_power": 0.0001775851931863565, "reference_active": true, "delta_db": -0.2526874035513747}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6896254802287544e-05, "output_power": 2.2530412693679333e-05, "reference_active": true, "delta_db": -0.7692266356569395}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.519942395248337e-07, "output_power": 4.905948329409264e-07, "reference_active": true, "delta_db": -1.8549154398976317}], "active_band_count": 3, "active_band_mae_db": 0.958943159701982}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.911272017593447e-05, "log_rms_mae_db": 1.1759349145174627, "rms_envelope_nrmse": 0.09850921659538188, "envelope_correlation": 0.9938312573533331, "rms_gain_error_db": -0.30062883473065805, "reference_mean_power": 0.00014098678071692043, "output_mean_power": 0.00013155746927618283}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1608995504129325e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.7499181258859675e-05, "output_power": 3.454701957188585e-05, "reference_active": true, "delta_db": -0.35611199602501553}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.267009960974534e-06, "output_power": 7.328792957845219e-06, "reference_active": true, "delta_db": -0.5231600808751218}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.898653312592319e-07, "output_power": 7.392739580620212e-07, "reference_active": true, "delta_db": -0.28747644357382884}], "active_band_count": 3, "active_band_mae_db": 0.38891617349132207}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.617115763934814e-05, "log_rms_mae_db": 0.7951812072507982, "rms_envelope_nrmse": 0.0647160345193018, "envelope_correlation": 0.9977099059732996, "rms_gain_error_db": -0.3006242437238433, "reference_mean_power": 0.00014167955800585476, "output_mean_power": 0.00013220405280752528}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.105176097335646e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.391055546581272e-05, "output_power": 3.12800244040371e-05, "reference_active": true, "delta_db": -0.35067820504102964}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.965549503856847e-06, "output_power": 3.5562261620140694e-06, "reference_active": true, "delta_db": -0.4731400315439661}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.243578010746913e-08, "output_power": 4.63300455125904e-08, "reference_active": true, "delta_db": -1.2957081556983698}], "active_band_count": 3, "active_band_mae_db": 0.7065087974277885}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.0412813835527566e-05, "log_rms_mae_db": 1.154405612714809, "rms_envelope_nrmse": 0.12157014722497442, "envelope_correlation": 0.9899425304608284, "rms_gain_error_db": -0.17913084106849, "reference_mean_power": 5.063950126149281e-05, "output_mean_power": 4.859329355294149e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.808534933602357e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3975319757086038e-05, "output_power": 1.3639756024861424e-05, "reference_active": true, "delta_db": -0.1055515124654276}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.037166885946856e-06, "output_power": 3.7729963915994074e-06, "reference_active": true, "delta_db": -0.29390312529596185}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.22277075461544e-07, "output_power": 8.135078619311532e-07, "reference_active": true, "delta_db": -0.04656428169281065}], "active_band_count": 3, "active_band_mae_db": 0.14867297315140002}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6032760748614375e-05, "log_rms_mae_db": 0.7899656309803106, "rms_envelope_nrmse": 0.0645173068176863, "envelope_correlation": 0.997259264361805, "rms_gain_error_db": -0.17572649312016145, "reference_mean_power": 5.0785427984468614e-05, "output_mean_power": 4.877153982309456e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.5120507652027295e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2965326164159397e-05, "output_power": 1.2740419117983303e-05, "reference_active": true, "delta_db": -0.07599731538918851}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9046258858040845e-06, "output_power": 1.7741106002045947e-06, "reference_active": true, "delta_db": -0.3082899175426808}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.694645968158745e-08, "output_power": 5.081814554360756e-08, "reference_active": true, "delta_db": -0.4944791677031341}], "active_band_count": 3, "active_band_mae_db": 0.29292213354500113}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9397076594110816, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "7b3158ef198d28524363d8d12e40db1413ad745bdccccca7c3e2ba9316d7f987", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9926576161093406, "standard_deviation": 0.0009445926703496385, "minimum": 0.9911774366149272, "maximum": 0.9938312573533331, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1742820207459275, "standard_deviation": 0.021840831361711353, "minimum": 1.1450985893149195, "maximum": 1.214032172359525, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4442310079470265, "standard_deviation": 0.19446993399238444, "minimum": 0.16277023117357658, "maximum": 0.7227769144824038, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10426446055590899, "standard_deviation": 0.005901725583869922, "minimum": 0.09819479164572889, "maximum": 0.11276653068067477, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9976015118489765, "standard_deviation": 0.0003805681792525427, "minimum": 0.996849489678693, "maximum": 0.9981462295236456, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7799962665956839, "standard_deviation": 0.024476513116124542, "minimum": 0.7423687149268742, "maximum": 0.8069078808748003, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.442911436521718, "standard_deviation": 0.22311642194716222, "minimum": 0.21184389706934018, "maximum": 0.7610750131416159, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0617122000791537, "standard_deviation": 0.003734796356919538, "minimum": 0.056195072687303005, "maximum": 0.06702612083887874, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9896639326119374, "standard_deviation": 0.0012025762481241572, "minimum": 0.9876797802530358, "maximum": 0.9909903729999106, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.1595900548588949, "standard_deviation": 0.021483406467686685, "minimum": 1.1243199030860063, "maximum": 1.1857715768523585, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.4625730941310663, "standard_deviation": 0.17092305575785002, "minimum": 0.14867297315140002, "maximum": 0.6410882732620796, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12520358434027962, "standard_deviation": 0.007786923284222493, "minimum": 0.1153614893175511, "maximum": 0.13944049906826078, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9966952016630135, "standard_deviation": 0.0005131223069198763, "minimum": 0.9956723951850195, "maximum": 0.997259264361805, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7992877524817501, "standard_deviation": 0.025494808286096182, "minimum": 0.7569156871166439, "maximum": 0.8275980493544961, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.5015668090101991, "standard_deviation": 0.20752873919025053, "minimum": 0.2139946679407246, "maximum": 0.7494690003125027, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07480032516940899, "standard_deviation": 0.006742725509741603, "minimum": 0.0645173068176863, "maximum": 0.08350738597043335, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.997227274525083, "standard_deviation": 0.0003540779847142442, "minimum": 0.9966335982841567, "maximum": 0.9977630702987417, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0645778311048422, "standard_deviation": 0.029166672725947723, "minimum": 1.0249278634770684, "maximum": 1.1034881687104074, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7917573971429538, "standard_deviation": 0.3007259105546997, "minimum": 0.23025555716954624, "maximum": 1.2560161933479201, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.0626565510399501, "standard_deviation": 0.0038111796185781427, "minimum": 0.05648279563714588, "maximum": 0.06851870090471487, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9990875915149526, "standard_deviation": 0.00018683385989712168, "minimum": 0.9987221307129227, "maximum": 0.999364218049963, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.738362952446448, "standard_deviation": 0.031386622564738, "minimum": 0.7005729209645017, "maximum": 0.7865406981944174, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7248569618756351, "standard_deviation": 0.29756038225066594, "minimum": 0.22757331412000684, "maximum": 1.2117235781464608, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.035704642057072467, "standard_deviation": 0.0031022880829445266, "minimum": 0.03006004626770539, "maximum": 0.04130659500132369, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1450258577648026, "standard_deviation": 0.041506564397370785, "minimum": 0.07847907698750209, "maximum": 0.193605754981697, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.022177956268147, "standard_deviation": 0.005456021010286924, "minimum": 5.012789163325151, "maximum": 5.030223865933167, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3151250825523884, "standard_deviation": 0.011141786507280673, "minimum": 0.3010822738553939, "maximum": 0.3365930555791749, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07818075725606213, "standard_deviation": 0.019008488077749734, "minimum": -0.10070810702193875, "maximum": -0.04119968962439123, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9977163816761808, "standard_deviation": 0.00019877651789812487, "minimum": 0.9974659812573309, "maximum": 0.9979720493330795, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.8047615018834762, "standard_deviation": 0.01810680345735729, "minimum": 0.7765383142686484, "maximum": 0.8260350084839123, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4248853959825788, "standard_deviation": 0.17032769605161924, "minimum": 0.2443864495300703, "maximum": 0.6628012427559584, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05037495126768118, "standard_deviation": 0.001969989621312788, "minimum": 0.04771939160263433, "maximum": 0.05272253035637401, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9993350513895997, "standard_deviation": 0.00012260713063463936, "minimum": 0.9991642236423174, "maximum": 0.999521613084723, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.47766033364294325, "standard_deviation": 0.014303927316811623, "minimum": 0.46069532842599364, "maximum": 0.5041752253363069, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.3676599981715005, "standard_deviation": 0.19447239645558234, "minimum": 0.10042384869469496, "maximum": 0.6538630562806086, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.027477316004060906, "standard_deviation": 0.0018516934179994727, "minimum": 0.02500276473330833, "maximum": 0.030502084258368697, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 2.117157220840454, "predicted_mos": 2.117157220840454, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "cf80c5314a295baef04db14617cd8a52247bf4ec276d636c0f33002056423e13", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.861831599846482}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7836484318437906, "全帯域_10ms_rms_envelope_nrmse": 0.04175808472541596, "全帯域_10ms_envelope_correlation": 0.9984110791051095, "全帯域_10ms_modulation_mae_db": 0.3079827995528445, "全帯域_40ms_log_rms_mae_db": 0.4418571948444878, "全帯域_40ms_rms_envelope_nrmse": 0.02159042933864722, "全帯域_40ms_envelope_correlation": 0.9995656497204519, "全帯域_40ms_modulation_mae_db": 0.28354007930548447, "300–1000 Hz_10ms_log_rms_mae_db": 1.1392197702212925, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06060346034982933, "300–1000 Hz_10ms_envelope_correlation": 0.9974550356751003, "300–1000 Hz_10ms_modulation_mae_db": 0.809450358073461, "300–1000 Hz_40ms_log_rms_mae_db": 0.7736516672767856, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03496970024745567, "300–1000 Hz_40ms_envelope_correlation": 0.9991475960729632, "300–1000 Hz_40ms_modulation_mae_db": 0.7247906112489432, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3211216793927343, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10947897150744983, "1000–3000 Hz_10ms_envelope_correlation": 0.9916263424642435, "1000–3000 Hz_10ms_modulation_mae_db": 0.3603984470696779, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8433378857917883, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.059509105220247584, "1000–3000 Hz_40ms_envelope_correlation": 0.9974586205464312, "1000–3000 Hz_40ms_modulation_mae_db": 0.22388698524238668, "3000–6000 Hz_10ms_log_rms_mae_db": 1.308700458314868, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12455486909984455, "3000–6000 Hz_10ms_envelope_correlation": 0.9893431669938623, "3000–6000 Hz_10ms_modulation_mae_db": 0.4441619503238927, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8870960974722818, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07261290769470982, "3000–6000 Hz_40ms_envelope_correlation": 0.996339378199752, "3000–6000 Hz_40ms_modulation_mae_db": 0.5234890867608444, "mr_stft_db": 5.282944311195293, "band_mae_db": 0.08549100944730857, "rms_gain_error_db": -0.0379191862175221, "output_peak": 0.302160785214487}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8150519729894469, "全帯域_10ms_rms_envelope_nrmse": 0.051266134319159634, "全帯域_10ms_envelope_correlation": 0.997620143631149, "全帯域_10ms_modulation_mae_db": 0.4020413976122561, "全帯域_40ms_log_rms_mae_db": 0.4678039888034819, "全帯域_40ms_rms_envelope_nrmse": 0.025010110940358436, "全帯域_40ms_envelope_correlation": 0.9994455991630435, "全帯域_40ms_modulation_mae_db": 0.4897120646044184, "300–1000 Hz_10ms_log_rms_mae_db": 1.1604632389295002, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06811407621811542, "300–1000 Hz_10ms_envelope_correlation": 0.9967065643226802, "300–1000 Hz_10ms_modulation_mae_db": 0.8680689975925701, "300–1000 Hz_40ms_log_rms_mae_db": 0.8051252014845354, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03597096024866368, "300–1000 Hz_40ms_envelope_correlation": 0.9990691207031116, "300–1000 Hz_40ms_modulation_mae_db": 0.9993953541487993, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3359685710511688, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10628768787348589, "1000–3000 Hz_10ms_envelope_correlation": 0.9922828734349054, "1000–3000 Hz_10ms_modulation_mae_db": 0.41925825068103095, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8724048157545732, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05337990955231378, "1000–3000 Hz_40ms_envelope_correlation": 0.9982261197400872, "1000–3000 Hz_40ms_modulation_mae_db": 0.44765875835408636, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2947031777988216, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12956615746229644, "3000–6000 Hz_10ms_envelope_correlation": 0.9886881522980486, "3000–6000 Hz_10ms_modulation_mae_db": 0.3496629463177288, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8612959381141082, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08388047132345319, "3000–6000 Hz_40ms_envelope_correlation": 0.995124152077278, "3000–6000 Hz_40ms_modulation_mae_db": 0.6460379454954132, "mr_stft_db": 5.2797749596999815, "band_mae_db": 0.16936302274754672, "rms_gain_error_db": -0.07254252993278987, "output_peak": 0.3128529465607517}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8243062520340184, "全帯域_10ms_rms_envelope_nrmse": 0.04890758751076122, "全帯域_10ms_envelope_correlation": 0.9978395999821644, "全帯域_10ms_modulation_mae_db": 0.7927128997044853, "全帯域_40ms_log_rms_mae_db": 0.47482246549888263, "全帯域_40ms_rms_envelope_nrmse": 0.025026360167055083, "全帯域_40ms_envelope_correlation": 0.9994488927907136, "全帯域_40ms_modulation_mae_db": 0.5763851074752436, "300–1000 Hz_10ms_log_rms_mae_db": 1.1496426745125763, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06362041531419908, "300–1000 Hz_10ms_envelope_correlation": 0.9971390093178886, "300–1000 Hz_10ms_modulation_mae_db": 1.0731825098631684, "300–1000 Hz_40ms_log_rms_mae_db": 0.8047802503757807, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03792556829495168, "300–1000 Hz_40ms_envelope_correlation": 0.9989489970188902, "300–1000 Hz_40ms_modulation_mae_db": 0.9449535102265149, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2967734178480685, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1077022179123302, "1000–3000 Hz_10ms_envelope_correlation": 0.9920609233685075, "1000–3000 Hz_10ms_modulation_mae_db": 0.38841918579131635, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8251425276923753, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.057045017529113465, "1000–3000 Hz_40ms_envelope_correlation": 0.9979169107331415, "1000–3000 Hz_40ms_modulation_mae_db": 0.5651377052420912, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3140625553083822, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14610792511363674, "3000–6000 Hz_10ms_envelope_correlation": 0.9866095229046379, "3000–6000 Hz_10ms_modulation_mae_db": 0.9198957764458685, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8919194517244582, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08871337157702423, "3000–6000 Hz_40ms_envelope_correlation": 0.9963116041955066, "3000–6000 Hz_40ms_modulation_mae_db": 0.7097172402390731, "mr_stft_db": 5.289357706324353, "band_mae_db": 0.22534744662758172, "rms_gain_error_db": -0.07141621381352375, "output_peak": 0.29580958542393787}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7851816836058606, "全帯域_10ms_rms_envelope_nrmse": 0.04819093215116915, "全帯域_10ms_envelope_correlation": 0.9978853398341309, "全帯域_10ms_modulation_mae_db": 0.3533586635157539, "全帯域_40ms_log_rms_mae_db": 0.4451640412457252, "全帯域_40ms_rms_envelope_nrmse": 0.024688892833172636, "全帯域_40ms_envelope_correlation": 0.999447700437555, "全帯域_40ms_modulation_mae_db": 0.49884345549775216, "300–1000 Hz_10ms_log_rms_mae_db": 1.1691295022220463, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0657837917843353, "300–1000 Hz_10ms_envelope_correlation": 0.9969448635003586, "300–1000 Hz_10ms_modulation_mae_db": 0.8211387468835475, "300–1000 Hz_40ms_log_rms_mae_db": 0.8012610039998874, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035883341994541164, "300–1000 Hz_40ms_envelope_correlation": 0.9990691469500913, "300–1000 Hz_40ms_modulation_mae_db": 1.0323185138086013, "1000–3000 Hz_10ms_log_rms_mae_db": 1.302274372815253, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1048917466159252, "1000–3000 Hz_10ms_envelope_correlation": 0.9924292923415853, "1000–3000 Hz_10ms_modulation_mae_db": 0.6395752567041809, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8421253156520706, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05667015017819444, "1000–3000 Hz_40ms_envelope_correlation": 0.9978636043092799, "1000–3000 Hz_40ms_modulation_mae_db": 0.7932736456248554, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2960771817546746, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11207122703333575, "3000–6000 Hz_10ms_envelope_correlation": 0.9913457262966202, "3000–6000 Hz_10ms_modulation_mae_db": 0.40992228303404277, "3000–6000 Hz_40ms_log_rms_mae_db": 0.843097830914095, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0634327060395984, "3000–6000 Hz_40ms_envelope_correlation": 0.9971435843276452, "3000–6000 Hz_40ms_modulation_mae_db": 0.5310320175408751, "mr_stft_db": 5.273190277346492, "band_mae_db": 0.09425522484671453, "rms_gain_error_db": -0.05804012440693079, "output_peak": 0.32557300453483956}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7670057127763715, "全帯域_10ms_rms_envelope_nrmse": 0.04143113182766407, "全帯域_10ms_envelope_correlation": 0.9984473539198436, "全帯域_10ms_modulation_mae_db": 0.5859608202930574, "全帯域_40ms_log_rms_mae_db": 0.44826690856306023, "全帯域_40ms_rms_envelope_nrmse": 0.02109677424207399, "全帯域_40ms_envelope_correlation": 0.9995958948108883, "全帯域_40ms_modulation_mae_db": 0.6379225340449786, "300–1000 Hz_10ms_log_rms_mae_db": 1.1265034559072462, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.062087659295189945, "300–1000 Hz_10ms_envelope_correlation": 0.9972800523399411, "300–1000 Hz_10ms_modulation_mae_db": 1.1095834917630831, "300–1000 Hz_40ms_log_rms_mae_db": 0.7529308772971561, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03149662250588018, "300–1000 Hz_40ms_envelope_correlation": 0.9992865119272353, "300–1000 Hz_40ms_modulation_mae_db": 1.0252514199745821, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3175430356658355, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10770284005363696, "1000–3000 Hz_10ms_envelope_correlation": 0.9921092548899284, "1000–3000 Hz_10ms_modulation_mae_db": 0.45022673387970635, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8527514262398977, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06174601885604761, "1000–3000 Hz_40ms_envelope_correlation": 0.9975583436314864, "1000–3000 Hz_40ms_modulation_mae_db": 0.8496178325209446, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2648407144472789, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11142100507970987, "3000–6000 Hz_10ms_envelope_correlation": 0.9915774555438197, "3000–6000 Hz_10ms_modulation_mae_db": 0.5387733215248082, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8444241576803813, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06071391815604497, "3000–6000 Hz_40ms_envelope_correlation": 0.997422683902861, "3000–6000 Hz_40ms_modulation_mae_db": 0.47807871459649975, "mr_stft_db": 5.262400731501959, "band_mae_db": 0.12811820042054975, "rms_gain_error_db": -0.050096026273738936, "output_peak": 0.318740337882499}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7822028085246886, "全帯域_10ms_rms_envelope_nrmse": 0.04633527181442521, "全帯域_10ms_envelope_correlation": 0.9980410209606794, "全帯域_10ms_modulation_mae_db": 0.5979780788168214, "全帯域_40ms_log_rms_mae_db": 0.45125995886689985, "全帯域_40ms_rms_envelope_nrmse": 0.02525041604081467, "全帯域_40ms_envelope_correlation": 0.999403320716377, "全帯域_40ms_modulation_mae_db": 0.25018119709473335, "300–1000 Hz_10ms_log_rms_mae_db": 1.1840212688313823, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06041904625171703, "300–1000 Hz_10ms_envelope_correlation": 0.9974377299019616, "300–1000 Hz_10ms_modulation_mae_db": 1.171865830340735, "300–1000 Hz_40ms_log_rms_mae_db": 0.7768559813241115, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03355525655280827, "300–1000 Hz_40ms_envelope_correlation": 0.9991844681107467, "300–1000 Hz_40ms_modulation_mae_db": 0.992283691374407, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3218526074835626, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10500283227873283, "1000–3000 Hz_10ms_envelope_correlation": 0.9923115473490933, "1000–3000 Hz_10ms_modulation_mae_db": 0.32819121264518253, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8636938222471224, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.054318561173177946, "1000–3000 Hz_40ms_envelope_correlation": 0.9979117116143937, "1000–3000 Hz_40ms_modulation_mae_db": 0.3849447835529533, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3096165117925058, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13128711837336407, "3000–6000 Hz_10ms_envelope_correlation": 0.988490838884403, "3000–6000 Hz_10ms_modulation_mae_db": 0.5790034997908565, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8896378472135963, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08730194743794993, "3000–6000 Hz_40ms_envelope_correlation": 0.9951307341189424, "3000–6000 Hz_40ms_modulation_mae_db": 0.7107594928738722, "mr_stft_db": 5.2807133484611235, "band_mae_db": 0.16249931300456755, "rms_gain_error_db": -0.05283323012380874, "output_peak": 0.3183685210522212}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8188113324824469, "全帯域_10ms_rms_envelope_nrmse": 0.05325282450591231, "全帯域_10ms_envelope_correlation": 0.9974548596288042, "全帯域_10ms_modulation_mae_db": 0.7804697301177819, "全帯域_40ms_log_rms_mae_db": 0.4916086999121072, "全帯域_40ms_rms_envelope_nrmse": 0.028615598716924713, "全帯域_40ms_envelope_correlation": 0.9992876181126462, "全帯域_40ms_modulation_mae_db": 0.6323244338382659, "300–1000 Hz_10ms_log_rms_mae_db": 1.1234572249289643, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07055471426595725, "300–1000 Hz_10ms_envelope_correlation": 0.9965405989465566, "300–1000 Hz_10ms_modulation_mae_db": 1.3035766888682818, "300–1000 Hz_40ms_log_rms_mae_db": 0.7663887669930814, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038792512360560034, "300–1000 Hz_40ms_envelope_correlation": 0.9990060778689319, "300–1000 Hz_40ms_modulation_mae_db": 1.0632643226312004, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3122904254935044, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11174130188621959, "1000–3000 Hz_10ms_envelope_correlation": 0.9917015143256013, "1000–3000 Hz_10ms_modulation_mae_db": 0.49332443787642344, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8569317136015536, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07160233182943719, "1000–3000 Hz_40ms_envelope_correlation": 0.9968535736614039, "1000–3000 Hz_40ms_modulation_mae_db": 0.8432672175464894, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2636542794084735, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12792110291992329, "3000–6000 Hz_10ms_envelope_correlation": 0.9887206708192862, "3000–6000 Hz_10ms_modulation_mae_db": 0.4750741701823025, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8404853157650839, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07960554482464446, "3000–6000 Hz_40ms_envelope_correlation": 0.9954800045048735, "3000–6000 Hz_40ms_modulation_mae_db": 0.4605277416459644, "mr_stft_db": 5.283983116670536, "band_mae_db": 0.170745809598781, "rms_gain_error_db": -0.0883523068231372, "output_peak": 0.3273845009418357}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.78694027443253, "全帯域_10ms_rms_envelope_nrmse": 0.04678472044207352, "全帯域_10ms_envelope_correlation": 0.9980413173052815, "全帯域_10ms_modulation_mae_db": 0.5797872225448019, "全帯域_40ms_log_rms_mae_db": 0.47803461270185826, "全帯域_40ms_rms_envelope_nrmse": 0.02323698926731981, "全帯域_40ms_envelope_correlation": 0.9995422035068015, "全帯域_40ms_modulation_mae_db": 0.4668727854701759, "300–1000 Hz_10ms_log_rms_mae_db": 1.147880288448701, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06135918046812049, "300–1000 Hz_10ms_envelope_correlation": 0.9973103002352228, "300–1000 Hz_10ms_modulation_mae_db": 0.6350111473486545, "300–1000 Hz_40ms_log_rms_mae_db": 0.8018012971386455, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.033372488386684794, "300–1000 Hz_40ms_envelope_correlation": 0.9991733799726039, "300–1000 Hz_40ms_modulation_mae_db": 0.5407343081618085, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3018131443505634, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10184763286343518, "1000–3000 Hz_10ms_envelope_correlation": 0.993095767582096, "1000–3000 Hz_10ms_modulation_mae_db": 0.6622404045333692, "1000–3000 Hz_40ms_log_rms_mae_db": 0.816685402662004, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05900778583284647, "1000–3000 Hz_40ms_envelope_correlation": 0.9979307979609706, "1000–3000 Hz_40ms_modulation_mae_db": 0.9868629362758984, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3290222730671775, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13165369190966, "3000–6000 Hz_10ms_envelope_correlation": 0.9880630727478409, "3000–6000 Hz_10ms_modulation_mae_db": 0.2064925549419975, "3000–6000 Hz_40ms_log_rms_mae_db": 0.918173360759199, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0791425553538254, "3000–6000 Hz_40ms_envelope_correlation": 0.9956216830612271, "3000–6000 Hz_40ms_modulation_mae_db": 0.2135393623374727, "mr_stft_db": 5.2762979489927275, "band_mae_db": 0.18189472530639875, "rms_gain_error_db": -0.08116989522062679, "output_peak": 0.3204794459979373}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.827971023930219, "spectral_convergence": 0.19567147871409102, "spectral_convergence_status": "ok", "amplitude_floor": 8.606911899432486e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.291576514038253, "spectral_convergence": 0.2014074850671189, "spectral_convergence_status": "ok", "amplitude_floor": 7.696353352907002e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.729285395617408, "spectral_convergence": 0.20169837512484565, "spectral_convergence_status": "ok", "amplitude_floor": 7.358558224304984e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00011977037496359504, "output_power": 0.00012187219372144412, "delta_db": 0.07555219383148976, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0009579981539513103, "output_power": 0.0009489319846555594, "delta_db": -0.04129587009235841, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0008712676276581917, "output_power": 0.0008621611605750654, "delta_db": -0.04563123463135781, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00010621716934048885, "output_power": 0.00010436305955005071, "delta_db": -0.07647920834981128, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.322826988453831e-05, "output_power": 5.067554732903406e-05, "delta_db": -0.21343902172037243, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 7.685697629736477e-05, "output_power": 7.84726862040739e-05, "delta_db": 0.09035224752332219, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.3518932532436965e-05, "output_power": 3.3091880727035625e-05, "delta_db": -0.055687289982448096, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.08549100944730857, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.0379191862175221, "pitch": null, "output_rms_dbfs": -26.576625059530052, "output_peak": 0.302160785214487, "reference_rms_dbfs": -26.53870587331253, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.282944311195293}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014088342118781798, "log_rms_mae_db": 0.7836484318437906, "rms_envelope_nrmse": 0.04175808472541596, "envelope_correlation": 0.9984110791051095, "rms_gain_error_db": -0.037028295113046575, "reference_mean_power": 0.002217082801939853, "output_mean_power": 0.0021982601323453504}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1112299552930035e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003498826441717729, "output_power": 0.00033560296454039303, "reference_active": true, "delta_db": -0.18096611460926612}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.422870023578459e-05, "output_power": 7.94840876097928e-05, "reference_active": true, "delta_db": -0.25179905610543596}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2432690798089743e-05, "output_power": 1.1103165416803034e-05, "reference_active": true, "delta_db": -0.4911832279438314}], "active_band_count": 3, "active_band_mae_db": 0.3079827995528445}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00013937350370136096, "log_rms_mae_db": 0.4418571948444878, "rms_envelope_nrmse": 0.02159042933864722, "envelope_correlation": 0.9995656497204519, "rms_gain_error_db": -0.03479458142116671, "reference_mean_power": 0.002205255256660357, "output_mean_power": 0.002187657893229495}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.0212502799160329e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00029633227983582455, "output_power": 0.0002858249233709727, "reference_active": true, "delta_db": -0.1567886655278347}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2550897730277734e-05, "output_power": 4.10841206425832e-05, "reference_active": true, "delta_db": -0.15234731329750348}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.293923839625812e-07, "output_power": 8.204472871983423e-07, "reference_active": true, "delta_db": -0.5414842590911153}], "active_band_count": 3, "active_band_mae_db": 0.28354007930548447}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.0001225394829970322, "log_rms_mae_db": 1.1392197702212925, "rms_envelope_nrmse": 0.06060346034982933, "envelope_correlation": 0.9974550356751003, "rms_gain_error_db": 0.0022648587117882627, "reference_mean_power": 0.0009458112547504951, "output_mean_power": 0.0009463046267848467}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 7.572635748614283e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021454762051170055, "output_power": 0.00019903598268831602, "reference_active": true, "delta_db": -0.3259210488934722}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.152647446601531e-05, "output_power": 5.2518338019160806e-05, "reference_active": true, "delta_db": -0.6875105618274456}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.926247906815959e-06, "output_power": 5.000415417810657e-06, "reference_active": true, "delta_db": -1.4149194634994653}], "active_band_count": 3, "active_band_mae_db": 0.809450358073461}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00011593520090475466, "log_rms_mae_db": 0.7736516672767856, "rms_envelope_nrmse": 0.03496970024745567, "envelope_correlation": 0.9991475960729632, "rms_gain_error_db": 0.0023516072227123147, "reference_mean_power": 0.000949032375443528, "output_mean_power": 0.0009495463943437068}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 7.167599035150202e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00018822421406971632, "output_power": 0.00017599065613450022, "reference_active": true, "delta_db": -0.2918588197458144}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6896254802287544e-05, "output_power": 2.4061588382792472e-05, "reference_active": true, "delta_db": -0.48367517288750317}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.519942395248337e-07, "output_power": 5.449174676372622e-07, "reference_active": true, "delta_db": -1.3988378411135118}], "active_band_count": 3, "active_band_mae_db": 0.7247906112489432}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.911272017593447e-05, "log_rms_mae_db": 1.3211216793927343, "rms_envelope_nrmse": 0.10947897150744983, "envelope_correlation": 0.9916263424642435, "rms_gain_error_db": -0.08170841312368615, "reference_mean_power": 0.00014098678071692043, "output_mean_power": 0.00013835904403674044}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1608995504129325e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.7499181258859675e-05, "output_power": 3.637896032001672e-05, "reference_active": true, "delta_db": -0.13171502495565973}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.267009960974534e-06, "output_power": 7.608887553432621e-06, "reference_active": true, "delta_db": -0.3602729490676815}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.898653312592319e-07, "output_power": 9.046358383947868e-07, "reference_active": true, "delta_db": 0.5892073671856924}], "active_band_count": 3, "active_band_mae_db": 0.3603984470696779}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.617115763934814e-05, "log_rms_mae_db": 0.8433378857917883, "rms_envelope_nrmse": 0.059509105220247584, "envelope_correlation": 0.9974586205464312, "rms_gain_error_db": -0.08157907588972084, "reference_mean_power": 0.00014167955800585476, "output_mean_power": 0.00013904304999864988}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.105176097335646e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.391055546581272e-05, "output_power": 3.304410281305803e-05, "reference_active": true, "delta_db": -0.11240938968210992}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.965549503856847e-06, "output_power": 3.670109551730106e-06, "reference_active": true, "delta_db": -0.3362434774108447}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.243578010746913e-08, "output_power": 6.572556849989883e-08, "reference_active": true, "delta_db": 0.22300808863420546}], "active_band_count": 3, "active_band_mae_db": 0.22388698524238668}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.0412813835527566e-05, "log_rms_mae_db": 1.308700458314868, "rms_envelope_nrmse": 0.12455486909984455, "envelope_correlation": 0.9893431669938623, "rms_gain_error_db": -0.13333711005522358, "reference_mean_power": 5.063950126149281e-05, "output_mean_power": 4.910839142014078e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.808534933602357e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3975319757086038e-05, "output_power": 1.3102267927688192e-05, "reference_active": true, "delta_db": -0.28015277329816446}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.037166885946856e-06, "output_power": 3.5839745350228673e-06, "reference_active": true, "delta_db": -0.5171178714506814}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.22277075461544e-07, "output_power": 7.269368118750923e-07, "reference_active": true, "delta_db": -0.5352152062228324}], "active_band_count": 3, "active_band_mae_db": 0.4441619503238927}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6032760748614375e-05, "log_rms_mae_db": 0.8870960974722818, "rms_envelope_nrmse": 0.07261290769470982, "envelope_correlation": 0.996339378199752, "rms_gain_error_db": -0.13423523446020014, "reference_mean_power": 5.0785427984468614e-05, "output_mean_power": 4.923972211173974e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.5120507652027295e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2965326164159397e-05, "output_power": 1.2280381706170697e-05, "reference_active": true, "delta_db": -0.23571580620796556}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9046258858040845e-06, "output_power": 1.616666439796808e-06, "reference_active": true, "delta_db": -0.7118925960095606}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.694645968158745e-08, "output_power": 4.933792082252373e-08, "reference_active": true, "delta_db": -0.622858858065007}], "active_band_count": 3, "active_band_mae_db": 0.5234890867608444}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9352496148523464, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "9600f53c5c171012ebaa821c1622f227f10a667a43ed795cbda400eeba79564a", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.992202189469495, "standard_deviation": 0.000459719623633057, "minimum": 0.9916263424642435, "maximum": 0.993095767582096, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.3137046567625863, "standard_deviation": 0.01305232720096159, "minimum": 1.2967734178480685, "maximum": 1.3359685710511688, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.46770424114761094, "standard_deviation": 0.12418728664732478, "minimum": 0.32819121264518253, "maximum": 0.6622404045333692, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10683190387390196, "standard_deviation": 0.003044291470497446, "minimum": 0.10184763286343518, "maximum": 0.11174130188621959, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9977149602746493, "standard_deviation": 0.00042116941942438345, "minimum": 0.9968535736614039, "maximum": 0.9982261197400872, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8466341137051732, "standard_deviation": 0.01885521055972901, "minimum": 0.816685402662004, "maximum": 0.8724048157545732, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.636831233044963, "standard_deviation": 0.26986406543047636, "minimum": 0.22388698524238668, "maximum": 0.9868629362758984, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05915986002142232, "standard_deviation": 0.005721708496257165, "minimum": 0.05337990955231378, "maximum": 0.07160233182943719, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9891048258110648, "standard_deviation": 0.001656256413926628, "minimum": 0.9866095229046379, "maximum": 0.9915774555438197, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2975846439865228, "standard_deviation": 0.023183069889987792, "minimum": 1.2636542794084735, "maximum": 1.3290222730671775, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.49037331282018715, "standard_deviation": 0.20836678908726547, "minimum": 0.2064925549419975, "maximum": 0.9198957764458685, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12682288712397133, "standard_deviation": 0.011236952354776987, "minimum": 0.11142100507970987, "maximum": 0.14610792511363674, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9960717280485107, "standard_deviation": 0.000881490767498544, "minimum": 0.995124152077278, "maximum": 0.997422683902861, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8720162499554005, "standard_deviation": 0.028713516534220662, "minimum": 0.8404853157650839, "maximum": 0.918173360759199, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.5341477001862518, "standard_deviation": 0.16301291139189464, "minimum": 0.2135393623374727, "maximum": 0.7107594928738722, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0769254278009063, "standard_deviation": 0.010491925505250542, "minimum": 0.06071391815604497, "maximum": 0.08871337157702423, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9971017692799637, "standard_deviation": 0.0003401768531006074, "minimum": 0.9965405989465566, "maximum": 0.9974550356751003, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.1500396780002138, "standard_deviation": 0.02073744738296047, "minimum": 1.1234572249289643, "maximum": 1.1840212688313823, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.9739847213416877, "standard_deviation": 0.2244261568506093, "minimum": 0.6350111473486545, "maximum": 1.3035766888682818, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06406779299343299, "standard_deviation": 0.0037448978413387856, "minimum": 0.06041904625171703, "maximum": 0.07055471426595725, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9991106623280717, "standard_deviation": 0.00010835839609445428, "minimum": 0.9989489970188902, "maximum": 0.9992865119272353, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7853493807362479, "standard_deviation": 0.02039581771524359, "minimum": 0.7529308772971561, "maximum": 0.8051252014845354, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.9153739664468571, "standard_deviation": 0.18444789315768015, "minimum": 0.5407343081618085, "maximum": 1.0632643226312004, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03524580632394318, "standard_deviation": 0.002425826526806225, "minimum": 0.03149662250588018, "maximum": 0.038792512360560034, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.15221434399993106, "standard_deviation": 0.046850119262138966, "minimum": 0.08549100944730857, "maximum": 0.22534744662758172, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.278582800024058, "standard_deviation": 0.008162671773839864, "minimum": 5.262400731501959, "maximum": 5.289357706324353, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3151711409510637, "standard_deviation": 0.011071318485492823, "minimum": 0.29580958542393787, "maximum": 0.3273845009418357, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06404618910150978, "standard_deviation": 0.017111167308017487, "minimum": -0.0883523068231372, "maximum": -0.0379191862175221, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9979675892958954, "standard_deviation": 0.0003473248322919263, "minimum": 0.9974548596288042, "maximum": 0.9984473539198436, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7953935585861442, "standard_deviation": 0.020922794528636997, "minimum": 0.7670057127763715, "maximum": 0.8243062520340184, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.5500364515197254, "standard_deviation": 0.18347443627732538, "minimum": 0.3079827995528445, "maximum": 0.7927128997044853, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.047240835912072635, "standard_deviation": 0.004155359493712926, "minimum": 0.04143113182766407, "maximum": 0.05325282450591231, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9994671099073096, "standard_deviation": 9.956502760361143e-05, "minimum": 0.9992876181126462, "maximum": 0.9995958948108883, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4623522338045629, "standard_deviation": 0.018220952083971818, "minimum": 0.4418571948444878, "maximum": 0.4916086999121072, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4794727071663816, "standard_deviation": 0.14612373960247535, "minimum": 0.25018119709473335, "maximum": 0.6379225340449786, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.02431444644329582, "standard_deviation": 0.002373711014329991, "minimum": 0.02109677424207399, "maximum": 0.028615598716924713, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 2.3136861324310303, "predicted_mos": 2.3136861324310303, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "45536fb5bcb5ed32ed29409bd09b2c80efddb43b258210e536c87c4986495bf1", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.551334300078452}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8022946439734778, "全帯域_10ms_rms_envelope_nrmse": 0.044781517426019754, "全帯域_10ms_envelope_correlation": 0.9981569790564666, "全帯域_10ms_modulation_mae_db": 0.3237278944893717, "全帯域_40ms_log_rms_mae_db": 0.4787039087276016, "全帯域_40ms_rms_envelope_nrmse": 0.024569140688306807, "全帯域_40ms_envelope_correlation": 0.9994218252995768, "全帯域_40ms_modulation_mae_db": 0.14328704220882363, "300–1000 Hz_10ms_log_rms_mae_db": 1.0128616965427368, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05773253780242194, "300–1000 Hz_10ms_envelope_correlation": 0.997670299339707, "300–1000 Hz_10ms_modulation_mae_db": 0.5668372001434056, "300–1000 Hz_40ms_log_rms_mae_db": 0.6702773822465438, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03227807698948255, "300–1000 Hz_40ms_envelope_correlation": 0.9992683891443369, "300–1000 Hz_40ms_modulation_mae_db": 0.34158981583975545, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1374997703842238, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10588006637235683, "1000–3000 Hz_10ms_envelope_correlation": 0.9922531904057462, "1000–3000 Hz_10ms_modulation_mae_db": 0.7396574732304521, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7484975730541069, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06491884001389298, "1000–3000 Hz_40ms_envelope_correlation": 0.9970927435697248, "1000–3000 Hz_40ms_modulation_mae_db": 0.7286772123187545, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1271132854733974, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11966029288716437, "3000–6000 Hz_10ms_envelope_correlation": 0.9902413752955038, "3000–6000 Hz_10ms_modulation_mae_db": 0.25877750704278824, "3000–6000 Hz_40ms_log_rms_mae_db": 0.775038697724547, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.061062121072130104, "3000–6000 Hz_40ms_envelope_correlation": 0.9975698617988682, "3000–6000 Hz_40ms_modulation_mae_db": 0.43215224721959494, "mr_stft_db": 4.99859959212502, "band_mae_db": 0.1171244580303316, "rms_gain_error_db": -0.029033980898374567, "output_peak": 0.3062420427279415}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7965089730411374, "全帯域_10ms_rms_envelope_nrmse": 0.04727792256369342, "全帯域_10ms_envelope_correlation": 0.9979510691593567, "全帯域_10ms_modulation_mae_db": 0.4788713869089771, "全帯域_40ms_log_rms_mae_db": 0.4571518971124952, "全帯域_40ms_rms_envelope_nrmse": 0.025126832414145577, "全帯域_40ms_envelope_correlation": 0.9994066088551314, "全帯域_40ms_modulation_mae_db": 0.6607128287406263, "300–1000 Hz_10ms_log_rms_mae_db": 1.0102757340372173, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06246749458456202, "300–1000 Hz_10ms_envelope_correlation": 0.9972442189054964, "300–1000 Hz_10ms_modulation_mae_db": 1.0692052686185616, "300–1000 Hz_40ms_log_rms_mae_db": 0.6978292964888062, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.033656236061942145, "300–1000 Hz_40ms_envelope_correlation": 0.9991820005872338, "300–1000 Hz_40ms_modulation_mae_db": 0.9830781162896751, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1332300529092, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10271099069873026, "1000–3000 Hz_10ms_envelope_correlation": 0.9927940367720448, "1000–3000 Hz_10ms_modulation_mae_db": 0.5434682134712917, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7332076889802078, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05643807895562937, "1000–3000 Hz_40ms_envelope_correlation": 0.997947000276887, "1000–3000 Hz_40ms_modulation_mae_db": 0.7595656847854015, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0510052345801595, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.10558795923085423, "3000–6000 Hz_10ms_envelope_correlation": 0.992456107015435, "3000–6000 Hz_10ms_modulation_mae_db": 0.18536115104717701, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7557370119493989, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06570965667018586, "3000–6000 Hz_40ms_envelope_correlation": 0.9971152124051091, "3000–6000 Hz_40ms_modulation_mae_db": 0.25166681836676985, "mr_stft_db": 4.998892922067664, "band_mae_db": 0.09401734168009745, "rms_gain_error_db": -0.03919760057618296, "output_peak": 0.33447239224896097}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8189941492700534, "全帯域_10ms_rms_envelope_nrmse": 0.04776108728654004, "全帯域_10ms_envelope_correlation": 0.9979125717402797, "全帯域_10ms_modulation_mae_db": 0.3017799774855206, "全帯域_40ms_log_rms_mae_db": 0.48836142353765094, "全帯域_40ms_rms_envelope_nrmse": 0.025443018812066988, "全帯域_40ms_envelope_correlation": 0.9993905979328983, "全帯域_40ms_modulation_mae_db": 0.2521498855931539, "300–1000 Hz_10ms_log_rms_mae_db": 1.0761625703217472, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.061435724918111945, "300–1000 Hz_10ms_envelope_correlation": 0.9973236859475904, "300–1000 Hz_10ms_modulation_mae_db": 0.2963182239441213, "300–1000 Hz_40ms_log_rms_mae_db": 0.7322814851843261, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03581218107760084, "300–1000 Hz_40ms_envelope_correlation": 0.9990643386589816, "300–1000 Hz_40ms_modulation_mae_db": 0.1394997244425313, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1345669048103983, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10537365586575177, "1000–3000 Hz_10ms_envelope_correlation": 0.9923287890234531, "1000–3000 Hz_10ms_modulation_mae_db": 0.3270835335792844, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7789666343714686, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.056967733642985595, "1000–3000 Hz_40ms_envelope_correlation": 0.9978026138544748, "1000–3000 Hz_40ms_modulation_mae_db": 0.46307638639761084, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1331922071230924, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12364996485312207, "3000–6000 Hz_10ms_envelope_correlation": 0.9895152747906486, "3000–6000 Hz_10ms_modulation_mae_db": 0.18480134177302845, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7909729709641796, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07388627463633822, "3000–6000 Hz_40ms_envelope_correlation": 0.9961989548072044, "3000–6000 Hz_40ms_modulation_mae_db": 0.4592730410595219, "mr_stft_db": 4.998729109167525, "band_mae_db": 0.15838330362776112, "rms_gain_error_db": -0.04727765870845678, "output_peak": 0.32113430276089927}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8226731088083459, "全帯域_10ms_rms_envelope_nrmse": 0.05009215527127919, "全帯域_10ms_envelope_correlation": 0.9977355877271604, "全帯域_10ms_modulation_mae_db": 0.29372129180571177, "全帯域_40ms_log_rms_mae_db": 0.46581074396312266, "全帯域_40ms_rms_envelope_nrmse": 0.026830414569852273, "全帯域_40ms_envelope_correlation": 0.9993602478349052, "全帯域_40ms_modulation_mae_db": 0.27477459231863427, "300–1000 Hz_10ms_log_rms_mae_db": 1.0666383560455168, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06387606664580993, "300–1000 Hz_10ms_envelope_correlation": 0.9971060894334172, "300–1000 Hz_10ms_modulation_mae_db": 0.7059693318989476, "300–1000 Hz_40ms_log_rms_mae_db": 0.7672775848526562, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037636712525578604, "300–1000 Hz_40ms_envelope_correlation": 0.9989745135148057, "300–1000 Hz_40ms_modulation_mae_db": 0.5262583576910344, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1246289479367941, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09443177364971389, "1000–3000 Hz_10ms_envelope_correlation": 0.994071368116061, "1000–3000 Hz_10ms_modulation_mae_db": 0.43924730349469016, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7723375306672191, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05684456483934133, "1000–3000 Hz_40ms_envelope_correlation": 0.9980502584786498, "1000–3000 Hz_40ms_modulation_mae_db": 0.6251239602319115, "3000–6000 Hz_10ms_log_rms_mae_db": 1.120038586124329, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11733046482750262, "3000–6000 Hz_10ms_envelope_correlation": 0.9906909378640892, "3000–6000 Hz_10ms_modulation_mae_db": 0.22583987992625598, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7316696855506534, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06336830107720894, "3000–6000 Hz_40ms_envelope_correlation": 0.9974437512152359, "3000–6000 Hz_40ms_modulation_mae_db": 0.08539076843565407, "mr_stft_db": 5.0024693675588265, "band_mae_db": 0.1324348636333419, "rms_gain_error_db": -0.07849550800660347, "output_peak": 0.2946890106343724}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.801126003053763, "全帯域_10ms_rms_envelope_nrmse": 0.04687971424529899, "全帯域_10ms_envelope_correlation": 0.9981092614875674, "全帯域_10ms_modulation_mae_db": 0.7178893818881783, "全帯域_40ms_log_rms_mae_db": 0.47267646361174126, "全帯域_40ms_rms_envelope_nrmse": 0.02612515177709864, "全帯域_40ms_envelope_correlation": 0.9994842355742266, "全帯域_40ms_modulation_mae_db": 0.9303988944452996, "300–1000 Hz_10ms_log_rms_mae_db": 1.0853647882079716, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06235234882150207, "300–1000 Hz_10ms_envelope_correlation": 0.9973278548422437, "300–1000 Hz_10ms_modulation_mae_db": 1.4408086839081369, "300–1000 Hz_40ms_log_rms_mae_db": 0.755907528552255, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03693641273635597, "300–1000 Hz_40ms_envelope_correlation": 0.9990967694554895, "300–1000 Hz_40ms_modulation_mae_db": 1.2318823991551617, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1370263875722928, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09027528758781099, "1000–3000 Hz_10ms_envelope_correlation": 0.9945715010977821, "1000–3000 Hz_10ms_modulation_mae_db": 0.5251729095233734, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7643557747942916, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0544160116321206, "1000–3000 Hz_40ms_envelope_correlation": 0.9981939560285795, "1000–3000 Hz_40ms_modulation_mae_db": 0.49810623491153033, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0766037664488872, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12641639357240309, "3000–6000 Hz_10ms_envelope_correlation": 0.9894966159781279, "3000–6000 Hz_10ms_modulation_mae_db": 0.8693877288044577, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7329521262841162, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07220191248870786, "3000–6000 Hz_40ms_envelope_correlation": 0.9970450541915592, "3000–6000 Hz_40ms_modulation_mae_db": 1.040401909069097, "mr_stft_db": 5.001655241223077, "band_mae_db": 0.17472605946495862, "rms_gain_error_db": -0.11705239987671587, "output_peak": 0.35419355771169414}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8039257139658369, "全帯域_10ms_rms_envelope_nrmse": 0.0500819059899357, "全帯域_10ms_envelope_correlation": 0.9976914404486288, "全帯域_10ms_modulation_mae_db": 0.3706479097679478, "全帯域_40ms_log_rms_mae_db": 0.5081248500927781, "全帯域_40ms_rms_envelope_nrmse": 0.026561064700195754, "全帯域_40ms_envelope_correlation": 0.9993238355613885, "全帯域_40ms_modulation_mae_db": 0.3013393338400854, "300–1000 Hz_10ms_log_rms_mae_db": 1.087977476303404, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06717136154097852, "300–1000 Hz_10ms_envelope_correlation": 0.9968689739665471, "300–1000 Hz_10ms_modulation_mae_db": 0.787954370747982, "300–1000 Hz_40ms_log_rms_mae_db": 0.739626610142179, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03986687805041316, "300–1000 Hz_40ms_envelope_correlation": 0.9988914663455739, "300–1000 Hz_40ms_modulation_mae_db": 0.6993675060137668, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1151096656281874, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1031112579337997, "1000–3000 Hz_10ms_envelope_correlation": 0.9928628111645933, "1000–3000 Hz_10ms_modulation_mae_db": 0.6840443643770978, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7270578984887252, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.061377530416462905, "1000–3000 Hz_40ms_envelope_correlation": 0.9976722368389096, "1000–3000 Hz_40ms_modulation_mae_db": 0.5976503413878761, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0588116202323121, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1311826427331654, "3000–6000 Hz_10ms_envelope_correlation": 0.9883375236507925, "3000–6000 Hz_10ms_modulation_mae_db": 0.3781376528501448, "3000–6000 Hz_40ms_log_rms_mae_db": 0.708432584683317, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06717563179895346, "3000–6000 Hz_40ms_envelope_correlation": 0.9971754668539209, "3000–6000 Hz_40ms_modulation_mae_db": 0.5226773318286703, "mr_stft_db": 4.98748727890834, "band_mae_db": 0.14591486325138067, "rms_gain_error_db": -0.02470913554861226, "output_peak": 0.32301402740891455}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7770998042381113, "全帯域_10ms_rms_envelope_nrmse": 0.04657768874053709, "全帯域_10ms_envelope_correlation": 0.9980860400083744, "全帯域_10ms_modulation_mae_db": 0.2281947470571873, "全帯域_40ms_log_rms_mae_db": 0.4595607810892284, "全帯域_40ms_rms_envelope_nrmse": 0.025555712110809165, "全帯域_40ms_envelope_correlation": 0.9994676869030937, "全帯域_40ms_modulation_mae_db": 0.08357601165083965, "300–1000 Hz_10ms_log_rms_mae_db": 1.031532194688845, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06171581863969577, "300–1000 Hz_10ms_envelope_correlation": 0.9973121909601348, "300–1000 Hz_10ms_modulation_mae_db": 1.09141742943968, "300–1000 Hz_40ms_log_rms_mae_db": 0.6861567783183911, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03322330349401132, "300–1000 Hz_40ms_envelope_correlation": 0.9992336514304567, "300–1000 Hz_40ms_modulation_mae_db": 0.8756110289441641, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1509846219730007, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10153533889759557, "1000–3000 Hz_10ms_envelope_correlation": 0.9930124903724488, "1000–3000 Hz_10ms_modulation_mae_db": 0.25168573722830695, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7754067688666667, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.059617798673745254, "1000–3000 Hz_40ms_envelope_correlation": 0.9977302162594451, "1000–3000 Hz_40ms_modulation_mae_db": 0.3391897200309195, "3000–6000 Hz_10ms_log_rms_mae_db": 1.093972917216284, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11755524542420286, "3000–6000 Hz_10ms_envelope_correlation": 0.9904995165687807, "3000–6000 Hz_10ms_modulation_mae_db": 0.12814257700620083, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7623692280817793, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.05744925290289784, "3000–6000 Hz_40ms_envelope_correlation": 0.9976619919249756, "3000–6000 Hz_40ms_modulation_mae_db": 0.34655321146533197, "mr_stft_db": 4.993384955073214, "band_mae_db": 0.12640007316104426, "rms_gain_error_db": -0.09629144441950425, "output_peak": 0.3238613378374603}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8155422303462724, "全帯域_10ms_rms_envelope_nrmse": 0.04949771223304339, "全帯域_10ms_envelope_correlation": 0.9978070543417811, "全帯域_10ms_modulation_mae_db": 0.31514818697529456, "全帯域_40ms_log_rms_mae_db": 0.4756096143475417, "全帯域_40ms_rms_envelope_nrmse": 0.02735267414595342, "全帯域_40ms_envelope_correlation": 0.9993576288505968, "全帯域_40ms_modulation_mae_db": 0.34012932661489176, "300–1000 Hz_10ms_log_rms_mae_db": 0.979792232580757, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.060236579648140436, "300–1000 Hz_10ms_envelope_correlation": 0.9974186499036979, "300–1000 Hz_10ms_modulation_mae_db": 0.5740248418020423, "300–1000 Hz_40ms_log_rms_mae_db": 0.6638146966909846, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03456605078539712, "300–1000 Hz_40ms_envelope_correlation": 0.9991254460812604, "300–1000 Hz_40ms_modulation_mae_db": 0.6192995905341906, "1000–3000 Hz_10ms_log_rms_mae_db": 1.136447021688177, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09831017949952563, "1000–3000 Hz_10ms_envelope_correlation": 0.9935043276318927, "1000–3000 Hz_10ms_modulation_mae_db": 0.4705006132318032, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7579794649018484, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05292784121737975, "1000–3000 Hz_40ms_envelope_correlation": 0.9983326106885008, "1000–3000 Hz_40ms_modulation_mae_db": 0.47958723715055446, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1089552169005648, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11098477971568989, "3000–6000 Hz_10ms_envelope_correlation": 0.9917951635664496, "3000–6000 Hz_10ms_modulation_mae_db": 0.5261469759279813, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7655074035102754, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06439089710508705, "3000–6000 Hz_40ms_envelope_correlation": 0.9974509325485421, "3000–6000 Hz_40ms_modulation_mae_db": 0.5743101257860938, "mr_stft_db": 4.990189982201216, "band_mae_db": 0.18679800731289614, "rms_gain_error_db": -0.08493455190464394, "output_peak": 0.3445333910669668}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.425565874966605, "spectral_convergence": 0.19402452313204918, "spectral_convergence_status": "ok", "amplitude_floor": 8.606911899432486e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 4.95625515355488, "spectral_convergence": 0.1987101634337316, "spectral_convergence_status": "ok", "amplitude_floor": 7.696353352907002e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.613977747853573, "spectral_convergence": 0.20112071553949787, "spectral_convergence_status": "ok", "amplitude_floor": 7.358558224304984e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00011977037496359504, "output_power": 0.00012172416665472263, "delta_db": 0.07027400773188933, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0009579981539513103, "output_power": 0.0009471375578619676, "delta_db": -0.049516137016398204, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0008712676276581917, "output_power": 0.0008761410185517211, "delta_db": 0.024224353762344226, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00010621716934048885, "output_power": 9.90100398292028e-05, "delta_db": -0.3051548818688654, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.322826988453831e-05, "output_power": 5.370764487676742e-05, "delta_db": 0.03893758405573028, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 7.685697629736477e-05, "output_power": 7.417716252795638e-05, "delta_db": -0.15413078075163428, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.3518932532436965e-05, "output_power": 3.217561326122112e-05, "delta_db": -0.17763346102545952, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.1171244580303316, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.029033980898374567, "pitch": null, "output_rms_dbfs": -26.567739854210902, "output_peak": 0.3062420427279415, "reference_rms_dbfs": -26.53870587331253, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 4.99859959212502}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014088342118781798, "log_rms_mae_db": 0.8022946439734778, "rms_envelope_nrmse": 0.044781517426019754, "envelope_correlation": 0.9981569790564666, "rms_gain_error_db": -0.02859044461928966, "reference_mean_power": 0.002217082801939853, "output_mean_power": 0.0022025352548022056}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1112299552930035e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003498826441717729, "output_power": 0.0003434623401471367, "reference_active": true, "delta_db": -0.08043275345480483}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.422870023578459e-05, "output_power": 8.88312192194889e-05, "reference_active": true, "delta_db": 0.2310552391091285}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2432690798089743e-05, "output_power": 1.0680597864951676e-05, "reference_active": true, "delta_db": -0.6596956909041818}], "active_band_count": 3, "active_band_mae_db": 0.3237278944893717}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00013937350370136096, "log_rms_mae_db": 0.4787039087276016, "rms_envelope_nrmse": 0.024569140688306807, "envelope_correlation": 0.9994218252995768, "rms_gain_error_db": -0.025080272754551602, "reference_mean_power": 0.002205255256660357, "output_mean_power": 0.002192556728108781}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.0212502799160329e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00029633227983582455, "output_power": 0.0002909144294390047, "reference_active": true, "delta_db": -0.08013699371315702}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2550897730277734e-05, "output_power": 4.401692912488983e-05, "reference_active": true, "delta_db": 0.14711013208860135}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.293923839625812e-07, "output_power": 8.870287764677964e-07, "reference_active": true, "delta_db": -0.20261400082471248}], "active_band_count": 3, "active_band_mae_db": 0.14328704220882363}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.0001225394829970322, "log_rms_mae_db": 1.0128616965427368, "rms_envelope_nrmse": 0.05773253780242194, "envelope_correlation": 0.997670299339707, "rms_gain_error_db": 0.05747466030066761, "reference_mean_power": 0.0009458112547504951, "output_mean_power": 0.0009584113399480488}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 7.572635748614283e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021454762051170055, "output_power": 0.00020880735375066804, "reference_active": true, "delta_db": -0.11777912728404386}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.152647446601531e-05, "output_power": 5.773139463858458e-05, "reference_active": true, "delta_db": -0.27649981216988595}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.926247906815959e-06, "output_power": 5.1271351539768724e-06, "reference_active": true, "delta_db": -1.306232660976287}], "active_band_count": 3, "active_band_mae_db": 0.5668372001434056}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00011593520090475466, "log_rms_mae_db": 0.6702773822465438, "rms_envelope_nrmse": 0.03227807698948255, "envelope_correlation": 0.9992683891443369, "rms_gain_error_db": 0.05826764456178138, "reference_mean_power": 0.000949032375443528, "output_mean_power": 0.0009618509820283011}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 7.167599035150202e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00018822421406971632, "output_power": 0.0001843332124059769, "reference_active": true, "delta_db": -0.09071900742986216}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6896254802287544e-05, "output_power": 2.5482261087340222e-05, "reference_active": true, "delta_db": -0.23453849301836877}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.519942395248337e-07, "output_power": 6.40122833668154e-07, "reference_active": true, "delta_db": -0.6995119470710355}], "active_band_count": 3, "active_band_mae_db": 0.34158981583975545}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.911272017593447e-05, "log_rms_mae_db": 1.1374997703842238, "rms_envelope_nrmse": 0.10588006637235683, "envelope_correlation": 0.9922531904057462, "rms_gain_error_db": -0.14941529659763092, "reference_mean_power": 0.00014098678071692043, "output_mean_power": 0.00013621874173186767}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1608995504129325e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.7499181258859675e-05, "output_power": 3.600380370459882e-05, "reference_active": true, "delta_db": -0.17673400400722267}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.267009960974534e-06, "output_power": 6.649065517700697e-06, "reference_active": true, "delta_db": -0.945878485451609}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.898653312592319e-07, "output_power": 6.136448011393561e-07, "reference_active": true, "delta_db": -1.0963599302325249}], "active_band_count": 3, "active_band_mae_db": 0.7396574732304521}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.617115763934814e-05, "log_rms_mae_db": 0.7484975730541069, "rms_envelope_nrmse": 0.06491884001389298, "envelope_correlation": 0.9970927435697248, "rms_gain_error_db": -0.14948343394020147, "reference_mean_power": 0.00014167955800585476, "output_mean_power": 0.00013688594230286115}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.105176097335646e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.391055546581272e-05, "output_power": 3.2533253993437395e-05, "reference_active": true, "delta_db": -0.18007399899384285}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.965549503856847e-06, "output_power": 3.255404949200063e-06, "reference_active": true, "delta_db": -0.8569835634758327}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.243578010746913e-08, "output_power": 4.792213242902658e-08, "reference_active": true, "delta_db": -1.1489740744865882}], "active_band_count": 3, "active_band_mae_db": 0.7286772123187545}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.0412813835527566e-05, "log_rms_mae_db": 1.1271132854733974, "rms_envelope_nrmse": 0.11966029288716437, "envelope_correlation": 0.9902413752955038, "rms_gain_error_db": -0.1768939367854625, "reference_mean_power": 5.063950126149281e-05, "output_mean_power": 4.8618328765058716e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.808534933602357e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3975319757086038e-05, "output_power": 1.3102530810033504e-05, "reference_active": true, "delta_db": -0.2800656378440015}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.037166885946856e-06, "output_power": 3.6755422803930625e-06, "reference_active": true, "delta_db": -0.40755279504026587}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.22277075461544e-07, "output_power": 8.056506721520269e-07, "reference_active": true, "delta_db": -0.08871408824409731}], "active_band_count": 3, "active_band_mae_db": 0.25877750704278824}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6032760748614375e-05, "log_rms_mae_db": 0.775038697724547, "rms_envelope_nrmse": 0.061062121072130104, "envelope_correlation": 0.9975698617988682, "rms_gain_error_db": -0.17615123752630574, "reference_mean_power": 5.0785427984468614e-05, "output_mean_power": 4.876677015029889e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.5120507652027295e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2965326164159397e-05, "output_power": 1.2181406885227377e-05, "reference_active": true, "delta_db": -0.27085996828626235}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9046258858040845e-06, "output_power": 1.7251701761107007e-06, "reference_active": true, "delta_db": -0.429777408677292}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.694645968158745e-08, "output_power": 4.96460605957564e-08, "reference_active": true, "delta_db": -0.5958193646952306}], "active_band_count": 3, "active_band_mae_db": 0.43215224721959494}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9396748320757172, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "e0943775f6cb62f271e14bc469ff34b501fb15966e93d51df9f4f9530ca4bcb1", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9931748143230028, "standard_deviation": 0.0008191422083809164, "minimum": 0.9922531904057462, "maximum": 0.9945715010977821, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1336866716127842, "standard_deviation": 0.010424304463259797, "minimum": 1.1151096656281874, "maximum": 1.1509846219730007, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.49760751851703744, "standard_deviation": 0.16471038789207465, "minimum": 0.25168573722830695, "maximum": 0.7396574732304521, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10020356881316059, "standard_deviation": 0.005489433581952146, "minimum": 0.09027528758781099, "maximum": 0.10588006637235683, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978527044993963, "standard_deviation": 0.00038215618677369404, "minimum": 0.9970927435697248, "maximum": 0.9983326106885008, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7572261667655669, "standard_deviation": 0.019442715662406605, "minimum": 0.7270578984887252, "maximum": 0.7789666343714686, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5613720971518199, "standard_deviation": 0.1426136133039841, "minimum": 0.3391897200309195, "maximum": 0.7595656847854015, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05793854992394472, "standard_deviation": 0.0038780903149126947, "minimum": 0.05292784121737975, "maximum": 0.06491884001389298, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9903790643412285, "standard_deviation": 0.001317080715867954, "minimum": 0.9883375236507925, "maximum": 0.992456107015435, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.0962116042623784, "standard_deviation": 0.03136070631957026, "minimum": 1.0510052345801595, "maximum": 1.1331922071230924, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.34457435179725426, "standard_deviation": 0.24747355940780771, "minimum": 0.12814257700620083, "maximum": 0.8693877288044577, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.11904596790551306, "standard_deviation": 0.00823287998824469, "minimum": 0.10558795923085423, "maximum": 0.1311826427331654, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.997207653218177, "standard_deviation": 0.0004638407988801119, "minimum": 0.9961989548072044, "maximum": 0.9976619919249756, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7528349635935334, "standard_deviation": 0.026785645676078197, "minimum": 0.708432584683317, "maximum": 0.7909729709641796, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.4640531816538417, "standard_deviation": 0.2805889706510212, "minimum": 0.08539076843565407, "maximum": 1.040401909069097, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06565550596893867, "standard_deviation": 0.005453531254481743, "minimum": 0.05744925290289784, "maximum": 0.07388627463633822, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9972839954123542, "standard_deviation": 0.00023211205475515424, "minimum": 0.9968689739665471, "maximum": 0.997670299339707, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0438256310910243, "standard_deviation": 0.04066720441880476, "minimum": 0.979792232580757, "maximum": 1.087977476303404, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8165669188128597, "standard_deviation": 0.3652684962426673, "minimum": 0.2963182239441213, "maximum": 1.4408086839081369, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.062123491575152824, "standard_deviation": 0.0027308647539683313, "minimum": 0.05773253780242194, "maximum": 0.06717136154097852, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9991045719022673, "standard_deviation": 0.00012758039509316627, "minimum": 0.9988914663455739, "maximum": 0.9992683891443369, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7141464203095178, "standard_deviation": 0.03973568915947435, "minimum": 0.6638146966909846, "maximum": 0.7672775848526562, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.677073317363785, "standard_deviation": 0.35233584042682975, "minimum": 0.1394997244425313, "maximum": 1.2318823991551617, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.035496981465097714, "standard_deviation": 0.0025531966369050168, "minimum": 0.03227807698948255, "maximum": 0.03986687805041316, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.14197487127022645, "standard_deviation": 0.030746818201342927, "minimum": 0.09401734168009745, "maximum": 0.18679800731289614, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 4.99642605604061, "standard_deviation": 0.00545132200524993, "minimum": 4.98748727890834, "maximum": 5.0024693675588265, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.32526750779965125, "standard_deviation": 0.019323457991027942, "minimum": 0.2946890106343724, "maximum": 0.35419355771169414, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06462403499238677, "standard_deviation": 0.03415039136028169, "minimum": -0.11705239987671587, "maximum": -0.02470913554861226, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9979312504962019, "standard_deviation": 0.00017669999889064527, "minimum": 0.9976914404486288, "maximum": 0.9981569790564666, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.8047705783371247, "standard_deviation": 0.01460377588866072, "minimum": 0.7770998042381113, "maximum": 0.8226731088083459, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3787475970472737, "standard_deviation": 0.15491897825757783, "minimum": 0.2281947470571873, "maximum": 0.7178893818881783, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.047868712969543446, "standard_deviation": 0.0018910243847797658, "minimum": 0.044781517426019754, "maximum": 0.05009215527127919, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9994015833514771, "standard_deviation": 5.534577409928035e-05, "minimum": 0.9993238355613885, "maximum": 0.9994842355742266, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.47574996031026995, "standard_deviation": 0.016613849143398994, "minimum": 0.4571518971124952, "maximum": 0.5081248500927781, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.3732959894265443, "standard_deviation": 0.28296251634436553, "minimum": 0.08357601165083965, "maximum": 0.9303988944452996, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.025945501152303575, "standard_deviation": 0.0009368191659552341, "minimum": 0.024569140688306807, "maximum": 0.02735267414595342, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 2.1968376636505127, "predicted_mos": 2.1968376636505127, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "44c53b47f5db50c49c79a966089370fa7da6a0aaa74e911a39aa5414164235ba", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.551281600259244}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8054927934821627, "全帯域_10ms_rms_envelope_nrmse": 0.050127639842202455, "全帯域_10ms_envelope_correlation": 0.9977918388551512, "全帯域_10ms_modulation_mae_db": 0.23597796487556702, "全帯域_40ms_log_rms_mae_db": 0.4940089179160665, "全帯域_40ms_rms_envelope_nrmse": 0.025543760746973062, "全帯域_40ms_envelope_correlation": 0.9995029556349907, "全帯域_40ms_modulation_mae_db": 0.28820455894675323, "300–1000 Hz_10ms_log_rms_mae_db": 1.077935772793828, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06473981339209053, "300–1000 Hz_10ms_envelope_correlation": 0.997051101123729, "300–1000 Hz_10ms_modulation_mae_db": 1.0431579558351018, "300–1000 Hz_40ms_log_rms_mae_db": 0.7315071531820712, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035915951175804484, "300–1000 Hz_40ms_envelope_correlation": 0.999096699089901, "300–1000 Hz_40ms_modulation_mae_db": 0.9527122387605598, "1000–3000 Hz_10ms_log_rms_mae_db": 1.205023767872423, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10077945824106499, "1000–3000 Hz_10ms_envelope_correlation": 0.9934612734628047, "1000–3000 Hz_10ms_modulation_mae_db": 0.5034103850594179, "1000–3000 Hz_40ms_log_rms_mae_db": 0.829945298988688, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06642032178411748, "1000–3000 Hz_40ms_envelope_correlation": 0.997491252740881, "1000–3000 Hz_40ms_modulation_mae_db": 0.8107677950221, "3000–6000 Hz_10ms_log_rms_mae_db": 1.119531344915794, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11985025696757179, "3000–6000 Hz_10ms_envelope_correlation": 0.9901905903293252, "3000–6000 Hz_10ms_modulation_mae_db": 0.18251537075586008, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7466812068077475, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06288621937100373, "3000–6000 Hz_40ms_envelope_correlation": 0.9973653014101985, "3000–6000 Hz_40ms_modulation_mae_db": 0.3496032828210192, "mr_stft_db": 5.0851720907913505, "band_mae_db": 0.15995007136857659, "rms_gain_error_db": -0.10161756093608487, "output_peak": 0.3363339629664417}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7898397292242432, "全帯域_10ms_rms_envelope_nrmse": 0.05009206696723193, "全帯域_10ms_envelope_correlation": 0.9977638229844724, "全帯域_10ms_modulation_mae_db": 0.25843892150277376, "全帯域_40ms_log_rms_mae_db": 0.4582757626382982, "全帯域_40ms_rms_envelope_nrmse": 0.027163315798199455, "全帯域_40ms_envelope_correlation": 0.9993740372981502, "全帯域_40ms_modulation_mae_db": 0.35791952977497976, "300–1000 Hz_10ms_log_rms_mae_db": 1.0264494307847891, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05982250492513037, "300–1000 Hz_10ms_envelope_correlation": 0.99745851537878, "300–1000 Hz_10ms_modulation_mae_db": 0.8206383884332956, "300–1000 Hz_40ms_log_rms_mae_db": 0.7087754048362412, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03552344940860988, "300–1000 Hz_40ms_envelope_correlation": 0.9990712618700498, "300–1000 Hz_40ms_modulation_mae_db": 0.7115753397214797, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1528351121101315, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09864587544074965, "1000–3000 Hz_10ms_envelope_correlation": 0.9935417609173167, "1000–3000 Hz_10ms_modulation_mae_db": 0.6937477470776162, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7508467513896703, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.054046548297761225, "1000–3000 Hz_40ms_envelope_correlation": 0.9983433365431896, "1000–3000 Hz_40ms_modulation_mae_db": 0.5895944331481457, "3000–6000 Hz_10ms_log_rms_mae_db": 1.126546188657664, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1197280511108557, "3000–6000 Hz_10ms_envelope_correlation": 0.990658890741984, "3000–6000 Hz_10ms_modulation_mae_db": 0.4481349329835009, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8046794158385538, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07570590906332952, "3000–6000 Hz_40ms_envelope_correlation": 0.9966493112955065, "3000–6000 Hz_40ms_modulation_mae_db": 0.5457924112409723, "mr_stft_db": 5.081582766721688, "band_mae_db": 0.1509946051868804, "rms_gain_error_db": -0.09291881388491101, "output_peak": 0.31370121966387754}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.794025539467194, "全帯域_10ms_rms_envelope_nrmse": 0.05089814617588739, "全帯域_10ms_envelope_correlation": 0.997668970489765, "全帯域_10ms_modulation_mae_db": 0.5807805010270674, "全帯域_40ms_log_rms_mae_db": 0.4719395961689859, "全帯域_40ms_rms_envelope_nrmse": 0.0294720286669076, "全帯域_40ms_envelope_correlation": 0.99921824559585, "全帯域_40ms_modulation_mae_db": 0.6049215519811465, "300–1000 Hz_10ms_log_rms_mae_db": 1.1123768609382034, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.060617491715915225, "300–1000 Hz_10ms_envelope_correlation": 0.9974302510695827, "300–1000 Hz_10ms_modulation_mae_db": 0.8007882280033213, "300–1000 Hz_40ms_log_rms_mae_db": 0.7684750013817297, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.034691488485719735, "300–1000 Hz_40ms_envelope_correlation": 0.9991542919692193, "300–1000 Hz_40ms_modulation_mae_db": 0.8658665751788616, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2174124539191906, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11189688830992989, "1000–3000 Hz_10ms_envelope_correlation": 0.9914612260573877, "1000–3000 Hz_10ms_modulation_mae_db": 0.7054016940276323, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8049111966681799, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0638867416889704, "1000–3000 Hz_40ms_envelope_correlation": 0.9973748878640077, "1000–3000 Hz_40ms_modulation_mae_db": 0.27161820653464513, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1619840995685833, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13716941629517304, "3000–6000 Hz_10ms_envelope_correlation": 0.9878413153262824, "3000–6000 Hz_10ms_modulation_mae_db": 0.614465154220024, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8049385857408122, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07666060562805849, "3000–6000 Hz_40ms_envelope_correlation": 0.9970331458813917, "3000–6000 Hz_40ms_modulation_mae_db": 0.4717628047368589, "mr_stft_db": 5.0842328796201395, "band_mae_db": 0.15132006777288526, "rms_gain_error_db": -0.08126059496347178, "output_peak": 0.31471998208607027}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.775997323098837, "全帯域_10ms_rms_envelope_nrmse": 0.0477385024290097, "全帯域_10ms_envelope_correlation": 0.9979641162160471, "全帯域_10ms_modulation_mae_db": 0.39740750813566317, "全帯域_40ms_log_rms_mae_db": 0.4658560308715516, "全帯域_40ms_rms_envelope_nrmse": 0.0259551556512233, "全帯域_40ms_envelope_correlation": 0.9994236030292003, "全帯域_40ms_modulation_mae_db": 0.3320843426042269, "300–1000 Hz_10ms_log_rms_mae_db": 1.0739365497192594, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0610554802074142, "300–1000 Hz_10ms_envelope_correlation": 0.997457270412886, "300–1000 Hz_10ms_modulation_mae_db": 1.2072337766910337, "300–1000 Hz_40ms_log_rms_mae_db": 0.7196295101778762, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.034100930252950384, "300–1000 Hz_40ms_envelope_correlation": 0.9992690862279643, "300–1000 Hz_40ms_modulation_mae_db": 1.153803331733916, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1619629068770225, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11221255696207622, "1000–3000 Hz_10ms_envelope_correlation": 0.9912406797167409, "1000–3000 Hz_10ms_modulation_mae_db": 0.1729976046698558, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7897332124194001, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06558587786485384, "1000–3000 Hz_40ms_envelope_correlation": 0.9969608781912426, "1000–3000 Hz_40ms_modulation_mae_db": 0.2131706939527888, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1582621933555495, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11721172099786124, "3000–6000 Hz_10ms_envelope_correlation": 0.9907360582002749, "3000–6000 Hz_10ms_modulation_mae_db": 0.4675242771390149, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7975328719497222, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0677790010513737, "3000–6000 Hz_40ms_envelope_correlation": 0.9970610091833018, "3000–6000 Hz_40ms_modulation_mae_db": 0.5786779183588517, "mr_stft_db": 5.07455429683624, "band_mae_db": 0.09248255845743689, "rms_gain_error_db": -0.08039411714715018, "output_peak": 0.3036092253779891}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8019678081263837, "全帯域_10ms_rms_envelope_nrmse": 0.04719221137955673, "全帯域_10ms_envelope_correlation": 0.9980151902420749, "全帯域_10ms_modulation_mae_db": 0.561740108439313, "全帯域_40ms_log_rms_mae_db": 0.48528559630367574, "全帯域_40ms_rms_envelope_nrmse": 0.025955147524949013, "全帯域_40ms_envelope_correlation": 0.9994245622269134, "全帯域_40ms_modulation_mae_db": 0.2607230384239596, "300–1000 Hz_10ms_log_rms_mae_db": 1.0513011154213103, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05575897334049583, "300–1000 Hz_10ms_envelope_correlation": 0.9978184886659403, "300–1000 Hz_10ms_modulation_mae_db": 0.6223499543404479, "300–1000 Hz_40ms_log_rms_mae_db": 0.7358323364717224, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029833078331324765, "300–1000 Hz_40ms_envelope_correlation": 0.999370643456493, "300–1000 Hz_40ms_modulation_mae_db": 0.6352348464439833, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1954266920313081, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1068931551745533, "1000–3000 Hz_10ms_envelope_correlation": 0.9924552916154058, "1000–3000 Hz_10ms_modulation_mae_db": 0.3586131031974779, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7927678075031965, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06307269643006773, "1000–3000 Hz_40ms_envelope_correlation": 0.9977101804814541, "1000–3000 Hz_40ms_modulation_mae_db": 0.27234436850117544, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1666990178320773, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13053444555075824, "3000–6000 Hz_10ms_envelope_correlation": 0.9882758025717135, "3000–6000 Hz_10ms_modulation_mae_db": 0.2387744213375098, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8050148873367551, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07745754301581319, "3000–6000 Hz_40ms_envelope_correlation": 0.9957809010047869, "3000–6000 Hz_40ms_modulation_mae_db": 0.22873343154315603, "mr_stft_db": 5.075174708657792, "band_mae_db": 0.18951882700706266, "rms_gain_error_db": -0.08391422180619022, "output_peak": 0.3030727767165679}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8109917986994515, "全帯域_10ms_rms_envelope_nrmse": 0.05101854331079856, "全帯域_10ms_envelope_correlation": 0.9976458794165708, "全帯域_10ms_modulation_mae_db": 0.354152483439091, "全帯域_40ms_log_rms_mae_db": 0.48417464282134215, "全帯域_40ms_rms_envelope_nrmse": 0.029132822099728825, "全帯域_40ms_envelope_correlation": 0.9992347468480451, "全帯域_40ms_modulation_mae_db": 0.28571098932146416, "300–1000 Hz_10ms_log_rms_mae_db": 1.0548260174016517, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06071802087726804, "300–1000 Hz_10ms_envelope_correlation": 0.9973860906336101, "300–1000 Hz_10ms_modulation_mae_db": 0.23462608201447277, "300–1000 Hz_40ms_log_rms_mae_db": 0.7024392724745725, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0356144684862793, "300–1000 Hz_40ms_envelope_correlation": 0.9990742762109476, "300–1000 Hz_40ms_modulation_mae_db": 0.22530170366000543, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1853023864538743, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10364336984571247, "1000–3000 Hz_10ms_envelope_correlation": 0.9929271779483396, "1000–3000 Hz_10ms_modulation_mae_db": 0.5633744971395588, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7852286440253947, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06143562539643303, "1000–3000 Hz_40ms_envelope_correlation": 0.997834758886436, "1000–3000 Hz_40ms_modulation_mae_db": 0.6435462510171949, "3000–6000 Hz_10ms_log_rms_mae_db": 1.141088908873271, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13144178850649338, "3000–6000 Hz_10ms_envelope_correlation": 0.9885806359902216, "3000–6000 Hz_10ms_modulation_mae_db": 0.4755426026633631, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7775916133055091, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07689146342213624, "3000–6000 Hz_40ms_envelope_correlation": 0.9965502596527913, "3000–6000 Hz_40ms_modulation_mae_db": 0.338979788675773, "mr_stft_db": 5.0740708418291645, "band_mae_db": 0.13326601861131165, "rms_gain_error_db": -0.07073004547142134, "output_peak": 0.31516907365354896}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8262948615456298, "全帯域_10ms_rms_envelope_nrmse": 0.052080728253714084, "全帯域_10ms_envelope_correlation": 0.9975264496467696, "全帯域_10ms_modulation_mae_db": 0.2904170881649694, "全帯域_40ms_log_rms_mae_db": 0.48465525305811913, "全帯域_40ms_rms_envelope_nrmse": 0.02712566424206729, "全帯域_40ms_envelope_correlation": 0.9993204764097152, "全帯域_40ms_modulation_mae_db": 0.1123907157020183, "300–1000 Hz_10ms_log_rms_mae_db": 1.1188941193638677, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0651887675201834, "300–1000 Hz_10ms_envelope_correlation": 0.9970080455577909, "300–1000 Hz_10ms_modulation_mae_db": 0.6708271998521237, "300–1000 Hz_40ms_log_rms_mae_db": 0.78174696861647, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0372593962764738, "300–1000 Hz_40ms_envelope_correlation": 0.9990017549391647, "300–1000 Hz_40ms_modulation_mae_db": 0.5620054936953707, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1501015382956359, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0987574896336692, "1000–3000 Hz_10ms_envelope_correlation": 0.9932313409868815, "1000–3000 Hz_10ms_modulation_mae_db": 0.22239508470549962, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7825595012587626, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05615532656689239, "1000–3000 Hz_40ms_envelope_correlation": 0.9977836667299458, "1000–3000 Hz_40ms_modulation_mae_db": 0.465649209478078, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1049035177340174, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11885846904195796, "3000–6000 Hz_10ms_envelope_correlation": 0.9906628465386885, "3000–6000 Hz_10ms_modulation_mae_db": 0.5416054362109137, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7540156898329351, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07389032659307607, "3000–6000 Hz_40ms_envelope_correlation": 0.9966815693132315, "3000–6000 Hz_40ms_modulation_mae_db": 0.6800879726832209, "mr_stft_db": 5.080818571478655, "band_mae_db": 0.17168852447876384, "rms_gain_error_db": -0.0616147479400984, "output_peak": 0.31049363150022685}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7769241527231169, "全帯域_10ms_rms_envelope_nrmse": 0.04994055890005748, "全帯域_10ms_envelope_correlation": 0.9977121370251663, "全帯域_10ms_modulation_mae_db": 0.6814079362202564, "全帯域_40ms_log_rms_mae_db": 0.45846922529466577, "全帯域_40ms_rms_envelope_nrmse": 0.027719552764509936, "全帯域_40ms_envelope_correlation": 0.9992750864998503, "全帯域_40ms_modulation_mae_db": 0.6650025385988171, "300–1000 Hz_10ms_log_rms_mae_db": 1.1182567455398653, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06692373811219428, "300–1000 Hz_10ms_envelope_correlation": 0.996786546881916, "300–1000 Hz_10ms_modulation_mae_db": 0.7126084937036765, "300–1000 Hz_40ms_log_rms_mae_db": 0.7971886773539121, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04013283240742649, "300–1000 Hz_40ms_envelope_correlation": 0.9987924443189392, "300–1000 Hz_40ms_modulation_mae_db": 0.6490945025087964, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1559008966032376, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10008400577780623, "1000–3000 Hz_10ms_envelope_correlation": 0.993017030736921, "1000–3000 Hz_10ms_modulation_mae_db": 0.47961345884093526, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7839512103024603, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05941753303011516, "1000–3000 Hz_40ms_envelope_correlation": 0.997482229505606, "1000–3000 Hz_40ms_modulation_mae_db": 0.8115775828648468, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1172788929130841, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11271470309931773, "3000–6000 Hz_10ms_envelope_correlation": 0.9913517978825608, "3000–6000 Hz_10ms_modulation_mae_db": 0.6438242295004247, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7487509094863787, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06660641478114221, "3000–6000 Hz_40ms_envelope_correlation": 0.9970236354337203, "3000–6000 Hz_40ms_modulation_mae_db": 0.6421183215299131, "mr_stft_db": 5.072632594920523, "band_mae_db": 0.08260244430844998, "rms_gain_error_db": -0.04381678827725329, "output_peak": 0.3238363875048371}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.56629708209998, "spectral_convergence": 0.19270729521179356, "spectral_convergence_status": "ok", "amplitude_floor": 8.606911899432486e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.058495561790864, "spectral_convergence": 0.19416711521142083, "spectral_convergence_status": "ok", "amplitude_floor": 7.696353352907002e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.6307236284832065, "spectral_convergence": 0.19812709383235738, "spectral_convergence_status": "ok", "amplitude_floor": 7.358558224304984e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00011977037496359504, "output_power": 0.00012064346448890969, "delta_db": 0.031543910356430935, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0009579981539513103, "output_power": 0.0009400220809501648, "delta_db": -0.08226616981078186, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0008712676276581917, "output_power": 0.0008505375857320402, "delta_db": -0.10458067837505249, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00010621716934048885, "output_power": 0.0001017474885916305, "delta_db": -0.18671024958990648, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.322826988453831e-05, "output_power": 4.7858474093719416e-05, "delta_db": -0.4618350265302851, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 7.685697629736477e-05, "output_power": 7.29926283649055e-05, "delta_db": -0.22404292193003178, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.3518932532436965e-05, "output_power": 3.374095212403184e-05, "delta_db": 0.02867154298754738, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.15995007136857659, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.10161756093608487, "pitch": null, "output_rms_dbfs": -26.64032343424861, "output_peak": 0.3363339629664417, "reference_rms_dbfs": -26.53870587331253, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.0851720907913505}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014088342118781798, "log_rms_mae_db": 0.8054927934821627, "rms_envelope_nrmse": 0.050127639842202455, "envelope_correlation": 0.9977918388551512, "rms_gain_error_db": -0.10476040216473781, "reference_mean_power": 0.002217082801939853, "output_mean_power": 0.002164242259420423}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1112299552930035e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003498826441717729, "output_power": 0.0003423636452321259, "reference_active": true, "delta_db": -0.09434758191715963}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.422870023578459e-05, "output_power": 7.98584026027504e-05, "reference_active": true, "delta_db": -0.23139480175406268}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2432690798089743e-05, "output_power": 1.1385339404583487e-05, "reference_active": true, "delta_db": -0.3821915109554788}], "active_band_count": 3, "active_band_mae_db": 0.23597796487556702}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00013937350370136096, "log_rms_mae_db": 0.4940089179160665, "rms_envelope_nrmse": 0.025543760746973062, "envelope_correlation": 0.9995029556349907, "rms_gain_error_db": -0.10507625259224225, "reference_mean_power": 0.002205255256660357, "output_mean_power": 0.002152540050330414}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.0212502799160329e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00029633227983582455, "output_power": 0.00029077914136541516, "reference_active": true, "delta_db": -0.08215712485558581}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2550897730277734e-05, "output_power": 4.181128349482408e-05, "reference_active": true, "delta_db": -0.07615227738187691}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.293923839625812e-07, "output_power": 7.898937578325859e-07, "reference_active": true, "delta_db": -0.706304274602797}], "active_band_count": 3, "active_band_mae_db": 0.28820455894675323}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.0001225394829970322, "log_rms_mae_db": 1.077935772793828, "rms_envelope_nrmse": 0.06473981339209053, "envelope_correlation": 0.997051101123729, "rms_gain_error_db": -0.06716854884194727, "reference_mean_power": 0.0009458112547504951, "output_mean_power": 0.0009312957536525822}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 7.572635748614283e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021454762051170055, "output_power": 0.00020192587599485, "reference_active": true, "delta_db": -0.26331726641653586}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.152647446601531e-05, "output_power": 5.0080477958800015e-05, "reference_active": true, "delta_db": -0.8939356520606048}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.926247906815959e-06, "output_power": 4.398209750565953e-06, "reference_active": true, "delta_db": -1.9722209490281652}], "active_band_count": 3, "active_band_mae_db": 1.0431579558351018}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00011593520090475466, "log_rms_mae_db": 0.7315071531820712, "rms_envelope_nrmse": 0.035915951175804484, "envelope_correlation": 0.999096699089901, "rms_gain_error_db": -0.0677722208432892, "reference_mean_power": 0.000949032375443528, "output_mean_power": 0.0009343375568221392}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 7.167599035150202e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00018822421406971632, "output_power": 0.00017808253321348775, "reference_active": true, "delta_db": -0.24054167571842933}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6896254802287544e-05, "output_power": 2.2645378469665127e-05, "reference_active": true, "delta_db": -0.7471222701913853}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.519942395248337e-07, "output_power": 4.888405642944463e-07, "reference_active": true, "delta_db": -1.8704727703718649}], "active_band_count": 3, "active_band_mae_db": 0.9527122387605598}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.911272017593447e-05, "log_rms_mae_db": 1.205023767872423, "rms_envelope_nrmse": 0.10077945824106499, "envelope_correlation": 0.9934612734628047, "rms_gain_error_db": -0.29154365730984755, "reference_mean_power": 0.00014098678071692043, "output_mean_power": 0.00013183296759321719}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1608995504129325e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.7499181258859675e-05, "output_power": 3.435623636507832e-05, "reference_active": true, "delta_db": -0.38016203678756644}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.267009960974534e-06, "output_power": 7.225478868912742e-06, "reference_active": true, "delta_db": -0.5848182564507375}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.898653312592319e-07, "output_power": 6.966713742084895e-07, "reference_active": true, "delta_db": -0.5452508619399499}], "active_band_count": 3, "active_band_mae_db": 0.5034103850594179}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.617115763934814e-05, "log_rms_mae_db": 0.829945298988688, "rms_envelope_nrmse": 0.06642032178411748, "envelope_correlation": 0.997491252740881, "rms_gain_error_db": -0.29156332734170337, "reference_mean_power": 0.00014167955800585476, "output_mean_power": 0.00013248016507649295}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.105176097335646e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.391055546581272e-05, "output_power": 3.1101499600736126e-05, "reference_active": true, "delta_db": -0.3755357409407551}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.965549503856847e-06, "output_power": 3.496398236757042e-06, "reference_active": true, "delta_db": -0.5468248320565151}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.243578010746913e-08, "output_power": 4.410006821022362e-08, "reference_active": true, "delta_db": -1.50994281206903}], "active_band_count": 3, "active_band_mae_db": 0.8107677950221}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.0412813835527566e-05, "log_rms_mae_db": 1.119531344915794, "rms_envelope_nrmse": 0.11985025696757179, "envelope_correlation": 0.9901905903293252, "rms_gain_error_db": -0.16409239279315313, "reference_mean_power": 5.063950126149281e-05, "output_mean_power": 4.8761850707060266e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.808534933602357e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3975319757086038e-05, "output_power": 1.3535503489702369e-05, "reference_active": true, "delta_db": -0.13887338218703466}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.037166885946856e-06, "output_power": 3.7334553479731183e-06, "reference_active": true, "delta_db": -0.33965740837413594}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.22277075461544e-07, "output_power": 8.093132495094943e-07, "reference_active": true, "delta_db": -0.06901532170640959}], "active_band_count": 3, "active_band_mae_db": 0.18251537075586008}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6032760748614375e-05, "log_rms_mae_db": 0.7466812068077475, "rms_envelope_nrmse": 0.06288621937100373, "envelope_correlation": 0.9973653014101985, "rms_gain_error_db": -0.16308259524195387, "reference_mean_power": 5.0785427984468614e-05, "output_mean_power": 4.891373847655199e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.5120507652027295e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2965326164159397e-05, "output_power": 1.2613285722024309e-05, "reference_active": true, "delta_db": -0.11955212952744673}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9046258858040845e-06, "output_power": 1.7573897494113366e-06, "reference_active": true, "delta_db": -0.34941593639606366}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.694645968158745e-08, "output_power": 4.982904356269566e-08, "reference_active": true, "delta_db": -0.5798417825395473}], "active_band_count": 3, "active_band_mae_db": 0.3496032828210192}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.940314102566783, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "1bfa73d5d010129e27f735326b42c8058270f7c32527b4509439661c74c3bfe6", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9926669726802249, "standard_deviation": 0.0008813846746132826, "minimum": 0.9912406797167409, "maximum": 0.9935417609173167, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.177995719270353, "standard_deviation": 0.02618012966569687, "minimum": 1.1501015382956359, "maximum": 1.2174124539191906, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.46244419683974924, "standard_deviation": 0.19888022864029867, "minimum": 0.1729976046698558, "maximum": 0.7054016940276323, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10411409992319524, "standard_deviation": 0.005606855282756395, "minimum": 0.09864587544074965, "maximum": 0.11221255696207622, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9976226488678455, "standard_deviation": 0.0004025416400080971, "minimum": 0.9969608781912426, "maximum": 0.9983433365431896, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.789992952819469, "standard_deviation": 0.02227552733690626, "minimum": 0.7508467513896703, "maximum": 0.829945298988688, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5097835675648719, "standard_deviation": 0.24170835832856877, "minimum": 0.2131706939527888, "maximum": 0.8115775828648468, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06125258388240141, "standard_deviation": 0.004424678287081904, "minimum": 0.054046548297761225, "maximum": 0.06642032178411748, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9897872421976313, "standard_deviation": 0.0013397339731454606, "minimum": 0.9878413153262824, "maximum": 0.9913517978825608, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.137036770481255, "standard_deviation": 0.023325548340134103, "minimum": 1.1049035177340174, "maximum": 1.1666990178320773, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.45154830310132643, "standard_deviation": 0.16480129688104098, "minimum": 0.18251537075586008, "maximum": 0.6438242295004247, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12343860644624864, "standard_deviation": 0.008488103706245085, "minimum": 0.11271470309931773, "maximum": 0.13716941629517304, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9967681416468661, "standard_deviation": 0.000481308865245725, "minimum": 0.9957809010047869, "maximum": 0.9973653014101985, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7799006475373018, "standard_deviation": 0.02654297373777711, "minimum": 0.7466812068077475, "maximum": 0.8050148873367551, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.47946949144872064, "standard_deviation": 0.16056774808916416, "minimum": 0.22873343154315603, "maximum": 0.6800879726832209, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07223468536574164, "standard_deviation": 0.005634935730875778, "minimum": 0.06288621937100373, "maximum": 0.07745754301581319, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9972995387155293, "standard_deviation": 0.0003281743857525205, "minimum": 0.996786546881916, "maximum": 0.9978184886659403, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.079247076495347, "standard_deviation": 0.03461234787230746, "minimum": 1.0264494307847891, "maximum": 1.1188941193638677, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7640287598591842, "standard_deviation": 0.2904603138218077, "minimum": 0.23462608201447277, "maximum": 1.2072337766910337, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06185309876133649, "standard_deviation": 0.0035833780702084527, "minimum": 0.05575897334049583, "maximum": 0.06692373811219428, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9991038072603349, "standard_deviation": 0.0001733743956530159, "minimum": 0.9987924443189392, "maximum": 0.999370643456493, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7431992905618244, "standard_deviation": 0.03511722114450216, "minimum": 0.7024392724745725, "maximum": 0.7971886773539121, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7194492539628716, "standard_deviation": 0.2791792337841215, "minimum": 0.22530170366000543, "maximum": 1.153803331733916, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0353839493530736, "standard_deviation": 0.0029121083640124097, "minimum": 0.029833078331324765, "maximum": 0.04013283240742649, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.14147788964892088, "standard_deviation": 0.03719363872252042, "minimum": 0.08260244430844998, "maximum": 0.18951882700706266, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.078529843856944, "standard_deviation": 0.004970266216190874, "minimum": 5.072632594920523, "maximum": 5.0851720907913505, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.31511703243369493, "standard_deviation": 0.01087079792285499, "minimum": 0.3030727767165679, "maximum": 0.3363339629664417, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07703336130332264, "standard_deviation": 0.01818180822746475, "minimum": -0.10161756093608487, "maximum": -0.04381678827725329, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9977610506095022, "standard_deviation": 0.00016298619490988882, "minimum": 0.9975264496467696, "maximum": 0.9980151902420749, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7976917507958774, "standard_deviation": 0.017118105799619667, "minimum": 0.775997323098837, "maximum": 0.8262948615456298, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4200403139755876, "standard_deviation": 0.167280287725274, "minimum": 0.23597796487556702, "maximum": 0.6814079362202564, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.049886049657307294, "standard_deviation": 0.0016516657977007118, "minimum": 0.04719221137955673, "maximum": 0.052080728253714084, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9993467141928394, "standard_deviation": 0.00010141144220759694, "minimum": 0.99921824559585, "maximum": 0.9995029556349907, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4753331281340881, "standard_deviation": 0.013573016877338763, "minimum": 0.4582757626382982, "maximum": 0.4940089179160665, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.3633696581691707, "standard_deviation": 0.18343765228285153, "minimum": 0.1123907157020183, "maximum": 0.6650025385988171, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.02725843093681981, "standard_deviation": 0.0014633538947371701, "minimum": 0.025543760746973062, "maximum": 0.0294720286669076, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 2.092656135559082, "predicted_mos": 2.092656135559082, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "12080603465cf91491b716e79f5a8e4ee6465a035fae133b6ed25c32c5483f57", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 12.281000200193375}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7982077403702049, "全帯域_10ms_rms_envelope_nrmse": 0.048300821456384965, "全帯域_10ms_envelope_correlation": 0.9978785812452575, "全帯域_10ms_modulation_mae_db": 0.2772854095379241, "全帯域_40ms_log_rms_mae_db": 0.46623548014452326, "全帯域_40ms_rms_envelope_nrmse": 0.027494818799088133, "全帯域_40ms_envelope_correlation": 0.9993085820962712, "全帯域_40ms_modulation_mae_db": 0.6012489591462297, "300–1000 Hz_10ms_log_rms_mae_db": 1.0080594207175864, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.059573481208233955, "300–1000 Hz_10ms_envelope_correlation": 0.9974557619497983, "300–1000 Hz_10ms_modulation_mae_db": 0.6140199580938306, "300–1000 Hz_40ms_log_rms_mae_db": 0.6591617132215434, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03715366862701211, "300–1000 Hz_40ms_envelope_correlation": 0.9989646242280982, "300–1000 Hz_40ms_modulation_mae_db": 0.9236889984364923, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1741997157542805, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10082823017420656, "1000–3000 Hz_10ms_envelope_correlation": 0.9929066702490109, "1000–3000 Hz_10ms_modulation_mae_db": 0.3760552286630541, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7651913836480391, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05499059538784711, "1000–3000 Hz_40ms_envelope_correlation": 0.997839187763425, "1000–3000 Hz_40ms_modulation_mae_db": 0.15950528739782494, "3000–6000 Hz_10ms_log_rms_mae_db": 1.118023720306457, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12028443899984376, "3000–6000 Hz_10ms_envelope_correlation": 0.9904377394034838, "3000–6000 Hz_10ms_modulation_mae_db": 0.6451731975251785, "3000–6000 Hz_40ms_log_rms_mae_db": 0.765402999229684, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06976405311345647, "3000–6000 Hz_40ms_envelope_correlation": 0.9971261605394768, "3000–6000 Hz_40ms_modulation_mae_db": 0.7031501331804996, "mr_stft_db": 5.041706699286684, "band_mae_db": 0.1310365794072565, "rms_gain_error_db": -0.05785772296413716, "output_peak": 0.30193712847394844}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7957471128142736, "全帯域_10ms_rms_envelope_nrmse": 0.048572667531979904, "全帯域_10ms_envelope_correlation": 0.9979107055791804, "全帯域_10ms_modulation_mae_db": 0.4403471626618078, "全帯域_40ms_log_rms_mae_db": 0.462218575272388, "全帯域_40ms_rms_envelope_nrmse": 0.02434369705415133, "全帯域_40ms_envelope_correlation": 0.9995221075988001, "全帯域_40ms_modulation_mae_db": 0.3327961561471035, "300–1000 Hz_10ms_log_rms_mae_db": 1.0479688699450025, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06274483279568725, "300–1000 Hz_10ms_envelope_correlation": 0.9972385704458271, "300–1000 Hz_10ms_modulation_mae_db": 1.0154257365231825, "300–1000 Hz_40ms_log_rms_mae_db": 0.6899346522851483, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.032424538076629664, "300–1000 Hz_40ms_envelope_correlation": 0.9992755543268371, "300–1000 Hz_40ms_modulation_mae_db": 1.1239996563103416, "1000–3000 Hz_10ms_log_rms_mae_db": 1.133170881248736, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09275556770313921, "1000–3000 Hz_10ms_envelope_correlation": 0.9941021428329075, "1000–3000 Hz_10ms_modulation_mae_db": 0.23766827667349788, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7622003258893756, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04978821743912888, "1000–3000 Hz_40ms_envelope_correlation": 0.998374701865803, "1000–3000 Hz_40ms_modulation_mae_db": 0.24433191473711455, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1188493262495003, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11654802959030562, "3000–6000 Hz_10ms_envelope_correlation": 0.9911822589789041, "3000–6000 Hz_10ms_modulation_mae_db": 0.9386870864709674, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7492637159144565, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07482269631270087, "3000–6000 Hz_40ms_envelope_correlation": 0.9967302713415879, "3000–6000 Hz_40ms_modulation_mae_db": 1.0288158065243405, "mr_stft_db": 5.029670706890614, "band_mae_db": 0.10606672033921084, "rms_gain_error_db": -0.0918643217359677, "output_peak": 0.3188837681013432}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7794798989592278, "全帯域_10ms_rms_envelope_nrmse": 0.048164349492634255, "全帯域_10ms_envelope_correlation": 0.9979177684365399, "全帯域_10ms_modulation_mae_db": 0.20603399684870424, "全帯域_40ms_log_rms_mae_db": 0.45691335239237235, "全帯域_40ms_rms_envelope_nrmse": 0.02483959617580438, "全帯域_40ms_envelope_correlation": 0.9994728756241192, "全帯域_40ms_modulation_mae_db": 0.20034751312035137, "300–1000 Hz_10ms_log_rms_mae_db": 1.069001734480479, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06484089335095938, "300–1000 Hz_10ms_envelope_correlation": 0.9970665232116266, "300–1000 Hz_10ms_modulation_mae_db": 0.23061189053832354, "300–1000 Hz_40ms_log_rms_mae_db": 0.7540585890984313, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038049616236180736, "300–1000 Hz_40ms_envelope_correlation": 0.9990115627623759, "300–1000 Hz_40ms_modulation_mae_db": 0.32450550291994756, "1000–3000 Hz_10ms_log_rms_mae_db": 1.160298706153982, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10431376341576575, "1000–3000 Hz_10ms_envelope_correlation": 0.9923939573019246, "1000–3000 Hz_10ms_modulation_mae_db": 0.5676587792937801, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7349693978474313, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05119320393735858, "1000–3000 Hz_40ms_envelope_correlation": 0.99808746884968, "1000–3000 Hz_40ms_modulation_mae_db": 0.3901977823164177, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1069208542668683, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.10837651899251519, "3000–6000 Hz_10ms_envelope_correlation": 0.9919617552872048, "3000–6000 Hz_10ms_modulation_mae_db": 0.4677247129890036, "3000–6000 Hz_40ms_log_rms_mae_db": 0.735438122740363, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.05801910551602735, "3000–6000 Hz_40ms_envelope_correlation": 0.997642710216022, "3000–6000 Hz_40ms_modulation_mae_db": 0.7957910259660744, "mr_stft_db": 5.041653330450625, "band_mae_db": 0.11473309997259186, "rms_gain_error_db": -0.07326200121912377, "output_peak": 0.3164626622237774}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7918740784933685, "全帯域_10ms_rms_envelope_nrmse": 0.046782117507920475, "全帯域_10ms_envelope_correlation": 0.9980781389338238, "全帯域_10ms_modulation_mae_db": 0.6275732512498639, "全帯域_40ms_log_rms_mae_db": 0.43691249864259707, "全帯域_40ms_rms_envelope_nrmse": 0.023773405199290498, "全帯域_40ms_envelope_correlation": 0.9995439180413543, "全帯域_40ms_modulation_mae_db": 0.7615605882136837, "300–1000 Hz_10ms_log_rms_mae_db": 1.0260623393151362, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06070647051665572, "300–1000 Hz_10ms_envelope_correlation": 0.9974220154371033, "300–1000 Hz_10ms_modulation_mae_db": 1.1742378823417623, "300–1000 Hz_40ms_log_rms_mae_db": 0.6859538890721117, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03445643606345813, "300–1000 Hz_40ms_envelope_correlation": 0.9991708817719179, "300–1000 Hz_40ms_modulation_mae_db": 1.1521018911412855, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1810477470753358, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11060246943354657, "1000–3000 Hz_10ms_envelope_correlation": 0.9917379252858166, "1000–3000 Hz_10ms_modulation_mae_db": 0.7522525865797182, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7801452045771151, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05915676860197754, "1000–3000 Hz_40ms_envelope_correlation": 0.997901868482206, "1000–3000 Hz_40ms_modulation_mae_db": 0.39332810586054195, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1113862131423642, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11966198257078546, "3000–6000 Hz_10ms_envelope_correlation": 0.9901561205882895, "3000–6000 Hz_10ms_modulation_mae_db": 0.21649092795482192, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7374293171173633, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.05729208153328477, "3000–6000 Hz_40ms_envelope_correlation": 0.9976924521745, "3000–6000 Hz_40ms_modulation_mae_db": 0.3587299393595605, "mr_stft_db": 5.030656569554336, "band_mae_db": 0.14122460415889218, "rms_gain_error_db": -0.09873017774354538, "output_peak": 0.3211886376994422}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8107040230845745, "全帯域_10ms_rms_envelope_nrmse": 0.051386346269623726, "全帯域_10ms_envelope_correlation": 0.9976269421477328, "全帯域_10ms_modulation_mae_db": 0.3336954319412908, "全帯域_40ms_log_rms_mae_db": 0.5106607646920408, "全帯域_40ms_rms_envelope_nrmse": 0.027481469861597965, "全帯域_40ms_envelope_correlation": 0.9993412851271285, "全帯域_40ms_modulation_mae_db": 0.32422701142772753, "300–1000 Hz_10ms_log_rms_mae_db": 1.0423037372125559, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06598844647334594, "300–1000 Hz_10ms_envelope_correlation": 0.9969009624583834, "300–1000 Hz_10ms_modulation_mae_db": 0.5139438789097172, "300–1000 Hz_40ms_log_rms_mae_db": 0.7319798044458701, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03859092453887386, "300–1000 Hz_40ms_envelope_correlation": 0.9989177576113539, "300–1000 Hz_40ms_modulation_mae_db": 0.4716153916944294, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1488066851506904, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10698694426387702, "1000–3000 Hz_10ms_envelope_correlation": 0.9920888732130017, "1000–3000 Hz_10ms_modulation_mae_db": 0.5232780017578026, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7620429342177543, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.056342579827842805, "1000–3000 Hz_40ms_envelope_correlation": 0.997860329482716, "1000–3000 Hz_40ms_modulation_mae_db": 0.21023151340235502, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1150730909320485, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13688459182211246, "3000–6000 Hz_10ms_envelope_correlation": 0.9876468604814588, "3000–6000 Hz_10ms_modulation_mae_db": 0.458785855623639, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7518972755165346, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08358321504409914, "3000–6000 Hz_40ms_envelope_correlation": 0.9958902905996213, "3000–6000 Hz_40ms_modulation_mae_db": 0.6716029886692786, "mr_stft_db": 5.041880952679416, "band_mae_db": 0.11814441171584787, "rms_gain_error_db": -0.08236766185214359, "output_peak": 0.37556571074784273}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8120828550024785, "全帯域_10ms_rms_envelope_nrmse": 0.046492255010349426, "全帯域_10ms_envelope_correlation": 0.9980596853942121, "全帯域_10ms_modulation_mae_db": 0.4812506501159037, "全帯域_40ms_log_rms_mae_db": 0.4755598092142713, "全帯域_40ms_rms_envelope_nrmse": 0.024828568341761253, "全帯域_40ms_envelope_correlation": 0.9994701722148789, "全帯域_40ms_modulation_mae_db": 0.5662747050885248, "300–1000 Hz_10ms_log_rms_mae_db": 1.0536959208155607, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05920224503753981, "300–1000 Hz_10ms_envelope_correlation": 0.9975064778441364, "300–1000 Hz_10ms_modulation_mae_db": 0.7548188138467148, "300–1000 Hz_40ms_log_rms_mae_db": 0.7069725506510762, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03107632661827931, "300–1000 Hz_40ms_envelope_correlation": 0.9992949962279397, "300–1000 Hz_40ms_modulation_mae_db": 0.6733654472197038, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1435127741283377, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10504235675436539, "1000–3000 Hz_10ms_envelope_correlation": 0.9927498902193009, "1000–3000 Hz_10ms_modulation_mae_db": 0.6483048255862154, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7451441869570082, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06306166406100489, "1000–3000 Hz_40ms_envelope_correlation": 0.9977224591400988, "1000–3000 Hz_40ms_modulation_mae_db": 0.8517999449809347, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1310914134169492, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12783975033943062, "3000–6000 Hz_10ms_envelope_correlation": 0.989075144952173, "3000–6000 Hz_10ms_modulation_mae_db": 1.051661521699633, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7510009868379803, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0814767301189864, "3000–6000 Hz_40ms_envelope_correlation": 0.9957792031072392, "3000–6000 Hz_40ms_modulation_mae_db": 1.0382445956496689, "mr_stft_db": 5.0234329243871105, "band_mae_db": 0.17816352592649448, "rms_gain_error_db": -0.07207736912824966, "output_peak": 0.3240143139686291}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8356130876136116, "全帯域_10ms_rms_envelope_nrmse": 0.04639327672299419, "全帯域_10ms_envelope_correlation": 0.9980511839559102, "全帯域_10ms_modulation_mae_db": 0.26156747898606175, "全帯域_40ms_log_rms_mae_db": 0.49152879701945035, "全帯域_40ms_rms_envelope_nrmse": 0.02395574766227044, "全帯域_40ms_envelope_correlation": 0.9994908094596121, "全帯域_40ms_modulation_mae_db": 0.23866449193866912, "300–1000 Hz_10ms_log_rms_mae_db": 1.144998619107437, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06414369647723779, "300–1000 Hz_10ms_envelope_correlation": 0.997063836308021, "300–1000 Hz_10ms_modulation_mae_db": 0.23869683297567293, "300–1000 Hz_40ms_log_rms_mae_db": 0.7985251942662659, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03495335705618647, "300–1000 Hz_40ms_envelope_correlation": 0.99909489193328, "300–1000 Hz_40ms_modulation_mae_db": 0.2814801415468178, "1000–3000 Hz_10ms_log_rms_mae_db": 1.128070782564703, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09754296500065374, "1000–3000 Hz_10ms_envelope_correlation": 0.9936499973080106, "1000–3000 Hz_10ms_modulation_mae_db": 0.6053842099141296, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7387147485288224, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05926930772091879, "1000–3000 Hz_40ms_envelope_correlation": 0.9978460631616313, "1000–3000 Hz_40ms_modulation_mae_db": 0.9745592801907351, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1272616650391132, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.10471494267355426, "3000–6000 Hz_10ms_envelope_correlation": 0.9929099323436232, "3000–6000 Hz_10ms_modulation_mae_db": 0.6874556945183802, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7657408270591217, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.05355135861885386, "3000–6000 Hz_40ms_envelope_correlation": 0.9985957029176332, "3000–6000 Hz_40ms_modulation_mae_db": 0.631063758459922, "mr_stft_db": 5.034517468918799, "band_mae_db": 0.17361515446146836, "rms_gain_error_db": -0.06662263988543025, "output_peak": 0.3099938208965641}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8148509570402993, "全帯域_10ms_rms_envelope_nrmse": 0.0486954844430028, "全帯域_10ms_envelope_correlation": 0.9978642153532995, "全帯域_10ms_modulation_mae_db": 0.58741039245693, "全帯域_40ms_log_rms_mae_db": 0.47273130006993763, "全帯域_40ms_rms_envelope_nrmse": 0.02598586698610598, "全帯域_40ms_envelope_correlation": 0.9994008608038165, "全帯域_40ms_modulation_mae_db": 0.8495635349362128, "300–1000 Hz_10ms_log_rms_mae_db": 1.0492885476902614, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06139474453752111, "300–1000 Hz_10ms_envelope_correlation": 0.9973384285097419, "300–1000 Hz_10ms_modulation_mae_db": 1.347979837043429, "300–1000 Hz_40ms_log_rms_mae_db": 0.7355171700905377, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035867061425696505, "300–1000 Hz_40ms_envelope_correlation": 0.9990653317967935, "300–1000 Hz_40ms_modulation_mae_db": 1.1715711643405786, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1609200405119484, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10347668314031574, "1000–3000 Hz_10ms_envelope_correlation": 0.9929468734506709, "1000–3000 Hz_10ms_modulation_mae_db": 0.7738101981906643, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7562819593176288, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06027089766310535, "1000–3000 Hz_40ms_envelope_correlation": 0.9979375240304141, "1000–3000 Hz_40ms_modulation_mae_db": 1.2288145518917817, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1062660918686567, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12789198757614456, "3000–6000 Hz_10ms_envelope_correlation": 0.9892367048782648, "3000–6000 Hz_10ms_modulation_mae_db": 0.7715271461835034, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7799136785028667, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07573845022486057, "3000–6000 Hz_40ms_envelope_correlation": 0.9966669763819624, "3000–6000 Hz_40ms_modulation_mae_db": 0.9196735783951588, "mr_stft_db": 5.032770906020828, "band_mae_db": 0.1313601647232117, "rms_gain_error_db": -0.07820682407869536, "output_peak": 0.321919650445413}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.530976691942979, "spectral_convergence": 0.18854873929857136, "spectral_convergence_status": "ok", "amplitude_floor": 8.606911899432486e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 4.991198253645789, "spectral_convergence": 0.19160473784800203, "spectral_convergence_status": "ok", "amplitude_floor": 7.696353352907002e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.602945152271284, "spectral_convergence": 0.19608437903582748, "spectral_convergence_status": "ok", "amplitude_floor": 7.358558224304984e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00011977037496359504, "output_power": 0.00012150836069781857, "delta_db": 0.06256752522658048, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0009579981539513103, "output_power": 0.0009449742016800078, "delta_db": -0.059447200093238374, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0008712676276581917, "output_power": 0.0008631834489915843, "delta_db": -0.04048473499642608, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00010621716934048885, "output_power": 0.0001043828221294107, "delta_db": -0.07565688992888712, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.322826988453831e-05, "output_power": 5.1031858401650007e-05, "delta_db": -0.18300966121657858, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 7.685697629736477e-05, "output_power": 7.288066081497188e-05, "delta_db": -0.23070992709752355, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.3518932532436965e-05, "output_power": 3.153204717231274e-05, "delta_db": -0.2653801172915612, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.1310365794072565, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.05785772296413716, "pitch": null, "output_rms_dbfs": -26.596563596276663, "output_peak": 0.30193712847394844, "reference_rms_dbfs": -26.53870587331253, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.041706699286684}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.00014088342118781798, "log_rms_mae_db": 0.7982077403702049, "rms_envelope_nrmse": 0.048300821456384965, "envelope_correlation": 0.9978785812452575, "rms_gain_error_db": -0.05700572037036955, "reference_mean_power": 0.002217082801939853, "output_mean_power": 0.002188171418628117}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1112299552930035e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003498826441717729, "output_power": 0.0003474524939128392, "reference_active": true, "delta_db": -0.03026966697974904}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.422870023578459e-05, "output_power": 8.123541578389083e-05, "reference_active": true, "delta_db": -0.15714691341038606}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2432690798089743e-05, "output_power": 1.0718183005007222e-05, "reference_active": true, "delta_db": -0.6444396482236372}], "active_band_count": 3, "active_band_mae_db": 0.2772854095379241}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00013937350370136096, "log_rms_mae_db": 0.46623548014452326, "rms_envelope_nrmse": 0.027494818799088133, "envelope_correlation": 0.9993085820962712, "rms_gain_error_db": -0.05651477342855546, "reference_mean_power": 0.002205255256660357, "output_mean_power": 0.002176744163372568}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.0212502799160329e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00029633227983582455, "output_power": 0.00029640028967925725, "reference_active": true, "delta_db": 0.0009966147084414824}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2550897730277734e-05, "output_power": 4.132304615945609e-05, "reference_active": true, "delta_db": -0.12716398802552545}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.293923839625812e-07, "output_power": 6.318885440396032e-07, "reference_active": true, "delta_db": -1.675586274704722}], "active_band_count": 3, "active_band_mae_db": 0.6012489591462297}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 0.0001225394829970322, "log_rms_mae_db": 1.0080594207175864, "rms_envelope_nrmse": 0.059573481208233955, "envelope_correlation": 0.9974557619497983, "rms_gain_error_db": 0.009074680240898293, "reference_mean_power": 0.0009458112547504951, "output_mean_power": 0.0009477896146949509}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 7.572635748614283e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021454762051170055, "output_power": 0.00021171507308466144, "reference_active": true, "delta_db": -0.05771923478083929}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.152647446601531e-05, "output_power": 5.5852329397673464e-05, "reference_active": true, "delta_db": -0.4202073958043811}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.926247906815959e-06, "output_power": 5.059233308753251e-06, "reference_active": true, "delta_db": -1.3641332436962714}], "active_band_count": 3, "active_band_mae_db": 0.6140199580938306}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 0.00011593520090475466, "log_rms_mae_db": 0.6591617132215434, "rms_envelope_nrmse": 0.03715366862701211, "envelope_correlation": 0.9989646242280982, "rms_gain_error_db": 0.008435632031137284, "reference_mean_power": 0.000949032375443528, "output_mean_power": 0.0009508775446325229}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 7.167599035150202e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00018822421406971632, "output_power": 0.00018811248273640276, "reference_active": true, "delta_db": -0.0025787707311727497}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6896254802287544e-05, "output_power": 2.4366812771211336e-05, "reference_active": true, "delta_db": -0.4289308411767915}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.519942395248337e-07, "output_power": 4.38792075251694e-07, "reference_active": true, "delta_db": -2.3395573834015124}], "active_band_count": 3, "active_band_mae_db": 0.9236889984364923}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.911272017593447e-05, "log_rms_mae_db": 1.1741997157542805, "rms_envelope_nrmse": 0.10082823017420656, "envelope_correlation": 0.9929066702490109, "rms_gain_error_db": -0.08426201782263765, "reference_mean_power": 0.00014098678071692043, "output_mean_power": 0.0001382777143243981}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1608995504129325e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.7499181258859675e-05, "output_power": 3.575381497183264e-05, "reference_active": true, "delta_db": -0.20699397316739868}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.267009960974534e-06, "output_power": 7.65589061092369e-06, "reference_active": true, "delta_db": -0.3335274139587091}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.898653312592319e-07, "output_power": 9.043103096914841e-07, "reference_active": true, "delta_db": 0.5876442988630545}], "active_band_count": 3, "active_band_mae_db": 0.3760552286630541}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.617115763934814e-05, "log_rms_mae_db": 0.7651913836480391, "rms_envelope_nrmse": 0.05499059538784711, "envelope_correlation": 0.997839187763425, "rms_gain_error_db": -0.08429594600639626, "reference_mean_power": 0.00014167955800585476, "output_mean_power": 0.00013895609430677891}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.105176097335646e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.391055546581272e-05, "output_power": 3.245014156737605e-05, "reference_active": true, "delta_db": -0.19118307920916675}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.965549503856847e-06, "output_power": 3.792288232987747e-06, "reference_active": true, "delta_db": -0.1940203726746534}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.243578010746913e-08, "output_power": 6.110859539052174e-08, "reference_active": true, "delta_db": -0.09331241030965465}], "active_band_count": 3, "active_band_mae_db": 0.15950528739782494}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.0412813835527566e-05, "log_rms_mae_db": 1.118023720306457, "rms_envelope_nrmse": 0.12028443899984376, "envelope_correlation": 0.9904377394034838, "rms_gain_error_db": -0.27541784009088144, "reference_mean_power": 5.063950126149281e-05, "output_mean_power": 4.752779167256615e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.808534933602357e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3975319757086038e-05, "output_power": 1.257917177451335e-05, "reference_active": true, "delta_db": -0.4570970572553311}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.037166885946856e-06, "output_power": 3.715567696615437e-06, "reference_active": true, "delta_db": -0.36051523943364805}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.22277075461544e-07, "output_power": 6.356637607942735e-07, "reference_active": true, "delta_db": -1.1179072958865564}], "active_band_count": 3, "active_band_mae_db": 0.6451731975251785}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6032760748614375e-05, "log_rms_mae_db": 0.765402999229684, "rms_envelope_nrmse": 0.06976405311345647, "envelope_correlation": 0.9971261605394768, "rms_gain_error_db": -0.2761113305715561, "reference_mean_power": 5.0785427984468614e-05, "output_mean_power": 4.765714085211674e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.5120507652027295e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2965326164159397e-05, "output_power": 1.163171748748924e-05, "reference_active": true, "delta_db": -0.471396011885997}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9046258858040845e-06, "output_power": 1.7122657848181772e-06, "reference_active": true, "delta_db": -0.4623850401903804}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.694645968158745e-08, "output_power": 4.3440998070594007e-08, "reference_active": true, "delta_db": -1.1756693474651214}], "active_band_count": 3, "active_band_mae_db": 0.7031501331804996}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9421157672038335, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "a7f8194a66e7d7d9256027e8587c12c567b4062374b87934a1eeba19673996e8", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9928220412325806, "standard_deviation": 0.0007790306132313109, "minimum": 0.9917379252858166, "maximum": 0.9941021428329075, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1537534165735017, "standard_deviation": 0.018783778341905946, "minimum": 1.128070782564703, "maximum": 1.1810477470753358, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5605515133323578, "standard_deviation": 0.18192285418064422, "minimum": 0.23766827667349788, "maximum": 0.7738101981906643, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10269362248573374, "standard_deviation": 0.0055871147561348325, "minimum": 0.09275556770313921, "maximum": 0.11060246943354657, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9979462003469968, "standard_deviation": 0.00020160924585764585, "minimum": 0.9977224591400988, "maximum": 0.998374701865803, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7555862676228968, "standard_deviation": 0.015118855114886478, "minimum": 0.7349693978474313, "maximum": 0.7801452045771151, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5565960475972132, "standard_deviation": 0.4041250649575482, "minimum": 0.15950528739782494, "maximum": 1.2288145518917817, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05675915432989799, "standard_deviation": 0.004582240474261506, "minimum": 0.04978821743912888, "maximum": 0.06306166406100489, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9903258146141752, "standard_deviation": 0.0016926697577489464, "minimum": 0.9876468604814588, "maximum": 0.9929099323436232, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.1168590469027446, "standard_deviation": 0.008945967279979239, "minimum": 1.1062660918686567, "maximum": 1.1310914134169492, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6546882678706408, "standard_deviation": 0.27213670204713386, "minimum": 0.21649092795482192, "maximum": 1.051661521699633, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12027528032058649, "standard_deviation": 0.010617222595436526, "minimum": 0.10471494267355426, "maximum": 0.13688459182211246, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9970154709097554, "standard_deviation": 0.0009530622984004654, "minimum": 0.9957792031072392, "maximum": 0.9985957029176332, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7545108653647963, "standard_deviation": 0.015082084989359172, "minimum": 0.735438122740363, "maximum": 0.7799136785028667, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7683839782755629, "standard_deviation": 0.22821808749134787, "minimum": 0.3587299393595605, "maximum": 1.0382445956496689, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06928096131028368, "standard_deviation": 0.011612294232402086, "minimum": 0.05355135861885386, "maximum": 0.08358321504409914, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9972490720205798, "standard_deviation": 0.00021902360588289834, "minimum": 0.9969009624583834, "maximum": 0.9975064778441364, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0551723986605024, "standard_deviation": 0.04067523222732359, "minimum": 1.0080594207175864, "maximum": 1.144998619107437, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7362168537840791, "standard_deviation": 0.41609063382589956, "minimum": 0.23061189053832354, "maximum": 1.347979837043429, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.062324351299647626, "standard_deviation": 0.002508327263723345, "minimum": 0.05920224503753981, "maximum": 0.06598844647334594, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9990994500823245, "standard_deviation": 0.00013859121101374028, "minimum": 0.9989177576113539, "maximum": 0.9992949962279397, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.720262945391373, "standard_deviation": 0.04414911932964932, "minimum": 0.6591617132215434, "maximum": 0.7985251942662659, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7652910242011997, "standard_deviation": 0.37635631574797, "minimum": 0.2814801415468178, "maximum": 1.1715711643405786, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0353214910802896, "standard_deviation": 0.0026480177067706137, "minimum": 0.03107632661827931, "maximum": 0.03859092453887386, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1367930325881217, "standard_deviation": 0.02653352586344023, "minimum": 0.10606672033921084, "maximum": 0.17816352592649448, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.034536194773551, "standard_deviation": 0.006773255140705188, "minimum": 5.0234329243871105, "maximum": 5.041880952679416, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.32374571156962006, "standard_deviation": 0.02215744855049179, "minimum": 0.30193712847394844, "maximum": 0.37556571074784273, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07762358982591161, "standard_deviation": 0.013269876154201915, "minimum": -0.09873017774354538, "maximum": -0.05785772296413716, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9979234026307445, "standard_deviation": 0.00014756995911319783, "minimum": 0.9976269421477328, "maximum": 0.9980781389338238, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.8048199691722548, "standard_deviation": 0.01720449276070588, "minimum": 0.7794798989592278, "maximum": 0.8356130876136116, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.40189547172481077, "standard_deviation": 0.15645839189949104, "minimum": 0.20603399684870424, "maximum": 0.6275732512498639, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.048098414804361216, "standard_deviation": 0.0016325746840169357, "minimum": 0.04639327672299419, "maximum": 0.051386346269623726, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9994438263707476, "standard_deviation": 8.497346377148573e-05, "minimum": 0.9993085820962712, "maximum": 0.9995439180413543, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4715950721809476, "standard_deviation": 0.022282503049747406, "minimum": 0.43691249864259707, "maximum": 0.5106607646920408, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.48433537000231275, "standard_deviation": 0.24501614496089358, "minimum": 0.20034751312035137, "maximum": 0.8495635349362128, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.02533789626000875, "standard_deviation": 0.0014890651753627661, "minimum": 0.023773405199290498, "maximum": 0.027494818799088133, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "language": "ja", "style": "whisper", "speaker": "jvs_jvs018", "source_utterance_id": "VOICEACTRESS100_005", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 144000, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs018_whisper10_VOICEACTRESS100_005.wav", "source_file_sha256": "163d3cbdf7e987c158925ce6d2946625b27edda6d3717a35d8e281fb170f1c3d", "decoded_pcm_sha256": "e95e1bb0ca185383d8b6b3f7b7367171455483ebcd1f6d4bd41ecb95bd74cc3b", "original_source_sha256": "163d3cbdf7e987c158925ce6d2946625b27edda6d3717a35d8e281fb170f1c3d", "corpus_entry_id": "jvs_jvs018_whisper10_VOICEACTRESS100_005"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 3.381962299346924, "predicted_mos": 3.381962299346924, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "adf68481c52628406a33bc283c6cca28b12710636f9d116886fcab9be05875ae", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 11.714842299930751}, "waveform_sha256": "391020a5020bedc44b73cea52cfc9a89f328d6bf606ebf09557f3f0afed75f39"}, "rows": [{"case": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 1.8279356956481934, "predicted_mos": 1.8279356956481934, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "b5995217973faf7962c6944ac41075c1843facbb2aaf20ac979fc0b072d0f9cc", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 11.389068000018597}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.637245269148285, "全帯域_10ms_rms_envelope_nrmse": 0.12173118268926647, "全帯域_10ms_envelope_correlation": 0.9886892503851504, "全帯域_10ms_modulation_mae_db": 0.6726912549506694, "全帯域_40ms_log_rms_mae_db": 0.8843192840771208, "全帯域_40ms_rms_envelope_nrmse": 0.06163244128666284, "全帯域_40ms_envelope_correlation": 0.9969337697055167, "全帯域_40ms_modulation_mae_db": 1.100144442307275, "300–1000 Hz_10ms_log_rms_mae_db": 2.4311075316881494, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24832489819722725, "300–1000 Hz_10ms_envelope_correlation": 0.9595447724730573, "300–1000 Hz_10ms_modulation_mae_db": 0.30935697261300665, "300–1000 Hz_40ms_log_rms_mae_db": 1.7927030465179492, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14095486352061, "300–1000 Hz_40ms_envelope_correlation": 0.9870934587949295, "300–1000 Hz_40ms_modulation_mae_db": 0.4460849436265999, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5956431500047703, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18387391758235458, "1000–3000 Hz_10ms_envelope_correlation": 0.9793399030507569, "1000–3000 Hz_10ms_modulation_mae_db": 0.7320573187459716, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9054725913181143, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09101811755268896, "1000–3000 Hz_40ms_envelope_correlation": 0.9952681147465837, "1000–3000 Hz_40ms_modulation_mae_db": 0.7968685691190385, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2947800063776325, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15126018401020913, "3000–6000 Hz_10ms_envelope_correlation": 0.98666809922525, "3000–6000 Hz_10ms_modulation_mae_db": 0.8367190881403687, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8959413768075107, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08594727902667681, "3000–6000 Hz_40ms_envelope_correlation": 0.9959386547796276, "3000–6000 Hz_40ms_modulation_mae_db": 1.6850207358679707, "mr_stft_db": 6.038882086343409, "band_mae_db": 0.5978204357095255, "rms_gain_error_db": -0.025136467348846957, "output_peak": 0.04170952340722672}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5790652628177297, "全帯域_10ms_rms_envelope_nrmse": 0.1344336842990895, "全帯域_10ms_envelope_correlation": 0.9861966030219507, "全帯域_10ms_modulation_mae_db": 0.6000749087864269, "全帯域_40ms_log_rms_mae_db": 0.8238585592638886, "全帯域_40ms_rms_envelope_nrmse": 0.0636730075241263, "全帯域_40ms_envelope_correlation": 0.9968948803460643, "全帯域_40ms_modulation_mae_db": 0.7605666544795028, "300–1000 Hz_10ms_log_rms_mae_db": 2.4278913787205934, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2463453652465608, "300–1000 Hz_10ms_envelope_correlation": 0.9603536282914195, "300–1000 Hz_10ms_modulation_mae_db": 1.0039775771179535, "300–1000 Hz_40ms_log_rms_mae_db": 1.7198666889002592, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14179983146652417, "300–1000 Hz_40ms_envelope_correlation": 0.9869477035822987, "300–1000 Hz_40ms_modulation_mae_db": 1.0927210871966648, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5766815533567673, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16277024794145098, "1000–3000 Hz_10ms_envelope_correlation": 0.9827301989964906, "1000–3000 Hz_10ms_modulation_mae_db": 0.5115939160301595, "1000–3000 Hz_40ms_log_rms_mae_db": 0.957364473908028, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08901928456822004, "1000–3000 Hz_40ms_envelope_correlation": 0.9949368309183647, "1000–3000 Hz_40ms_modulation_mae_db": 0.9446289925453778, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2692725190720036, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17993947537224125, "3000–6000 Hz_10ms_envelope_correlation": 0.9811231277236012, "3000–6000 Hz_10ms_modulation_mae_db": 1.2426418214048212, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8112616081548352, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09635329878809004, "3000–6000 Hz_40ms_envelope_correlation": 0.9951407707554709, "3000–6000 Hz_40ms_modulation_mae_db": 1.935533819126037, "mr_stft_db": 6.036496231208797, "band_mae_db": 0.5593109633526566, "rms_gain_error_db": -0.14231887980989394, "output_peak": 0.0324396607862574}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.639586957043008, "全帯域_10ms_rms_envelope_nrmse": 0.14541860351467475, "全帯域_10ms_envelope_correlation": 0.9842456388997622, "全帯域_10ms_modulation_mae_db": 0.2289609081514469, "全帯域_40ms_log_rms_mae_db": 0.9073270886955219, "全帯域_40ms_rms_envelope_nrmse": 0.08630434293732614, "全帯域_40ms_envelope_correlation": 0.9942009769335142, "全帯域_40ms_modulation_mae_db": 0.5019298598941749, "300–1000 Hz_10ms_log_rms_mae_db": 2.3592937553842512, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2674656285150539, "300–1000 Hz_10ms_envelope_correlation": 0.9500990423809142, "300–1000 Hz_10ms_modulation_mae_db": 0.4713621120204439, "300–1000 Hz_40ms_log_rms_mae_db": 1.7767787334636604, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17339960445363384, "300–1000 Hz_40ms_envelope_correlation": 0.977712661608712, "300–1000 Hz_40ms_modulation_mae_db": 0.3857200725089902, "1000–3000 Hz_10ms_log_rms_mae_db": 1.536135433723311, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17922607591772494, "1000–3000 Hz_10ms_envelope_correlation": 0.9790016213363241, "1000–3000 Hz_10ms_modulation_mae_db": 0.11901157339682737, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8806424782218337, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0898151424335678, "1000–3000 Hz_40ms_envelope_correlation": 0.9946123519732899, "1000–3000 Hz_40ms_modulation_mae_db": 0.4516985751188915, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2495702125522308, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18435871599927034, "3000–6000 Hz_10ms_envelope_correlation": 0.9819712451312665, "3000–6000 Hz_10ms_modulation_mae_db": 0.5109660649011052, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8049039699444442, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11248996886078805, "3000–6000 Hz_40ms_envelope_correlation": 0.9937909293462764, "3000–6000 Hz_40ms_modulation_mae_db": 0.7074488167548384, "mr_stft_db": 6.038001627941855, "band_mae_db": 0.5683109249737495, "rms_gain_error_db": 0.10271157564986878, "output_peak": 0.03809881832744406}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5862549675760478, "全帯域_10ms_rms_envelope_nrmse": 0.13863870862549166, "全帯域_10ms_envelope_correlation": 0.98547607312246, "全帯域_10ms_modulation_mae_db": 0.38532960901371954, "全帯域_40ms_log_rms_mae_db": 0.8530561446101466, "全帯域_40ms_rms_envelope_nrmse": 0.06749901960229705, "全帯域_40ms_envelope_correlation": 0.9963704309614195, "全帯域_40ms_modulation_mae_db": 0.6988316222984571, "300–1000 Hz_10ms_log_rms_mae_db": 2.4299371868265918, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2746531546493093, "300–1000 Hz_10ms_envelope_correlation": 0.9490855864732489, "300–1000 Hz_10ms_modulation_mae_db": 0.2569507677005356, "300–1000 Hz_40ms_log_rms_mae_db": 1.8272623744580447, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17037411039881017, "300–1000 Hz_40ms_envelope_correlation": 0.9796565722633118, "300–1000 Hz_40ms_modulation_mae_db": 0.5456034379139648, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5462319259668955, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20941099741818817, "1000–3000 Hz_10ms_envelope_correlation": 0.9737448881768741, "1000–3000 Hz_10ms_modulation_mae_db": 0.7385093578280868, "1000–3000 Hz_40ms_log_rms_mae_db": 0.892252475683486, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10629721789799354, "1000–3000 Hz_40ms_envelope_correlation": 0.9938113237473278, "1000–3000 Hz_40ms_modulation_mae_db": 0.35684784567268, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2458355399280818, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14914904307916413, "3000–6000 Hz_10ms_envelope_correlation": 0.9870334461906408, "3000–6000 Hz_10ms_modulation_mae_db": 0.5219777392063351, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7818430771475047, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0652328437854809, "3000–6000 Hz_40ms_envelope_correlation": 0.9974689935366178, "3000–6000 Hz_40ms_modulation_mae_db": 1.0184533285320372, "mr_stft_db": 6.021958836694753, "band_mae_db": 0.5002836520499555, "rms_gain_error_db": 0.05088077398004688, "output_peak": 0.03324638718415392}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5713302871543653, "全帯域_10ms_rms_envelope_nrmse": 0.14484732857324925, "全帯域_10ms_envelope_correlation": 0.983942966068325, "全帯域_10ms_modulation_mae_db": 0.584552814706089, "全帯域_40ms_log_rms_mae_db": 0.8100951721432065, "全帯域_40ms_rms_envelope_nrmse": 0.07036022717940842, "全帯域_40ms_envelope_correlation": 0.9960360707883198, "全帯域_40ms_modulation_mae_db": 0.9490419014943753, "300–1000 Hz_10ms_log_rms_mae_db": 2.3977541740399833, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26108973702359645, "300–1000 Hz_10ms_envelope_correlation": 0.9527937363643324, "300–1000 Hz_10ms_modulation_mae_db": 0.24444007636218226, "300–1000 Hz_40ms_log_rms_mae_db": 1.730023926649115, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13730617828704933, "300–1000 Hz_40ms_envelope_correlation": 0.9862733630801078, "300–1000 Hz_40ms_modulation_mae_db": 0.4823456010923084, "1000–3000 Hz_10ms_log_rms_mae_db": 1.504080212293048, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17019927398615575, "1000–3000 Hz_10ms_envelope_correlation": 0.9812037750078162, "1000–3000 Hz_10ms_modulation_mae_db": 0.6261662656516075, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8595049256692069, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0855759014630258, "1000–3000 Hz_40ms_envelope_correlation": 0.9951455157850825, "1000–3000 Hz_40ms_modulation_mae_db": 0.9414402009480044, "3000–6000 Hz_10ms_log_rms_mae_db": 1.273127408618329, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18260909513357895, "3000–6000 Hz_10ms_envelope_correlation": 0.9802065237281654, "3000–6000 Hz_10ms_modulation_mae_db": 0.8528253477837148, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7959471563070946, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09684310889146032, "3000–6000 Hz_40ms_envelope_correlation": 0.9943141349852516, "3000–6000 Hz_40ms_modulation_mae_db": 1.2132104959504308, "mr_stft_db": 6.040650905869218, "band_mae_db": 0.6017333093413704, "rms_gain_error_db": -0.047163770236387174, "output_peak": 0.033799875407571484}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6152933129815978, "全帯域_10ms_rms_envelope_nrmse": 0.1312358278035874, "全帯域_10ms_envelope_correlation": 0.9868202694080876, "全帯域_10ms_modulation_mae_db": 0.4470970736863567, "全帯域_40ms_log_rms_mae_db": 0.8688528275843236, "全帯域_40ms_rms_envelope_nrmse": 0.0728881167732376, "全帯域_40ms_envelope_correlation": 0.9957720248778584, "全帯域_40ms_modulation_mae_db": 0.718999049882744, "300–1000 Hz_10ms_log_rms_mae_db": 2.430498711777017, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25080755821022227, "300–1000 Hz_10ms_envelope_correlation": 0.9579158534073813, "300–1000 Hz_10ms_modulation_mae_db": 0.6015400322652851, "300–1000 Hz_40ms_log_rms_mae_db": 1.708029663723128, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14596462257568152, "300–1000 Hz_40ms_envelope_correlation": 0.985462563777229, "300–1000 Hz_40ms_modulation_mae_db": 0.7444767148158431, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5542073659712055, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1864005172537816, "1000–3000 Hz_10ms_envelope_correlation": 0.977398764679076, "1000–3000 Hz_10ms_modulation_mae_db": 0.21136217919761838, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9405901860464286, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1006068230851554, "1000–3000 Hz_40ms_envelope_correlation": 0.9932086900475757, "1000–3000 Hz_40ms_modulation_mae_db": 0.6928567956920211, "3000–6000 Hz_10ms_log_rms_mae_db": 1.268851334230873, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15447694844008414, "3000–6000 Hz_10ms_envelope_correlation": 0.9862189732611826, "3000–6000 Hz_10ms_modulation_mae_db": 0.5075370878904458, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8059059884250013, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09619142341022725, "3000–6000 Hz_40ms_envelope_correlation": 0.9949560790847025, "3000–6000 Hz_40ms_modulation_mae_db": 0.953887738534451, "mr_stft_db": 6.028013112066435, "band_mae_db": 0.3942554421515522, "rms_gain_error_db": -0.10630227664047168, "output_peak": 0.032716144054101004}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5676155013752207, "全帯域_10ms_rms_envelope_nrmse": 0.1481187119789634, "全帯域_10ms_envelope_correlation": 0.9832142960882263, "全帯域_10ms_modulation_mae_db": 0.4665210395835872, "全帯域_40ms_log_rms_mae_db": 0.8138722552593574, "全帯域_40ms_rms_envelope_nrmse": 0.07747636650399664, "全帯域_40ms_envelope_correlation": 0.9951510351465332, "全帯域_40ms_modulation_mae_db": 0.8558927123001167, "300–1000 Hz_10ms_log_rms_mae_db": 2.3105186876604464, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3068598192550923, "300–1000 Hz_10ms_envelope_correlation": 0.9355877538479113, "300–1000 Hz_10ms_modulation_mae_db": 0.22301601062307033, "300–1000 Hz_40ms_log_rms_mae_db": 1.6968186460166712, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1930859769269968, "300–1000 Hz_40ms_envelope_correlation": 0.9730789718876274, "300–1000 Hz_40ms_modulation_mae_db": 0.1944199454702447, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5448587720880445, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1704491310662834, "1000–3000 Hz_10ms_envelope_correlation": 0.9809788723606301, "1000–3000 Hz_10ms_modulation_mae_db": 0.48922994497850314, "1000–3000 Hz_40ms_log_rms_mae_db": 0.976585688578043, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10248110593208068, "1000–3000 Hz_40ms_envelope_correlation": 0.9929570461385222, "1000–3000 Hz_40ms_modulation_mae_db": 0.5845972848806404, "3000–6000 Hz_10ms_log_rms_mae_db": 1.234916363596929, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19183648039507045, "3000–6000 Hz_10ms_envelope_correlation": 0.9788468009378767, "3000–6000 Hz_10ms_modulation_mae_db": 0.6772982577444201, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7887447490839808, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09776955683744086, "3000–6000 Hz_40ms_envelope_correlation": 0.9944575465826402, "3000–6000 Hz_40ms_modulation_mae_db": 0.9538544770985441, "mr_stft_db": 6.0342031247548675, "band_mae_db": 0.5420004941554192, "rms_gain_error_db": -0.05206245565249201, "output_peak": 0.03682187189337933}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5458178098325375, "全帯域_10ms_rms_envelope_nrmse": 0.13933565519792598, "全帯域_10ms_envelope_correlation": 0.9851534696110869, "全帯域_10ms_modulation_mae_db": 0.5920221158002089, "全帯域_40ms_log_rms_mae_db": 0.8324574325525405, "全帯域_40ms_rms_envelope_nrmse": 0.06452248265307602, "全帯域_40ms_envelope_correlation": 0.9966578424244747, "全帯域_40ms_modulation_mae_db": 0.6725502559725284, "300–1000 Hz_10ms_log_rms_mae_db": 2.4001338659143885, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2775740719433375, "300–1000 Hz_10ms_envelope_correlation": 0.9514728358634544, "300–1000 Hz_10ms_modulation_mae_db": 0.80753945635951, "300–1000 Hz_40ms_log_rms_mae_db": 1.7543932104496416, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16113556416559552, "300–1000 Hz_40ms_envelope_correlation": 0.9844962447301552, "300–1000 Hz_40ms_modulation_mae_db": 0.770485220488235, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5127782700000978, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1664362360400858, "1000–3000 Hz_10ms_envelope_correlation": 0.9819544750253051, "1000–3000 Hz_10ms_modulation_mae_db": 0.5069638340161681, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8920356382727948, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08263194699945557, "1000–3000 Hz_40ms_envelope_correlation": 0.9954973387884104, "1000–3000 Hz_40ms_modulation_mae_db": 0.5627998031518524, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2610246141484185, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15684047777901167, "3000–6000 Hz_10ms_envelope_correlation": 0.9854318142695732, "3000–6000 Hz_10ms_modulation_mae_db": 0.4530840060231707, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8298502056240185, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06994128691959942, "3000–6000 Hz_40ms_envelope_correlation": 0.997132427080072, "3000–6000 Hz_40ms_modulation_mae_db": 0.5846390912650808, "mr_stft_db": 6.021342176009587, "band_mae_db": 0.5855603870918643, "rms_gain_error_db": -0.029052862226222102, "output_peak": 0.03495121979802746}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.278231818940552, "spectral_convergence": 0.6153744635247785, "spectral_convergence_status": "ok", "amplitude_floor": 9.167242110941195e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.885199756729999, "spectral_convergence": 0.6160039295476967, "spectral_convergence_status": "ok", "amplitude_floor": 5.84028801806317e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.953214683359677, "spectral_convergence": 0.6456352962503513, "spectral_convergence_status": "ok", "amplitude_floor": 2.8939654187001563e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.3843123087683508e-07, "output_power": 1.3067880076125314e-07, "delta_db": -0.2502894018865874, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.81286342317638e-08, "output_power": 1.410580064530741e-07, "delta_db": 3.160680589811373, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 9.335883160942139e-07, "output_power": 9.438105740375566e-07, "delta_db": 0.047294308245371744, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.7505166473017637e-06, "output_power": 1.764758244413392e-06, "delta_db": 0.0351897423055969, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.470519881244434e-07, "output_power": 5.91017938313475e-07, "delta_db": 0.3357206188651206, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.7292398267785066e-06, "output_power": 2.5780450303596042e-06, "delta_db": -0.24751201305553447, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.57439203602588e-07, "output_power": 9.339111676241833e-07, "delta_db": -0.10805637579709342, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.5978204357095255, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.025136467348846957, "pitch": null, "output_rms_dbfs": -51.49765604922326, "output_peak": 0.04170952340722672, "reference_rms_dbfs": -51.47251958187441, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.038882086343409}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.1370250428801243e-05, "log_rms_mae_db": 1.637245269148285, "rms_envelope_nrmse": 0.12173118268926647, "envelope_correlation": 0.9886892503851504, "rms_gain_error_db": -0.02513770797026922, "reference_mean_power": 7.130327548553108e-06, "output_mean_power": 7.089175205539757e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.4304416670730408e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2770281801289633e-06, "output_power": 1.2906074166337738e-06, "reference_active": true, "delta_db": 0.04593675576927611}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.124025700263392e-07, "output_power": 2.2149864375963327e-07, "reference_active": true, "delta_db": 0.18211304061000386}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.509706557401959e-07, "output_power": 9.997470804941713e-08, "reference_active": true, "delta_db": -1.7900239684727282}], "active_band_count": 3, "active_band_mae_db": 0.6726912549506694}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.27501987121069e-06, "log_rms_mae_db": 0.8843192840771208, "rms_envelope_nrmse": 0.06163244128666284, "envelope_correlation": 0.9969337697055167, "rms_gain_error_db": -0.025144793274277755, "reference_mean_power": 7.166117032249278e-06, "output_mean_power": 7.1247465082614235e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.171922661595567e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0939532041259814e-06, "output_power": 1.1212496528732182e-06, "reference_active": true, "delta_db": 0.10703576955201094}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.164609293708589e-07, "output_power": 1.0706771345323795e-07, "reference_active": true, "delta_db": -0.3652172355672498}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0690330771826293e-08, "output_power": 5.574078887947953e-09, "reference_active": true, "delta_db": -2.8281803218025643}], "active_band_count": 3, "active_band_mae_db": 1.100144442307275}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 6.556092771800097e-06, "log_rms_mae_db": 2.4311075316881494, "rms_envelope_nrmse": 0.24832489819722725, "envelope_correlation": 0.9595447724730573, "rms_gain_error_db": 0.3845205715587003, "reference_mean_power": 7.945163829144021e-07, "output_mean_power": 8.680703326484372e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.0791155245365873e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.4868570435085076e-07, "output_power": 1.6669115816852322e-07, "reference_active": true, "delta_db": 0.4964334955175703}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.530749650867304e-08, "output_power": 3.7105187788360626e-08, "reference_active": true, "delta_db": 0.21567709042135663}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.4918697573140088e-08, "output_power": 2.6189148152798938e-08, "reference_active": true, "delta_db": 0.21596033190009303}], "active_band_count": 3, "active_band_mae_db": 0.30935697261300665}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.158309417730701e-06, "log_rms_mae_db": 1.7927030465179492, "rms_envelope_nrmse": 0.14095486352061, "envelope_correlation": 0.9870934587949295, "rms_gain_error_db": 0.3844971018649185, "reference_mean_power": 7.985041710031799e-07, "output_mean_power": 8.724225835592527e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.7036737518374816e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3140926226909544e-07, "output_power": 1.517648499731957e-07, "reference_active": true, "delta_db": 0.625452197429688}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.929219128746953e-08, "output_power": 1.896791823047465e-08, "reference_active": true, "delta_db": -0.07361890664936069}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4692549483461402e-09, "output_power": 1.7022193958045841e-09, "reference_active": true, "delta_db": 0.6391837268007511}], "active_band_count": 3, "active_band_mae_db": 0.4460849436265999}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 7.401330296636983e-06, "log_rms_mae_db": 1.5956431500047703, "rms_envelope_nrmse": 0.18387391758235458, "envelope_correlation": 0.9793399030507569, "rms_gain_error_db": 0.2729960164792726, "reference_mean_power": 1.4849128654353035e-06, "output_mean_power": 1.5812501207507184e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.41811499304529e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.69138926350769e-07, "output_power": 2.7268034434866556e-07, "reference_active": true, "delta_db": 0.05677318177605681}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.521731226006148e-08, "output_power": 4.82414299128626e-08, "reference_active": true, "delta_db": 0.2811542805073419}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6338303134826183e-08, "output_power": 1.7169725121318652e-08, "reference_active": true, "delta_db": -1.858244493954516}], "active_band_count": 3, "active_band_mae_db": 0.7320573187459716}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 6.380552881753602e-06, "log_rms_mae_db": 0.9054725913181143, "rms_envelope_nrmse": 0.09101811755268896, "envelope_correlation": 0.9952681147465837, "rms_gain_error_db": 0.27299105147534714, "reference_mean_power": 1.4923708236731126e-06, "output_mean_power": 1.5891901149566637e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.994698288619123e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.551906678142862e-07, "output_power": 2.577937631106076e-07, "reference_active": true, "delta_db": 0.04407617691607787}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4359212852663977e-08, "output_power": 2.2828357259341992e-08, "reference_active": true, "delta_db": -0.2818858977505129}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5357702928828252e-09, "output_power": 9.546889575433425e-10, "reference_active": true, "delta_db": -2.0646436326905246}], "active_band_count": 3, "active_band_mae_db": 0.7968685691190385}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0774952268311018e-05, "log_rms_mae_db": 1.2947800063776325, "rms_envelope_nrmse": 0.15126018401020913, "envelope_correlation": 0.98666809922525, "rms_gain_error_db": -0.26079927841580836, "reference_mean_power": 1.995223201702535e-06, "output_mean_power": 1.8789341443284892e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.579487211503375e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.151593028482198e-07, "output_power": 6.981887202962112e-07, "reference_active": true, "delta_db": -0.10429964130964073}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2474197679576555e-07, "output_power": 1.1752664879387203e-07, "reference_active": true, "delta_db": -0.2587626940136365}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.137663053230787e-08, "output_power": 4.963524965729775e-08, "reference_active": true, "delta_db": -2.1470949290978285}], "active_band_count": 3, "active_band_mae_db": 0.8367190881403687}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 7.143885674653834e-06, "log_rms_mae_db": 0.8959413768075107, "rms_envelope_nrmse": 0.08594727902667681, "envelope_correlation": 0.9959386547796276, "rms_gain_error_db": -0.2607993040357229, "reference_mean_power": 2.0052568878051223e-06, "output_mean_power": 1.88838301860423e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.5118360803946574e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.45069205976456e-07, "output_power": 6.360127446299473e-07, "reference_active": true, "delta_db": -0.061404919648033116}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.385509447185785e-08, "output_power": 6.624629711270651e-08, "reference_active": true, "delta_db": -1.023678444909466}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.733755662328774e-09, "output_power": 2.2984830092250654e-09, "reference_active": true, "delta_db": -3.9699788430464134}], "active_band_count": 3, "active_band_mae_db": 1.6850207358679707}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5313317099663643, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "37742f160c64015d4ac147f39805e1a49e7dc993a62d3638cde2db0c02c6858b", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9795440623291591, "standard_deviation": 0.0029116398994481446, "minimum": 0.9737448881768741, "maximum": 0.9827301989964906, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.5463270854255176, "standard_deviation": 0.030312474660187508, "minimum": 1.504080212293048, "maximum": 1.5956431500047703, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.49186179873061775, "standard_deviation": 0.22516288635620277, "minimum": 0.11901157339682737, "maximum": 0.7385093578280868, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17859579965075317, "standard_deviation": 0.014994850229085059, "minimum": 0.16277024794145098, "maximum": 0.20941099741818817, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9944296515181446, "standard_deviation": 0.0009774377210995807, "minimum": 0.9929570461385222, "maximum": 0.9954973387884104, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.9130560572122419, "standard_deviation": 0.04072187524889736, "minimum": 0.8595049256692069, "maximum": 0.976585688578043, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6664672583910634, "standard_deviation": 0.21716497379036884, "minimum": 0.35684784567268, "maximum": 0.9446289925453778, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09343069249152347, "standard_deviation": 0.008582525402599855, "minimum": 0.08263194699945557, "maximum": 0.10629721789799354, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9834375038084446, "standard_deviation": 0.003253600888478064, "minimum": 0.9788468009378767, "maximum": 0.9870334461906408, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2621722498155623, "standard_deviation": 0.01870143279028782, "minimum": 1.234916363596929, "maximum": 1.2947800063776325, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7003811766367977, "standard_deviation": 0.267917173671645, "minimum": 0.4530840060231707, "maximum": 1.2426418214048212, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16880880252607874, "standard_deviation": 0.01744180816004337, "minimum": 0.14914904307916413, "maximum": 0.19183648039507045, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9953999420188324, "standard_deviation": 0.0013359256828203918, "minimum": 0.9937909293462764, "maximum": 0.9974689935366178, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8142997664367988, "standard_deviation": 0.036092044037669316, "minimum": 0.7818430771475047, "maximum": 0.8959413768075107, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.1315060628911737, "standard_deviation": 0.4651101327124337, "minimum": 0.5846390912650808, "maximum": 1.935533819126037, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09009609581497045, "standard_deviation": 0.015692608136516652, "minimum": 0.0652328437854809, "maximum": 0.11248996886078805, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.952106651137715, "standard_deviation": 0.007964117854403215, "minimum": 0.9355877538479113, "maximum": 0.9603536282914195, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.398391911501428, "standard_deviation": 0.0434581765837821, "minimum": 2.3105186876604464, "maximum": 2.4311075316881494, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4897728756327484, "standard_deviation": 0.2918699240138436, "minimum": 0.22301601062307033, "maximum": 1.0039775771179535, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.26664002913004997, "standard_deviation": 0.020109936726481304, "minimum": 0.2463453652465608, "maximum": 0.3068598192550923, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9825901924655465, "standard_deviation": 0.005176545460904852, "minimum": 0.9730789718876274, "maximum": 0.9870934587949295, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.7507345362723086, "standard_deviation": 0.045390267502353886, "minimum": 1.6968186460166712, "maximum": 1.8272623744580447, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5827321278891064, "standard_deviation": 0.2780621261837277, "minimum": 0.1944199454702447, "maximum": 1.0927210871966648, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15800259397436267, "standard_deviation": 0.01984652044409891, "minimum": 0.13730617828704933, "maximum": 0.1930859769269968, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.5436594511032616, "standard_deviation": 0.06878549335547351, "minimum": 0.3942554421515522, "maximum": 0.6017333093413704, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.032443512611115, "standard_deviation": 0.007672087601498344, "minimum": 6.021342176009587, "maximum": 6.040650905869218, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.035472937607270175, "standard_deviation": 0.0032169064122438825, "minimum": 0.0324396607862574, "maximum": 0.04170952340722672, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.031055545285549775, "standard_deviation": 0.07872974992657657, "minimum": -0.14231887980989394, "maximum": 0.10271157564986878, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9854673208256312, "standard_deviation": 0.0017620611422904451, "minimum": 0.9832142960882263, "maximum": 0.9886892503851504, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.5927761709910988, "standard_deviation": 0.03423523680530324, "minimum": 1.5458178098325375, "maximum": 1.639586957043008, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.49715621558481304, "standard_deviation": 0.1443808735749515, "minimum": 0.2289609081514469, "maximum": 0.6726912549506694, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.13796996283528107, "standard_deviation": 0.00869845367496358, "minimum": 0.12173118268926647, "maximum": 0.1481187119789634, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9960021288979627, "standard_deviation": 0.0009451511795877733, "minimum": 0.9942009769335142, "maximum": 0.9969337697055167, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8492298455232632, "standard_deviation": 0.03528042396299774, "minimum": 0.8100951721432065, "maximum": 0.9073270886955219, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7822445623286467, "standard_deviation": 0.18374771305983287, "minimum": 0.5019298598941749, "maximum": 1.100144442307275, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.07054450055751638, "standard_deviation": 0.008230012687249637, "minimum": 0.06163244128666284, "maximum": 0.08630434293732614, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 1.7627079486846924, "predicted_mos": 1.7627079486846924, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "f8873b402610779b0f246fe178a2bd3f7fcb8b20ae9ab67303047b5145102f0e", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 9.811951799783856}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6551773644327519, "全帯域_10ms_rms_envelope_nrmse": 0.12111307911912678, "全帯域_10ms_envelope_correlation": 0.9887881033268743, "全帯域_10ms_modulation_mae_db": 0.6518959235444824, "全帯域_40ms_log_rms_mae_db": 0.9099283257814753, "全帯域_40ms_rms_envelope_nrmse": 0.06167505731550127, "全帯域_40ms_envelope_correlation": 0.9969477526663628, "全帯域_40ms_modulation_mae_db": 1.1019414943720411, "300–1000 Hz_10ms_log_rms_mae_db": 2.3350794237723944, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25142500407587626, "300–1000 Hz_10ms_envelope_correlation": 0.9583839190071055, "300–1000 Hz_10ms_modulation_mae_db": 0.27356917488463867, "300–1000 Hz_40ms_log_rms_mae_db": 1.6799543875149263, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14128168508096614, "300–1000 Hz_40ms_envelope_correlation": 0.9869361762511522, "300–1000 Hz_40ms_modulation_mae_db": 0.3294076332478685, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5630108935358455, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1791391208824223, "1000–3000 Hz_10ms_envelope_correlation": 0.9799231335033374, "1000–3000 Hz_10ms_modulation_mae_db": 0.6779558277127822, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8663351657963341, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08548882288882935, "1000–3000 Hz_40ms_envelope_correlation": 0.9955356653362357, "1000–3000 Hz_40ms_modulation_mae_db": 0.9162435245639139, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2344654302755884, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1515872715667208, "3000–6000 Hz_10ms_envelope_correlation": 0.986683335040179, "3000–6000 Hz_10ms_modulation_mae_db": 0.8674898670263311, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7986899052481136, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08508948868976066, "3000–6000 Hz_40ms_envelope_correlation": 0.9961439676648293, "3000–6000 Hz_40ms_modulation_mae_db": 1.6996714364221581, "mr_stft_db": 6.036480925381279, "band_mae_db": 0.6025931122406909, "rms_gain_error_db": -0.060158484109058274, "output_peak": 0.04175637797148717}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.587646532946292, "全帯域_10ms_rms_envelope_nrmse": 0.1355723238571248, "全帯域_10ms_envelope_correlation": 0.9859581937684775, "全帯域_10ms_modulation_mae_db": 0.5923138576492241, "全帯域_40ms_log_rms_mae_db": 0.8282115628613677, "全帯域_40ms_rms_envelope_nrmse": 0.06474926795441774, "全帯域_40ms_envelope_correlation": 0.9967846480027456, "全帯域_40ms_modulation_mae_db": 0.8837067079719434, "300–1000 Hz_10ms_log_rms_mae_db": 2.2959928566277, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24165551356484577, "300–1000 Hz_10ms_envelope_correlation": 0.9629782290700323, "300–1000 Hz_10ms_modulation_mae_db": 1.0668435428689411, "300–1000 Hz_40ms_log_rms_mae_db": 1.5842931248928125, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13861902284087002, "300–1000 Hz_40ms_envelope_correlation": 0.9884304052278832, "300–1000 Hz_40ms_modulation_mae_db": 1.1342820641154943, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5439870377785496, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16369076953057835, "1000–3000 Hz_10ms_envelope_correlation": 0.9825200105776636, "1000–3000 Hz_10ms_modulation_mae_db": 0.47942423259271133, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8870277131560353, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08819384834185877, "1000–3000 Hz_40ms_envelope_correlation": 0.9950565983080466, "1000–3000 Hz_40ms_modulation_mae_db": 0.93545130494429, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2537525560786347, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18495228577416195, "3000–6000 Hz_10ms_envelope_correlation": 0.9800015401063961, "3000–6000 Hz_10ms_modulation_mae_db": 1.297431060227633, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7887219151085912, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09805318345357968, "3000–6000 Hz_40ms_envelope_correlation": 0.9949462311374305, "3000–6000 Hz_40ms_modulation_mae_db": 2.069349354382694, "mr_stft_db": 6.041648036469773, "band_mae_db": 0.6072913225573338, "rms_gain_error_db": -0.1430482677167251, "output_peak": 0.03202105014367454}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6790682441964144, "全帯域_10ms_rms_envelope_nrmse": 0.14960304358047483, "全帯域_10ms_envelope_correlation": 0.983293033443839, "全帯域_10ms_modulation_mae_db": 0.2940431213075276, "全帯域_40ms_log_rms_mae_db": 0.9372915115993251, "全帯域_40ms_rms_envelope_nrmse": 0.09174435438571929, "全帯域_40ms_envelope_correlation": 0.993416495472924, "全帯域_40ms_modulation_mae_db": 0.8325933814033523, "300–1000 Hz_10ms_log_rms_mae_db": 2.269241949826014, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2684530898225367, "300–1000 Hz_10ms_envelope_correlation": 0.9494771159026468, "300–1000 Hz_10ms_modulation_mae_db": 0.42052443643054077, "300–1000 Hz_40ms_log_rms_mae_db": 1.6501780066816085, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16866713931693272, "300–1000 Hz_40ms_envelope_correlation": 0.9787658537328778, "300–1000 Hz_40ms_modulation_mae_db": 0.25404916693302826, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5143209841036909, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18240061260972926, "1000–3000 Hz_10ms_envelope_correlation": 0.9781487567919632, "1000–3000 Hz_10ms_modulation_mae_db": 0.13746410309644488, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8289368769647514, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09584712074094066, "1000–3000 Hz_40ms_envelope_correlation": 0.9938502684338468, "1000–3000 Hz_40ms_modulation_mae_db": 0.5001556846456781, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2421957733345463, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19093280584499472, "3000–6000 Hz_10ms_envelope_correlation": 0.9811553834169546, "3000–6000 Hz_10ms_modulation_mae_db": 0.6312971762011519, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7840923821142295, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12106088495168242, "3000–6000 Hz_40ms_envelope_correlation": 0.993129541900023, "3000–6000 Hz_40ms_modulation_mae_db": 0.9339151069538737, "mr_stft_db": 6.0413788524617935, "band_mae_db": 0.5911897990308183, "rms_gain_error_db": 0.09326225802234724, "output_peak": 0.03813186283943337}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5989114440607415, "全帯域_10ms_rms_envelope_nrmse": 0.1419003763365473, "全帯域_10ms_envelope_correlation": 0.9848132802204371, "全帯域_10ms_modulation_mae_db": 0.4085838530479256, "全帯域_40ms_log_rms_mae_db": 0.843891784437963, "全帯域_40ms_rms_envelope_nrmse": 0.0703603459897908, "全帯域_40ms_envelope_correlation": 0.9960705087817703, "全帯域_40ms_modulation_mae_db": 0.687171837943811, "300–1000 Hz_10ms_log_rms_mae_db": 2.3536468117562213, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27527983413702045, "300–1000 Hz_10ms_envelope_correlation": 0.9497174071911487, "300–1000 Hz_10ms_modulation_mae_db": 0.24238077715942705, "300–1000 Hz_40ms_log_rms_mae_db": 1.7149583676961304, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17422680467162155, "300–1000 Hz_40ms_envelope_correlation": 0.9793373059205501, "300–1000 Hz_40ms_modulation_mae_db": 0.5473655884930347, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5240775641610997, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21358368093010235, "1000–3000 Hz_10ms_envelope_correlation": 0.973262008468795, "1000–3000 Hz_10ms_modulation_mae_db": 0.7269918475156661, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8158862695947999, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10635622300333093, "1000–3000 Hz_40ms_envelope_correlation": 0.994257353102282, "1000–3000 Hz_40ms_modulation_mae_db": 0.4047824143805084, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2213310548362333, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15864129743332492, "3000–6000 Hz_10ms_envelope_correlation": 0.9852283532410954, "3000–6000 Hz_10ms_modulation_mae_db": 0.5734320974866373, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7559879693974993, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07290996120895649, "3000–6000 Hz_40ms_envelope_correlation": 0.9967844968640918, "3000–6000 Hz_40ms_modulation_mae_db": 1.0008657149881772, "mr_stft_db": 6.02089102604279, "band_mae_db": 0.5281921038137128, "rms_gain_error_db": 0.06249382592682333, "output_peak": 0.033301849486586654}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5857297254877576, "全帯域_10ms_rms_envelope_nrmse": 0.1467360973343724, "全帯域_10ms_envelope_correlation": 0.9835004997834729, "全帯域_10ms_modulation_mae_db": 0.5494538891232517, "全帯域_40ms_log_rms_mae_db": 0.8192976981619794, "全帯域_40ms_rms_envelope_nrmse": 0.07279542580920546, "全帯域_40ms_envelope_correlation": 0.9957739590033461, "全帯域_40ms_modulation_mae_db": 0.8228402209621118, "300–1000 Hz_10ms_log_rms_mae_db": 2.28634830543553, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26412388273026605, "300–1000 Hz_10ms_envelope_correlation": 0.9512113210778248, "300–1000 Hz_10ms_modulation_mae_db": 0.33602074195899895, "300–1000 Hz_40ms_log_rms_mae_db": 1.5834613317256716, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1375952032068733, "300–1000 Hz_40ms_envelope_correlation": 0.9859519520411366, "300–1000 Hz_40ms_modulation_mae_db": 0.5782045423379025, "1000–3000 Hz_10ms_log_rms_mae_db": 1.489074645077577, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1684437116672907, "1000–3000 Hz_10ms_envelope_correlation": 0.9814518917403624, "1000–3000 Hz_10ms_modulation_mae_db": 0.5906033925667071, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8140208658716377, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08309703688035114, "1000–3000 Hz_40ms_envelope_correlation": 0.9953944198120288, "1000–3000 Hz_40ms_modulation_mae_db": 0.9311405975886705, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2216171878620752, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18088952738706765, "3000–6000 Hz_10ms_envelope_correlation": 0.9805759661596855, "3000–6000 Hz_10ms_modulation_mae_db": 0.7323184758399038, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7351189033070962, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09582819970828525, "3000–6000 Hz_40ms_envelope_correlation": 0.9944286346985846, "3000–6000 Hz_40ms_modulation_mae_db": 1.047457862054921, "mr_stft_db": 6.038038695834294, "band_mae_db": 0.5663285513189708, "rms_gain_error_db": -0.07263569278559764, "output_peak": 0.03392224764699451}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6333249735530915, "全帯域_10ms_rms_envelope_nrmse": 0.1315243361218731, "全帯域_10ms_envelope_correlation": 0.9867779630440158, "全帯域_10ms_modulation_mae_db": 0.41392121987818636, "全帯域_40ms_log_rms_mae_db": 0.8626136244585726, "全帯域_40ms_rms_envelope_nrmse": 0.0731885104389241, "全帯域_40ms_envelope_correlation": 0.9957754162903635, "全帯域_40ms_modulation_mae_db": 0.77511826540038, "300–1000 Hz_10ms_log_rms_mae_db": 2.299500935945658, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24444275791565237, "300–1000 Hz_10ms_envelope_correlation": 0.9601838432325264, "300–1000 Hz_10ms_modulation_mae_db": 0.5781446625669855, "300–1000 Hz_40ms_log_rms_mae_db": 1.5632421761047035, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14055943789121556, "300–1000 Hz_40ms_envelope_correlation": 0.9866783876291771, "300–1000 Hz_40ms_modulation_mae_db": 0.8028413074070032, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5375358699053683, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18622329165843454, "1000–3000 Hz_10ms_envelope_correlation": 0.9773557472777868, "1000–3000 Hz_10ms_modulation_mae_db": 0.31734870716495567, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8680546963906511, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1005010360688219, "1000–3000 Hz_40ms_envelope_correlation": 0.9931861093045045, "1000–3000 Hz_40ms_modulation_mae_db": 0.5644952172590488, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2712060707836288, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1586308728949899, "3000–6000 Hz_10ms_envelope_correlation": 0.9854256735945734, "3000–6000 Hz_10ms_modulation_mae_db": 0.518141831520356, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8086540975854323, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09642511961346216, "3000–6000 Hz_40ms_envelope_correlation": 0.9949381454163769, "3000–6000 Hz_40ms_modulation_mae_db": 0.8491893550417142, "mr_stft_db": 6.032693014361847, "band_mae_db": 0.4306849058270907, "rms_gain_error_db": -0.1258168273058945, "output_peak": 0.032550744590041474}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6020249655281258, "全帯域_10ms_rms_envelope_nrmse": 0.14914073618127358, "全帯域_10ms_envelope_correlation": 0.9829722363901497, "全帯域_10ms_modulation_mae_db": 0.4785022863229571, "全帯域_40ms_log_rms_mae_db": 0.822248805281995, "全帯域_40ms_rms_envelope_nrmse": 0.0765439724659324, "全帯域_40ms_envelope_correlation": 0.9952728412745911, "全帯域_40ms_modulation_mae_db": 0.9687304378906791, "300–1000 Hz_10ms_log_rms_mae_db": 2.2262928388410637, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.30251448130585934, "300–1000 Hz_10ms_envelope_correlation": 0.9372607062048539, "300–1000 Hz_10ms_modulation_mae_db": 0.14423043395517127, "300–1000 Hz_40ms_log_rms_mae_db": 1.57806456011448, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1856593765958414, "300–1000 Hz_40ms_envelope_correlation": 0.9750455464882896, "300–1000 Hz_40ms_modulation_mae_db": 0.31165290286290603, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5300036913969968, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16804767622274805, "1000–3000 Hz_10ms_envelope_correlation": 0.9814782978460989, "1000–3000 Hz_10ms_modulation_mae_db": 0.4277706926734122, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8936491134544723, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09792690825090232, "1000–3000 Hz_40ms_envelope_correlation": 0.9935943304753232, "1000–3000 Hz_40ms_modulation_mae_db": 0.5182448416643399, "3000–6000 Hz_10ms_log_rms_mae_db": 1.225788288968595, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19710270645287942, "3000–6000 Hz_10ms_envelope_correlation": 0.977728103964101, "3000–6000 Hz_10ms_modulation_mae_db": 0.6790378298336218, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7545131957355053, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09533553150984495, "3000–6000 Hz_40ms_envelope_correlation": 0.9947863866958708, "3000–6000 Hz_40ms_modulation_mae_db": 0.987507952619282, "mr_stft_db": 6.030893349330071, "band_mae_db": 0.4628115417919795, "rms_gain_error_db": -0.060433575059676566, "output_peak": 0.036570504959887506}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5661693063230255, "全帯域_10ms_rms_envelope_nrmse": 0.14053493680591467, "全帯域_10ms_envelope_correlation": 0.9848863562015497, "全帯域_10ms_modulation_mae_db": 0.4825249871251123, "全帯域_40ms_log_rms_mae_db": 0.8457666192899701, "全帯域_40ms_rms_envelope_nrmse": 0.06524158001264646, "全帯域_40ms_envelope_correlation": 0.9965963908128737, "全帯域_40ms_modulation_mae_db": 0.5101202921946634, "300–1000 Hz_10ms_log_rms_mae_db": 2.313701201609776, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2791521202120779, "300–1000 Hz_10ms_envelope_correlation": 0.9513300224836829, "300–1000 Hz_10ms_modulation_mae_db": 0.9153352727813996, "300–1000 Hz_40ms_log_rms_mae_db": 1.6221334210459992, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16300816187521625, "300–1000 Hz_40ms_envelope_correlation": 0.9844077494742637, "300–1000 Hz_40ms_modulation_mae_db": 0.8971808161757, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4779341109881297, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1692914953389418, "1000–3000 Hz_10ms_envelope_correlation": 0.98126912785444, "1000–3000 Hz_10ms_modulation_mae_db": 0.3696522682625374, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8417674924332765, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08241808204898483, "1000–3000 Hz_40ms_envelope_correlation": 0.995523964371222, "1000–3000 Hz_40ms_modulation_mae_db": 0.47984187670104567, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2231328911968726, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15905829832943671, "3000–6000 Hz_10ms_envelope_correlation": 0.9850122338477374, "3000–6000 Hz_10ms_modulation_mae_db": 0.44243468240675266, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7950953559009122, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07011722123367532, "3000–6000 Hz_40ms_envelope_correlation": 0.9971362769916841, "3000–6000 Hz_40ms_modulation_mae_db": 0.5804579841231875, "mr_stft_db": 6.025074486188042, "band_mae_db": 0.582802635911294, "rms_gain_error_db": -0.04031384860998802, "output_peak": 0.03537546984835849}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.285210711692313, "spectral_convergence": 0.6141570696387517, "spectral_convergence_status": "ok", "amplitude_floor": 9.167242110941195e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.886891770022755, "spectral_convergence": 0.615703676232407, "spectral_convergence_status": "ok", "amplitude_floor": 5.84028801806317e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.93734029442877, "spectral_convergence": 0.6431388021961212, "spectral_convergence_status": "ok", "amplitude_floor": 2.8939654187001563e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.3843123087683508e-07, "output_power": 1.2259731259153694e-07, "delta_db": -0.5275313020720969, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.81286342317638e-08, "output_power": 1.382326078102843e-07, "delta_db": 3.0728081846024007, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 9.335883160942139e-07, "output_power": 9.436151796546189e-07, "delta_db": 0.04639510781386451, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.7505166473017637e-06, "output_power": 1.739562868903202e-06, "delta_db": -0.027261161888184563, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.470519881244434e-07, "output_power": 5.700378896325895e-07, "delta_db": 0.17875122879688676, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.7292398267785066e-06, "output_power": 2.5819564589571936e-06, "delta_db": -0.24092785921304893, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.57439203602588e-07, "output_power": 9.303867399936158e-07, "delta_db": -0.12447694129835359, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.6025931122406909, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.060158484109058274, "pitch": null, "output_rms_dbfs": -51.53267806598347, "output_peak": 0.04175637797148717, "reference_rms_dbfs": -51.47251958187441, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.036480925381279}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.1370250428801243e-05, "log_rms_mae_db": 1.6551773644327519, "rms_envelope_nrmse": 0.12111307911912678, "envelope_correlation": 0.9887881033268743, "rms_gain_error_db": -0.060160861079605, "reference_mean_power": 7.130327548553108e-06, "output_mean_power": 7.0322353107342486e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.4304416670730408e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2770281801289633e-06, "output_power": 1.2769276584859976e-06, "reference_active": true, "delta_db": -0.0003418696143005247}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.124025700263392e-07, "output_power": 2.2083329749434195e-07, "reference_active": true, "delta_db": 0.16904790094686387}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.509706557401959e-07, "output_power": 1.0006051674742154e-07, "reference_active": true, "delta_db": -1.7862980000722828}], "active_band_count": 3, "active_band_mae_db": 0.6518959235444824}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.27501987121069e-06, "log_rms_mae_db": 0.9099283257814753, "rms_envelope_nrmse": 0.06167505731550127, "envelope_correlation": 0.9969477526663628, "rms_gain_error_db": -0.06016748772313771, "reference_mean_power": 7.166117032249278e-06, "output_mean_power": 7.067521652965355e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.171922661595567e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0939532041259814e-06, "output_power": 1.1071904169022073e-06, "reference_active": true, "delta_db": 0.052235735230549196}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.164609293708589e-07, "output_power": 1.0840883589436377e-07, "reference_active": true, "delta_db": -0.31115570557245437}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0690330771826293e-08, "output_power": 5.429349995953765e-09, "reference_active": true, "delta_db": -2.94243304231312}], "active_band_count": 3, "active_band_mae_db": 1.1019414943720411}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 6.556092771800097e-06, "log_rms_mae_db": 2.3350794237723944, "rms_envelope_nrmse": 0.25142500407587626, "envelope_correlation": 0.9583839190071055, "rms_gain_error_db": 0.36937007624016166, "reference_mean_power": 7.945163829144021e-07, "output_mean_power": 8.650473188489969e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.0791155245365873e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.4868570435085076e-07, "output_power": 1.680634730028333e-07, "reference_active": true, "delta_db": 0.5320411940025751}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.530749650867304e-08, "output_power": 3.7041123251712e-08, "reference_active": true, "delta_db": 0.20817223110048294}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.4918697573140088e-08, "output_power": 2.4461096972536278e-08, "reference_active": true, "delta_db": -0.08049409955085794}], "active_band_count": 3, "active_band_mae_db": 0.27356917488463867}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.158309417730701e-06, "log_rms_mae_db": 1.6799543875149263, "rms_envelope_nrmse": 0.14128168508096614, "envelope_correlation": 0.9869361762511522, "rms_gain_error_db": 0.3693486594116086, "reference_mean_power": 7.985041710031799e-07, "output_mean_power": 8.693848242013929e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.7036737518374816e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3140926226909544e-07, "output_power": 1.5284828912603142e-07, "reference_active": true, "delta_db": 0.6563460473229142}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.929219128746953e-08, "output_power": 1.853517875728977e-08, "reference_active": true, "delta_db": -0.17384780606291925}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4692549483461402e-09, "output_power": 1.523702102086279e-09, "reference_active": true, "delta_db": 0.1580290463577719}], "active_band_count": 3, "active_band_mae_db": 0.3294076332478685}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 7.401330296636983e-06, "log_rms_mae_db": 1.5630108935358455, "rms_envelope_nrmse": 0.1791391208824223, "envelope_correlation": 0.9799231335033374, "rms_gain_error_db": 0.19138189201429417, "reference_mean_power": 1.4849128654353035e-06, "output_mean_power": 1.5518121905898507e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.41811499304529e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.69138926350769e-07, "output_power": 2.720615243477009e-07, "reference_active": true, "delta_db": 0.04690611472068235}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.521731226006148e-08, "output_power": 4.623072542537453e-08, "reference_active": true, "delta_db": 0.09625964092731475}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6338303134826183e-08, "output_power": 1.7041884556583524e-08, "reference_active": true, "delta_db": -1.8907017274903493}], "active_band_count": 3, "active_band_mae_db": 0.6779558277127822}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 6.380552881753602e-06, "log_rms_mae_db": 0.8663351657963341, "rms_envelope_nrmse": 0.08548882288882935, "envelope_correlation": 0.9955356653362357, "rms_gain_error_db": 0.1913778227210504, "reference_mean_power": 1.4923708236731126e-06, "output_mean_power": 1.5596046886053343e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.994698288619123e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.551906678142862e-07, "output_power": 2.571637702242261e-07, "reference_active": true, "delta_db": 0.03344995813176914}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4359212852663977e-08, "output_power": 2.1823129859295276e-08, "reference_active": true, "delta_db": -0.4774621337367791}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5357702928828252e-09, "output_power": 9.17369748086424e-10, "reference_active": true, "delta_db": -2.2378184818231937}], "active_band_count": 3, "active_band_mae_db": 0.9162435245639139}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0774952268311018e-05, "log_rms_mae_db": 1.2344654302755884, "rms_envelope_nrmse": 0.1515872715667208, "envelope_correlation": 0.986683335040179, "rms_gain_error_db": -0.2909122332003897, "reference_mean_power": 1.995223201702535e-06, "output_mean_power": 1.8659511208774515e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.579487211503375e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.151593028482198e-07, "output_power": 6.848568010588611e-07, "reference_active": true, "delta_db": -0.18803019413418948}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2474197679576555e-07, "output_power": 1.1987489207985992e-07, "reference_active": true, "delta_db": -0.17284392872670684}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.137663053230787e-08, "output_power": 4.8566874522320564e-08, "reference_active": true, "delta_db": -2.241595478218097}], "active_band_count": 3, "active_band_mae_db": 0.8674898670263311}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 7.143885674653834e-06, "log_rms_mae_db": 0.7986899052481136, "rms_envelope_nrmse": 0.08508948868976066, "envelope_correlation": 0.9961439676648293, "rms_gain_error_db": -0.29091210364877584, "reference_mean_power": 2.0052568878051223e-06, "output_mean_power": 1.875334772506143e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.5118360803946574e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.45069205976456e-07, "output_power": 6.21705518357523e-07, "reference_active": true, "delta_db": -0.16021587981812008}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.385509447185785e-08, "output_power": 6.840727353505594e-08, "reference_active": true, "delta_db": -0.8842717118484908}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.733755662328774e-09, "output_power": 2.254169193721527e-09, "reference_active": true, "delta_db": -4.054526717599863}], "active_band_count": 3, "active_band_mae_db": 1.6996714364221581}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5311617915211535, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "c0fadbb4b5f3c08e970598d17fadae772029a5e490aa00602a6fa94f99694371", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9794261217575558, "standard_deviation": 0.0030576698709940424, "minimum": 0.973262008468795, "maximum": 0.9825200105776636, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.5224930996184072, "standard_deviation": 0.02817791815249915, "minimum": 1.4779341109881297, "maximum": 1.5630108935358455, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4659013839481521, "standard_deviation": 0.19622347420197797, "minimum": 0.13746410309644488, "maximum": 0.7269918475156661, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1788525448550309, "standard_deviation": 0.016122888457300158, "minimum": 0.16369076953057835, "maximum": 0.21358368093010235, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9945498386429362, "standard_deviation": 0.0009440488598819345, "minimum": 0.9931861093045045, "maximum": 0.9955356653362357, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8519597742077447, "standard_deviation": 0.03118620266889131, "minimum": 0.8140208658716377, "maximum": 0.8936491134544723, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6562944327184369, "standard_deviation": 0.22906655243103016, "minimum": 0.4047824143805084, "maximum": 0.93545130494429, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09247863477800249, "standard_deviation": 0.008899620572302742, "minimum": 0.08241808204898483, "maximum": 0.10635622300333093, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9827263236713403, "standard_deviation": 0.00324980225139199, "minimum": 0.977728103964101, "maximum": 0.986683335040179, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2366861566670218, "standard_deviation": 0.018061329880550203, "minimum": 1.2213310548362333, "maximum": 1.2712060707836288, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7176978775677985, "standard_deviation": 0.26835655998021973, "minimum": 0.44243468240675266, "maximum": 1.297431060227633, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17272438321044703, "standard_deviation": 0.017617119036873265, "minimum": 0.1515872715667208, "maximum": 0.19710270645287942, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9952867101711114, "standard_deviation": 0.001324309427524213, "minimum": 0.993129541900023, "maximum": 0.9971362769916841, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7776092155496724, "standard_deviation": 0.0258727652568458, "minimum": 0.7351189033070962, "maximum": 0.8086540975854323, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.146051845823251, "standard_deviation": 0.48813561398818545, "minimum": 0.5804579841231875, "maximum": 2.069349354382694, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09185244879615587, "standard_deviation": 0.016113016984666682, "minimum": 0.07011722123367532, "maximum": 0.12106088495168242, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9525678205212277, "standard_deviation": 0.008067259264612357, "minimum": 0.9372607062048539, "maximum": 0.9629782290700323, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.2974755404767944, "standard_deviation": 0.03932786076474998, "minimum": 2.2262928388410637, "maximum": 2.3536468117562213, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.49713113032576284, "standard_deviation": 0.33322490578032576, "minimum": 0.14423043395517127, "maximum": 1.0668435428689411, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2658808354705169, "standard_deviation": 0.020254184785191715, "minimum": 0.24165551356484577, "maximum": 0.30251448130585934, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9831941720956663, "standard_deviation": 0.004833279427708916, "minimum": 0.9750455464882896, "maximum": 0.9884304052278832, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.6220356719720415, "standard_deviation": 0.054881455322643734, "minimum": 1.5632421761047035, "maximum": 1.7149583676961304, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6068730026966171, "standard_deviation": 0.31483150407830046, "minimum": 0.25404916693302826, "maximum": 1.1342820641154943, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1562021039349421, "standard_deviation": 0.018962420265298503, "minimum": 0.1375952032068733, "maximum": 0.1856593765958414, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.5464867465614863, "standard_deviation": 0.06687122467965975, "minimum": 0.4306849058270907, "maximum": 0.6072913225573338, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.033387298258736, "standard_deviation": 0.007514483517627953, "minimum": 6.02089102604279, "maximum": 6.041648036469773, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.035453763435807965, "standard_deviation": 0.003280586209366418, "minimum": 0.03202105014367454, "maximum": 0.04175637797148717, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.043331326454721195, "standard_deviation": 0.08284890517671076, "minimum": -0.1430482677167251, "maximum": 0.09326225802234724, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9851237082723521, "standard_deviation": 0.0019866851420458635, "minimum": 0.9829722363901497, "maximum": 0.9887881033268743, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.6135065695660251, "standard_deviation": 0.038644004217652975, "minimum": 1.5661693063230255, "maximum": 1.6790682441964144, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.48390489224983335, "standard_deviation": 0.11396723781414286, "minimum": 0.2940431213075276, "maximum": 0.6518959235444824, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.1395156161670884, "standard_deviation": 0.009793029969100912, "minimum": 0.12111307911912678, "maximum": 0.14960304358047483, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9958297515381221, "standard_deviation": 0.0011305796624984591, "minimum": 0.993416495472924, "maximum": 0.9969477526663628, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.858656241484081, "standard_deviation": 0.043117115537905926, "minimum": 0.8192976981619794, "maximum": 0.9372915115993251, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.8227778297673727, "standard_deviation": 0.17786766649654537, "minimum": 0.5101202921946634, "maximum": 1.1019414943720411, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.07203731429651719, "standard_deviation": 0.009411722166238697, "minimum": 0.06167505731550127, "maximum": 0.09174435438571929, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 1.9807405471801758, "predicted_mos": 1.9807405471801758, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "b661230f3546617a46831cd2aee46d161976974200c3c7cfba00537bb4dea79a", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 9.793484100140631}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.641468220594707, "全帯域_10ms_rms_envelope_nrmse": 0.14721950438945697, "全帯域_10ms_envelope_correlation": 0.983478891010911, "全帯域_10ms_modulation_mae_db": 0.6126350789356763, "全帯域_40ms_log_rms_mae_db": 0.845569964386691, "全帯域_40ms_rms_envelope_nrmse": 0.07933856648984709, "全帯域_40ms_envelope_correlation": 0.9949169634332136, "全帯域_40ms_modulation_mae_db": 1.0475477474457469, "300–1000 Hz_10ms_log_rms_mae_db": 2.7241626129527208, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3011714514334404, "300–1000 Hz_10ms_envelope_correlation": 0.9490567702848773, "300–1000 Hz_10ms_modulation_mae_db": 0.4573065027543605, "300–1000 Hz_40ms_log_rms_mae_db": 2.0119402896423444, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19769439915129025, "300–1000 Hz_40ms_envelope_correlation": 0.980983903559734, "300–1000 Hz_40ms_modulation_mae_db": 0.49940499438875824, "1000–3000 Hz_10ms_log_rms_mae_db": 1.904301072535164, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20894224543937018, "1000–3000 Hz_10ms_envelope_correlation": 0.971458791669867, "1000–3000 Hz_10ms_modulation_mae_db": 0.26808429328453204, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1752653057845577, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1265207164547627, "1000–3000 Hz_40ms_envelope_correlation": 0.9893925774065706, "1000–3000 Hz_40ms_modulation_mae_db": 0.20978460144529473, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5378292429621705, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18698229662102728, "3000–6000 Hz_10ms_envelope_correlation": 0.9795103042699523, "3000–6000 Hz_10ms_modulation_mae_db": 1.394017591749071, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0403159455476723, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10261266706488761, "3000–6000 Hz_40ms_envelope_correlation": 0.9943072403972304, "3000–6000 Hz_40ms_modulation_mae_db": 1.9876769078163405, "mr_stft_db": 6.22032352970016, "band_mae_db": 0.6565354727181422, "rms_gain_error_db": -0.007751002612756873, "output_peak": 0.03533316827205785}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5607317227299524, "全帯域_10ms_rms_envelope_nrmse": 0.1362340148352457, "全帯域_10ms_envelope_correlation": 0.9859091521002273, "全帯域_10ms_modulation_mae_db": 0.7101526354747266, "全帯域_40ms_log_rms_mae_db": 0.8933519540626235, "全帯域_40ms_rms_envelope_nrmse": 0.06996867358684256, "全帯域_40ms_envelope_correlation": 0.996362941359289, "全帯域_40ms_modulation_mae_db": 0.9517013704342038, "300–1000 Hz_10ms_log_rms_mae_db": 2.5475621883559536, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2884815459025825, "300–1000 Hz_10ms_envelope_correlation": 0.9446408168781989, "300–1000 Hz_10ms_modulation_mae_db": 0.6131747758796231, "300–1000 Hz_40ms_log_rms_mae_db": 1.7778841047870932, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16014020491093134, "300–1000 Hz_40ms_envelope_correlation": 0.9827266506877697, "300–1000 Hz_40ms_modulation_mae_db": 0.45553276701808554, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8999147710040472, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19079760831254333, "1000–3000 Hz_10ms_envelope_correlation": 0.9760873147836135, "1000–3000 Hz_10ms_modulation_mae_db": 0.2179913274885413, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1380682509142312, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10197857035736076, "1000–3000 Hz_40ms_envelope_correlation": 0.993185116491036, "1000–3000 Hz_40ms_modulation_mae_db": 0.274657086375429, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6100878328637398, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16791902355176072, "3000–6000 Hz_10ms_envelope_correlation": 0.9838135006427847, "3000–6000 Hz_10ms_modulation_mae_db": 0.8839171992699288, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0691350922040301, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08137909481917008, "3000–6000 Hz_40ms_envelope_correlation": 0.9969924203709396, "3000–6000 Hz_40ms_modulation_mae_db": 1.3688600027109998, "mr_stft_db": 6.199448975162468, "band_mae_db": 0.6874825224828439, "rms_gain_error_db": -0.19521754698225588, "output_peak": 0.03211193516815744}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6668821357942336, "全帯域_10ms_rms_envelope_nrmse": 0.1397512918152169, "全帯域_10ms_envelope_correlation": 0.9850505121846365, "全帯域_10ms_modulation_mae_db": 0.5163767783719101, "全帯域_40ms_log_rms_mae_db": 0.9088681726775486, "全帯域_40ms_rms_envelope_nrmse": 0.07217417311601648, "全帯域_40ms_envelope_correlation": 0.9957866463971375, "全帯域_40ms_modulation_mae_db": 0.8172334850356043, "300–1000 Hz_10ms_log_rms_mae_db": 2.597002622543055, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2998075071557189, "300–1000 Hz_10ms_envelope_correlation": 0.9412519157846212, "300–1000 Hz_10ms_modulation_mae_db": 0.5062109851170803, "300–1000 Hz_40ms_log_rms_mae_db": 1.8824139865293668, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16743397742740296, "300–1000 Hz_40ms_envelope_correlation": 0.981869170415129, "300–1000 Hz_40ms_modulation_mae_db": 0.16957168077207485, "1000–3000 Hz_10ms_log_rms_mae_db": 1.899622541142499, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2161863491381336, "1000–3000 Hz_10ms_envelope_correlation": 0.9692080016453142, "1000–3000 Hz_10ms_modulation_mae_db": 0.26129047230099184, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1849545785487672, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11957097589471564, "1000–3000 Hz_40ms_envelope_correlation": 0.9905297753129607, "1000–3000 Hz_40ms_modulation_mae_db": 0.2133773731311346, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5245611279020792, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14604413437885955, "3000–6000 Hz_10ms_envelope_correlation": 0.9874161515116892, "3000–6000 Hz_10ms_modulation_mae_db": 0.7817740296947074, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0024976860114272, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07406753545364328, "3000–6000 Hz_40ms_envelope_correlation": 0.9966688328777737, "3000–6000 Hz_40ms_modulation_mae_db": 1.4218971096796789, "mr_stft_db": 6.207845846327864, "band_mae_db": 0.685904291186068, "rms_gain_error_db": -0.04288953367885365, "output_peak": 0.03855820455055342}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.564721957430329, "全帯域_10ms_rms_envelope_nrmse": 0.13821803803610197, "全帯域_10ms_envelope_correlation": 0.9853657053327819, "全帯域_10ms_modulation_mae_db": 0.6848332565866042, "全帯域_40ms_log_rms_mae_db": 0.8281879290003515, "全帯域_40ms_rms_envelope_nrmse": 0.07083966184459212, "全帯域_40ms_envelope_correlation": 0.9959529385202, "全帯域_40ms_modulation_mae_db": 0.8001072366180554, "300–1000 Hz_10ms_log_rms_mae_db": 2.6533076381506078, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2516072791590687, "300–1000 Hz_10ms_envelope_correlation": 0.9562297115570143, "300–1000 Hz_10ms_modulation_mae_db": 0.6588980755751157, "300–1000 Hz_40ms_log_rms_mae_db": 1.9578969142046856, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14455621026952475, "300–1000 Hz_40ms_envelope_correlation": 0.9848506681365008, "300–1000 Hz_40ms_modulation_mae_db": 0.5171806690750579, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8914221680049679, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18136000293943247, "1000–3000 Hz_10ms_envelope_correlation": 0.9784473798334984, "1000–3000 Hz_10ms_modulation_mae_db": 0.4329782171508941, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1320458282909502, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0893867938868545, "1000–3000 Hz_40ms_envelope_correlation": 0.9946900164822869, "1000–3000 Hz_40ms_modulation_mae_db": 0.4921253440924714, "3000–6000 Hz_10ms_log_rms_mae_db": 1.55509745398414, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18411483003358875, "3000–6000 Hz_10ms_envelope_correlation": 0.9798977274636556, "3000–6000 Hz_10ms_modulation_mae_db": 1.0168720879711572, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0342664323047315, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09386937327258506, "3000–6000 Hz_40ms_envelope_correlation": 0.9946482319647317, "3000–6000 Hz_40ms_modulation_mae_db": 1.0309209992385604, "mr_stft_db": 6.202959789524587, "band_mae_db": 0.5458270690251347, "rms_gain_error_db": -0.06151611054366955, "output_peak": 0.030950430463130202}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5643853299324066, "全帯域_10ms_rms_envelope_nrmse": 0.14942410660555652, "全帯域_10ms_envelope_correlation": 0.9829055882420529, "全帯域_10ms_modulation_mae_db": 0.628829301377178, "全帯域_40ms_log_rms_mae_db": 0.8692483928659426, "全帯域_40ms_rms_envelope_nrmse": 0.09075727551419184, "全帯域_40ms_envelope_correlation": 0.9934810340641534, "全帯域_40ms_modulation_mae_db": 0.8303754363745228, "300–1000 Hz_10ms_log_rms_mae_db": 2.6977392775983953, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.28063684574077974, "300–1000 Hz_10ms_envelope_correlation": 0.9466374372372701, "300–1000 Hz_10ms_modulation_mae_db": 0.8221992483779531, "300–1000 Hz_40ms_log_rms_mae_db": 1.978080181124807, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.174818280770087, "300–1000 Hz_40ms_envelope_correlation": 0.9784387910580972, "300–1000 Hz_40ms_modulation_mae_db": 0.8604095604670768, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8264204086975249, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19103684172552032, "1000–3000 Hz_10ms_envelope_correlation": 0.9766290588695075, "1000–3000 Hz_10ms_modulation_mae_db": 0.833509349238339, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0879170744075048, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12185997089826019, "1000–3000 Hz_40ms_envelope_correlation": 0.9911950814231214, "1000–3000 Hz_40ms_modulation_mae_db": 1.1192265127100087, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5638767822740056, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18781288595961715, "3000–6000 Hz_10ms_envelope_correlation": 0.9790628867205319, "3000–6000 Hz_10ms_modulation_mae_db": 1.1372158662391751, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0687778955752874, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11551823001038782, "3000–6000 Hz_40ms_envelope_correlation": 0.9919020716842897, "3000–6000 Hz_40ms_modulation_mae_db": 1.7937195172154734, "mr_stft_db": 6.201257138769133, "band_mae_db": 0.6521000728836231, "rms_gain_error_db": -0.1582353240120587, "output_peak": 0.028704461574444683}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6242791093973454, "全帯域_10ms_rms_envelope_nrmse": 0.1364952276444292, "全帯域_10ms_envelope_correlation": 0.9857625845441473, "全帯域_10ms_modulation_mae_db": 0.6422049833976531, "全帯域_40ms_log_rms_mae_db": 0.8976685421542112, "全帯域_40ms_rms_envelope_nrmse": 0.06950226057461896, "全帯域_40ms_envelope_correlation": 0.9960888104884067, "全帯域_40ms_modulation_mae_db": 0.6512504553370912, "300–1000 Hz_10ms_log_rms_mae_db": 2.692275463597846, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25585189574313877, "300–1000 Hz_10ms_envelope_correlation": 0.9598825859407559, "300–1000 Hz_10ms_modulation_mae_db": 0.4132076634173583, "300–1000 Hz_40ms_log_rms_mae_db": 1.9813857801441819, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1538171515607267, "300–1000 Hz_40ms_envelope_correlation": 0.986773824021252, "300–1000 Hz_40ms_modulation_mae_db": 0.4614441897887605, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8588835218572248, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2124602051692089, "1000–3000 Hz_10ms_envelope_correlation": 0.9702220825829705, "1000–3000 Hz_10ms_modulation_mae_db": 0.4340180261542974, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1689292628619379, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12386109460764225, "1000–3000 Hz_40ms_envelope_correlation": 0.9898618713643887, "1000–3000 Hz_40ms_modulation_mae_db": 0.4748598838857668, "3000–6000 Hz_10ms_log_rms_mae_db": 1.576324508079607, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17581114741425066, "3000–6000 Hz_10ms_envelope_correlation": 0.9817665608684835, "3000–6000 Hz_10ms_modulation_mae_db": 0.9852477478896094, "3000–6000 Hz_40ms_log_rms_mae_db": 1.052537761978538, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08301780277857983, "3000–6000 Hz_40ms_envelope_correlation": 0.9958051514612749, "3000–6000 Hz_40ms_modulation_mae_db": 1.4525424735315766, "mr_stft_db": 6.2090244044572165, "band_mae_db": 0.7537644481731387, "rms_gain_error_db": -0.023753821532052057, "output_peak": 0.033223901964471024}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6114424058738386, "全帯域_10ms_rms_envelope_nrmse": 0.15571678250391302, "全帯域_10ms_envelope_correlation": 0.9817393564181213, "全帯域_10ms_modulation_mae_db": 0.44625921264406077, "全帯域_40ms_log_rms_mae_db": 0.8994792709877029, "全帯域_40ms_rms_envelope_nrmse": 0.09757522254105773, "全帯域_40ms_envelope_correlation": 0.9924195406604926, "全帯域_40ms_modulation_mae_db": 0.29130131189048863, "300–1000 Hz_10ms_log_rms_mae_db": 2.7001033444607256, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.33802607989611116, "300–1000 Hz_10ms_envelope_correlation": 0.93994309206371, "300–1000 Hz_10ms_modulation_mae_db": 0.6929217794506327, "300–1000 Hz_40ms_log_rms_mae_db": 1.947001345460722, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.24410274007261304, "300–1000 Hz_40ms_envelope_correlation": 0.9722669680987955, "300–1000 Hz_40ms_modulation_mae_db": 0.9590357633077623, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8524505834569074, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21915823040123827, "1000–3000 Hz_10ms_envelope_correlation": 0.9689304380092185, "1000–3000 Hz_10ms_modulation_mae_db": 0.272283008646201, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1646641046018895, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12802919209116526, "1000–3000 Hz_40ms_envelope_correlation": 0.9891672331746321, "1000–3000 Hz_40ms_modulation_mae_db": 0.12681109769962237, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5509296676634117, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1653075317193681, "3000–6000 Hz_10ms_envelope_correlation": 0.9837882994096233, "3000–6000 Hz_10ms_modulation_mae_db": 0.7444021741536483, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0701089956012637, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08599624786522743, "3000–6000 Hz_40ms_envelope_correlation": 0.9955263195777738, "3000–6000 Hz_40ms_modulation_mae_db": 0.9981545120802874, "mr_stft_db": 6.206280175374009, "band_mae_db": 0.6503066471167809, "rms_gain_error_db": 0.053718076343394636, "output_peak": 0.04376567180468862}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6182036779939848, "全帯域_10ms_rms_envelope_nrmse": 0.13855965567591147, "全帯域_10ms_envelope_correlation": 0.9853264669124701, "全帯域_10ms_modulation_mae_db": 0.6899952510805306, "全帯域_40ms_log_rms_mae_db": 0.8666272402271261, "全帯域_40ms_rms_envelope_nrmse": 0.06468457861180056, "全帯域_40ms_envelope_correlation": 0.99661293061019, "全帯域_40ms_modulation_mae_db": 1.2753450235884904, "300–1000 Hz_10ms_log_rms_mae_db": 2.7137064640297885, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.297917574063643, "300–1000 Hz_10ms_envelope_correlation": 0.9376379251949417, "300–1000 Hz_10ms_modulation_mae_db": 0.660346936389315, "300–1000 Hz_40ms_log_rms_mae_db": 1.9987359856397213, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16160678609717619, "300–1000 Hz_40ms_envelope_correlation": 0.9805855211264652, "300–1000 Hz_40ms_modulation_mae_db": 0.8128549067768681, "1000–3000 Hz_10ms_log_rms_mae_db": 1.843233276698193, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19477439119306098, "1000–3000 Hz_10ms_envelope_correlation": 0.9754410956538282, "1000–3000 Hz_10ms_modulation_mae_db": 0.5944261677452078, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1226664097156038, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09851302199340661, "1000–3000 Hz_40ms_envelope_correlation": 0.9935694049446985, "1000–3000 Hz_40ms_modulation_mae_db": 0.715554057292365, "3000–6000 Hz_10ms_log_rms_mae_db": 1.581004167869172, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16845474558926898, "3000–6000 Hz_10ms_envelope_correlation": 0.983264672839141, "3000–6000 Hz_10ms_modulation_mae_db": 0.9800664612633817, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0793435323605036, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09509388652104794, "3000–6000 Hz_40ms_envelope_correlation": 0.9945029659298931, "3000–6000 Hz_40ms_modulation_mae_db": 1.5971535017908458, "mr_stft_db": 6.193668190789258, "band_mae_db": 0.4982548330608572, "rms_gain_error_db": -0.021669507919805812, "output_peak": 0.03339549456683027}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.5338392375472205, "spectral_convergence": 0.6329702270068748, "spectral_convergence_status": "ok", "amplitude_floor": 9.167242110941195e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.12112772822395, "spectral_convergence": 0.6307816555375428, "spectral_convergence_status": "ok", "amplitude_floor": 5.84028801806317e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.006003623329309, "spectral_convergence": 0.6546511715692167, "spectral_convergence_status": "ok", "amplitude_floor": 2.8939654187001563e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.3843123087683508e-07, "output_power": 1.458131300508192e-07, "delta_db": 0.2256255221345233, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.81286342317638e-08, "output_power": 1.199144227659506e-07, "delta_db": 2.4554173845540643, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 9.335883160942139e-07, "output_power": 1.097938408200542e-06, "delta_db": 0.704225700301965, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.7505166473017637e-06, "output_power": 1.5740333628521323e-06, "delta_db": -0.46152311906155896, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.470519881244434e-07, "output_power": 5.882888031331742e-07, "delta_db": 0.3156198185665593, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.7292398267785066e-06, "output_power": 2.5840725940048644e-06, "delta_db": -0.23736990080381204, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.57439203602588e-07, "output_power": 1.0016313121547774e-06, "delta_db": 0.1959668636045128, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.6565354727181422, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.007751002612756873, "pitch": null, "output_rms_dbfs": -51.48027058448717, "output_peak": 0.03533316827205785, "reference_rms_dbfs": -51.47251958187441, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.22032352970016}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.1370250428801243e-05, "log_rms_mae_db": 1.641468220594707, "rms_envelope_nrmse": 0.14721950438945697, "envelope_correlation": 0.983478891010911, "rms_gain_error_db": -0.00774953596543422, "reference_mean_power": 7.130327548553108e-06, "output_mean_power": 7.117615561310943e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.4304416670730408e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2770281801289633e-06, "output_power": 1.1685294611939773e-06, "reference_active": true, "delta_db": -0.3856081454390165}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.124025700263392e-07, "output_power": 2.0381270946436236e-07, "reference_active": true, "delta_db": -0.1792850482536555}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.509706557401959e-07, "output_power": 1.1261372835436796e-07, "reference_active": true, "delta_db": -1.2730120431143568}], "active_band_count": 3, "active_band_mae_db": 0.6126350789356763}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.27501987121069e-06, "log_rms_mae_db": 0.845569964386691, "rms_envelope_nrmse": 0.07933856648984709, "envelope_correlation": 0.9949169634332136, "rms_gain_error_db": -0.00774644910773037, "reference_mean_power": 7.166117032249278e-06, "output_mean_power": 7.153346323738115e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.171922661595567e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0939532041259814e-06, "output_power": 1.0126618235168605e-06, "reference_active": true, "delta_db": -0.3353430688596095}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.164609293708589e-07, "output_power": 9.948091106476177e-08, "reference_active": true, "delta_db": -0.6844049753686408}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0690330771826293e-08, "output_power": 6.5569462441904804e-09, "reference_active": true, "delta_db": -2.1228951981089903}], "active_band_count": 3, "active_band_mae_db": 1.0475477474457469}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 6.556092771800097e-06, "log_rms_mae_db": 2.7241626129527208, "rms_envelope_nrmse": 0.3011714514334404, "envelope_correlation": 0.9490567702848773, "rms_gain_error_db": 0.8493888884370746, "reference_mean_power": 7.945163829144021e-07, "output_mean_power": 9.66143743018832e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.0791155245365873e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.4868570435085076e-07, "output_power": 1.4157703820005794e-07, "reference_active": true, "delta_db": -0.21276391898804273}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.530749650867304e-08, "output_power": 3.307948891651742e-08, "reference_active": true, "delta_db": -0.2830813382911451}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.4918697573140088e-08, "output_power": 2.0366570936564814e-08, "reference_active": true, "delta_db": -0.8760742509838938}], "active_band_count": 3, "active_band_mae_db": 0.4573065027543605}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.158309417730701e-06, "log_rms_mae_db": 2.0119402896423444, "rms_envelope_nrmse": 0.19769439915129025, "envelope_correlation": 0.980983903559734, "rms_gain_error_db": 0.8493777265824951, "reference_mean_power": 7.985041710031799e-07, "output_mean_power": 9.709904571105796e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.7036737518374816e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3140926226909544e-07, "output_power": 1.2631355850035415e-07, "reference_active": true, "delta_db": -0.17176006939110186}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.929219128746953e-08, "output_power": 1.6400921441456572e-08, "reference_active": true, "delta_db": -0.705133110272257}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4692549483461402e-09, "output_power": 1.273400399305914e-09, "reference_active": true, "delta_db": -0.6213218035029159}], "active_band_count": 3, "active_band_mae_db": 0.49940499438875824}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 7.401330296636983e-06, "log_rms_mae_db": 1.904301072535164, "rms_envelope_nrmse": 0.20894224543937018, "envelope_correlation": 0.971458791669867, "rms_gain_error_db": -0.04343986012020187, "reference_mean_power": 1.4849128654353035e-06, "output_mean_power": 1.470134211000121e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.41811499304529e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.69138926350769e-07, "output_power": 2.5260687178536113e-07, "reference_active": true, "delta_db": -0.2753135488866473}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.521731226006148e-08, "output_power": 4.58901467301961e-08, "reference_active": true, "delta_db": 0.06414702227306095}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6338303134826183e-08, "output_power": 2.931345591258044e-08, "reference_active": true, "delta_db": 0.464792308693888}], "active_band_count": 3, "active_band_mae_db": 0.26808429328453204}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 6.380552881753602e-06, "log_rms_mae_db": 1.1752653057845577, "rms_envelope_nrmse": 0.1265207164547627, "envelope_correlation": 0.9893925774065706, "rms_gain_error_db": -0.0434379696885762, "reference_mean_power": 1.4923708236731126e-06, "output_mean_power": 1.477518586757452e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.994698288619123e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.551906678142862e-07, "output_power": 2.4224843883062135e-07, "reference_active": true, "delta_db": -0.22603801501215923}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4359212852663977e-08, "output_power": 2.400237676979541e-08, "reference_active": true, "delta_db": -0.0640900166342751}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5357702928828252e-09, "output_power": 1.6605380815769593e-09, "reference_active": true, "delta_db": 0.33922577268944987}], "active_band_count": 3, "active_band_mae_db": 0.20978460144529473}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0774952268311018e-05, "log_rms_mae_db": 1.5378292429621705, "rms_envelope_nrmse": 0.18698229662102728, "envelope_correlation": 0.9795103042699523, "rms_gain_error_db": -0.34332748046660266, "reference_mean_power": 1.995223201702535e-06, "output_mean_power": 1.8435662051275953e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.579487211503375e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.151593028482198e-07, "output_power": 5.984714583584996e-07, "reference_active": true, "delta_db": -0.7735934900689595}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2474197679576555e-07, "output_power": 1.0226370408842503e-07, "reference_active": true, "delta_db": -0.8629110283417409}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.137663053230787e-08, "output_power": 4.528401002617931e-08, "reference_active": true, "delta_db": -2.5455482568365118}], "active_band_count": 3, "active_band_mae_db": 1.394017591749071}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 7.143885674653834e-06, "log_rms_mae_db": 1.0403159455476723, "rms_envelope_nrmse": 0.10261266706488761, "envelope_correlation": 0.9943072403972304, "rms_gain_error_db": -0.3433276671468861, "reference_mean_power": 2.0052568878051223e-06, "output_mean_power": 1.8528371506984252e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.5118360803946574e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.45069205976456e-07, "output_power": 5.409836600995392e-07, "reference_active": true, "delta_db": -0.7642216238423551}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.385509447185785e-08, "output_power": 5.8760136153708013e-08, "reference_active": true, "delta_db": -1.5444665912943112}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.733755662328774e-09, "output_power": 2.471752210348389e-09, "reference_active": true, "delta_db": -3.6543425083123555}], "active_band_count": 3, "active_band_mae_db": 1.9876769078163405}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5175377349077543, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "53edc68c56f3b6a3bdddbb39040f3409692670f62f1b992da69e9749c1c1f183", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9733030203809772, "standard_deviation": 0.0037537151062870485, "minimum": 0.9689304380092185, "maximum": 0.9784473798334984, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.8720310429245661, "standard_deviation": 0.03028921685983755, "minimum": 1.8264204086975249, "maximum": 1.904301072535164, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.41432260775112556, "standard_deviation": 0.21126031885237634, "minimum": 0.2179913274885413, "maximum": 0.833509349238339, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.20183948428981352, "standard_deviation": 0.014025309948748827, "minimum": 0.18136000293943247, "maximum": 0.21915823040123827, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9914488845749618, "standard_deviation": 0.0021002777039124203, "minimum": 0.9891672331746321, "maximum": 0.9946900164822869, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.1468138518906803, "standard_deviation": 0.032554202278544574, "minimum": 1.0879170744075048, "maximum": 1.1849545785487672, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.4532994945790116, "standard_deviation": 0.3315716808866391, "minimum": 0.12681109769962237, "maximum": 1.1192265127100087, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.11371504202302099, "standard_deviation": 0.0147994412939037, "minimum": 0.0893867938868545, "maximum": 0.12802919209116526, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9823150129657328, "standard_deviation": 0.002826565090824465, "minimum": 0.9790628867205319, "maximum": 0.9874161515116892, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5624638479497908, "standard_deviation": 0.026823983696053537, "minimum": 1.5245611279020792, "maximum": 1.6100878328637398, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.9904391447788348, "standard_deviation": 0.20725224745113627, "minimum": 0.7444021741536483, "maximum": 1.394017591749071, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17280582440846765, "standard_deviation": 0.014032284160808779, "minimum": 0.14604413437885955, "maximum": 0.18781288595961715, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9950441542829884, "standard_deviation": 0.001608561283097324, "minimum": 0.9919020716842897, "maximum": 0.9969924203709396, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.0521229176979316, "standard_deviation": 0.02550170192680448, "minimum": 1.0024976860114272, "maximum": 1.0793435323605036, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.4563656280079704, "standard_deviation": 0.34137140156648926, "minimum": 0.9981545120802874, "maximum": 1.9876769078163405, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09144435472319112, "standard_deviation": 0.013241894664212567, "minimum": 0.07406753545364328, "maximum": 0.11551823001038782, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9469100318676738, "standard_deviation": 0.007851298427791626, "minimum": 0.9376379251949417, "maximum": 0.9598825859407559, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.6657324514611367, "standard_deviation": 0.06264217292731288, "minimum": 2.5475621883559536, "maximum": 2.7241626129527208, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6030332458701799, "standard_deviation": 0.13589221551568872, "minimum": 0.4132076634173583, "maximum": 0.8221992483779531, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2891875223868104, "standard_deviation": 0.02755505733316924, "minimum": 0.2516072791590687, "maximum": 0.33802607989611116, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9810619371379679, "standard_deviation": 0.004389410444060907, "minimum": 0.9722669680987955, "maximum": 0.986773824021252, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.9419173234416154, "standard_deviation": 0.0772064264965117, "minimum": 1.7778841047870932, "maximum": 2.0119402896423444, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5919293164493056, "standard_deviation": 0.2629017662992153, "minimum": 0.16957168077207485, "maximum": 0.9590357633077623, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.17552121878246904, "standard_deviation": 0.03189504640349053, "minimum": 0.14455621026952475, "maximum": 0.24410274007261304, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.6412719195808236, "standard_deviation": 0.0817465553656113, "minimum": 0.4982548330608572, "maximum": 0.7537644481731387, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.205101006263087, "standard_deviation": 0.007910731514021939, "minimum": 6.193668190789258, "maximum": 6.22032352970016, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.03450540854554169, "standard_deviation": 0.004747248152432355, "minimum": 0.028704461574444683, "maximum": 0.04376567180468862, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.05716434636725723, "standard_deviation": 0.08159960940401595, "minimum": -0.19521754698225588, "maximum": 0.053718076343394636, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9844422820931685, "standard_deviation": 0.0015350523896242303, "minimum": 0.9817393564181213, "maximum": 0.9859091521002273, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.6065143199683498, "standard_deviation": 0.039569221082691224, "minimum": 1.5607317227299524, "maximum": 1.6668821357942336, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.6164108122335424, "standard_deviation": 0.09155483839156224, "minimum": 0.44625921264406077, "maximum": 0.7101526354747266, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.14270232768822896, "standard_deviation": 0.007184403655940632, "minimum": 0.1362340148352457, "maximum": 0.15571678250391302, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9952027256916354, "standard_deviation": 0.0015031257099489869, "minimum": 0.9924195406604926, "maximum": 0.99661293061019, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8761251832952747, "standard_deviation": 0.02865433806262743, "minimum": 0.8281879290003515, "maximum": 0.9088681726775486, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.8331077583405254, "standard_deviation": 0.28874050365871334, "minimum": 0.29130131189048863, "maximum": 1.2753450235884904, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.07685505153487092, "standard_deviation": 0.011566372735810316, "minimum": 0.06468457861180056, "maximum": 0.09757522254105773, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 1.6871883869171143, "predicted_mos": 1.6871883869171143, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "387ac8fcb3698980a59055bc7c12f4c621fb1ca251b4afb57f754a1094529c2c", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 9.099673200398684}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6183871777228895, "全帯域_10ms_rms_envelope_nrmse": 0.14685288899310112, "全帯域_10ms_envelope_correlation": 0.9837171034347802, "全帯域_10ms_modulation_mae_db": 0.3615334573895463, "全帯域_40ms_log_rms_mae_db": 0.8827501418116014, "全帯域_40ms_rms_envelope_nrmse": 0.07986695797501224, "全帯域_40ms_envelope_correlation": 0.9949192891208529, "全帯域_40ms_modulation_mae_db": 0.5796899309353669, "300–1000 Hz_10ms_log_rms_mae_db": 2.395094906105189, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24123771948791214, "300–1000 Hz_10ms_envelope_correlation": 0.961135965850391, "300–1000 Hz_10ms_modulation_mae_db": 0.23993977522103735, "300–1000 Hz_40ms_log_rms_mae_db": 1.7329756073575395, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1386220704242785, "300–1000 Hz_40ms_envelope_correlation": 0.9869700404474218, "300–1000 Hz_40ms_modulation_mae_db": 0.17343695845056148, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5250347508264523, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21363516305446978, "1000–3000 Hz_10ms_envelope_correlation": 0.9715615133632539, "1000–3000 Hz_10ms_modulation_mae_db": 0.35813391318159765, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8581974605250784, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12068946040836549, "1000–3000 Hz_40ms_envelope_correlation": 0.9909308297903, "1000–3000 Hz_40ms_modulation_mae_db": 0.5101401553262822, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1589956844458629, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19402850746211345, "3000–6000 Hz_10ms_envelope_correlation": 0.9783897232208523, "3000–6000 Hz_10ms_modulation_mae_db": 0.39587286448071063, "3000–6000 Hz_40ms_log_rms_mae_db": 0.755653868384136, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09788692007894802, "3000–6000 Hz_40ms_envelope_correlation": 0.9944568134576593, "3000–6000 Hz_40ms_modulation_mae_db": 0.34539489788248234, "mr_stft_db": 5.998337242976084, "band_mae_db": 0.5122913176790361, "rms_gain_error_db": 0.05650939919108006, "output_peak": 0.03672298959257386}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.682948563115452, "全帯域_10ms_rms_envelope_nrmse": 0.14905360061371647, "全帯域_10ms_envelope_correlation": 0.9831363877453843, "全帯域_10ms_modulation_mae_db": 0.44339906394315126, "全帯域_40ms_log_rms_mae_db": 0.8943078257832429, "全帯域_40ms_rms_envelope_nrmse": 0.07007524193666753, "全帯域_40ms_envelope_correlation": 0.9960575694565155, "全帯域_40ms_modulation_mae_db": 0.7398006430696968, "300–1000 Hz_10ms_log_rms_mae_db": 2.365853699838965, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2759354579969245, "300–1000 Hz_10ms_envelope_correlation": 0.9505024284520723, "300–1000 Hz_10ms_modulation_mae_db": 0.3601138496142346, "300–1000 Hz_40ms_log_rms_mae_db": 1.7449710694155296, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1745953053567387, "300–1000 Hz_40ms_envelope_correlation": 0.9800351366944449, "300–1000 Hz_40ms_modulation_mae_db": 0.6279298033096802, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5193484819506602, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.185341107896181, "1000–3000 Hz_10ms_envelope_correlation": 0.9774194995991927, "1000–3000 Hz_10ms_modulation_mae_db": 0.5709781057829638, "1000–3000 Hz_40ms_log_rms_mae_db": 0.90624911945684, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0972339908815508, "1000–3000 Hz_40ms_envelope_correlation": 0.9938086730524556, "1000–3000 Hz_40ms_modulation_mae_db": 0.7588165778660386, "3000–6000 Hz_10ms_log_rms_mae_db": 1.145757640931295, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16002970791124793, "3000–6000 Hz_10ms_envelope_correlation": 0.9850998115213639, "3000–6000 Hz_10ms_modulation_mae_db": 0.27512032030404915, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7490791895661744, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06935546578377004, "3000–6000 Hz_40ms_envelope_correlation": 0.9971522123791686, "3000–6000 Hz_40ms_modulation_mae_db": 0.5469212976121308, "mr_stft_db": 5.995515321266648, "band_mae_db": 0.6293480914610866, "rms_gain_error_db": 0.014963483091615952, "output_peak": 0.0321274617554218}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6746707645688736, "全帯域_10ms_rms_envelope_nrmse": 0.1516585344707293, "全帯域_10ms_envelope_correlation": 0.9823857752461458, "全帯域_10ms_modulation_mae_db": 0.5868296956486626, "全帯域_40ms_log_rms_mae_db": 0.8433161387873741, "全帯域_40ms_rms_envelope_nrmse": 0.06624220807852593, "全帯域_40ms_envelope_correlation": 0.9966882892501278, "全帯域_40ms_modulation_mae_db": 0.6812048952947604, "300–1000 Hz_10ms_log_rms_mae_db": 2.3969850951086227, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.29797700073817013, "300–1000 Hz_10ms_envelope_correlation": 0.9382681492289039, "300–1000 Hz_10ms_modulation_mae_db": 0.4123787950636337, "300–1000 Hz_40ms_log_rms_mae_db": 1.6811770296463697, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15483559418406126, "300–1000 Hz_40ms_envelope_correlation": 0.9823927422077945, "300–1000 Hz_40ms_modulation_mae_db": 0.4061002124357156, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5270587156933526, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2049698519288189, "1000–3000 Hz_10ms_envelope_correlation": 0.972303177092963, "1000–3000 Hz_10ms_modulation_mae_db": 0.4851822088970186, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8684183370022521, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10820653015468122, "1000–3000 Hz_40ms_envelope_correlation": 0.9923254520650558, "1000–3000 Hz_40ms_modulation_mae_db": 0.7526160863146031, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1265920511248253, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16358140281217426, "3000–6000 Hz_10ms_envelope_correlation": 0.984294009221626, "3000–6000 Hz_10ms_modulation_mae_db": 0.46437660936538544, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7031423178259427, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07729356371632227, "3000–6000 Hz_40ms_envelope_correlation": 0.996390875630071, "3000–6000 Hz_40ms_modulation_mae_db": 0.5204454559300541, "mr_stft_db": 5.991109977180863, "band_mae_db": 0.5405938909835657, "rms_gain_error_db": -0.1640417665997469, "output_peak": 0.03264412178167892}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6205756812168073, "全帯域_10ms_rms_envelope_nrmse": 0.14556987584643719, "全帯域_10ms_envelope_correlation": 0.9838448016980446, "全帯域_10ms_modulation_mae_db": 0.1666763688464691, "全帯域_40ms_log_rms_mae_db": 0.8742700913640856, "全帯域_40ms_rms_envelope_nrmse": 0.06940192304751328, "全帯域_40ms_envelope_correlation": 0.996109492313918, "全帯域_40ms_modulation_mae_db": 0.431147245634473, "300–1000 Hz_10ms_log_rms_mae_db": 2.3684806460132317, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27920724182334195, "300–1000 Hz_10ms_envelope_correlation": 0.9461021827801633, "300–1000 Hz_10ms_modulation_mae_db": 0.5979011080586935, "300–1000 Hz_40ms_log_rms_mae_db": 1.7611395642936902, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13825532938899948, "300–1000 Hz_40ms_envelope_correlation": 0.9861319528531972, "300–1000 Hz_40ms_modulation_mae_db": 0.5981889552142995, "1000–3000 Hz_10ms_log_rms_mae_db": 1.445541347216604, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1803819437841628, "1000–3000 Hz_10ms_envelope_correlation": 0.9798707410402053, "1000–3000 Hz_10ms_modulation_mae_db": 0.9187953225003316, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8289336371860088, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08284345078053797, "1000–3000 Hz_40ms_envelope_correlation": 0.9960171858278795, "1000–3000 Hz_40ms_modulation_mae_db": 0.675567555709829, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1536500357869859, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16269277949578506, "3000–6000 Hz_10ms_envelope_correlation": 0.9848133439087249, "3000–6000 Hz_10ms_modulation_mae_db": 0.30504067755512865, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7350364750625593, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08824345310166756, "3000–6000 Hz_40ms_envelope_correlation": 0.9954981175464259, "3000–6000 Hz_40ms_modulation_mae_db": 0.9695323094557802, "mr_stft_db": 5.9882624412514085, "band_mae_db": 0.4768715740308725, "rms_gain_error_db": 0.0035073347482320865, "output_peak": 0.03155155794450642}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.642631358739481, "全帯域_10ms_rms_envelope_nrmse": 0.13178855166282682, "全帯域_10ms_envelope_correlation": 0.986719587342524, "全帯域_10ms_modulation_mae_db": 0.3068925766523805, "全帯域_40ms_log_rms_mae_db": 0.8287377557150177, "全帯域_40ms_rms_envelope_nrmse": 0.05837117451347525, "全帯域_40ms_envelope_correlation": 0.9972517618780966, "全帯域_40ms_modulation_mae_db": 0.4880589700377868, "300–1000 Hz_10ms_log_rms_mae_db": 2.401203497332356, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27464812524881066, "300–1000 Hz_10ms_envelope_correlation": 0.9529768991340624, "300–1000 Hz_10ms_modulation_mae_db": 0.2296070245231515, "300–1000 Hz_40ms_log_rms_mae_db": 1.7448483141932691, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16081078980988736, "300–1000 Hz_40ms_envelope_correlation": 0.9848440611032842, "300–1000 Hz_40ms_modulation_mae_db": 0.5082268535768187, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5073984330072159, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1804712334772004, "1000–3000 Hz_10ms_envelope_correlation": 0.9791849194727155, "1000–3000 Hz_10ms_modulation_mae_db": 0.6404480305551378, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8652653955036773, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08514691834022647, "1000–3000 Hz_40ms_envelope_correlation": 0.9953369022858075, "1000–3000 Hz_40ms_modulation_mae_db": 0.5205640029755546, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1651614329397482, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14625413640454432, "3000–6000 Hz_10ms_envelope_correlation": 0.9875766492670209, "3000–6000 Hz_10ms_modulation_mae_db": 0.7601673969108035, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7579329344453318, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08228012348003233, "3000–6000 Hz_40ms_envelope_correlation": 0.9963384603356195, "3000–6000 Hz_40ms_modulation_mae_db": 1.1791421153237405, "mr_stft_db": 5.999285825193529, "band_mae_db": 0.46007119122389656, "rms_gain_error_db": -0.044127601612543935, "output_peak": 0.03257705410744232}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6212843950890152, "全帯域_10ms_rms_envelope_nrmse": 0.1353789442163208, "全帯域_10ms_envelope_correlation": 0.9861127324560675, "全帯域_10ms_modulation_mae_db": 0.47041722028577104, "全帯域_40ms_log_rms_mae_db": 0.822161249680347, "全帯域_40ms_rms_envelope_nrmse": 0.06543140707265478, "全帯域_40ms_envelope_correlation": 0.9965693608933034, "全帯域_40ms_modulation_mae_db": 1.0129958238964591, "300–1000 Hz_10ms_log_rms_mae_db": 2.355452194542591, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.29774403780654235, "300–1000 Hz_10ms_envelope_correlation": 0.9440967259750038, "300–1000 Hz_10ms_modulation_mae_db": 0.1799554711259913, "300–1000 Hz_40ms_log_rms_mae_db": 1.7110871989688694, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.183779713339327, "300–1000 Hz_40ms_envelope_correlation": 0.9791294674161938, "300–1000 Hz_40ms_modulation_mae_db": 0.4950094290846329, "1000–3000 Hz_10ms_log_rms_mae_db": 1.465137849067976, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18381016375325393, "1000–3000 Hz_10ms_envelope_correlation": 0.9779063693237928, "1000–3000 Hz_10ms_modulation_mae_db": 0.05593894770804508, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8286175132980307, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09951021032643033, "1000–3000 Hz_40ms_envelope_correlation": 0.9933337167384897, "1000–3000 Hz_40ms_modulation_mae_db": 0.1906496231209779, "3000–6000 Hz_10ms_log_rms_mae_db": 1.167259110195889, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13572064208628434, "3000–6000 Hz_10ms_envelope_correlation": 0.9892456977911593, "3000–6000 Hz_10ms_modulation_mae_db": 0.37242894669525156, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7387125415943617, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06071712830617054, "3000–6000 Hz_40ms_envelope_correlation": 0.9977984867344116, "3000–6000 Hz_40ms_modulation_mae_db": 0.9365665110219389, "mr_stft_db": 5.99446674137797, "band_mae_db": 0.4484204266407584, "rms_gain_error_db": 0.023561257165949763, "output_peak": 0.034116673456877286}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6252909534120292, "全帯域_10ms_rms_envelope_nrmse": 0.14809787203536975, "全帯域_10ms_envelope_correlation": 0.9835548229900264, "全帯域_10ms_modulation_mae_db": 0.3290299578711506, "全帯域_40ms_log_rms_mae_db": 0.8081174711449414, "全帯域_40ms_rms_envelope_nrmse": 0.07093745217196666, "全帯域_40ms_envelope_correlation": 0.9960642677400736, "全帯域_40ms_modulation_mae_db": 0.782848767288454, "300–1000 Hz_10ms_log_rms_mae_db": 2.4135827079137133, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.29212798744449237, "300–1000 Hz_10ms_envelope_correlation": 0.9450505574860518, "300–1000 Hz_10ms_modulation_mae_db": 0.20244995619662484, "300–1000 Hz_40ms_log_rms_mae_db": 1.7609972865484567, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19076430723581564, "300–1000 Hz_40ms_envelope_correlation": 0.9764651258443053, "300–1000 Hz_40ms_modulation_mae_db": 0.24380539119819908, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5149349294056094, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20536984861858532, "1000–3000 Hz_10ms_envelope_correlation": 0.9733725274004312, "1000–3000 Hz_10ms_modulation_mae_db": 0.7245265602744055, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8652589718358047, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10928487630806573, "1000–3000 Hz_40ms_envelope_correlation": 0.9924538437325003, "1000–3000 Hz_40ms_modulation_mae_db": 0.3910913309120299, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1731648226429208, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16200968894965095, "3000–6000 Hz_10ms_envelope_correlation": 0.9844788220665482, "3000–6000 Hz_10ms_modulation_mae_db": 0.5306536492745023, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7357416540082186, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08064876658159736, "3000–6000 Hz_40ms_envelope_correlation": 0.9960344926359547, "3000–6000 Hz_40ms_modulation_mae_db": 0.7418139805344115, "mr_stft_db": 5.987691861052439, "band_mae_db": 0.527131550309206, "rms_gain_error_db": 0.08118240962879372, "output_peak": 0.03259478466134627}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6205738955578257, "全帯域_10ms_rms_envelope_nrmse": 0.1493377337085122, "全帯域_10ms_envelope_correlation": 0.9829297075807394, "全帯域_10ms_modulation_mae_db": 0.5298064311752978, "全帯域_40ms_log_rms_mae_db": 0.9055433277839403, "全帯域_40ms_rms_envelope_nrmse": 0.08556698587783733, "全帯域_40ms_envelope_correlation": 0.9940665976399801, "全帯域_40ms_modulation_mae_db": 0.8332778718616217, "300–1000 Hz_10ms_log_rms_mae_db": 2.4090394401578834, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2606028073599362, "300–1000 Hz_10ms_envelope_correlation": 0.9545193967338589, "300–1000 Hz_10ms_modulation_mae_db": 0.4526768644469981, "300–1000 Hz_40ms_log_rms_mae_db": 1.763140678463722, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14165102080266848, "300–1000 Hz_40ms_envelope_correlation": 0.9863692907224626, "300–1000 Hz_40ms_modulation_mae_db": 0.5243678858127258, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4621145110900606, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17421521764951495, "1000–3000 Hz_10ms_envelope_correlation": 0.9804145781147737, "1000–3000 Hz_10ms_modulation_mae_db": 0.2840662243596199, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8090102105691246, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09068740918439805, "1000–3000 Hz_40ms_envelope_correlation": 0.9945363368919082, "1000–3000 Hz_40ms_modulation_mae_db": 0.5121715422273599, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1435423434509653, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1870225039148724, "3000–6000 Hz_10ms_envelope_correlation": 0.979719313462492, "3000–6000 Hz_10ms_modulation_mae_db": 0.8402494117616492, "3000–6000 Hz_40ms_log_rms_mae_db": 0.803312229184926, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11384570916686826, "3000–6000 Hz_40ms_envelope_correlation": 0.9931118609858952, "3000–6000 Hz_40ms_modulation_mae_db": 1.175969743168871, "mr_stft_db": 5.996096133786875, "band_mae_db": 0.6560050826518582, "rms_gain_error_db": -0.037137859566919736, "output_peak": 0.0311258160753238}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.159802050450024, "spectral_convergence": 0.6054323650135277, "spectral_convergence_status": "ok", "amplitude_floor": 9.167242110941195e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.862466570256485, "spectral_convergence": 0.6140858545622966, "spectral_convergence_status": "ok", "amplitude_floor": 5.84028801806317e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.972743108221741, "spectral_convergence": 0.6410896742395935, "spectral_convergence_status": "ok", "amplitude_floor": 2.8939654187001563e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.3843123087683508e-07, "output_power": 1.377009670415887e-07, "delta_db": -0.02297090276005366, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.81286342317638e-08, "output_power": 1.3471476910235446e-07, "delta_db": 2.96085528309362, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 9.335883160942139e-07, "output_power": 9.178070990059546e-07, "delta_db": -0.07403995323859162, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.7505166473017637e-06, "output_power": 1.7099001344446137e-06, "delta_db": -0.10195498774799083, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.470519881244434e-07, "output_power": 5.942014425628854e-07, "delta_db": 0.3590510111263696, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.7292398267785066e-06, "output_power": 2.7674380168543325e-06, "delta_db": 0.06036202483472612, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.57439203602588e-07, "output_power": 9.55940144672806e-07, "delta_db": -0.006805060951900753, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.5122913176790361, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.05650939919108006, "pitch": null, "output_rms_dbfs": -51.41601018268333, "output_peak": 0.03672298959257386, "reference_rms_dbfs": -51.47251958187441, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.998337242976084}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.1370250428801243e-05, "log_rms_mae_db": 1.6183871777228895, "rms_envelope_nrmse": 0.14685288899310112, "envelope_correlation": 0.9837171034347802, "rms_gain_error_db": 0.056508730662753186, "reference_mean_power": 7.130327548553108e-06, "output_mean_power": 7.223710849508411e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.4304416670730408e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2770281801289633e-06, "output_power": 1.3862804573323094e-06, "reference_active": true, "delta_db": 0.3565062001912809}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.124025700263392e-07, "output_power": 2.3230170053473323e-07, "reference_active": true, "delta_db": 0.3889262169585399}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.509706557401959e-07, "output_power": 1.3962903800910835e-07, "reference_active": true, "delta_db": -0.339167955018818}], "active_band_count": 3, "active_band_mae_db": 0.3615334573895463}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.27501987121069e-06, "log_rms_mae_db": 0.8827501418116014, "rms_envelope_nrmse": 0.07986695797501224, "envelope_correlation": 0.9949192891208529, "rms_gain_error_db": 0.05651467816897705, "reference_mean_power": 7.166117032249278e-06, "output_mean_power": 7.259978997300033e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.171922661595567e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0939532041259814e-06, "output_power": 1.208414226745087e-06, "reference_active": true, "delta_db": 0.43217084966519764}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.164609293708589e-07, "output_power": 1.1706681503241041e-07, "reference_active": true, "delta_db": 0.02253551419056255}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0690330771826293e-08, "output_power": 7.953436172034003e-09, "reference_active": true, "delta_db": -1.2843634289503405}], "active_band_count": 3, "active_band_mae_db": 0.5796899309353669}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 6.556092771800097e-06, "log_rms_mae_db": 2.395094906105189, "rms_envelope_nrmse": 0.24123771948791214, "envelope_correlation": 0.961135965850391, "rms_gain_error_db": 0.30801756416075876, "reference_mean_power": 7.945163829144021e-07, "output_mean_power": 8.529127628988609e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.0791155245365873e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.4868570435085076e-07, "output_power": 1.6114994283600986e-07, "reference_active": true, "delta_db": 0.3496094127242647}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.530749650867304e-08, "output_power": 3.475820580441566e-08, "reference_active": true, "delta_db": -0.06809574479670831}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.4918697573140088e-08, "output_power": 2.6713866795590728e-08, "reference_active": true, "delta_db": 0.302114168142139}], "active_band_count": 3, "active_band_mae_db": 0.23993977522103735}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.158309417730701e-06, "log_rms_mae_db": 1.7329756073575395, "rms_envelope_nrmse": 0.1386220704242785, "envelope_correlation": 0.9869700404474218, "rms_gain_error_db": 0.3080201115569646, "reference_mean_power": 7.985041710031799e-07, "output_mean_power": 8.571941533257339e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.7036737518374816e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3140926226909544e-07, "output_power": 1.4719865261281907e-07, "reference_active": true, "delta_db": 0.4927785751589102}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.929219128746953e-08, "output_power": 1.917407115452717e-08, "reference_active": true, "delta_db": -0.0266722472751689}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4692549483461402e-09, "output_power": 1.4695459403314898e-09, "reference_active": true, "delta_db": 0.0008600529176053008}], "active_band_count": 3, "active_band_mae_db": 0.17343695845056148}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 7.401330296636983e-06, "log_rms_mae_db": 1.5250347508264523, "rms_envelope_nrmse": 0.21363516305446978, "envelope_correlation": 0.9715615133632539, "rms_gain_error_db": 0.22098939046795935, "reference_mean_power": 1.4849128654353035e-06, "output_mean_power": 1.5624276251923493e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.41811499304529e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.69138926350769e-07, "output_power": 2.6459620170377263e-07, "reference_active": true, "delta_db": -0.07392910019051674}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.521731226006148e-08, "output_power": 4.9739944240961606e-08, "reference_active": true, "delta_db": 0.41400549992577484}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6338303134826183e-08, "output_power": 2.3011295943725922e-08, "reference_active": true, "delta_db": -0.5864671394285014}], "active_band_count": 3, "active_band_mae_db": 0.35813391318159765}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 6.380552881753602e-06, "log_rms_mae_db": 0.8581974605250784, "rms_envelope_nrmse": 0.12068946040836549, "envelope_correlation": 0.9909308297903, "rms_gain_error_db": 0.22099765049748588, "reference_mean_power": 1.4923708236731126e-06, "output_mean_power": 1.5702778870177461e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.994698288619123e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.551906678142862e-07, "output_power": 2.5329306688604264e-07, "reference_active": true, "delta_db": -0.03241485937873379}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4359212852663977e-08, "output_power": 2.508297979984197e-08, "reference_active": true, "delta_db": 0.1271587807182099}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5357702928828252e-09, "output_power": 1.1200607534998448e-09, "reference_active": true, "delta_db": -1.3708468258819029}], "active_band_count": 3, "active_band_mae_db": 0.5101401553262822}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0774952268311018e-05, "log_rms_mae_db": 1.1589956844458629, "rms_envelope_nrmse": 0.19402850746211345, "envelope_correlation": 0.9783897232208523, "rms_gain_error_db": 0.15011274076869313, "reference_mean_power": 1.995223201702535e-06, "output_mean_power": 2.0653932839443575e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.579487211503375e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.151593028482198e-07, "output_power": 8.111084677053525e-07, "reference_active": true, "delta_db": 0.5467614296678084}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2474197679576555e-07, "output_power": 1.3625060240850692e-07, "reference_active": true, "delta_db": 0.383258090430409}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.137663053230787e-08, "output_power": 8.634945700041934e-08, "reference_active": true, "delta_db": 0.2575990733439145}], "active_band_count": 3, "active_band_mae_db": 0.39587286448071063}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 7.143885674653834e-06, "log_rms_mae_db": 0.755653868384136, "rms_envelope_nrmse": 0.09788692007894802, "envelope_correlation": 0.9944568134576593, "rms_gain_error_db": 0.15011285588319437, "reference_mean_power": 2.0052568878051223e-06, "output_mean_power": 2.075779900163843e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.5118360803946574e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.45069205976456e-07, "output_power": 7.34643121852032e-07, "reference_active": true, "delta_db": 0.5647010660474395}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.385509447185785e-08, "output_power": 8.64863357747328e-08, "reference_active": true, "delta_db": 0.13418044891698266}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.733755662328774e-09, "output_power": 5.305286771122598e-09, "reference_active": true, "delta_db": -0.33730317868302495}], "active_band_count": 3, "active_band_mae_db": 0.34539489788248234}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5114770442855936, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "606e16e596cc5603b35db79c57214f3ea81a1d9ce468cfa2b2d44b96f3c66483", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.976504165675916, "standard_deviation": 0.0035556972905090673, "minimum": 0.9715615133632539, "maximum": 0.9804145781147737, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4958211272822415, "standard_deviation": 0.03270602043317992, "minimum": 1.445541347216604, "maximum": 1.5270587156933526, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.50475866415739, "standard_deviation": 0.2711212821058268, "minimum": 0.05593894770804508, "maximum": 0.9187953225003316, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1910243162702734, "standard_deviation": 0.014653322170531667, "minimum": 0.17421521764951495, "maximum": 0.21363516305446978, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9935928675480497, "standard_deviation": 0.0016866282565968795, "minimum": 0.9909308297903, "maximum": 0.9960171858278795, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8537438306721021, "standard_deviation": 0.030484892114374353, "minimum": 0.8090102105691246, "maximum": 0.90624911945684, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5389521093065844, "standard_deviation": 0.1918776922163772, "minimum": 0.1906496231209779, "maximum": 0.7588165778660386, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.099200355798032, "standard_deviation": 0.013016860793411668, "minimum": 0.08284345078053797, "maximum": 0.12068946040836549, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9842021713074735, "standard_deviation": 0.003624698762974799, "minimum": 0.9783897232208523, "maximum": 0.9892456977911593, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.1542653901898117, "standard_deviation": 0.015215981367624594, "minimum": 1.1265920511248253, "maximum": 1.1731648226429208, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.49298873454343506, "standard_deviation": 0.20735373081774855, "minimum": 0.27512032030404915, "maximum": 0.8402494117616492, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16391742112958407, "standard_deviation": 0.01915328676722838, "minimum": 0.13572064208628434, "maximum": 0.19402850746211345, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9958476649631507, "standard_deviation": 0.001493781718530724, "minimum": 0.9931118609858952, "maximum": 0.9977984867344116, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7473264012589562, "standard_deviation": 0.02836247750681985, "minimum": 0.7031423178259427, "maximum": 0.803312229184926, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.8019732888661761, "standard_deviation": 0.31275582460401447, "minimum": 0.34539489788248234, "maximum": 1.1791421153237405, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08378389127692204, "standard_deviation": 0.01654848158918922, "minimum": 0.06071712830617054, "maximum": 0.11384570916686826, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9490815382050635, "standard_deviation": 0.007161159079371478, "minimum": 0.9382681492289039, "maximum": 0.961135965850391, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.388211523376569, "standard_deviation": 0.021820699375918882, "minimum": 2.355452194542591, "maximum": 2.4135827079137133, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.3343778555312956, "standard_deviation": 0.147033703407233, "minimum": 0.1799554711259913, "maximum": 0.5979011080586935, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2774350472382663, "standard_deviation": 0.01948272734904986, "minimum": 0.24123771948791214, "maximum": 0.29797700073817013, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.982792227161138, "standard_deviation": 0.003906449866078192, "minimum": 0.9764651258443053, "maximum": 0.9869700404474218, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.7375420936109307, "standard_deviation": 0.02870684206268341, "minimum": 1.6811770296463697, "maximum": 1.763140678463722, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.44713318613532915, "standard_deviation": 0.1627577314388645, "minimum": 0.17343695845056148, "maximum": 0.6279298033096802, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.16041426631772204, "standard_deviation": 0.020762010121709317, "minimum": 0.13825532938899948, "maximum": 0.19076430723581564, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.5313416406225351, "standard_deviation": 0.07609662544254851, "minimum": 0.4484204266407584, "maximum": 0.6560050826518582, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.993845693010727, "standard_deviation": 0.004383954373012318, "minimum": 5.987691861052439, "maximum": 5.999285825193529, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.03293255742189634, "standard_deviation": 0.0017692947695077846, "minimum": 0.0311258160753238, "maximum": 0.03672298959257386, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.008197917994192372, "standard_deviation": 0.07585112866993458, "minimum": -0.1640417665997469, "maximum": 0.08118240962879372, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.984050114811714, "standard_deviation": 0.0015417557192309438, "minimum": 0.9823857752461458, "maximum": 0.986719587342524, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.6382953486777967, "standard_deviation": 0.026237214706073618, "minimum": 1.6183871777228895, "maximum": 1.682948563115452, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3993230964765536, "standard_deviation": 0.1353401923961507, "minimum": 0.1666763688464691, "maximum": 0.5868296956486626, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.1447172501933767, "standard_deviation": 0.00716545245447416, "minimum": 0.13178855166282682, "maximum": 0.1516585344707293, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9959658285366084, "standard_deviation": 0.001019866521267811, "minimum": 0.9940665976399801, "maximum": 0.9972517618780966, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8574005002588188, "standard_deviation": 0.036444897454348785, "minimum": 0.8081174711449414, "maximum": 0.9055433277839403, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6936280185023274, "standard_deviation": 0.1911921776416532, "minimum": 0.431147245634473, "maximum": 1.0129958238964591, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.07073666883420662, "standard_deviation": 0.008508913468096685, "minimum": 0.05837117451347525, "maximum": 0.08556698587783733, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 1.9217102527618408, "predicted_mos": 1.9217102527618408, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "23297adc581706dc775af6ef1599b01c89b6ca841aa3faf10293728ecd13a92d", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.112916700076312}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.606482057169033, "全帯域_10ms_rms_envelope_nrmse": 0.12174055238620397, "全帯域_10ms_envelope_correlation": 0.9886886324038016, "全帯域_10ms_modulation_mae_db": 0.66832598062889, "全帯域_40ms_log_rms_mae_db": 0.8547867256565262, "全帯域_40ms_rms_envelope_nrmse": 0.061559734065231755, "全帯域_40ms_envelope_correlation": 0.9969402598107888, "全帯域_40ms_modulation_mae_db": 1.1041279466957241, "300–1000 Hz_10ms_log_rms_mae_db": 2.547171475034708, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24854626864186233, "300–1000 Hz_10ms_envelope_correlation": 0.9595900753828264, "300–1000 Hz_10ms_modulation_mae_db": 0.31144953904149014, "300–1000 Hz_40ms_log_rms_mae_db": 1.9342851105132666, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1410059128077861, "300–1000 Hz_40ms_envelope_correlation": 0.9871812205371369, "300–1000 Hz_40ms_modulation_mae_db": 0.4527310556603626, "1000–3000 Hz_10ms_log_rms_mae_db": 1.667927473666642, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1839853165856901, "1000–3000 Hz_10ms_envelope_correlation": 0.9793361077538344, "1000–3000 Hz_10ms_modulation_mae_db": 0.732994038972515, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0020631793033963, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09112820586453366, "1000–3000 Hz_40ms_envelope_correlation": 0.9952741133240204, "1000–3000 Hz_40ms_modulation_mae_db": 0.7947273841345361, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3827572666479266, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15123768026040066, "3000–6000 Hz_10ms_envelope_correlation": 0.9866696627696501, "3000–6000 Hz_10ms_modulation_mae_db": 0.8339901115041605, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0181384526262858, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08570080759828709, "3000–6000 Hz_40ms_envelope_correlation": 0.9959589643310321, "3000–6000 Hz_40ms_modulation_mae_db": 1.6813484964751721, "mr_stft_db": 6.051824468785102, "band_mae_db": 0.6237107294559358, "rms_gain_error_db": -0.022968459119471207, "output_peak": 0.041731184164169405}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5368745605043967, "全帯域_10ms_rms_envelope_nrmse": 0.13397522953435495, "全帯域_10ms_envelope_correlation": 0.986292046285489, "全帯域_10ms_modulation_mae_db": 0.6142293551172157, "全帯域_40ms_log_rms_mae_db": 0.7869323866132178, "全帯域_40ms_rms_envelope_nrmse": 0.06317289116720488, "全帯域_40ms_envelope_correlation": 0.9969461819576865, "全帯域_40ms_modulation_mae_db": 0.7926289669880342, "300–1000 Hz_10ms_log_rms_mae_db": 2.5347231014179785, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24666229666514516, "300–1000 Hz_10ms_envelope_correlation": 0.9603474448498421, "300–1000 Hz_10ms_modulation_mae_db": 1.0081004451369562, "300–1000 Hz_40ms_log_rms_mae_db": 1.8559604247781671, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14209051189922056, "300–1000 Hz_40ms_envelope_correlation": 0.9869721956487332, "300–1000 Hz_40ms_modulation_mae_db": 1.096175908566675, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6388415494644746, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16289593289908696, "1000–3000 Hz_10ms_envelope_correlation": 0.9827131313598898, "1000–3000 Hz_10ms_modulation_mae_db": 0.5123077804301756, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0556595531991315, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0891275810831009, "1000–3000 Hz_40ms_envelope_correlation": 0.9949305940223157, "1000–3000 Hz_40ms_modulation_mae_db": 0.9421611281756578, "3000–6000 Hz_10ms_log_rms_mae_db": 1.353684440441687, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18004710903136573, "3000–6000 Hz_10ms_envelope_correlation": 0.9810927379512665, "3000–6000 Hz_10ms_modulation_mae_db": 1.2380115491840291, "3000–6000 Hz_40ms_log_rms_mae_db": 0.926276122991365, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09628022659611075, "3000–6000 Hz_40ms_envelope_correlation": 0.9951369094016428, "3000–6000 Hz_40ms_modulation_mae_db": 1.9309073020282284, "mr_stft_db": 6.0503809245692475, "band_mae_db": 0.5985382700079879, "rms_gain_error_db": -0.14203514838476686, "output_peak": 0.03240777334203268}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5985081792547138, "全帯域_10ms_rms_envelope_nrmse": 0.1456461509381787, "全帯域_10ms_envelope_correlation": 0.9841997834658821, "全帯域_10ms_modulation_mae_db": 0.224597403636287, "全帯域_40ms_log_rms_mae_db": 0.8877077026975396, "全帯域_40ms_rms_envelope_nrmse": 0.08661976670368003, "全帯域_40ms_envelope_correlation": 0.9941600674534926, "全帯域_40ms_modulation_mae_db": 0.4606202147001915, "300–1000 Hz_10ms_log_rms_mae_db": 2.47992958420884, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26776071601826545, "300–1000 Hz_10ms_envelope_correlation": 0.9500763998632308, "300–1000 Hz_10ms_modulation_mae_db": 0.47654679369576175, "300–1000 Hz_40ms_log_rms_mae_db": 1.9219836586149859, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1731550954144753, "300–1000 Hz_40ms_envelope_correlation": 0.9778378414695849, "300–1000 Hz_40ms_modulation_mae_db": 0.3990987457587816, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5998051586185698, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17934511111286058, "1000–3000 Hz_10ms_envelope_correlation": 0.978985767181262, "1000–3000 Hz_10ms_modulation_mae_db": 0.11828418503294376, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9867957259502484, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08981098404389273, "1000–3000 Hz_40ms_envelope_correlation": 0.9946226331121866, "1000–3000 Hz_40ms_modulation_mae_db": 0.4485530514585892, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3325413591775455, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18455043660622616, "3000–6000 Hz_10ms_envelope_correlation": 0.981950352799703, "3000–6000 Hz_10ms_modulation_mae_db": 0.5150583900630668, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9189764181178949, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1126375054398304, "3000–6000 Hz_40ms_envelope_correlation": 0.9937881346501382, "3000–6000 Hz_40ms_modulation_mae_db": 0.7101458329735694, "mr_stft_db": 6.050309498406308, "band_mae_db": 0.555460985447553, "rms_gain_error_db": 0.10420030953478378, "output_peak": 0.038084859933323265}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5623022291784716, "全帯域_10ms_rms_envelope_nrmse": 0.13853404339859865, "全帯域_10ms_envelope_correlation": 0.9854968130932489, "全帯域_10ms_modulation_mae_db": 0.3978966510201243, "全帯域_40ms_log_rms_mae_db": 0.8161384633816673, "全帯域_40ms_rms_envelope_nrmse": 0.06734469262146672, "全帯域_40ms_envelope_correlation": 0.9963866183567058, "全帯域_40ms_modulation_mae_db": 0.695047150227817, "300–1000 Hz_10ms_log_rms_mae_db": 2.545805054824686, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27479064729315295, "300–1000 Hz_10ms_envelope_correlation": 0.9491395017542931, "300–1000 Hz_10ms_modulation_mae_db": 0.2537134062329031, "300–1000 Hz_40ms_log_rms_mae_db": 1.969826629829157, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1704384956481437, "300–1000 Hz_40ms_envelope_correlation": 0.9797186935426985, "300–1000 Hz_40ms_modulation_mae_db": 0.5431278607544826, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6171605587216007, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20954849716347695, "1000–3000 Hz_10ms_envelope_correlation": 0.9737354407522657, "1000–3000 Hz_10ms_modulation_mae_db": 0.7415014275113286, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9770191573546273, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10651155820018421, "1000–3000 Hz_40ms_envelope_correlation": 0.9938080563788079, "1000–3000 Hz_40ms_modulation_mae_db": 0.3607974423327862, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3247789314568634, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14938207438945128, "3000–6000 Hz_10ms_envelope_correlation": 0.9870017677089458, "3000–6000 Hz_10ms_modulation_mae_db": 0.5251376377363149, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8928565512818274, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06546649682944318, "3000–6000 Hz_40ms_envelope_correlation": 0.9974560039700129, "3000–6000 Hz_40ms_modulation_mae_db": 1.0104231891946662, "mr_stft_db": 6.0359493042745, "band_mae_db": 0.5427426588727272, "rms_gain_error_db": 0.051004102558959256, "output_peak": 0.03317352059298638}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5439719416161377, "全帯域_10ms_rms_envelope_nrmse": 0.14426534874644836, "全帯域_10ms_envelope_correlation": 0.984070710132003, "全帯域_10ms_modulation_mae_db": 0.5941879172870107, "全帯域_40ms_log_rms_mae_db": 0.788609972484311, "全帯域_40ms_rms_envelope_nrmse": 0.06979425193800552, "全帯域_40ms_envelope_correlation": 0.9961016444276131, "全帯域_40ms_modulation_mae_db": 0.9733307725819955, "300–1000 Hz_10ms_log_rms_mae_db": 2.510429964075124, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2619516747323964, "300–1000 Hz_10ms_envelope_correlation": 0.9525952139613149, "300–1000 Hz_10ms_modulation_mae_db": 0.24165885412741725, "300–1000 Hz_40ms_log_rms_mae_db": 1.8758783457988872, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13809802772210686, "300–1000 Hz_40ms_envelope_correlation": 0.9861877483873878, "300–1000 Hz_40ms_modulation_mae_db": 0.47835155135500323, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5670805212118888, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1703870034480965, "1000–3000 Hz_10ms_envelope_correlation": 0.9811807041636532, "1000–3000 Hz_10ms_modulation_mae_db": 0.6267888866135752, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9549241377752812, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08575754995809101, "1000–3000 Hz_40ms_envelope_correlation": 0.9951386309894708, "1000–3000 Hz_40ms_modulation_mae_db": 0.9402485973189284, "3000–6000 Hz_10ms_log_rms_mae_db": 1.345246904195976, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18269166476508017, "3000–6000 Hz_10ms_envelope_correlation": 0.980193443816821, "3000–6000 Hz_10ms_modulation_mae_db": 0.8482136200100566, "3000–6000 Hz_40ms_log_rms_mae_db": 0.892099132441745, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09677957760350615, "3000–6000 Hz_40ms_envelope_correlation": 0.9943224887426698, "3000–6000 Hz_40ms_modulation_mae_db": 1.2072200782814808, "mr_stft_db": 6.05401713919994, "band_mae_db": 0.5602946888429905, "rms_gain_error_db": -0.049533635483571876, "output_peak": 0.033776020239575426}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5821843715684039, "全帯域_10ms_rms_envelope_nrmse": 0.13134073280876926, "全帯域_10ms_envelope_correlation": 0.9867984236614017, "全帯域_10ms_modulation_mae_db": 0.4479508512475206, "全帯域_40ms_log_rms_mae_db": 0.8698758234413655, "全帯域_40ms_rms_envelope_nrmse": 0.0729678730946054, "全帯域_40ms_envelope_correlation": 0.9957607232291228, "全帯域_40ms_modulation_mae_db": 0.7525565677421548, "300–1000 Hz_10ms_log_rms_mae_db": 2.5493397062875984, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25085144504094953, "300–1000 Hz_10ms_envelope_correlation": 0.9579912389516223, "300–1000 Hz_10ms_modulation_mae_db": 0.5984179521367476, "300–1000 Hz_40ms_log_rms_mae_db": 1.8494445916570426, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1457266968030523, "300–1000 Hz_40ms_envelope_correlation": 0.9855826417255363, "300–1000 Hz_40ms_modulation_mae_db": 0.7404972051355223, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6272543213151849, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18666877653169606, "1000–3000 Hz_10ms_envelope_correlation": 0.977349582675641, "1000–3000 Hz_10ms_modulation_mae_db": 0.21152927989397938, "1000–3000 Hz_40ms_log_rms_mae_db": 1.044700868221807, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10079850174627487, "1000–3000 Hz_40ms_envelope_correlation": 0.9931931949485582, "1000–3000 Hz_40ms_modulation_mae_db": 0.6910825186327888, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3369704153815596, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15460195852834893, "3000–6000 Hz_10ms_envelope_correlation": 0.9861914014790184, "3000–6000 Hz_10ms_modulation_mae_db": 0.5104463989238631, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8973454881916838, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09624077002839582, "3000–6000 Hz_40ms_envelope_correlation": 0.9949416103289629, "3000–6000 Hz_40ms_modulation_mae_db": 0.9460940824981732, "mr_stft_db": 6.041340350074573, "band_mae_db": 0.421510879141578, "rms_gain_error_db": -0.10518171967954411, "output_peak": 0.032705819551063546}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5515943575651274, "全帯域_10ms_rms_envelope_nrmse": 0.14805579262493043, "全帯域_10ms_envelope_correlation": 0.9832268785256378, "全帯域_10ms_modulation_mae_db": 0.453631630556186, "全帯域_40ms_log_rms_mae_db": 0.8147049204506019, "全帯域_40ms_rms_envelope_nrmse": 0.07754002318946102, "全帯域_40ms_envelope_correlation": 0.9951433997266035, "全帯域_40ms_modulation_mae_db": 0.8431173631339418, "300–1000 Hz_10ms_log_rms_mae_db": 2.421190586338598, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3070991266925789, "300–1000 Hz_10ms_envelope_correlation": 0.9355971124632709, "300–1000 Hz_10ms_modulation_mae_db": 0.22644114828481846, "300–1000 Hz_40ms_log_rms_mae_db": 1.8307382223143949, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1927496060251899, "300–1000 Hz_40ms_envelope_correlation": 0.9732554212911313, "300–1000 Hz_40ms_modulation_mae_db": 0.1896004480125255, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6243210360618898, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17051933781727466, "1000–3000 Hz_10ms_envelope_correlation": 0.9809727914411339, "1000–3000 Hz_10ms_modulation_mae_db": 0.49296274824557446, "1000–3000 Hz_40ms_log_rms_mae_db": 1.089934732781239, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1025580399799105, "1000–3000 Hz_40ms_envelope_correlation": 0.9929538585186845, "1000–3000 Hz_40ms_modulation_mae_db": 0.5887551873619471, "3000–6000 Hz_10ms_log_rms_mae_db": 1.309356403094407, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19191504668934845, "3000–6000 Hz_10ms_envelope_correlation": 0.9788366305779345, "3000–6000 Hz_10ms_modulation_mae_db": 0.6839213077087732, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9027538224062991, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09776679293716499, "3000–6000 Hz_40ms_envelope_correlation": 0.994461561739949, "3000–6000 Hz_40ms_modulation_mae_db": 0.9525998860409167, "mr_stft_db": 6.0477726033728025, "band_mae_db": 0.5162256912212123, "rms_gain_error_db": -0.052929585287796455, "output_peak": 0.036857048293684525}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.529275917214631, "全帯域_10ms_rms_envelope_nrmse": 0.1395841740601228, "全帯域_10ms_envelope_correlation": 0.9851022679760842, "全帯域_10ms_modulation_mae_db": 0.5987907076624922, "全帯域_40ms_log_rms_mae_db": 0.8234141128173393, "全帯域_40ms_rms_envelope_nrmse": 0.06452881003070643, "全帯域_40ms_envelope_correlation": 0.9966578002686887, "全帯域_40ms_modulation_mae_db": 0.6607993150764453, "300–1000 Hz_10ms_log_rms_mae_db": 2.508196498443229, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27823465463517133, "300–1000 Hz_10ms_envelope_correlation": 0.9514140720767326, "300–1000 Hz_10ms_modulation_mae_db": 0.811098409288234, "300–1000 Hz_40ms_log_rms_mae_db": 1.8983492851936679, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16150554459837005, "300–1000 Hz_40ms_envelope_correlation": 0.9845687400452973, "300–1000 Hz_40ms_modulation_mae_db": 0.7761138770402104, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5858805129696119, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1666506279358885, "1000–3000 Hz_10ms_envelope_correlation": 0.9819242851534673, "1000–3000 Hz_10ms_modulation_mae_db": 0.5107201239627522, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0018220515071041, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08288011304078645, "1000–3000 Hz_40ms_envelope_correlation": 0.9954811854168545, "1000–3000 Hz_40ms_modulation_mae_db": 0.5611535361484719, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3448526604952915, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15700168877303236, "3000–6000 Hz_10ms_envelope_correlation": 0.9854038640739673, "3000–6000 Hz_10ms_modulation_mae_db": 0.45781967636045806, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9301762924699379, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07011941156031512, "3000–6000 Hz_40ms_envelope_correlation": 0.9971158111423186, "3000–6000 Hz_40ms_modulation_mae_db": 0.5883633700151516, "mr_stft_db": 6.033697816205155, "band_mae_db": 0.6122096488316389, "rms_gain_error_db": -0.027660256738911627, "output_peak": 0.034983724785176654}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.2950006229559765, "spectral_convergence": 0.615581661361619, "spectral_convergence_status": "ok", "amplitude_floor": 9.167242110941195e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.899558836501715, "spectral_convergence": 0.6157823960705368, "spectral_convergence_status": "ok", "amplitude_floor": 5.84028801806317e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.960913946897616, "spectral_convergence": 0.6452803714978628, "spectral_convergence_status": "ok", "amplitude_floor": 2.8939654187001563e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.3843123087683508e-07, "output_power": 1.2712998570568205e-07, "delta_db": -0.36986082332922954, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.81286342317638e-08, "output_power": 1.4250158460218123e-07, "delta_db": 3.2049001091238143, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 9.335883160942139e-07, "output_power": 9.45712034602974e-07, "delta_db": 0.056035078068343444, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.7505166473017637e-06, "output_power": 1.7661169786861444e-06, "delta_db": 0.038532204380133564, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.470519881244434e-07, "output_power": 5.921386802697503e-07, "delta_db": 0.34394830715559666, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.7292398267785066e-06, "output_power": 2.5790547476591524e-06, "delta_db": -0.24581138799123575, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.57439203602588e-07, "output_power": 9.341626230243578e-07, "delta_db": -0.10688719614319697, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.6237107294559358, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.022968459119471207, "pitch": null, "output_rms_dbfs": -51.495488040993884, "output_peak": 0.041731184164169405, "reference_rms_dbfs": -51.47251958187441, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.051824468785102}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.1370250428801243e-05, "log_rms_mae_db": 1.606482057169033, "rms_envelope_nrmse": 0.12174055238620397, "envelope_correlation": 0.9886886324038016, "rms_gain_error_db": -0.02297052316837956, "reference_mean_power": 7.130327548553108e-06, "output_mean_power": 7.092713677094365e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.4304416670730408e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2770281801289633e-06, "output_power": 1.2904001497146321e-06, "reference_active": true, "delta_db": 0.04523923840720926}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.124025700263392e-07, "output_power": 2.2124352117434823e-07, "reference_active": true, "delta_db": 0.1771079450019078}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.509706557401959e-07, "output_power": 1.001450448902027e-07, "reference_active": true, "delta_db": -1.7826307584775534}], "active_band_count": 3, "active_band_mae_db": 0.66832598062889}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.27501987121069e-06, "log_rms_mae_db": 0.8547867256565262, "rms_envelope_nrmse": 0.061559734065231755, "envelope_correlation": 0.9969402598107888, "rms_gain_error_db": -0.022980172185889144, "reference_mean_power": 7.166117032249278e-06, "output_mean_power": 7.128298526822974e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.171922661595567e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0939532041259814e-06, "output_power": 1.1212803022044203e-06, "reference_active": true, "delta_db": 0.10715448221746074}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.164609293708589e-07, "output_power": 1.0710428968362692e-07, "reference_active": true, "delta_db": -0.363733861928443}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0690330771826293e-08, "output_power": 5.557015311538686e-09, "reference_active": true, "delta_db": -2.8414954959412686}], "active_band_count": 3, "active_band_mae_db": 1.1041279466957241}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 6.556092771800097e-06, "log_rms_mae_db": 2.547171475034708, "rms_envelope_nrmse": 0.24854626864186233, "envelope_correlation": 0.9595900753828264, "rms_gain_error_db": 0.39563538190856307, "reference_mean_power": 7.945163829144021e-07, "output_mean_power": 8.702948127153531e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.0791155245365873e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.4868570435085076e-07, "output_power": 1.665882808438013e-07, "reference_active": true, "delta_db": 0.4937523186654268}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.530749650867304e-08, "output_power": 3.709976633095394e-08, "reference_active": true, "delta_db": 0.21504249423630828}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.4918697573140088e-08, "output_power": 2.6247063364746704e-08, "reference_active": true, "delta_db": 0.2255538042227354}], "active_band_count": 3, "active_band_mae_db": 0.31144953904149014}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.158309417730701e-06, "log_rms_mae_db": 1.9342851105132666, "rms_envelope_nrmse": 0.1410059128077861, "envelope_correlation": 0.9871812205371369, "rms_gain_error_db": 0.3956092812511014, "reference_mean_power": 7.985041710031799e-07, "output_mean_power": 8.746576866496684e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.7036737518374816e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3140926226909544e-07, "output_power": 1.5169275846658334e-07, "reference_active": true, "delta_db": 0.6233887168490688}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.929219128746953e-08, "output_power": 1.8952019995306418e-08, "reference_active": true, "delta_db": -0.07726053505550677}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4692549483461402e-09, "output_power": 1.709430913718329e-09, "reference_active": true, "delta_db": 0.6575439150765122}], "active_band_count": 3, "active_band_mae_db": 0.4527310556603626}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 7.401330296636983e-06, "log_rms_mae_db": 1.667927473666642, "rms_envelope_nrmse": 0.1839853165856901, "envelope_correlation": 0.9793361077538344, "rms_gain_error_db": 0.277141188478943, "reference_mean_power": 1.4849128654353035e-06, "output_mean_power": 1.5827600830060684e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.41811499304529e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.69138926350769e-07, "output_power": 2.7241039271869516e-07, "reference_active": true, "delta_db": 0.05247156720478449}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.521731226006148e-08, "output_power": 4.8265010680101996e-08, "reference_active": true, "delta_db": 0.28327662534401893}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6338303134826183e-08, "output_power": 1.7150010857978408e-08, "reference_active": true, "delta_db": -1.8632339243687415}], "active_band_count": 3, "active_band_mae_db": 0.732994038972515}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 6.380552881753602e-06, "log_rms_mae_db": 1.0020631793033963, "rms_envelope_nrmse": 0.09112820586453366, "envelope_correlation": 0.9952741133240204, "rms_gain_error_db": 0.2771348043714308, "reference_mean_power": 1.4923708236731126e-06, "output_mean_power": 1.590707139464996e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.994698288619123e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.551906678142862e-07, "output_power": 2.5755672307663606e-07, "reference_active": true, "delta_db": 0.04008102453869687}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4359212852663977e-08, "output_power": 2.283950600925394e-08, "reference_active": true, "delta_db": -0.27976543915380214}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5357702928828252e-09, "output_power": 9.54756653807547e-10, "reference_active": true, "delta_db": -2.0643356887111093}], "active_band_count": 3, "active_band_mae_db": 0.7947273841345361}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0774952268311018e-05, "log_rms_mae_db": 1.3827572666479266, "rms_envelope_nrmse": 0.15123768026040066, "envelope_correlation": 0.9866696627696501, "rms_gain_error_db": -0.25801904495678757, "reference_mean_power": 1.995223201702535e-06, "output_mean_power": 1.8801373712264773e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.579487211503375e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.151593028482198e-07, "output_power": 6.980029764031229e-07, "reference_active": true, "delta_db": -0.10545517816725239}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2474197679576555e-07, "output_power": 1.1777382113810439e-07, "reference_active": true, "delta_db": -0.24963856224340278}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.137663053230787e-08, "output_power": 4.963774505728586e-08, "reference_active": true, "delta_db": -2.146876594101826}], "active_band_count": 3, "active_band_mae_db": 0.8339901115041605}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 7.143885674653834e-06, "log_rms_mae_db": 1.0181384526262858, "rms_envelope_nrmse": 0.08570080759828709, "envelope_correlation": 0.9959589643310321, "rms_gain_error_db": -0.25801920204990564, "reference_mean_power": 2.0052568878051223e-06, "output_mean_power": 1.8895922391441432e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.5118360803946574e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.45069205976456e-07, "output_power": 6.357735008938104e-07, "reference_active": true, "delta_db": -0.06303887717864029}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.385509447185785e-08, "output_power": 6.640256861964216e-08, "reference_active": true, "delta_db": -1.0134457325279904}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.733755662328774e-09, "output_power": 2.299763061188111e-09, "reference_active": true, "delta_db": -3.967560879718886}], "active_band_count": 3, "active_band_mae_db": 1.6813484964751721}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.531100921840826, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "ec2aa7e331d7f5245d77d76517546f70133a766554cde33655e1e4cb87ab2205", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9795247263101434, "standard_deviation": 0.002911457555503387, "minimum": 0.9737354407522657, "maximum": 0.9827131313598898, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.6160338915037329, "standard_deviation": 0.03157306218793956, "minimum": 1.5670805212118888, "maximum": 1.667927473666642, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4933860588328555, "standard_deviation": 0.22601291837192, "minimum": 0.11828418503294376, "maximum": 0.7415014275113286, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1787500754367588, "standard_deviation": 0.014997365985448978, "minimum": 0.16289593289908696, "maximum": 0.20954849716347695, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9944252833388623, "standard_deviation": 0.0009785334621374676, "minimum": 0.9929538585186845, "maximum": 0.9954811854168545, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.0141149257616044, "standard_deviation": 0.04524921866129689, "minimum": 0.9549241377752812, "maximum": 1.089934732781239, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6659348556954632, "standard_deviation": 0.2158267886066214, "minimum": 0.3607974423327862, "maximum": 0.9421611281756578, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0935715667395968, "standard_deviation": 0.008582837637961981, "minimum": 0.08288011304078645, "maximum": 0.10651155820018421, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9834174826471633, "standard_deviation": 0.0032513656858488855, "minimum": 0.9788366305779345, "maximum": 0.9870017677089458, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.341273547611407, "standard_deviation": 0.02167642351748665, "minimum": 1.309356403094407, "maximum": 1.3827572666479266, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7015748364363403, "standard_deviation": 0.2642990350022255, "minimum": 0.45781967636045806, "maximum": 1.2380115491840291, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16892845738040674, "standard_deviation": 0.01743559936676969, "minimum": 0.14938207438945128, "maximum": 0.19191504668934845, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9953976855383408, "standard_deviation": 0.001331095306637194, "minimum": 0.9937881346501382, "maximum": 0.9974560039700129, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9223277850658798, "standard_deviation": 0.04150332921443095, "minimum": 0.892099132441745, "maximum": 1.0181384526262858, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.1283877796884199, "standard_deviation": 0.46300545794079595, "minimum": 0.5883633700151516, "maximum": 1.9309073020282284, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09012394857413168, "standard_deviation": 0.015641618376431764, "minimum": 0.06546649682944318, "maximum": 0.1126375054398304, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9520938824128916, "standard_deviation": 0.00797091598238279, "minimum": 0.9355971124632709, "maximum": 0.9603474448498421, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.5120982463288453, "standard_deviation": 0.04404887381117098, "minimum": 2.421190586338598, "maximum": 2.5493397062875984, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4909283184930411, "standard_deviation": 0.2933328244151115, "minimum": 0.22644114828481846, "maximum": 1.0081004451369562, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2669871037149403, "standard_deviation": 0.020127638294218927, "minimum": 0.24666229666514516, "maximum": 0.3070991266925789, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9826630628309383, "standard_deviation": 0.005127198073182505, "minimum": 0.9732554212911313, "maximum": 0.9871812205371369, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.8920582835874462, "standard_deviation": 0.047670068196583676, "minimum": 1.8307382223143949, "maximum": 1.969826629829157, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5844620815354453, "standard_deviation": 0.27865101388437347, "minimum": 0.1896004480125255, "maximum": 1.096175908566675, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15809623636479309, "standard_deviation": 0.019613319979705453, "minimum": 0.13809802772210686, "maximum": 0.1927496060251899, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.5538366939777029, "standard_deviation": 0.06478551869465345, "minimum": 0.421510879141578, "maximum": 0.6237107294559358, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.045661513110954, "standard_deviation": 0.007674273516257492, "minimum": 6.033697816205155, "maximum": 6.05401713919994, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.03546499386275148, "standard_deviation": 0.0032373136223339447, "minimum": 0.03240777334203268, "maximum": 0.041731184164169405, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.030638049075039888, "standard_deviation": 0.0790429739062103, "minimum": -0.14203514838476686, "maximum": 0.10420030953478378, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9854844444429436, "standard_deviation": 0.0017540726831885138, "minimum": 0.9832268785256378, "maximum": 0.9886886324038016, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.5638992017588644, "standard_deviation": 0.02884833892115658, "minimum": 1.529275917214631, "maximum": 1.606482057169033, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4999513121444658, "standard_deviation": 0.14694204570507735, "minimum": 0.224597403636287, "maximum": 0.66832598062889, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.1378927530622009, "standard_deviation": 0.008672240050790644, "minimum": 0.12174055238620397, "maximum": 0.14805579262493043, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9960120869038378, "standard_deviation": 0.000967105827931694, "minimum": 0.9941600674534926, "maximum": 0.9969461819576865, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8302712634428211, "standard_deviation": 0.03697772033862812, "minimum": 0.7869323866132178, "maximum": 0.8877077026975396, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.785278537143288, "standard_deviation": 0.19659184744047825, "minimum": 0.4606202147001915, "maximum": 1.1041279466957241, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.07044100535129522, "standard_deviation": 0.008410838188340434, "minimum": 0.061559734065231755, "maximum": 0.08661976670368003, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 1.7406797409057617, "predicted_mos": 1.7406797409057617, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "30eb1e79148c8add3391a6eb0b66a0b8e1d4d55fdb4d813d60483ab287cd3e77", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.506721700076014}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5967812308170775, "全帯域_10ms_rms_envelope_nrmse": 0.13238782204961458, "全帯域_10ms_envelope_correlation": 0.9865927978740445, "全帯域_10ms_modulation_mae_db": 0.4954228726647574, "全帯域_40ms_log_rms_mae_db": 0.842592478223403, "全帯域_40ms_rms_envelope_nrmse": 0.07197481449678453, "全帯域_40ms_envelope_correlation": 0.9958108222970368, "全帯域_40ms_modulation_mae_db": 0.8124143614655998, "300–1000 Hz_10ms_log_rms_mae_db": 2.3383745074712743, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25145302839264944, "300–1000 Hz_10ms_envelope_correlation": 0.9605171782490287, "300–1000 Hz_10ms_modulation_mae_db": 0.643539110774238, "300–1000 Hz_40ms_log_rms_mae_db": 1.7008854767051973, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1350994575848394, "300–1000 Hz_40ms_envelope_correlation": 0.9898526092718603, "300–1000 Hz_40ms_modulation_mae_db": 0.48205632181047253, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5781922435256814, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20203561377811155, "1000–3000 Hz_10ms_envelope_correlation": 0.9731036375441888, "1000–3000 Hz_10ms_modulation_mae_db": 0.5452096952398783, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8960320565914468, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11520531342572696, "1000–3000 Hz_40ms_envelope_correlation": 0.9912555187134898, "1000–3000 Hz_40ms_modulation_mae_db": 0.5271394615049533, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2496076842348371, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15116169496562537, "3000–6000 Hz_10ms_envelope_correlation": 0.9864989414202988, "3000–6000 Hz_10ms_modulation_mae_db": 0.5857546629668337, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7778097480821015, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09458158254958424, "3000–6000 Hz_40ms_envelope_correlation": 0.9946838221688751, "3000–6000 Hz_40ms_modulation_mae_db": 0.8397197655665009, "mr_stft_db": 5.986195696950929, "band_mae_db": 0.4948437700313502, "rms_gain_error_db": -0.04676243892748958, "output_peak": 0.03596068710431959}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5618650842420725, "全帯域_10ms_rms_envelope_nrmse": 0.12979880573896632, "全帯域_10ms_envelope_correlation": 0.9873132516985059, "全帯域_10ms_modulation_mae_db": 0.6110579000980771, "全帯域_40ms_log_rms_mae_db": 0.8793020815745659, "全帯域_40ms_rms_envelope_nrmse": 0.06654321170217903, "全帯域_40ms_envelope_correlation": 0.9965014210846579, "全帯域_40ms_modulation_mae_db": 0.8236139449353236, "300–1000 Hz_10ms_log_rms_mae_db": 2.436554387503582, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26789086104303184, "300–1000 Hz_10ms_envelope_correlation": 0.9569482386192179, "300–1000 Hz_10ms_modulation_mae_db": 0.2869925565822798, "300–1000 Hz_40ms_log_rms_mae_db": 1.8344715391729818, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1709385808410301, "300–1000 Hz_40ms_envelope_correlation": 0.9838018650255214, "300–1000 Hz_40ms_modulation_mae_db": 0.25059018078956646, "1000–3000 Hz_10ms_log_rms_mae_db": 1.522992180453397, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1612661302721599, "1000–3000 Hz_10ms_envelope_correlation": 0.9830671302551593, "1000–3000 Hz_10ms_modulation_mae_db": 0.3334904841313116, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8644825256211411, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09128999545840107, "1000–3000 Hz_40ms_envelope_correlation": 0.9944320879955857, "1000–3000 Hz_40ms_modulation_mae_db": 0.4553262237332954, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2430610455681756, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14857332676195878, "3000–6000 Hz_10ms_envelope_correlation": 0.9871212297298475, "3000–6000 Hz_10ms_modulation_mae_db": 0.7826436075706558, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7998342869605471, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06801038118652447, "3000–6000 Hz_40ms_envelope_correlation": 0.9972414899449933, "3000–6000 Hz_40ms_modulation_mae_db": 1.3338659388647465, "mr_stft_db": 5.992457571685204, "band_mae_db": 0.6653681325052864, "rms_gain_error_db": 0.06661657598575609, "output_peak": 0.032292063179462184}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5914772746706654, "全帯域_10ms_rms_envelope_nrmse": 0.14443587387180568, "全帯域_10ms_envelope_correlation": 0.9842584689563322, "全帯域_10ms_modulation_mae_db": 0.34395885317357333, "全帯域_40ms_log_rms_mae_db": 0.8030266419926658, "全帯域_40ms_rms_envelope_nrmse": 0.06659205462378108, "全帯域_40ms_envelope_correlation": 0.9964764081207708, "全帯域_40ms_modulation_mae_db": 0.732476295850289, "300–1000 Hz_10ms_log_rms_mae_db": 2.293384332506691, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24816749932625567, "300–1000 Hz_10ms_envelope_correlation": 0.9596359122448295, "300–1000 Hz_10ms_modulation_mae_db": 0.37571372355571064, "300–1000 Hz_40ms_log_rms_mae_db": 1.6466888433829208, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14287246417497695, "300–1000 Hz_40ms_envelope_correlation": 0.9867201374396201, "300–1000 Hz_40ms_modulation_mae_db": 0.5742226835021392, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4865622810986854, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20391341795040152, "1000–3000 Hz_10ms_envelope_correlation": 0.9731598984792743, "1000–3000 Hz_10ms_modulation_mae_db": 0.24188585933912124, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9071603836998261, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10075348549706645, "1000–3000 Hz_40ms_envelope_correlation": 0.9932919893187665, "1000–3000 Hz_40ms_modulation_mae_db": 0.4703995342826746, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2788731387492418, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16700731671945485, "3000–6000 Hz_10ms_envelope_correlation": 0.9839668582013916, "3000–6000 Hz_10ms_modulation_mae_db": 0.6078551903002121, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7976555919965244, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08839469310328707, "3000–6000 Hz_40ms_envelope_correlation": 0.9954680380480475, "3000–6000 Hz_40ms_modulation_mae_db": 1.1725249930850035, "mr_stft_db": 5.975987880195835, "band_mae_db": 0.4802517088408052, "rms_gain_error_db": 0.05189549631350921, "output_peak": 0.03620438374729519}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6018062939778042, "全帯域_10ms_rms_envelope_nrmse": 0.15640600678393257, "全帯域_10ms_envelope_correlation": 0.9818332364672714, "全帯域_10ms_modulation_mae_db": 0.6492016641385571, "全帯域_40ms_log_rms_mae_db": 0.808056425330734, "全帯域_40ms_rms_envelope_nrmse": 0.09222872183612493, "全帯域_40ms_envelope_correlation": 0.9934290926833489, "全帯域_40ms_modulation_mae_db": 0.6491028393048476, "300–1000 Hz_10ms_log_rms_mae_db": 2.395732914475097, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2694707089521108, "300–1000 Hz_10ms_envelope_correlation": 0.9491370710272921, "300–1000 Hz_10ms_modulation_mae_db": 0.5506097775212133, "300–1000 Hz_40ms_log_rms_mae_db": 1.6918788676371064, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1517338698453299, "300–1000 Hz_40ms_envelope_correlation": 0.9828843968920614, "300–1000 Hz_40ms_modulation_mae_db": 0.45803743194110197, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5015630872117023, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2118644593284856, "1000–3000 Hz_10ms_envelope_correlation": 0.976654340154811, "1000–3000 Hz_10ms_modulation_mae_db": 0.3053791351798019, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8234297795673996, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.14741282038886644, "1000–3000 Hz_40ms_envelope_correlation": 0.990278030525974, "1000–3000 Hz_40ms_modulation_mae_db": 0.28649225096633524, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2555458815950924, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1572463860467288, "3000–6000 Hz_10ms_envelope_correlation": 0.9853484198552197, "3000–6000 Hz_10ms_modulation_mae_db": 0.7639328010644709, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7848773973152778, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08249129755779736, "3000–6000 Hz_40ms_envelope_correlation": 0.9958838000634537, "3000–6000 Hz_40ms_modulation_mae_db": 0.699784308618244, "mr_stft_db": 5.979250417828781, "band_mae_db": 0.5364630938668059, "rms_gain_error_db": 0.12133655443270816, "output_peak": 0.03836056783241705}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4958085865564585, "全帯域_10ms_rms_envelope_nrmse": 0.12125772636541715, "全帯域_10ms_envelope_correlation": 0.9887734707135895, "全帯域_10ms_modulation_mae_db": 0.43527290944619085, "全帯域_40ms_log_rms_mae_db": 0.7345433122344104, "全帯域_40ms_rms_envelope_nrmse": 0.06008691224386152, "全帯域_40ms_envelope_correlation": 0.9971769338430457, "全帯域_40ms_modulation_mae_db": 0.8894401350238813, "300–1000 Hz_10ms_log_rms_mae_db": 2.3717326720167007, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25142671193371613, "300–1000 Hz_10ms_envelope_correlation": 0.9587822729846568, "300–1000 Hz_10ms_modulation_mae_db": 0.5414697588161836, "300–1000 Hz_40ms_log_rms_mae_db": 1.7019281944603861, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1351336300642138, "300–1000 Hz_40ms_envelope_correlation": 0.9885083980879229, "300–1000 Hz_40ms_modulation_mae_db": 0.5110819551398716, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4898829833178042, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1728041633313251, "1000–3000 Hz_10ms_envelope_correlation": 0.9808829097269378, "1000–3000 Hz_10ms_modulation_mae_db": 0.7496740341498458, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8313577351423319, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09758687333803061, "1000–3000 Hz_40ms_envelope_correlation": 0.9945382081960664, "1000–3000 Hz_40ms_modulation_mae_db": 0.8758819203484238, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1744832352441639, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14454966121225926, "3000–6000 Hz_10ms_envelope_correlation": 0.9876743321619336, "3000–6000 Hz_10ms_modulation_mae_db": 0.5696301552325532, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7629812743832781, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07570346897690909, "3000–6000 Hz_40ms_envelope_correlation": 0.9965099258429466, "3000–6000 Hz_40ms_modulation_mae_db": 0.8627749903731988, "mr_stft_db": 5.973316173711793, "band_mae_db": 0.6045907033450731, "rms_gain_error_db": -0.11178857870487975, "output_peak": 0.032036492199164796}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5851890747159718, "全帯域_10ms_rms_envelope_nrmse": 0.13297434620846887, "全帯域_10ms_envelope_correlation": 0.9865213070492129, "全帯域_10ms_modulation_mae_db": 0.8575227045041555, "全帯域_40ms_log_rms_mae_db": 0.8217267742286704, "全帯域_40ms_rms_envelope_nrmse": 0.06316304964589155, "全帯域_40ms_envelope_correlation": 0.9967750523541506, "全帯域_40ms_modulation_mae_db": 0.8484464189070478, "300–1000 Hz_10ms_log_rms_mae_db": 2.2973632879740578, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2474507213423956, "300–1000 Hz_10ms_envelope_correlation": 0.95947658291058, "300–1000 Hz_10ms_modulation_mae_db": 0.43258378866243613, "300–1000 Hz_40ms_log_rms_mae_db": 1.7031308544485566, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1512733429263295, "300–1000 Hz_40ms_envelope_correlation": 0.9846458380463661, "300–1000 Hz_40ms_modulation_mae_db": 0.31923644951083263, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5263520675139646, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16320891684318764, "1000–3000 Hz_10ms_envelope_correlation": 0.9827229500705811, "1000–3000 Hz_10ms_modulation_mae_db": 0.3474744087272114, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8704510196000422, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08512395746909865, "1000–3000 Hz_40ms_envelope_correlation": 0.9951537648943781, "1000–3000 Hz_40ms_modulation_mae_db": 0.35334486070243903, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2642082372146688, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16829733568803668, "3000–6000 Hz_10ms_envelope_correlation": 0.9841392668020499, "3000–6000 Hz_10ms_modulation_mae_db": 0.7086612394170139, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8035577637777351, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0863472948710842, "3000–6000 Hz_40ms_envelope_correlation": 0.9959899131659098, "3000–6000 Hz_40ms_modulation_mae_db": 0.8459523704930924, "mr_stft_db": 5.980434415226568, "band_mae_db": 0.4183231339981194, "rms_gain_error_db": -0.00689112937209256, "output_peak": 0.03429998090780006}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6118289144935432, "全帯域_10ms_rms_envelope_nrmse": 0.14844220924831483, "全帯域_10ms_envelope_correlation": 0.9831265444482139, "全帯域_10ms_modulation_mae_db": 0.4441931156206134, "全帯域_40ms_log_rms_mae_db": 0.8784307805832657, "全帯域_40ms_rms_envelope_nrmse": 0.08415731857993754, "全帯域_40ms_envelope_correlation": 0.9942615284337238, "全帯域_40ms_modulation_mae_db": 0.8579287416373976, "300–1000 Hz_10ms_log_rms_mae_db": 2.3506036765389107, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2684247324604345, "300–1000 Hz_10ms_envelope_correlation": 0.9498912300440902, "300–1000 Hz_10ms_modulation_mae_db": 0.18665789626230112, "300–1000 Hz_40ms_log_rms_mae_db": 1.6087245179706366, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.160974253775297, "300–1000 Hz_40ms_envelope_correlation": 0.9809571791142804, "300–1000 Hz_40ms_modulation_mae_db": 0.3803285582676541, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5085212626917348, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18365202407280506, "1000–3000 Hz_10ms_envelope_correlation": 0.9778560124919018, "1000–3000 Hz_10ms_modulation_mae_db": 0.747611994335558, "1000–3000 Hz_40ms_log_rms_mae_db": 0.860824327075972, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1062661652323334, "1000–3000 Hz_40ms_envelope_correlation": 0.9925707167636756, "1000–3000 Hz_40ms_modulation_mae_db": 1.1478151801258243, "3000–6000 Hz_10ms_log_rms_mae_db": 1.259705860334866, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14468504167019935, "3000–6000 Hz_10ms_envelope_correlation": 0.9876549441028698, "3000–6000 Hz_10ms_modulation_mae_db": 1.0130273357254254, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7984141667136921, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07611823424121693, "3000–6000 Hz_40ms_envelope_correlation": 0.9964689063386667, "3000–6000 Hz_40ms_modulation_mae_db": 1.5829617727325285, "mr_stft_db": 5.976635101978708, "band_mae_db": 0.5088854292772661, "rms_gain_error_db": -0.04276513679935234, "output_peak": 0.030910434716543384}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5762481903321477, "全帯域_10ms_rms_envelope_nrmse": 0.14368170901174965, "全帯域_10ms_envelope_correlation": 0.9844051444257952, "全帯域_10ms_modulation_mae_db": 0.6022546534115543, "全帯域_40ms_log_rms_mae_db": 0.8075472441414894, "全帯域_40ms_rms_envelope_nrmse": 0.06992193976428314, "全帯域_40ms_envelope_correlation": 0.996109519636508, "全帯域_40ms_modulation_mae_db": 0.9021198969235465, "300–1000 Hz_10ms_log_rms_mae_db": 2.365091913438893, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25946360173400435, "300–1000 Hz_10ms_envelope_correlation": 0.9548007096153688, "300–1000 Hz_10ms_modulation_mae_db": 0.6762159870621328, "300–1000 Hz_40ms_log_rms_mae_db": 1.6938207773963738, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.142193334563162, "300–1000 Hz_40ms_envelope_correlation": 0.9861598958925332, "300–1000 Hz_40ms_modulation_mae_db": 0.7032494949044583, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5411252345673827, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19624747001379225, "1000–3000 Hz_10ms_envelope_correlation": 0.9755295424888947, "1000–3000 Hz_10ms_modulation_mae_db": 0.39991864101166924, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8839368075133716, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10921883684852161, "1000–3000 Hz_40ms_envelope_correlation": 0.9923081425294006, "1000–3000 Hz_40ms_modulation_mae_db": 0.7790520943711452, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1932645275483102, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14517891448142034, "3000–6000 Hz_10ms_envelope_correlation": 0.9878187687792693, "3000–6000 Hz_10ms_modulation_mae_db": 0.7195480062321818, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7501668047814212, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06992264583177704, "3000–6000 Hz_40ms_envelope_correlation": 0.9971501635257878, "3000–6000 Hz_40ms_modulation_mae_db": 1.2253320768594744, "mr_stft_db": 5.981354631458028, "band_mae_db": 0.5063048885072232, "rms_gain_error_db": 0.057612207619073784, "output_peak": 0.03442518780146765}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.239292664804844, "spectral_convergence": 0.5962730367505685, "spectral_convergence_status": "ok", "amplitude_floor": 9.167242110941195e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.813126383682641, "spectral_convergence": 0.5995249865132424, "spectral_convergence_status": "ok", "amplitude_floor": 5.84028801806317e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.906168042365302, "spectral_convergence": 0.6384503247045056, "spectral_convergence_status": "ok", "amplitude_floor": 2.8939654187001563e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.3843123087683508e-07, "output_power": 1.3564911094902337e-07, "delta_db": -0.08817128772458936, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.81286342317638e-08, "output_power": 1.0939738462226728e-07, "delta_db": 2.056772566193602, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 9.335883160942139e-07, "output_power": 1.0676824461563386e-06, "delta_db": 0.5828669466193431, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.7505166473017637e-06, "output_power": 1.5467049744797751e-06, "delta_db": -0.5375876293334964, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.470519881244434e-07, "output_power": 5.525827534620008e-07, "delta_db": 0.04368725415423053, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.7292398267785066e-06, "output_power": 2.666647489878405e-06, "delta_db": -0.10076091030392159, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.57439203602588e-07, "output_power": 9.694316307878342e-07, "delta_db": 0.05405979589026882, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.4948437700313502, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.04676243892748958, "pitch": null, "output_rms_dbfs": -51.519282020801896, "output_peak": 0.03596068710431959, "reference_rms_dbfs": -51.47251958187441, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.986195696950929}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.1370250428801243e-05, "log_rms_mae_db": 1.5967812308170775, "rms_envelope_nrmse": 0.13238782204961458, "envelope_correlation": 0.9865927978740445, "rms_gain_error_db": -0.046762093144667866, "reference_mean_power": 7.130327548553108e-06, "output_mean_power": 7.053964526838495e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.4304416670730408e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2770281801289633e-06, "output_power": 1.1711431413639542e-06, "reference_active": true, "delta_db": -0.3759050156402305}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.124025700263392e-07, "output_power": 2.4147487392252317e-07, "reference_active": true, "delta_db": 0.5571218067522543}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.509706557401959e-07, "output_power": 1.3291327580838875e-07, "reference_active": true, "delta_db": -0.5532417956017872}], "active_band_count": 3, "active_band_mae_db": 0.4954228726647574}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 9.27501987121069e-06, "log_rms_mae_db": 0.842592478223403, "rms_envelope_nrmse": 0.07197481449678453, "envelope_correlation": 0.9958108222970368, "rms_gain_error_db": -0.046764391823403584, "reference_mean_power": 7.166117032249278e-06, "output_mean_power": 7.089366966815358e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.171922661595567e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0939532041259814e-06, "output_power": 1.0073779262227843e-06, "reference_active": true, "delta_db": -0.3580631432714915}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.164609293708589e-07, "output_power": 1.2968470943329596e-07, "reference_active": true, "delta_db": 0.4670852180386243}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0690330771826293e-08, "output_power": 7.3753336283391585e-09, "reference_active": true, "delta_db": -1.6120947230866838}], "active_band_count": 3, "active_band_mae_db": 0.8124143614655998}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 6.556092771800097e-06, "log_rms_mae_db": 2.3383745074712743, "rms_envelope_nrmse": 0.25145302839264944, "envelope_correlation": 0.9605171782490287, "rms_gain_error_db": 0.5198108835619527, "reference_mean_power": 7.945163829144021e-07, "output_mean_power": 8.955378480669924e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.0791155245365873e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.4868570435085076e-07, "output_power": 1.597233404316325e-07, "reference_active": true, "delta_db": 0.31099169870776333}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.530749650867304e-08, "output_power": 3.963938408119083e-08, "reference_active": true, "delta_db": 0.502599729343465}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.4918697573140088e-08, "output_power": 3.222759740662036e-08, "reference_active": true, "delta_db": 1.1170259042714856}], "active_band_count": 3, "active_band_mae_db": 0.643539110774238}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.158309417730701e-06, "log_rms_mae_db": 1.7008854767051973, "rms_envelope_nrmse": 0.1350994575848394, "envelope_correlation": 0.9898526092718603, "rms_gain_error_db": 0.5198147175314717, "reference_mean_power": 7.985041710031799e-07, "output_mean_power": 9.000334714747317e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.7036737518374816e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3140926226909544e-07, "output_power": 1.480052792148871e-07, "reference_active": true, "delta_db": 0.516512293873884}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.929219128746953e-08, "output_power": 2.0811274287038503e-08, "reference_active": true, "delta_db": 0.32917113719845953}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4692549483461402e-09, "output_power": 1.6871189965370168e-09, "reference_active": true, "delta_db": 0.6004855343590739}], "active_band_count": 3, "active_band_mae_db": 0.48205632181047253}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 7.401330296636983e-06, "log_rms_mae_db": 1.5781922435256814, "rms_envelope_nrmse": 0.20203561377811155, "envelope_correlation": 0.9731036375441888, "rms_gain_error_db": -0.20169992214348254, "reference_mean_power": 1.4849128654353035e-06, "output_mean_power": 1.4175258186371899e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.41811499304529e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.69138926350769e-07, "output_power": 2.2852841022557583e-07, "reference_active": true, "delta_db": -0.710363171470054}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.521731226006148e-08, "output_power": 3.910734654781986e-08, "reference_active": true, "delta_db": -0.6304639422928898}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6338303134826183e-08, "output_power": 2.8188241847530706e-08, "reference_active": true, "delta_db": 0.294801971956691}], "active_band_count": 3, "active_band_mae_db": 0.5452096952398783}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 6.380552881753602e-06, "log_rms_mae_db": 0.8960320565914468, "rms_envelope_nrmse": 0.11520531342572696, "envelope_correlation": 0.9912555187134898, "rms_gain_error_db": -0.20171948159426556, "reference_mean_power": 1.4923708236731126e-06, "output_mean_power": 1.4246389099836732e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.994698288619123e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.551906678142862e-07, "output_power": 2.1731948695482128e-07, "reference_active": true, "delta_db": -0.6976611733766889}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4359212852663977e-08, "output_power": 1.9909238883099454e-08, "reference_active": true, "delta_db": -0.876085927722755}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5357702928828252e-09, "output_power": 1.5330599360512445e-09, "reference_active": true, "delta_db": -0.007671283415415989}], "active_band_count": 3, "active_band_mae_db": 0.5271394615049533}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0774952268311018e-05, "log_rms_mae_db": 1.2496076842348371, "rms_envelope_nrmse": 0.15116169496562537, "envelope_correlation": 0.9864989414202988, "rms_gain_error_db": -0.16758910299529373, "reference_mean_power": 1.995223201702535e-06, "output_mean_power": 1.9196965133948927e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.579487211503375e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.151593028482198e-07, "output_power": 6.230172066054764e-07, "reference_active": true, "delta_db": -0.5990275109834132}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2474197679576555e-07, "output_power": 1.2770092538245372e-07, "reference_active": true, "delta_db": 0.1018142231402274}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.137663053230787e-08, "output_power": 6.380540623686853e-08, "reference_active": true, "delta_db": -1.0564222547768602}], "active_band_count": 3, "active_band_mae_db": 0.5857546629668337}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 7.143885674653834e-06, "log_rms_mae_db": 0.7778097480821015, "rms_envelope_nrmse": 0.09458158254958424, "envelope_correlation": 0.9946838221688751, "rms_gain_error_db": -0.16758943023214135, "reference_mean_power": 2.0052568878051223e-06, "output_mean_power": 1.929350241437012e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.5118360803946574e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.45069205976456e-07, "output_power": 5.624552410283833e-07, "reference_active": true, "delta_db": -0.595183422914409}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.385509447185785e-08, "output_power": 8.289348923163564e-08, "reference_active": true, "delta_db": -0.05009031799403676}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.733755662328774e-09, "output_power": 3.724351191186686e-09, "reference_active": true, "delta_db": -1.8738855557910568}], "active_band_count": 3, "active_band_mae_db": 0.8397197655665009}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5444665939207164, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "8f4262910838ee1dfa22bd29a80ca8867e0325b305f75b5c9669ca1fba657dfb", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9778720526514686, "standard_deviation": 0.003991024069420986, "minimum": 0.9731036375441888, "maximum": 0.9830671302551593, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.519398917547544, "standard_deviation": 0.030179986626059835, "minimum": 1.4865622810986854, "maximum": 1.5781922435256814, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4588305315142997, "standard_deviation": 0.19915510195586916, "minimum": 0.24188585933912124, "maximum": 0.7496740341498458, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1868740244487836, "standard_deviation": 0.019481646599387357, "minimum": 0.1612661302721599, "maximum": 0.2118644593284856, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.992978557367167, "standard_deviation": 0.001700946241074596, "minimum": 0.990278030525974, "maximum": 0.9951537648943781, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8672093293514415, "standard_deviation": 0.029197218384375584, "minimum": 0.8234297795673996, "maximum": 0.9071603836998261, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6119314407543863, "standard_deviation": 0.29502890671728427, "minimum": 0.28649225096633524, "maximum": 1.1478151801258243, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10660718095725566, "standard_deviation": 0.019115221656057807, "minimum": 0.08512395746909865, "maximum": 0.14741282038886644, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9862778451316101, "standard_deviation": 0.0015928058642146544, "minimum": 0.9839668582013916, "maximum": 0.9878187687792693, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2398437013111694, "standard_deviation": 0.03645993504187719, "minimum": 1.1744832352441639, "maximum": 1.2788731387492418, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7188816248136684, "standard_deviation": 0.14394813392318934, "minimum": 0.5696301552325532, "maximum": 1.0130273357254254, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15333745969321044, "standard_deviation": 0.009798141956745604, "minimum": 0.14454966121225926, "maximum": 0.16829733568803668, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.996174507387335, "standard_deviation": 0.000856017363340899, "minimum": 0.9946838221688751, "maximum": 0.9972414899449933, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7844121292513222, "standard_deviation": 0.019463065124586763, "minimum": 0.7501668047814212, "maximum": 0.8035577637777351, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.0703645270740987, "standard_deviation": 0.30487036323775374, "minimum": 0.699784308618244, "maximum": 1.5829617727325285, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08019619978977255, "standard_deviation": 0.009320580096549248, "minimum": 0.06801038118652447, "maximum": 0.09458158254958424, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9561486494618829, "standard_deviation": 0.004472614670654041, "minimum": 0.9491370710272921, "maximum": 0.9605171782490287, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.3561047114906506, "standard_deviation": 0.047953206489214396, "minimum": 2.293384332506691, "maximum": 2.436554387503582, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.46172282490456196, "standard_deviation": 0.17228007629541695, "minimum": 0.18665789626230112, "maximum": 0.6762159870621328, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.25796848314807475, "standard_deviation": 0.009518792160571856, "minimum": 0.2474507213423956, "maximum": 0.2694707089521108, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9854412899712708, "standard_deviation": 0.0029516132586926394, "minimum": 0.9809571791142804, "maximum": 0.9898526092718603, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.69769113389677, "standard_deviation": 0.06473206405850897, "minimum": 1.6087245179706366, "maximum": 1.8344715391729818, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.4598503844832621, "standard_deviation": 0.14408878533794928, "minimum": 0.25059018078956646, "maximum": 0.7032494949044583, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.14877736672189734, "standard_deviation": 0.01257155732403857, "minimum": 0.1350994575848394, "maximum": 0.1709385808410301, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.5268788575464912, "standard_deviation": 0.07657116433042899, "minimum": 0.4183231339981194, "maximum": 0.6653681325052864, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.98070398612948, "standard_deviation": 0.006144588507795117, "minimum": 5.973316173711793, "maximum": 5.992457571685204, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.03431122468605874, "standard_deviation": 0.0024937597812192598, "minimum": 0.030910434716543384, "maximum": 0.03836056783241705, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": 0.011156693818404124, "standard_deviation": 0.07628575856528798, "minimum": -0.11178857870487975, "maximum": 0.12133655443270816, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9853530277041207, "standard_deviation": 0.00232644777636616, "minimum": 0.9818332364672714, "maximum": 0.9887734707135895, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.5776255812257176, "standard_deviation": 0.03647876235314479, "minimum": 1.4958085865564585, "maximum": 1.6118289144935432, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.5548605841321849, "standard_deviation": 0.1605658818050533, "minimum": 0.34395885317357333, "maximum": 0.8575227045041555, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.13867306240978372, "standard_deviation": 0.011478029052969132, "minimum": 0.12125772636541715, "maximum": 0.15640600678393257, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9958175973066554, "standard_deviation": 0.0013026199892952927, "minimum": 0.9934290926833489, "maximum": 0.9971769338430457, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8219032172886506, "standard_deviation": 0.046757699751008186, "minimum": 0.7345433122344104, "maximum": 0.8793020815745659, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.8144428292559917, "standard_deviation": 0.08493962702329647, "minimum": 0.6491028393048476, "maximum": 0.9021198969235465, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.07183350286160542, "standard_deviation": 0.010955328407539808, "minimum": 0.06008691224386152, "maximum": 0.09222872183612493, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs066_falset10_BASIC5000_1205", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs066", "source_utterance_id": "BASIC5000_1205", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 97768, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs066_falset10_BASIC5000_1205.wav", "source_file_sha256": "47b0702615325483b782b56a91932d87648a80b90aecd59350be65638a6be8ce", "decoded_pcm_sha256": "8bb0378c60bf90dece3e4e34abf994e4b31fddfb237ef6fddfbbd69c8b1fa82a", "original_source_sha256": "47b0702615325483b782b56a91932d87648a80b90aecd59350be65638a6be8ce", "corpus_entry_id": "jvs_jvs066_falset10_BASIC5000_1205"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 3.948791027069092, "predicted_mos": 3.948791027069092, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 97768, "input_sample_rate": 24000, "input_seconds": 4.073666666666667, "input_float32_sha256": "37c6a01ca599f503a80f06442f657f28b2620bd608dd85ab4e1980b1e2a2540b", "internal_samples": 65179, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.472336299717426}, "waveform_sha256": "603a7d796056eb7b72ef989420d56351ffeb5e5813c6fb69d253568c16b7153c"}, "rows": [{"case": "jvs_jvs066_falset10_BASIC5000_1205", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 2.73468279838562, "predicted_mos": 2.73468279838562, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 97768, "input_sample_rate": 24000, "input_seconds": 4.073666666666667, "input_float32_sha256": "1207be511e85d016edfd54d417177c3361cf22ea97725c07c07ee8ca01fb6dcb", "internal_samples": 65179, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.911496799904853}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7210890024773221, "全帯域_10ms_rms_envelope_nrmse": 0.06658727124187341, "全帯域_10ms_envelope_correlation": 0.9967667026032996, "全帯域_10ms_modulation_mae_db": 1.1509589464913619, "全帯域_40ms_log_rms_mae_db": 0.3915257642076719, "全帯域_40ms_rms_envelope_nrmse": 0.03847630118630529, "全帯域_40ms_envelope_correlation": 0.9988623917609479, "全帯域_40ms_modulation_mae_db": 1.2687715599392504, "300–1000 Hz_10ms_log_rms_mae_db": 0.8985972779146445, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06804298772728015, "300–1000 Hz_10ms_envelope_correlation": 0.9967199619613765, "300–1000 Hz_10ms_modulation_mae_db": 0.8922079935805637, "300–1000 Hz_40ms_log_rms_mae_db": 0.5710891247032127, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04053226331709384, "300–1000 Hz_40ms_envelope_correlation": 0.9987672116050443, "300–1000 Hz_40ms_modulation_mae_db": 0.9478758232387086, "1000–3000 Hz_10ms_log_rms_mae_db": 0.97053358180519, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11535740658714273, "1000–3000 Hz_10ms_envelope_correlation": 0.9921329535201241, "1000–3000 Hz_10ms_modulation_mae_db": 1.1660343821987083, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5948677068133056, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.057673798711894916, "1000–3000 Hz_40ms_envelope_correlation": 0.9979726099574879, "1000–3000 Hz_40ms_modulation_mae_db": 1.5079227184355235, "3000–6000 Hz_10ms_log_rms_mae_db": 1.681759987482446, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17035788799422766, "3000–6000 Hz_10ms_envelope_correlation": 0.9799778040263798, "3000–6000 Hz_10ms_modulation_mae_db": 0.41684151527716057, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0165880640136655, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10336974881273063, "3000–6000 Hz_40ms_envelope_correlation": 0.9931523229571664, "3000–6000 Hz_40ms_modulation_mae_db": 0.4465262446215305, "mr_stft_db": 5.171905367438742, "band_mae_db": 1.4308115705270874, "rms_gain_error_db": -0.032579830216698566, "output_peak": 0.6629035877838274}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7106136445145677, "全帯域_10ms_rms_envelope_nrmse": 0.07801324366428228, "全帯域_10ms_envelope_correlation": 0.9955853131224849, "全帯域_10ms_modulation_mae_db": 0.7127198715752918, "全帯域_40ms_log_rms_mae_db": 0.3970418447323175, "全帯域_40ms_rms_envelope_nrmse": 0.04260985682880732, "全帯域_40ms_envelope_correlation": 0.9986596239894558, "全帯域_40ms_modulation_mae_db": 0.6238364778455425, "300–1000 Hz_10ms_log_rms_mae_db": 0.8988602600584247, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08933766731973641, "300–1000 Hz_10ms_envelope_correlation": 0.9943537007958758, "300–1000 Hz_10ms_modulation_mae_db": 0.5162213664569529, "300–1000 Hz_40ms_log_rms_mae_db": 0.6011127790911165, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05145268936291704, "300–1000 Hz_40ms_envelope_correlation": 0.9980586908086393, "300–1000 Hz_40ms_modulation_mae_db": 0.409289973131091, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9754240117187121, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10084741011421433, "1000–3000 Hz_10ms_envelope_correlation": 0.9940139280321117, "1000–3000 Hz_10ms_modulation_mae_db": 1.1701817089956863, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5796519935737429, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04989922411491055, "1000–3000 Hz_40ms_envelope_correlation": 0.9985526486050232, "1000–3000 Hz_40ms_modulation_mae_db": 1.8004644387064148, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6396320197890066, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15150252316232735, "3000–6000 Hz_10ms_envelope_correlation": 0.9837217857098016, "3000–6000 Hz_10ms_modulation_mae_db": 0.2754630639842058, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9530505678860411, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08181291631075438, "3000–6000 Hz_40ms_envelope_correlation": 0.9948748105383414, "3000–6000 Hz_40ms_modulation_mae_db": 0.4448653883618074, "mr_stft_db": 5.166221021232246, "band_mae_db": 1.5542646535587539, "rms_gain_error_db": -0.08580059362523872, "output_peak": 0.6548201018810722}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7245693801994889, "全帯域_10ms_rms_envelope_nrmse": 0.06103593317977833, "全帯域_10ms_envelope_correlation": 0.9972870036578358, "全帯域_10ms_modulation_mae_db": 0.27986560784030223, "全帯域_40ms_log_rms_mae_db": 0.40304913010365434, "全帯域_40ms_rms_envelope_nrmse": 0.03571411454030713, "全帯域_40ms_envelope_correlation": 0.9990313689306923, "全帯域_40ms_modulation_mae_db": 0.3426579322163978, "300–1000 Hz_10ms_log_rms_mae_db": 0.8241001581880667, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06858763686999171, "300–1000 Hz_10ms_envelope_correlation": 0.9966644237789573, "300–1000 Hz_10ms_modulation_mae_db": 0.3374365669447524, "300–1000 Hz_40ms_log_rms_mae_db": 0.5318484723883656, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.040334493381555835, "300–1000 Hz_40ms_envelope_correlation": 0.9987809449742701, "300–1000 Hz_40ms_modulation_mae_db": 0.5209870934653126, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9740540122021277, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08924012931930361, "1000–3000 Hz_10ms_envelope_correlation": 0.9953419410090576, "1000–3000 Hz_10ms_modulation_mae_db": 0.4584976185020671, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6289889765537023, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05631714846012408, "1000–3000 Hz_40ms_envelope_correlation": 0.9981519468624965, "1000–3000 Hz_40ms_modulation_mae_db": 0.25425752468109314, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6568375324609232, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15293426234473773, "3000–6000 Hz_10ms_envelope_correlation": 0.9833355643777522, "3000–6000 Hz_10ms_modulation_mae_db": 0.8017398324622046, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9609177085773725, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08014861224528598, "3000–6000 Hz_40ms_envelope_correlation": 0.9952387489322989, "3000–6000 Hz_40ms_modulation_mae_db": 0.7623651040845562, "mr_stft_db": 5.169771973406959, "band_mae_db": 1.53887524992982, "rms_gain_error_db": -0.043693976724619644, "output_peak": 0.617380149095918}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6983149182661919, "全帯域_10ms_rms_envelope_nrmse": 0.07403386405498447, "全帯域_10ms_envelope_correlation": 0.9960248706156437, "全帯域_10ms_modulation_mae_db": 1.0901929827440204, "全帯域_40ms_log_rms_mae_db": 0.40275933506429407, "全帯域_40ms_rms_envelope_nrmse": 0.04823577597326194, "全帯域_40ms_envelope_correlation": 0.9982558479229517, "全帯域_40ms_modulation_mae_db": 1.0314835591366711, "300–1000 Hz_10ms_log_rms_mae_db": 0.8754036767538628, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0834977907822292, "300–1000 Hz_10ms_envelope_correlation": 0.9950576874913876, "300–1000 Hz_10ms_modulation_mae_db": 1.100310442255133, "300–1000 Hz_40ms_log_rms_mae_db": 0.5507268284922837, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05735168419652865, "300–1000 Hz_40ms_envelope_correlation": 0.997548373804841, "300–1000 Hz_40ms_modulation_mae_db": 1.0717855867197847, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0241482129486434, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11989620027023748, "1000–3000 Hz_10ms_envelope_correlation": 0.9916569891383331, "1000–3000 Hz_10ms_modulation_mae_db": 1.3280709876069985, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6464399190702178, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0725102133296321, "1000–3000 Hz_40ms_envelope_correlation": 0.9970816771245985, "1000–3000 Hz_40ms_modulation_mae_db": 1.0503340599016495, "3000–6000 Hz_10ms_log_rms_mae_db": 1.658771997163894, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17907683395411364, "3000–6000 Hz_10ms_envelope_correlation": 0.9774556354345627, "3000–6000 Hz_10ms_modulation_mae_db": 1.0866655981351119, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9448034181119653, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10260525641074589, "3000–6000 Hz_40ms_envelope_correlation": 0.9928399163543236, "3000–6000 Hz_40ms_modulation_mae_db": 1.0137723944311352, "mr_stft_db": 5.155279085307807, "band_mae_db": 1.5454169838021667, "rms_gain_error_db": -0.07942682244930388, "output_peak": 0.6306174197238719}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7413975224522884, "全帯域_10ms_rms_envelope_nrmse": 0.0797132731964456, "全帯域_10ms_envelope_correlation": 0.9953630521693825, "全帯域_10ms_modulation_mae_db": 0.7688050130606365, "全帯域_40ms_log_rms_mae_db": 0.43114270596505555, "全帯域_40ms_rms_envelope_nrmse": 0.04942585546280604, "全帯域_40ms_envelope_correlation": 0.9981132633006253, "全帯域_40ms_modulation_mae_db": 0.7153693414878507, "300–1000 Hz_10ms_log_rms_mae_db": 0.9079247687823316, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09034525319918153, "300–1000 Hz_10ms_envelope_correlation": 0.9942249266027487, "300–1000 Hz_10ms_modulation_mae_db": 0.8754333910307078, "300–1000 Hz_40ms_log_rms_mae_db": 0.6141185110058597, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0606981432287939, "300–1000 Hz_40ms_envelope_correlation": 0.9972369231340269, "300–1000 Hz_40ms_modulation_mae_db": 0.8005574038633795, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9884355570008765, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0951938378106823, "1000–3000 Hz_10ms_envelope_correlation": 0.9946376913771062, "1000–3000 Hz_10ms_modulation_mae_db": 0.5579829896699563, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6160668131832011, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0480728050786813, "1000–3000 Hz_40ms_envelope_correlation": 0.9986103665039289, "1000–3000 Hz_40ms_modulation_mae_db": 0.4131544468073847, "3000–6000 Hz_10ms_log_rms_mae_db": 1.636964582513406, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16592830318814342, "3000–6000 Hz_10ms_envelope_correlation": 0.9803407552675092, "3000–6000 Hz_10ms_modulation_mae_db": 0.3564580382347284, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9197940812620302, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08362439153503262, "3000–6000 Hz_40ms_envelope_correlation": 0.9948400386642656, "3000–6000 Hz_40ms_modulation_mae_db": 0.28902791637227404, "mr_stft_db": 5.162879720168569, "band_mae_db": 1.5207626434496895, "rms_gain_error_db": 0.0013534136349177455, "output_peak": 0.6496695351418701}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7260102603870447, "全帯域_10ms_rms_envelope_nrmse": 0.061804692743937815, "全帯域_10ms_envelope_correlation": 0.9972165200490481, "全帯域_10ms_modulation_mae_db": 0.48058415101486274, "全帯域_40ms_log_rms_mae_db": 0.43369186382790065, "全帯域_40ms_rms_envelope_nrmse": 0.03718557635108823, "全帯域_40ms_envelope_correlation": 0.9989473930597979, "全帯域_40ms_modulation_mae_db": 0.6031176524810152, "300–1000 Hz_10ms_log_rms_mae_db": 0.8326791229965967, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07156053562247945, "300–1000 Hz_10ms_envelope_correlation": 0.9963813697175776, "300–1000 Hz_10ms_modulation_mae_db": 0.49485515561049476, "300–1000 Hz_40ms_log_rms_mae_db": 0.5314379822358987, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.045385937575254116, "300–1000 Hz_40ms_envelope_correlation": 0.9984805646501144, "300–1000 Hz_40ms_modulation_mae_db": 0.7494801360563302, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9553852442414301, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07595662861199756, "1000–3000 Hz_10ms_envelope_correlation": 0.9965917841706476, "1000–3000 Hz_10ms_modulation_mae_db": 0.22731346339074307, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5942514251053639, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04563792221424537, "1000–3000 Hz_40ms_envelope_correlation": 0.9987365600952866, "1000–3000 Hz_40ms_modulation_mae_db": 0.2860232686357476, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6195029645653987, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15519473355224972, "3000–6000 Hz_10ms_envelope_correlation": 0.9829462221860831, "3000–6000 Hz_10ms_modulation_mae_db": 0.10526431062599238, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9588783730586944, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09739202192149342, "3000–6000 Hz_40ms_envelope_correlation": 0.9927448947595771, "3000–6000 Hz_40ms_modulation_mae_db": 0.03481254717065627, "mr_stft_db": 5.153181086159016, "band_mae_db": 1.4958629907381442, "rms_gain_error_db": -0.03763643347457537, "output_peak": 0.6480511783724469}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.758622472012509, "全帯域_10ms_rms_envelope_nrmse": 0.07683651070625011, "全帯域_10ms_envelope_correlation": 0.9957012201609536, "全帯域_10ms_modulation_mae_db": 0.7979321707046875, "全帯域_40ms_log_rms_mae_db": 0.44972856095291813, "全帯域_40ms_rms_envelope_nrmse": 0.045235632152414246, "全帯域_40ms_envelope_correlation": 0.9984478534581002, "全帯域_40ms_modulation_mae_db": 1.0353707017145026, "300–1000 Hz_10ms_log_rms_mae_db": 0.8882553258856455, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08708569707156413, "300–1000 Hz_10ms_envelope_correlation": 0.9946176962186354, "300–1000 Hz_10ms_modulation_mae_db": 0.6028423511647532, "300–1000 Hz_40ms_log_rms_mae_db": 0.583288162642724, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.049561531433479786, "300–1000 Hz_40ms_envelope_correlation": 0.998157734696996, "300–1000 Hz_40ms_modulation_mae_db": 0.8354046703282972, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0529317301409622, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0943626312718454, "1000–3000 Hz_10ms_envelope_correlation": 0.9948280185968249, "1000–3000 Hz_10ms_modulation_mae_db": 0.6601620374999886, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6681059120346136, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05273630197701094, "1000–3000 Hz_40ms_envelope_correlation": 0.9984581108407334, "1000–3000 Hz_40ms_modulation_mae_db": 0.4607783345435499, "3000–6000 Hz_10ms_log_rms_mae_db": 1.664376755919198, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17567716826320914, "3000–6000 Hz_10ms_envelope_correlation": 0.9779029437951835, "3000–6000 Hz_10ms_modulation_mae_db": 0.34482049727513137, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9640333192499839, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10272034871707988, "3000–6000 Hz_40ms_envelope_correlation": 0.9919827460260439, "3000–6000 Hz_40ms_modulation_mae_db": 0.45322162019266904, "mr_stft_db": 5.159961731026384, "band_mae_db": 1.60191950191463, "rms_gain_error_db": -0.05970143947349943, "output_peak": 0.6470024551439951}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6801335441088259, "全帯域_10ms_rms_envelope_nrmse": 0.07272992269202146, "全帯域_10ms_envelope_correlation": 0.9961939537802607, "全帯域_10ms_modulation_mae_db": 0.49425640173274105, "全帯域_40ms_log_rms_mae_db": 0.38930045623855675, "全帯域_40ms_rms_envelope_nrmse": 0.0422782501569158, "全帯域_40ms_envelope_correlation": 0.9987067383631378, "全帯域_40ms_modulation_mae_db": 0.4561331875734507, "300–1000 Hz_10ms_log_rms_mae_db": 0.8536998467214304, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08330281629158076, "300–1000 Hz_10ms_envelope_correlation": 0.9951558745863717, "300–1000 Hz_10ms_modulation_mae_db": 0.655438170720739, "300–1000 Hz_40ms_log_rms_mae_db": 0.5712860861826234, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05239967826098446, "300–1000 Hz_40ms_envelope_correlation": 0.9980570854996996, "300–1000 Hz_40ms_modulation_mae_db": 0.7340326418052484, "1000–3000 Hz_10ms_log_rms_mae_db": 0.986100498692652, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11280507265898694, "1000–3000 Hz_10ms_envelope_correlation": 0.9925044381866137, "1000–3000 Hz_10ms_modulation_mae_db": 0.8886913088332461, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6014216949669934, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06029209244675581, "1000–3000 Hz_40ms_envelope_correlation": 0.9978847448627236, "1000–3000 Hz_40ms_modulation_mae_db": 0.745257327401065, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6392810180530146, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15495589930043674, "3000–6000 Hz_10ms_envelope_correlation": 0.9831525366059135, "3000–6000 Hz_10ms_modulation_mae_db": 0.06672541760113915, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8857583986553643, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08179725304660036, "3000–6000 Hz_40ms_envelope_correlation": 0.994974024637818, "3000–6000 Hz_40ms_modulation_mae_db": 0.13843915076329658, "mr_stft_db": 5.163288124809829, "band_mae_db": 1.7786963069329447, "rms_gain_error_db": -0.10101362479224828, "output_peak": 0.7131623124296222}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 97768, "output_samples": 97768, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.695276455671773, "spectral_convergence": 0.1796168556813696, "spectral_convergence_status": "ok", "amplitude_floor": 1.7496801023785185e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.1665112981811845, "spectral_convergence": 0.1898328466899765, "spectral_convergence_status": "ok", "amplitude_floor": 1.6784480256181157e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.653928348463268, "spectral_convergence": 0.19230196175354133, "spectral_convergence_status": "ok", "amplitude_floor": 1.5558256811894896e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.01876573628214e-07, "output_power": 4.011224278116923e-06, "delta_db": 9.026800208589156, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0014282687361772438, "output_power": 0.0014460024106309824, "delta_db": 0.053590870815961374, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.002893798215697645, "output_power": 0.0028800316063126016, "delta_db": -0.02070990661112998, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0011796153749935407, "output_power": 0.0011330333543927468, "delta_db": -0.17497729596565312, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.624359886340766e-05, "output_power": 1.5029405327475717e-05, "delta_db": -0.3374045894339309, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.5152799044228294e-05, "output_power": 2.3598530977765926e-05, "delta_db": -0.2770135234649145, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2062863831028078e-05, "output_power": 1.2415633535200706e-05, "delta_db": 0.1251845988088673, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.4308115705270874, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.032579830216698566, "pitch": null, "output_rms_dbfs": -22.585236160148607, "output_peak": 0.6629035877838274, "reference_rms_dbfs": -22.552656329931906, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.171905367438742}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 97768, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0003314896640837282, "log_rms_mae_db": 0.7210890024773221, "rms_envelope_nrmse": 0.06658727124187341, "envelope_correlation": 0.9967667026032996, "rms_gain_error_db": -0.032579689865797845, "reference_mean_power": 0.005567487969490699, "output_mean_power": 0.005525878329750096}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 4.765376195527077e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0029556164553593994, "output_power": 0.002896065156154037, "reference_active": true, "delta_db": -0.08839747358530789}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00036953756834478597, "output_power": 0.0003249543336863215, "reference_active": true, "delta_db": -0.5583626349009403}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 0.00011202447087610656, "output_power": 5.870853296823481e-05, "reference_active": true, "delta_db": -2.806116730987837}], "active_band_count": 3, "active_band_mae_db": 1.1509589464913619}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.0003156446105274747, "log_rms_mae_db": 0.3915257642076719, "rms_envelope_nrmse": 0.03847630118630529, "envelope_correlation": 0.9988623917609479, "rms_gain_error_db": -0.03257966294046611, "reference_mean_power": 0.005608881493358216, "output_mean_power": 0.005566962526059298}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 4.372836941600517e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0027064910584040595, "output_power": 0.0026403627323096, "reference_active": true, "delta_db": -0.10743002399324802}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00018117557189089236, "output_power": 0.0001547651492598117, "reference_active": true, "delta_db": -0.6842646997385409}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.701057462757455e-06, "output_power": 4.845706228681965e-06, "reference_active": true, "delta_db": -3.0146199560859626}], "active_band_count": 3, "active_band_mae_db": 1.2687715599392504}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0002506339510784735, "log_rms_mae_db": 0.8985972779146445, "rms_envelope_nrmse": 0.06804298772728015, "envelope_correlation": 0.9967199619613765, "rms_gain_error_db": -0.021834800320404652, "reference_mean_power": 0.0041004048785232925, "output_mean_power": 0.0040798412205275214}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 3.4168869077487306e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0021098794264420863, "output_power": 0.0020692848519253695, "reference_active": true, "delta_db": -0.08437358786476389}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00027960522877585594, "output_power": 0.0002551188203159074, "reference_active": true, "delta_db": -0.3980279066503546}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.021566680060571e-05, "output_power": 5.4432679675317414e-05, "reference_active": true, "delta_db": -2.1942224862265727}], "active_band_count": 3, "active_band_mae_db": 0.8922079935805637}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00024415679244648423, "log_rms_mae_db": 0.5710891247032127, "rms_envelope_nrmse": 0.04053226331709384, "envelope_correlation": 0.9987672116050443, "rms_gain_error_db": -0.021834816215585136, "reference_mean_power": 0.004130891145990147, "output_mean_power": 0.004110174583371611}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 3.1086003931775263e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0019093077513610485, "output_power": 0.001869373597950776, "reference_active": true, "delta_db": -0.09179831048707332}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00014045819894614964, "output_power": 0.00012501844932819636, "reference_active": true, "delta_db": -0.5057298747697123}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.796438388581124e-06, "output_power": 4.648216230166458e-06, "reference_active": true, "delta_db": -2.24609928445934}], "active_band_count": 3, "active_band_mae_db": 0.9478758232387086}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.00019827664142914133, "log_rms_mae_db": 0.97053358180519, "rms_envelope_nrmse": 0.11535740658714273, "envelope_correlation": 0.9921329535201241, "rms_gain_error_db": -0.01700067825389455, "reference_mean_power": 0.0008784725402011367, "output_mean_power": 0.0008750404367425966}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.1250771844458692e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007015897284632315, "output_power": 0.0006926778566065269, "reference_active": true, "delta_db": -0.05551917754757946}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.449911857407873e-05, "output_power": 6.614973771327963e-05, "reference_active": true, "delta_db": -1.063240522377725}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6127775103534605e-05, "output_power": 1.5106647119693703e-05, "reference_active": true, "delta_db": -2.3793434466708208}], "active_band_count": 3, "active_band_mae_db": 1.1660343821987083}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00017853730341036803, "log_rms_mae_db": 0.5948677068133056, "rms_envelope_nrmse": 0.057673798711894916, "envelope_correlation": 0.9979726099574879, "rms_gain_error_db": -0.017000684071357186, "reference_mean_power": 0.0008850039267330396, "output_mean_power": 0.0008815463046263656}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.078630941288297e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006783838060260436, "output_power": 0.000662657514487701, "reference_active": true, "delta_db": -0.10186344952948186}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3933140159486266e-05, "output_power": 2.5698626215755625e-05, "reference_active": true, "delta_db": -1.207141432901991}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.944075796645493e-06, "output_power": 9.273354583444871e-07, "reference_active": true, "delta_db": -3.214763272875098}], "active_band_count": 3, "active_band_mae_db": 1.5079227184355235}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 2.2340226127796077e-05, "log_rms_mae_db": 1.681759987482446, "rms_envelope_nrmse": 0.17035788799422766, "envelope_correlation": 0.9799778040263798, "rms_gain_error_db": -0.3985504252204063, "reference_mean_power": 1.7310253593278313e-05, "output_mean_power": 1.579240917129133e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.3633964732936534e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.958677073783288e-06, "output_power": 7.002070481756296e-06, "reference_active": true, "delta_db": -0.5561440541097143}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3383871013961803e-06, "output_power": 1.1797874829273459e-06, "reference_active": true, "delta_db": -0.5477795832742679}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.535118084866941e-07, "output_power": 4.3845851518031736e-07, "reference_active": true, "delta_db": -0.14660090844749948}], "active_band_count": 3, "active_band_mae_db": 0.41684151527716057}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 1.6591025056474894e-05, "log_rms_mae_db": 1.0165880640136655, "rms_envelope_nrmse": 0.10336974881273063, "envelope_correlation": 0.9931523229571664, "rms_gain_error_db": -0.39855047798823995, "reference_mean_power": 1.743895029874837e-05, "output_mean_power": 1.590982095122942e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.2324948655964946e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.384237970170313e-06, "output_power": 6.386887905930652e-06, "reference_active": true, "delta_db": -0.630163900815883}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2197399674362034e-07, "output_power": 4.1539720367688954e-07, "reference_active": true, "delta_db": -0.06822120630686508}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.206308596249792e-08, "output_power": 3.716419088535787e-08, "reference_active": true, "delta_db": 0.6411936267418433}], "active_band_count": 3, "active_band_mae_db": 0.4465262446215305}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8474961261810458, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "a952f6fb6cb3f9e75cf491166a51897e93582f9696150856d9a37852188b7449", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9939634680038523, "standard_deviation": 0.0017242887079205937, "minimum": 0.9916569891383331, "maximum": 0.9965917841706476, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.9908766060938242, "standard_deviation": 0.032030935732509945, "minimum": 0.9553852442414301, "maximum": 1.0529317301409622, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8071168120871743, "standard_deviation": 0.3928024268099643, "minimum": 0.22731346339074307, "maximum": 1.3280709876069985, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1004574145805513, "standard_deviation": 0.014849052558163624, "minimum": 0.07595662861199756, "maximum": 0.11989620027023748, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9981810831065348, "standard_deviation": 0.0005409599995703018, "minimum": 0.9970816771245985, "maximum": 0.9987365600952866, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6162243051626426, "standard_deviation": 0.02991227433083304, "minimum": 0.5796519935737429, "maximum": 0.6681059120346136, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8147740148890534, "standard_deviation": 0.5846524178771155, "minimum": 0.25425752468109314, "maximum": 1.8004644387064148, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05539243829165688, "standard_deviation": 0.008527624051479183, "minimum": 0.04563792221424537, "maximum": 0.0725102133296321, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9811041559253982, "standard_deviation": 0.002530701510029593, "minimum": 0.9774556354345627, "maximum": 0.9837217857098016, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.649640857243411, "standard_deviation": 0.0194951961074314, "minimum": 1.6195029645653987, "maximum": 1.681759987482446, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.4317472841994593, "standard_deviation": 0.34713444392317283, "minimum": 0.06672541760113915, "maximum": 1.0866655981351119, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16320345146993068, "standard_deviation": 0.010959003532755857, "minimum": 0.15150252316232735, "maximum": 0.17907683395411364, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9938309378587293, "standard_deviation": 0.0012780833016002888, "minimum": 0.9919827460260439, "maximum": 0.9952387489322989, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9504779913518897, "standard_deviation": 0.037612288415630954, "minimum": 0.8857583986553643, "maximum": 1.0165880640136655, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.44787879574974065, "standard_deviation": 0.3186549590373882, "minimum": 0.03481254717065627, "maximum": 1.0137723944311352, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0916838186249654, "standard_deviation": 0.010713286755122528, "minimum": 0.08014861224528598, "maximum": 0.10336974881273063, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9953969551441163, "standard_deviation": 0.001039807208546753, "minimum": 0.9942249266027487, "maximum": 0.9967199619613765, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8724400546626254, "standard_deviation": 0.032002613842193106, "minimum": 0.8241001581880667, "maximum": 0.9079247687823316, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6843431797205122, "standard_deviation": 0.25206142991751723, "minimum": 0.3374365669447524, "maximum": 1.100310442255133, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08022004811050543, "standard_deviation": 0.009347389993579478, "minimum": 0.06804298772728015, "maximum": 0.09034525319918153, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9981359411467039, "standard_deviation": 0.0005476478591241326, "minimum": 0.9972369231340269, "maximum": 0.9987809449742701, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5693634933427605, "standard_deviation": 0.030248130521129204, "minimum": 0.5314379822358987, "maximum": 0.6141185110058597, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.758676666076019, "standard_deviation": 0.21405406470710767, "minimum": 0.409289973131091, "maximum": 1.0717855867197847, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04971455259457595, "standard_deviation": 0.0073703685919833065, "minimum": 0.040334493381555835, "maximum": 0.0606981432287939, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.5583262376066545, "standard_deviation": 0.10183845576207491, "minimum": 1.4308115705270874, "maximum": 1.7786963069329447, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.162811013693695, "standard_deviation": 0.006553151896291694, "minimum": 5.153181086159016, "maximum": 5.171905367438742, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.652950842446578, "standard_deviation": 0.02818861315502918, "minimum": 0.617380149095918, "maximum": 0.7131623124296222, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.05481241339015827, "standard_deviation": 0.033364037008642884, "minimum": -0.10101362479224828, "maximum": 0.0013534136349177455, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9962673295198636, "standard_deviation": 0.0007423500813856808, "minimum": 0.9953630521693825, "maximum": 0.9972870036578358, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7200938430522799, "standard_deviation": 0.024364341612436367, "minimum": 0.6801335441088259, "maximum": 0.758622472012509, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.721914393145488, "standard_deviation": 0.3007718394139411, "minimum": 0.27986560784030223, "maximum": 1.1509589464913619, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07134433893494668, "standard_deviation": 0.007306831061667377, "minimum": 0.06103593317977833, "maximum": 0.0797132731964456, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9986280600982136, "standard_deviation": 0.0003300998790047114, "minimum": 0.9981132633006253, "maximum": 0.9990313689306923, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4122799576365461, "standard_deviation": 0.022625887313207187, "minimum": 0.38930045623855675, "maximum": 0.44972856095291813, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7595925515493351, "standard_deviation": 0.3207209358789124, "minimum": 0.3426579322163978, "maximum": 1.2687715599392504, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.04239517033148825, "standard_deviation": 0.005054066297214904, "minimum": 0.03571411454030713, "maximum": 0.04942585546280604, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_falset10_BASIC5000_1205", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 2.7793962955474854, "predicted_mos": 2.7793962955474854, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 97768, "input_sample_rate": 24000, "input_seconds": 4.073666666666667, "input_float32_sha256": "046303a3816a300f33568a05bbe47c568bf9d0160db464d66617fd4f92b74e12", "internal_samples": 65179, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.597183899953961}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7141248452698682, "全帯域_10ms_rms_envelope_nrmse": 0.06894384962740244, "全帯域_10ms_envelope_correlation": 0.9965310741076363, "全帯域_10ms_modulation_mae_db": 1.0883728350266029, "全帯域_40ms_log_rms_mae_db": 0.38669599461953175, "全帯域_40ms_rms_envelope_nrmse": 0.04021405685526301, "全帯域_40ms_envelope_correlation": 0.9987526463258866, "全帯域_40ms_modulation_mae_db": 1.1812293444438737, "300–1000 Hz_10ms_log_rms_mae_db": 0.9104238548420343, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06905221579697297, "300–1000 Hz_10ms_envelope_correlation": 0.9966217974494929, "300–1000 Hz_10ms_modulation_mae_db": 0.8898103157167467, "300–1000 Hz_40ms_log_rms_mae_db": 0.5788934085481248, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04185726656918803, "300–1000 Hz_40ms_envelope_correlation": 0.9986835643182894, "300–1000 Hz_40ms_modulation_mae_db": 0.9348886959720231, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9765578371292488, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12180742764278477, "1000–3000 Hz_10ms_envelope_correlation": 0.9912290148894306, "1000–3000 Hz_10ms_modulation_mae_db": 1.101795953562818, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5764970743610368, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0619236993343801, "1000–3000 Hz_40ms_envelope_correlation": 0.9976584639317968, "1000–3000 Hz_40ms_modulation_mae_db": 1.4229861569802236, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5590300818146796, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15502279733459, "3000–6000 Hz_10ms_envelope_correlation": 0.9845303289913226, "3000–6000 Hz_10ms_modulation_mae_db": 0.5491834046379991, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8890411594851771, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09416014313163192, "3000–6000 Hz_40ms_envelope_correlation": 0.9956529397354134, "3000–6000 Hz_40ms_modulation_mae_db": 0.4479465198294587, "mr_stft_db": 5.096914349534161, "band_mae_db": 1.448231657440347, "rms_gain_error_db": -0.024169963018932896, "output_peak": 0.6681272212391751}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7193100170363735, "全帯域_10ms_rms_envelope_nrmse": 0.0775731218082847, "全帯域_10ms_envelope_correlation": 0.9956257501253934, "全帯域_10ms_modulation_mae_db": 0.5993678329535156, "全帯域_40ms_log_rms_mae_db": 0.397365311097848, "全帯域_40ms_rms_envelope_nrmse": 0.04258945471936289, "全帯域_40ms_envelope_correlation": 0.9986467345074332, "全帯域_40ms_modulation_mae_db": 0.5218319151184131, "300–1000 Hz_10ms_log_rms_mae_db": 0.92700697948339, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08937573718745578, "300–1000 Hz_10ms_envelope_correlation": 0.9943395737551, "300–1000 Hz_10ms_modulation_mae_db": 0.43600408665727314, "300–1000 Hz_40ms_log_rms_mae_db": 0.6140562682802788, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.051550788807388365, "300–1000 Hz_40ms_envelope_correlation": 0.998034885542151, "300–1000 Hz_40ms_modulation_mae_db": 0.34111713129713817, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9547565145331419, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10241304864357527, "1000–3000 Hz_10ms_envelope_correlation": 0.9938079867524449, "1000–3000 Hz_10ms_modulation_mae_db": 1.0810064968691864, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5513931356419626, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.049715913140602606, "1000–3000 Hz_40ms_envelope_correlation": 0.9985468116535811, "1000–3000 Hz_40ms_modulation_mae_db": 1.769725575774042, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5417057187740257, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13554109033197445, "3000–6000 Hz_10ms_envelope_correlation": 0.9869872786164557, "3000–6000 Hz_10ms_modulation_mae_db": 0.689174499475793, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8707725338581295, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07393434812589304, "3000–6000 Hz_40ms_envelope_correlation": 0.996006615541839, "3000–6000 Hz_40ms_modulation_mae_db": 0.8891395214867309, "mr_stft_db": 5.095048278806658, "band_mae_db": 1.5564006669470236, "rms_gain_error_db": -0.07602047999986727, "output_peak": 0.6684159317561644}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7378875751068955, "全帯域_10ms_rms_envelope_nrmse": 0.0618274286077276, "全帯域_10ms_envelope_correlation": 0.9972117136408416, "全帯域_10ms_modulation_mae_db": 0.22621141494832606, "全帯域_40ms_log_rms_mae_db": 0.40404570891452113, "全帯域_40ms_rms_envelope_nrmse": 0.03720282292386944, "全帯域_40ms_envelope_correlation": 0.9989406201377813, "全帯域_40ms_modulation_mae_db": 0.26773465921168893, "300–1000 Hz_10ms_log_rms_mae_db": 0.8477116624848967, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06902964658842879, "300–1000 Hz_10ms_envelope_correlation": 0.9966217611150306, "300–1000 Hz_10ms_modulation_mae_db": 0.2968681322621458, "300–1000 Hz_40ms_log_rms_mae_db": 0.5312716319777132, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04098156900230797, "300–1000 Hz_40ms_envelope_correlation": 0.9987386551755071, "300–1000 Hz_40ms_modulation_mae_db": 0.46824500285817766, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9745207724287059, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08933851034441914, "1000–3000 Hz_10ms_envelope_correlation": 0.9953210702288756, "1000–3000 Hz_10ms_modulation_mae_db": 0.42441720284752066, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6102026223579915, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.056525273258044295, "1000–3000 Hz_40ms_envelope_correlation": 0.9981240768177381, "1000–3000 Hz_40ms_modulation_mae_db": 0.20212812890767137, "3000–6000 Hz_10ms_log_rms_mae_db": 1.562403091884107, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15448652208239008, "3000–6000 Hz_10ms_envelope_correlation": 0.9832373084999625, "3000–6000 Hz_10ms_modulation_mae_db": 0.8039254391304206, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8789750764471621, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08517112223037761, "3000–6000 Hz_40ms_envelope_correlation": 0.9950320174978046, "3000–6000 Hz_40ms_modulation_mae_db": 0.9065319637895533, "mr_stft_db": 5.0927927983966805, "band_mae_db": 1.4854627257098107, "rms_gain_error_db": -0.03362045249438012, "output_peak": 0.6322501655411179}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6966490206624388, "全帯域_10ms_rms_envelope_nrmse": 0.07281482605848265, "全帯域_10ms_envelope_correlation": 0.9961461068515071, "全帯域_10ms_modulation_mae_db": 1.0477769274521156, "全帯域_40ms_log_rms_mae_db": 0.3966382366297272, "全帯域_40ms_rms_envelope_nrmse": 0.046494490963492625, "全帯域_40ms_envelope_correlation": 0.9983691336530531, "全帯域_40ms_modulation_mae_db": 0.9819901281786402, "300–1000 Hz_10ms_log_rms_mae_db": 0.8830568873562396, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0833210949431892, "300–1000 Hz_10ms_envelope_correlation": 0.9950748516077774, "300–1000 Hz_10ms_modulation_mae_db": 1.1332772444165542, "300–1000 Hz_40ms_log_rms_mae_db": 0.5590866003885642, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05566202356351205, "300–1000 Hz_40ms_envelope_correlation": 0.9976835857724128, "300–1000 Hz_40ms_modulation_mae_db": 1.1156874517565472, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9947212472479476, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11434009491199765, "1000–3000 Hz_10ms_envelope_correlation": 0.9924249353739237, "1000–3000 Hz_10ms_modulation_mae_db": 1.2289198086244288, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6043132802226135, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06950458550832718, "1000–3000 Hz_40ms_envelope_correlation": 0.9973239381825768, "1000–3000 Hz_40ms_modulation_mae_db": 0.926904803867354, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5602666167166195, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17482507869250458, "3000–6000 Hz_10ms_envelope_correlation": 0.979026562456198, "3000–6000 Hz_10ms_modulation_mae_db": 1.1829347594258028, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8596975342116042, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10265773510374923, "3000–6000 Hz_40ms_envelope_correlation": 0.9935182310472533, "3000–6000 Hz_40ms_modulation_mae_db": 1.2186473154808273, "mr_stft_db": 5.0809207485262995, "band_mae_db": 1.532031338893429, "rms_gain_error_db": -0.06893346321541116, "output_peak": 0.6264787408863366}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7160647286855331, "全帯域_10ms_rms_envelope_nrmse": 0.07757733506489124, "全帯域_10ms_envelope_correlation": 0.9956025834525624, "全帯域_10ms_modulation_mae_db": 0.7384068497362618, "全帯域_40ms_log_rms_mae_db": 0.4168354162268996, "全帯域_40ms_rms_envelope_nrmse": 0.04699927717298382, "全帯域_40ms_envelope_correlation": 0.998292860812944, "全帯域_40ms_modulation_mae_db": 0.6711763578592375, "300–1000 Hz_10ms_log_rms_mae_db": 0.9096056390948659, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08740227786966942, "300–1000 Hz_10ms_envelope_correlation": 0.994591730634341, "300–1000 Hz_10ms_modulation_mae_db": 0.8679531773676525, "300–1000 Hz_40ms_log_rms_mae_db": 0.6028391596639361, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05847155018729856, "300–1000 Hz_40ms_envelope_correlation": 0.9974338636229132, "300–1000 Hz_40ms_modulation_mae_db": 0.8004614221948446, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9809367020356244, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10110489519845857, "1000–3000 Hz_10ms_envelope_correlation": 0.9939717133745809, "1000–3000 Hz_10ms_modulation_mae_db": 0.5620280706120853, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5741183475124431, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.051385862579449056, "1000–3000 Hz_40ms_envelope_correlation": 0.9984532160819116, "1000–3000 Hz_40ms_modulation_mae_db": 0.4260941705945022, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5382509527827384, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15616521662967398, "3000–6000 Hz_10ms_envelope_correlation": 0.9830264743830084, "3000–6000 Hz_10ms_modulation_mae_db": 0.6837794584249853, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8665548507227645, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08215729971287909, "3000–6000 Hz_40ms_envelope_correlation": 0.9957036072455934, "3000–6000 Hz_40ms_modulation_mae_db": 0.5610743874083209, "mr_stft_db": 5.088872468029996, "band_mae_db": 1.4605024886975464, "rms_gain_error_db": -0.013668808661026158, "output_peak": 0.6622531589956501}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7099107883776316, "全帯域_10ms_rms_envelope_nrmse": 0.061803991123806946, "全帯域_10ms_envelope_correlation": 0.9972162501004935, "全帯域_10ms_modulation_mae_db": 0.5155049122367245, "全帯域_40ms_log_rms_mae_db": 0.41783005166860754, "全帯域_40ms_rms_envelope_nrmse": 0.037012262209478425, "全帯域_40ms_envelope_correlation": 0.9989566863275267, "全帯域_40ms_modulation_mae_db": 0.6378976802549127, "300–1000 Hz_10ms_log_rms_mae_db": 0.8614952029048192, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07184624447927802, "300–1000 Hz_10ms_envelope_correlation": 0.996347250003353, "300–1000 Hz_10ms_modulation_mae_db": 0.5783689115159344, "300–1000 Hz_40ms_log_rms_mae_db": 0.5480630427202591, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04479598102222111, "300–1000 Hz_40ms_envelope_correlation": 0.9985139928493194, "300–1000 Hz_40ms_modulation_mae_db": 0.8382137909710644, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9305956357131668, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0765679750615881, "1000–3000 Hz_10ms_envelope_correlation": 0.9965443092096445, "1000–3000 Hz_10ms_modulation_mae_db": 0.3641902155185483, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5776019310009795, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.047545116930125794, "1000–3000 Hz_40ms_envelope_correlation": 0.998641647757311, "1000–3000 Hz_40ms_modulation_mae_db": 0.47665315201195974, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5235842233779195, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14658099931931215, "3000–6000 Hz_10ms_envelope_correlation": 0.9847847034304619, "3000–6000 Hz_10ms_modulation_mae_db": 0.05252210148899903, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8538975101953592, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08877589416158507, "3000–6000 Hz_40ms_envelope_correlation": 0.9940930635690709, "3000–6000 Hz_40ms_modulation_mae_db": 0.05657535406254619, "mr_stft_db": 5.0783903705671385, "band_mae_db": 1.477842671280253, "rms_gain_error_db": -0.037564791022290406, "output_peak": 0.6638342637966433}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7517492304445759, "全帯域_10ms_rms_envelope_nrmse": 0.07682757413452838, "全帯域_10ms_envelope_correlation": 0.9957019148071317, "全帯域_10ms_modulation_mae_db": 0.7807862060484871, "全帯域_40ms_log_rms_mae_db": 0.44092136805181553, "全帯域_40ms_rms_envelope_nrmse": 0.044888951281139615, "全帯域_40ms_envelope_correlation": 0.998470994036972, "全帯域_40ms_modulation_mae_db": 0.9971617698745581, "300–1000 Hz_10ms_log_rms_mae_db": 0.9345501157438121, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08702459477964113, "300–1000 Hz_10ms_envelope_correlation": 0.9946289149702033, "300–1000 Hz_10ms_modulation_mae_db": 0.6097230963211856, "300–1000 Hz_40ms_log_rms_mae_db": 0.5991514914444152, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04938239654255304, "300–1000 Hz_40ms_envelope_correlation": 0.9981694721607424, "300–1000 Hz_40ms_modulation_mae_db": 0.8277760365110992, "1000–3000 Hz_10ms_log_rms_mae_db": 1.010714200815249, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09528500241949492, "1000–3000 Hz_10ms_envelope_correlation": 0.9947644392800036, "1000–3000 Hz_10ms_modulation_mae_db": 0.6583622934252197, "1000–3000 Hz_40ms_log_rms_mae_db": 0.61753309224854, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0513476837357191, "1000–3000 Hz_40ms_envelope_correlation": 0.9986039629080592, "1000–3000 Hz_40ms_modulation_mae_db": 0.4261508858318455, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5969826943767285, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16258776959233034, "3000–6000 Hz_10ms_envelope_correlation": 0.9815459485798945, "3000–6000 Hz_10ms_modulation_mae_db": 0.6728655843204742, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8926440268945387, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08948436840008794, "3000–6000 Hz_40ms_envelope_correlation": 0.9947562802099644, "3000–6000 Hz_40ms_modulation_mae_db": 1.0520109984880461, "mr_stft_db": 5.085138580029628, "band_mae_db": 1.5288865890194703, "rms_gain_error_db": -0.05803100729780453, "output_peak": 0.654239352160045}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6856099798150519, "全帯域_10ms_rms_envelope_nrmse": 0.07172283781727572, "全帯域_10ms_envelope_correlation": 0.9962718174257383, "全帯域_10ms_modulation_mae_db": 0.3469520466113325, "全帯域_40ms_log_rms_mae_db": 0.39366775542452737, "全帯域_40ms_rms_envelope_nrmse": 0.043018012934749245, "全帯域_40ms_envelope_correlation": 0.9986195444691482, "全帯域_40ms_modulation_mae_db": 0.33363702294511405, "300–1000 Hz_10ms_log_rms_mae_db": 0.8898008808456058, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08180372950138981, "300–1000 Hz_10ms_envelope_correlation": 0.9953133208880495, "300–1000 Hz_10ms_modulation_mae_db": 0.6222763805663598, "300–1000 Hz_40ms_log_rms_mae_db": 0.5981588168136442, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04910954335941721, "300–1000 Hz_40ms_envelope_correlation": 0.998282921263176, "300–1000 Hz_40ms_modulation_mae_db": 0.6941200293140343, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0051068555047526, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11149520138755624, "1000–3000 Hz_10ms_envelope_correlation": 0.9926391817050398, "1000–3000 Hz_10ms_modulation_mae_db": 0.6050601083884893, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5859579228875605, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0661268594615075, "1000–3000 Hz_40ms_envelope_correlation": 0.9973624509659694, "1000–3000 Hz_40ms_modulation_mae_db": 0.545046261131653, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5985631931203523, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15315006936452377, "3000–6000 Hz_10ms_envelope_correlation": 0.9834913516200825, "3000–6000 Hz_10ms_modulation_mae_db": 0.21103050376195207, "3000–6000 Hz_40ms_log_rms_mae_db": 0.920277993442206, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0894777596930633, "3000–6000 Hz_40ms_envelope_correlation": 0.9941104443294413, "3000–6000 Hz_40ms_modulation_mae_db": 0.5903318974811468, "mr_stft_db": 5.0931519487332855, "band_mae_db": 1.67380644812342, "rms_gain_error_db": -0.07836947591511849, "output_peak": 0.7067156303380766}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 97768, "output_samples": 97768, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.624193377295328, "spectral_convergence": 0.18274498306568457, "spectral_convergence_status": "ok", "amplitude_floor": 1.7496801023785185e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.089166119494559, "spectral_convergence": 0.1917186300087954, "spectral_convergence_status": "ok", "amplitude_floor": 1.6784480256181157e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.577383551812594, "spectral_convergence": 0.19315559593967302, "spectral_convergence_status": "ok", "amplitude_floor": 1.5558256811894896e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.01876573628214e-07, "output_power": 4.004462676893898e-06, "delta_db": 9.019473258789379, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0014282687361772438, "output_power": 0.0014500252037333609, "delta_db": 0.06565621136183403, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.002893798215697645, "output_power": 0.0028855257581398477, "delta_db": -0.012432890556221023, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0011796153749935407, "output_power": 0.001135555724792494, "delta_db": -0.16531973385011045, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.624359886340766e-05, "output_power": 1.4662764464003367e-05, "delta_db": -0.44466397705063176, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.5152799044228294e-05, "output_power": 2.290697891232052e-05, "delta_db": -0.40618505050977366, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2062863831028078e-05, "output_power": 1.2129404331130592e-05, "delta_db": 0.023890479964482778, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.448231657440347, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.024169963018932896, "pitch": null, "output_rms_dbfs": -22.57682629295084, "output_peak": 0.6681272212391751, "reference_rms_dbfs": -22.552656329931906, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.096914349534161}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 97768, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0003314896640837282, "log_rms_mae_db": 0.7141248452698682, "rms_envelope_nrmse": 0.06894384962740244, "envelope_correlation": 0.9965310741076363, "rms_gain_error_db": -0.024169835745973006, "reference_mean_power": 0.005567487969490699, "output_mean_power": 0.005536589231361721}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 4.765376195527077e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0029556164553593994, "output_power": 0.0029050827204235843, "reference_active": true, "delta_db": -0.07489572655145392}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00036953756834478597, "output_power": 0.00032121451050651304, "reference_active": true, "delta_db": -0.608634408927954}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 0.00011202447087610656, "output_power": 6.182356780204138e-05, "reference_active": true, "delta_db": -2.5815883696004005}], "active_band_count": 3, "active_band_mae_db": 1.0883728350266029}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.0003156446105274747, "log_rms_mae_db": 0.38669599461953175, "rms_envelope_nrmse": 0.04021405685526301, "envelope_correlation": 0.9987526463258866, "rms_gain_error_db": -0.02416979989852964, "reference_mean_power": 0.005608881493358216, "output_mean_power": 0.005577753073308891}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 4.372836941600517e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0027064910584040595, "output_power": 0.002647581652127108, "reference_active": true, "delta_db": -0.09557233880691006}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00018117557189089236, "output_power": 0.00015246715107580336, "reference_active": true, "delta_db": -0.7492335550082212}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.701057462757455e-06, "output_power": 5.211117468726252e-06, "reference_active": true, "delta_db": -2.69888213951649}], "active_band_count": 3, "active_band_mae_db": 1.1812293444438737}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0002506339510784735, "log_rms_mae_db": 0.9104238548420343, "rms_envelope_nrmse": 0.06905221579697297, "envelope_correlation": 0.9966217974494929, "rms_gain_error_db": -0.01543076495394421, "reference_mean_power": 0.0041004048785232925, "output_mean_power": 0.004085861725410875}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 3.4168869077487306e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0021098794264420863, "output_power": 0.0020723405305856967, "reference_active": true, "delta_db": -0.07796516364056015}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00027960522877585594, "output_power": 0.0002518740817374343, "reference_active": true, "delta_db": -0.45361808530260883}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.021566680060571e-05, "output_power": 5.5143863898712505e-05, "reference_active": true, "delta_db": -2.137847698207071}], "active_band_count": 3, "active_band_mae_db": 0.8898103157167467}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00024415679244648423, "log_rms_mae_db": 0.5788934085481248, "rms_envelope_nrmse": 0.04185726656918803, "envelope_correlation": 0.9986835643182894, "rms_gain_error_db": -0.015430776944695258, "reference_mean_power": 0.004130891145990147, "output_mean_power": 0.004116239854030685}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 3.1086003931775263e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0019093077513610485, "output_power": 0.0018705421267972548, "reference_active": true, "delta_db": -0.08908442234715326}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00014045819894614964, "output_power": 0.0001230695484644808, "reference_active": true, "delta_db": -0.573964880892258}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.796438388581124e-06, "output_power": 4.761398960059173e-06, "reference_active": true, "delta_db": -2.141616784676658}], "active_band_count": 3, "active_band_mae_db": 0.9348886959720231}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.00019827664142914133, "log_rms_mae_db": 0.9765578371292488, "rms_envelope_nrmse": 0.12180742764278477, "envelope_correlation": 0.9912290148894306, "rms_gain_error_db": -0.0061686295485350795, "reference_mean_power": 0.0008784725402011367, "output_mean_power": 0.0008772256615926845}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.1250771844458692e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007015897284632315, "output_power": 0.0006954687904070373, "reference_active": true, "delta_db": -0.03805576639088962}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.449911857407873e-05, "output_power": 6.677387326746151e-05, "reference_active": true, "delta_db": -1.0224561023343939}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6127775103534605e-05, "output_power": 1.558169969602855e-05, "reference_active": true, "delta_db": -2.24487599196317}], "active_band_count": 3, "active_band_mae_db": 1.101795953562818}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00017853730341036803, "log_rms_mae_db": 0.5764970743610368, "rms_envelope_nrmse": 0.0619236993343801, "envelope_correlation": 0.9976584639317968, "rms_gain_error_db": -0.006168627269928286, "reference_mean_power": 0.0008850039267330396, "output_mean_power": 0.000883747778126435}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.078630941288297e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006783838060260436, "output_power": 0.0006660581596126325, "reference_active": true, "delta_db": -0.07963319115108491}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3933140159486266e-05, "output_power": 2.588508078890035e-05, "reference_active": true, "delta_db": -1.1757452616657726}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.944075796645493e-06, "output_power": 9.713040321352918e-07, "reference_active": true, "delta_db": -3.0135800181238137}], "active_band_count": 3, "active_band_mae_db": 1.4229861569802236}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 2.2340226127796077e-05, "log_rms_mae_db": 1.5590300818146796, "rms_envelope_nrmse": 0.15502279733459, "envelope_correlation": 0.9845303289913226, "rms_gain_error_db": -0.5316948474477975, "reference_mean_power": 1.7310253593278313e-05, "output_mean_power": 1.531559754052201e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.3633964732936534e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.958677073783288e-06, "output_power": 7.048815051779389e-06, "reference_active": true, "delta_db": -0.5272476779113826}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3383871013961803e-06, "output_power": 1.1142585287071092e-06, "reference_active": true, "delta_db": -0.7959577556642512}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.535118084866941e-07, "output_power": 4.2087596156352684e-07, "reference_active": true, "delta_db": -0.3243447803383634}], "active_band_count": 3, "active_band_mae_db": 0.5491834046379991}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 1.6591025056474894e-05, "log_rms_mae_db": 0.8890411594851771, "rms_envelope_nrmse": 0.09416014313163192, "envelope_correlation": 0.9956529397354134, "rms_gain_error_db": -0.5316948396556961, "reference_mean_power": 1.743895029874837e-05, "output_mean_power": 1.5429464585528472e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.2324948655964946e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.384237970170313e-06, "output_power": 6.51258346195772e-06, "reference_active": true, "delta_db": -0.54552382113155}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2197399674362034e-07, "output_power": 3.8015692772319986e-07, "reference_active": true, "delta_db": -0.4532278012164933}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.206308596249792e-08, "output_power": 2.9613962743472936e-08, "reference_active": true, "delta_db": -0.3450879371403329}], "active_band_count": 3, "active_band_mae_db": 0.4479465198294587}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8373049411231734, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "5dc180a8b45a1af556642bd5142cd86c6be1c2d1c08956f721eca862b96144ce", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.993837831351743, "standard_deviation": 0.0017171985767739917, "minimum": 0.9912290148894306, "maximum": 0.9965443092096445, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.9784887206759797, "standard_deviation": 0.02643842529307195, "minimum": 0.9305956357131668, "maximum": 1.010714200815249, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7532225187310371, "standard_deviation": 0.33427931761105356, "minimum": 0.3641902155185483, "maximum": 1.2289198086244288, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10154401945123434, "standard_deviation": 0.0145713606709726, "minimum": 0.0765679750615881, "maximum": 0.12180742764278477, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.998089321037368, "standard_deviation": 0.0005622194732602907, "minimum": 0.9973239381825768, "maximum": 0.998641647757311, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5872021757791409, "standard_deviation": 0.02205046455961825, "minimum": 0.5513931356419626, "maximum": 0.61753309224854, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7744611418874064, "standard_deviation": 0.5536812522810076, "minimum": 0.20212812890767137, "maximum": 1.769725575774042, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.056759374243519456, "standard_deviation": 0.008190492313052003, "minimum": 0.047545116930125794, "maximum": 0.06950458550832718, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9833287445721732, "standard_deviation": 0.0023531678966945456, "minimum": 0.979026562456198, "maximum": 0.9869872786164557, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5600983216058963, "standard_deviation": 0.02671371893049079, "minimum": 1.5235842233779195, "maximum": 1.5985631931203523, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6056769688333032, "standard_deviation": 0.34949613155130166, "minimum": 0.05252210148899903, "maximum": 1.1829347594258028, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15479494291841242, "standard_deviation": 0.011369410687497639, "minimum": 0.13554109033197445, "maximum": 0.17482507869250458, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9948591498970476, "standard_deviation": 0.0008980824777193239, "minimum": 0.9935182310472533, "maximum": 0.996006615541839, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8789825856571176, "standard_deviation": 0.021434779518282977, "minimum": 0.8538975101953592, "maximum": 0.920277993442206, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7152822447533287, "standard_deviation": 0.3738451294967881, "minimum": 0.05657535406254619, "maximum": 1.2186473154808273, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08822733381990841, "standard_deviation": 0.008429154424464111, "minimum": 0.07393434812589304, "maximum": 0.10265773510374923, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9954424000529185, "standard_deviation": 0.0009527403888382847, "minimum": 0.9943395737551, "maximum": 0.9966217974494929, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.895456402844458, "standard_deviation": 0.030628275981144246, "minimum": 0.8477116624848967, "maximum": 0.9345501157438121, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6792851681029816, "standard_deviation": 0.2698482931665756, "minimum": 0.2968681322621458, "maximum": 1.1332772444165542, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07985694264325313, "standard_deviation": 0.008559446308745094, "minimum": 0.06902964658842879, "maximum": 0.08937573718745578, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9981926175880639, "standard_deviation": 0.00046458255135988733, "minimum": 0.9974338636229132, "maximum": 0.9987386551755071, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5789400524796169, "standard_deviation": 0.029765773451914154, "minimum": 0.5312716319777132, "maximum": 0.6140562682802788, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7525636951093662, "standard_deviation": 0.24897772469762522, "minimum": 0.34111713129713817, "maximum": 1.1156874517565472, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04897638988173579, "standard_deviation": 0.0062534649127730865, "minimum": 0.04098156900230797, "maximum": 0.05847155018729856, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.5203955732639125, "standard_deviation": 0.07256978643049031, "minimum": 1.448231657440347, "maximum": 1.67380644812342, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.08890369282798, "standard_deviation": 0.0067984638194591865, "minimum": 5.0783903705671385, "maximum": 5.096914349534161, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.6602893080891512, "standard_deviation": 0.02468444174499332, "minimum": 0.6264787408863366, "maximum": 0.7067156303380766, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.04879730520310388, "standard_deviation": 0.024794481315213904, "minimum": -0.07836947591511849, "maximum": -0.013668808661026158, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.996288401313913, "standard_deviation": 0.0006596796849596933, "minimum": 0.9956025834525624, "maximum": 0.9972162501004935, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7164132731747961, "standard_deviation": 0.021062071183919152, "minimum": 0.6856099798150519, "maximum": 0.7517492304445759, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.6679223781266708, "standard_deviation": 0.3081826239699593, "minimum": 0.22621141494832606, "maximum": 1.0883728350266029, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07113637053029996, "standard_deviation": 0.0065140024942785014, "minimum": 0.061803991123806946, "maximum": 0.07757733506489124, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9986311525338432, "standard_deviation": 0.0002465842833969116, "minimum": 0.998292860812944, "maximum": 0.9989566863275267, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.40674998032918475, "standard_deviation": 0.017578831220014378, "minimum": 0.38669599461953175, "maximum": 0.44092136805181553, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6990823597358047, "standard_deviation": 0.3288301815413317, "minimum": 0.26773465921168893, "maximum": 1.1812293444438737, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.04230241613254239, "standard_deviation": 0.003877986460683939, "minimum": 0.037012262209478425, "maximum": 0.04699927717298382, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_falset10_BASIC5000_1205", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 2.3294930458068848, "predicted_mos": 2.3294930458068848, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 97768, "input_sample_rate": 24000, "input_seconds": 4.073666666666667, "input_float32_sha256": "0019bc9c9ff0cbc7307ff0cbef338e5a526e56c1fa97a1f397a03735b185add4", "internal_samples": 65179, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.689862499944866}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7329199767508349, "全帯域_10ms_rms_envelope_nrmse": 0.0753054782150965, "全帯域_10ms_envelope_correlation": 0.9962000110275632, "全帯域_10ms_modulation_mae_db": 1.3193678751463054, "全帯域_40ms_log_rms_mae_db": 0.4150475376509492, "全帯域_40ms_rms_envelope_nrmse": 0.04648627504075717, "全帯域_40ms_envelope_correlation": 0.9987432844013245, "全帯域_40ms_modulation_mae_db": 1.2846788074711275, "300–1000 Hz_10ms_log_rms_mae_db": 1.0231121319461005, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07818127965489556, "300–1000 Hz_10ms_envelope_correlation": 0.9957380122857705, "300–1000 Hz_10ms_modulation_mae_db": 1.0697230289626953, "300–1000 Hz_40ms_log_rms_mae_db": 0.6829363268491769, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04785665745882685, "300–1000 Hz_40ms_envelope_correlation": 0.9983908759206664, "300–1000 Hz_40ms_modulation_mae_db": 1.0140714692850723, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1015587945090999, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13393561834038847, "1000–3000 Hz_10ms_envelope_correlation": 0.9911259189095477, "1000–3000 Hz_10ms_modulation_mae_db": 1.7317083718148198, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6981698471999805, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09492322189965229, "1000–3000 Hz_40ms_envelope_correlation": 0.996622063762497, "1000–3000 Hz_40ms_modulation_mae_db": 1.7442119340255235, "3000–6000 Hz_10ms_log_rms_mae_db": 2.1702079485878967, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2024642178173923, "3000–6000 Hz_10ms_envelope_correlation": 0.9707015098925312, "3000–6000 Hz_10ms_modulation_mae_db": 0.4495492762532445, "3000–6000 Hz_40ms_log_rms_mae_db": 1.325564431247819, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11684480722902478, "3000–6000 Hz_40ms_envelope_correlation": 0.9897297422064548, "3000–6000 Hz_40ms_modulation_mae_db": 0.4517718666285226, "mr_stft_db": 5.463008213978031, "band_mae_db": 1.6610536258399766, "rms_gain_error_db": -0.20910152382681807, "output_peak": 0.6323744744473384}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.709006164717621, "全帯域_10ms_rms_envelope_nrmse": 0.06543356398006699, "全帯域_10ms_envelope_correlation": 0.9969086744544121, "全帯域_10ms_modulation_mae_db": 0.2335515493388084, "全帯域_40ms_log_rms_mae_db": 0.3968115236982091, "全帯域_40ms_rms_envelope_nrmse": 0.0360330580820139, "全帯域_40ms_envelope_correlation": 0.9990199315613849, "全帯域_40ms_modulation_mae_db": 0.14295414700356748, "300–1000 Hz_10ms_log_rms_mae_db": 0.9809792946964461, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07435496516744923, "300–1000 Hz_10ms_envelope_correlation": 0.9962596565194685, "300–1000 Hz_10ms_modulation_mae_db": 0.18277302554899152, "300–1000 Hz_40ms_log_rms_mae_db": 0.6102347956665712, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.042822725332900116, "300–1000 Hz_40ms_envelope_correlation": 0.9987723645194644, "300–1000 Hz_40ms_modulation_mae_db": 0.1259955483773222, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1428685984958393, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08919343024513497, "1000–3000 Hz_10ms_envelope_correlation": 0.9955344822722852, "1000–3000 Hz_10ms_modulation_mae_db": 0.48170442239579775, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6883944991594158, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0509273170253824, "1000–3000 Hz_40ms_envelope_correlation": 0.9987352897308014, "1000–3000 Hz_40ms_modulation_mae_db": 0.3631881206018757, "3000–6000 Hz_10ms_log_rms_mae_db": 2.2388938733028234, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.21009452824388514, "3000–6000 Hz_10ms_envelope_correlation": 0.9688618588402135, "3000–6000 Hz_10ms_modulation_mae_db": 0.6653256401384134, "3000–6000 Hz_40ms_log_rms_mae_db": 1.4099988080795305, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11387950397152002, "3000–6000 Hz_40ms_envelope_correlation": 0.9903014974007655, "3000–6000 Hz_40ms_modulation_mae_db": 0.8337527324617607, "mr_stft_db": 5.451340625594413, "band_mae_db": 1.656603000362102, "rms_gain_error_db": 0.04235999214024368, "output_peak": 0.6654677636332421}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.718528936973448, "全帯域_10ms_rms_envelope_nrmse": 0.07637142014180608, "全帯域_10ms_envelope_correlation": 0.9959429862678673, "全帯域_10ms_modulation_mae_db": 1.2476863581044852, "全帯域_40ms_log_rms_mae_db": 0.41395152473389585, "全帯域_40ms_rms_envelope_nrmse": 0.0491626464936751, "全帯域_40ms_envelope_correlation": 0.9983856674923767, "全帯域_40ms_modulation_mae_db": 1.1934211987285372, "300–1000 Hz_10ms_log_rms_mae_db": 0.9680049828371368, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07186473709778021, "300–1000 Hz_10ms_envelope_correlation": 0.9965093588686429, "300–1000 Hz_10ms_modulation_mae_db": 1.0962839176063675, "300–1000 Hz_40ms_log_rms_mae_db": 0.6386357905446753, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04720749740275167, "300–1000 Hz_40ms_envelope_correlation": 0.9985320736556393, "300–1000 Hz_40ms_modulation_mae_db": 0.9164529224521981, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1516743883651213, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10510283748339369, "1000–3000 Hz_10ms_envelope_correlation": 0.9936652899782824, "1000–3000 Hz_10ms_modulation_mae_db": 0.997492820410312, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7190001082968227, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06259850967107944, "1000–3000 Hz_40ms_envelope_correlation": 0.9978959685314701, "1000–3000 Hz_40ms_modulation_mae_db": 1.6614842784760953, "3000–6000 Hz_10ms_log_rms_mae_db": 2.158337656972189, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19494450464236274, "3000–6000 Hz_10ms_envelope_correlation": 0.9728956017725233, "3000–6000 Hz_10ms_modulation_mae_db": 0.40951815186816987, "3000–6000 Hz_40ms_log_rms_mae_db": 1.3373512955734759, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10967683182048063, "3000–6000 Hz_40ms_envelope_correlation": 0.9908592664989867, "3000–6000 Hz_40ms_modulation_mae_db": 0.7071364122766542, "mr_stft_db": 5.465133564344508, "band_mae_db": 1.5383793127419065, "rms_gain_error_db": -0.16623258902095037, "output_peak": 0.6561596741174672}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6588848381762011, "全帯域_10ms_rms_envelope_nrmse": 0.06615219512805848, "全帯域_10ms_envelope_correlation": 0.9968053633454672, "全帯域_10ms_modulation_mae_db": 0.5387103692260257, "全帯域_40ms_log_rms_mae_db": 0.37147948811592674, "全帯域_40ms_rms_envelope_nrmse": 0.0318885037397525, "全帯域_40ms_envelope_correlation": 0.9992141771268005, "全帯域_40ms_modulation_mae_db": 0.7651061208553788, "300–1000 Hz_10ms_log_rms_mae_db": 0.8843174960727679, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07391475039610923, "300–1000 Hz_10ms_envelope_correlation": 0.99615324024459, "300–1000 Hz_10ms_modulation_mae_db": 0.5521739990757625, "300–1000 Hz_40ms_log_rms_mae_db": 0.5744769622241496, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038222836553449074, "300–1000 Hz_40ms_envelope_correlation": 0.9989164237373345, "300–1000 Hz_40ms_modulation_mae_db": 0.8834235196508794, "1000–3000 Hz_10ms_log_rms_mae_db": 1.082201211655796, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10480299352383403, "1000–3000 Hz_10ms_envelope_correlation": 0.9936069369586934, "1000–3000 Hz_10ms_modulation_mae_db": 0.2868104895620607, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6891099883720873, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06327211613831449, "1000–3000 Hz_40ms_envelope_correlation": 0.9977349802662457, "1000–3000 Hz_40ms_modulation_mae_db": 0.3781532453083816, "3000–6000 Hz_10ms_log_rms_mae_db": 2.216064363619415, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.21004153773749804, "3000–6000 Hz_10ms_envelope_correlation": 0.9685000187719749, "3000–6000 Hz_10ms_modulation_mae_db": 0.5386271549356666, "3000–6000 Hz_40ms_log_rms_mae_db": 1.413188988429226, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12320130550505567, "3000–6000 Hz_40ms_envelope_correlation": 0.9884619235372686, "3000–6000 Hz_40ms_modulation_mae_db": 0.5242421076535432, "mr_stft_db": 5.465068132396205, "band_mae_db": 1.4180047591831204, "rms_gain_error_db": -0.005162742643066697, "output_peak": 0.7089246867407051}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7376386844761692, "全帯域_10ms_rms_envelope_nrmse": 0.06614046452600898, "全帯域_10ms_envelope_correlation": 0.9968071788117762, "全帯域_10ms_modulation_mae_db": 0.37468879005822625, "全帯域_40ms_log_rms_mae_db": 0.430702463847449, "全帯域_40ms_rms_envelope_nrmse": 0.03689971265321543, "全帯域_40ms_envelope_correlation": 0.9989547279569335, "全帯域_40ms_modulation_mae_db": 0.4385189204576352, "300–1000 Hz_10ms_log_rms_mae_db": 1.0392922008764611, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07002858276664893, "300–1000 Hz_10ms_envelope_correlation": 0.9965243491149333, "300–1000 Hz_10ms_modulation_mae_db": 0.4913217985513893, "300–1000 Hz_40ms_log_rms_mae_db": 0.6762115945315572, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.040206260522990436, "300–1000 Hz_40ms_envelope_correlation": 0.9987848591158152, "300–1000 Hz_40ms_modulation_mae_db": 0.672331457139951, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1090406343669756, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1130208119645517, "1000–3000 Hz_10ms_envelope_correlation": 0.9925978594140022, "1000–3000 Hz_10ms_modulation_mae_db": 0.8886265149641092, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6988044593131829, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06074364057561258, "1000–3000 Hz_40ms_envelope_correlation": 0.9980155968370253, "1000–3000 Hz_40ms_modulation_mae_db": 0.7612556754879143, "3000–6000 Hz_10ms_log_rms_mae_db": 2.224938691323647, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.21376265379634113, "3000–6000 Hz_10ms_envelope_correlation": 0.9673624217211096, "3000–6000 Hz_10ms_modulation_mae_db": 0.25016912963427623, "3000–6000 Hz_40ms_log_rms_mae_db": 1.4274349683859524, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13377185130016342, "3000–6000 Hz_40ms_envelope_correlation": 0.9865032399933727, "3000–6000 Hz_40ms_modulation_mae_db": 0.2407714271911486, "mr_stft_db": 5.461945917355389, "band_mae_db": 1.6176155165225765, "rms_gain_error_db": -0.03131178343778204, "output_peak": 0.6363461137339186}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7208876100990749, "全帯域_10ms_rms_envelope_nrmse": 0.06610783564972106, "全帯域_10ms_envelope_correlation": 0.9968157412681498, "全帯域_10ms_modulation_mae_db": 0.1917517102854328, "全帯域_40ms_log_rms_mae_db": 0.3903287983393828, "全帯域_40ms_rms_envelope_nrmse": 0.03845894676586046, "全帯域_40ms_envelope_correlation": 0.99886077085383, "全帯域_40ms_modulation_mae_db": 0.3649592379083577, "300–1000 Hz_10ms_log_rms_mae_db": 0.9528699166735635, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07371666723399736, "300–1000 Hz_10ms_envelope_correlation": 0.9961729544180442, "300–1000 Hz_10ms_modulation_mae_db": 0.2775803358118784, "300–1000 Hz_40ms_log_rms_mae_db": 0.6041828699905901, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04392593797712712, "300–1000 Hz_40ms_envelope_correlation": 0.9985634759441533, "300–1000 Hz_40ms_modulation_mae_db": 0.49078548097698665, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1004959405323609, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.107368025502769, "1000–3000 Hz_10ms_envelope_correlation": 0.9932965842184831, "1000–3000 Hz_10ms_modulation_mae_db": 0.4014528963571314, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7208081863101687, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06610296224941777, "1000–3000 Hz_40ms_envelope_correlation": 0.9975237992513727, "1000–3000 Hz_40ms_modulation_mae_db": 0.2949298735364191, "3000–6000 Hz_10ms_log_rms_mae_db": 2.1509208630216707, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19343479043865988, "3000–6000 Hz_10ms_envelope_correlation": 0.9734205959802898, "3000–6000 Hz_10ms_modulation_mae_db": 0.6656347837207578, "3000–6000 Hz_40ms_log_rms_mae_db": 1.3319514194047217, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11391363299731956, "3000–6000 Hz_40ms_envelope_correlation": 0.9902712763670866, "3000–6000 Hz_40ms_modulation_mae_db": 0.46412326241771856, "mr_stft_db": 5.450543306053437, "band_mae_db": 1.6043015720852958, "rms_gain_error_db": -0.0006195662446695575, "output_peak": 0.7147074700648599}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7438497443595384, "全帯域_10ms_rms_envelope_nrmse": 0.06297575358625382, "全帯域_10ms_envelope_correlation": 0.9971193639937821, "全帯域_10ms_modulation_mae_db": 0.33752244303331036, "全帯域_40ms_log_rms_mae_db": 0.40067620178164415, "全帯域_40ms_rms_envelope_nrmse": 0.032155319429172546, "全帯域_40ms_envelope_correlation": 0.9992193470090563, "全帯域_40ms_modulation_mae_db": 0.17603649703938085, "300–1000 Hz_10ms_log_rms_mae_db": 1.0190677844022988, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07042428134205136, "300–1000 Hz_10ms_envelope_correlation": 0.9964953418789319, "300–1000 Hz_10ms_modulation_mae_db": 0.2577968523207562, "300–1000 Hz_40ms_log_rms_mae_db": 0.6619617261178854, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03864284713379675, "300–1000 Hz_40ms_envelope_correlation": 0.9988868833488328, "300–1000 Hz_40ms_modulation_mae_db": 0.15833433821474055, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1522317626488592, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10456721503288921, "1000–3000 Hz_10ms_envelope_correlation": 0.9935541084420642, "1000–3000 Hz_10ms_modulation_mae_db": 1.179966996069161, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7558150768434166, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.057363197415684256, "1000–3000 Hz_40ms_envelope_correlation": 0.9980569760467386, "1000–3000 Hz_40ms_modulation_mae_db": 0.878598387080193, "3000–6000 Hz_10ms_log_rms_mae_db": 2.1833123333343867, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19411033827441104, "3000–6000 Hz_10ms_envelope_correlation": 0.9745234810914578, "3000–6000 Hz_10ms_modulation_mae_db": 0.17156530018633495, "3000–6000 Hz_40ms_log_rms_mae_db": 1.3784470111486007, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10918758042004507, "3000–6000 Hz_40ms_envelope_correlation": 0.9917342101770703, "3000–6000 Hz_40ms_modulation_mae_db": 0.33805859814922257, "mr_stft_db": 5.460738329164719, "band_mae_db": 1.6108311449386163, "rms_gain_error_db": -0.027792372729065134, "output_peak": 0.6862065280272723}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.706597663558, "全帯域_10ms_rms_envelope_nrmse": 0.07272807284772048, "全帯域_10ms_envelope_correlation": 0.9962794778110814, "全帯域_10ms_modulation_mae_db": 0.9182117459626099, "全帯域_40ms_log_rms_mae_db": 0.4021890486028598, "全帯域_40ms_rms_envelope_nrmse": 0.04070931304711016, "全帯域_40ms_envelope_correlation": 0.9989130967786432, "全帯域_40ms_modulation_mae_db": 0.8484046373200922, "300–1000 Hz_10ms_log_rms_mae_db": 0.9362562423120414, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08795310898990853, "300–1000 Hz_10ms_envelope_correlation": 0.994674252505028, "300–1000 Hz_10ms_modulation_mae_db": 1.1218515493839254, "300–1000 Hz_40ms_log_rms_mae_db": 0.6235960596160003, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04974399350315663, "300–1000 Hz_40ms_envelope_correlation": 0.998377080321482, "300–1000 Hz_40ms_modulation_mae_db": 1.0289277958658387, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1363980304913313, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09403254623413299, "1000–3000 Hz_10ms_envelope_correlation": 0.9948760312861128, "1000–3000 Hz_10ms_modulation_mae_db": 0.717732452355427, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6970652422874762, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05864150171161882, "1000–3000 Hz_40ms_envelope_correlation": 0.9980585153520144, "1000–3000 Hz_40ms_modulation_mae_db": 0.6629657010186043, "3000–6000 Hz_10ms_log_rms_mae_db": 2.16103766818506, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.22722725088589724, "3000–6000 Hz_10ms_envelope_correlation": 0.9631453575094822, "3000–6000 Hz_10ms_modulation_mae_db": 0.6830312224112455, "3000–6000 Hz_40ms_log_rms_mae_db": 1.34851787543449, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13616058195742936, "3000–6000 Hz_40ms_envelope_correlation": 0.9858808682348117, "3000–6000 Hz_40ms_modulation_mae_db": 0.7114803692734982, "mr_stft_db": 5.44950947309304, "band_mae_db": 1.566570351399351, "rms_gain_error_db": -0.14508942536518704, "output_peak": 0.6478531654007815}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 97768, "output_samples": 97768, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.053446981040276, "spectral_convergence": 0.17788678907920125, "spectral_convergence_status": "ok", "amplitude_floor": 1.7496801023785185e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.504179878030528, "spectral_convergence": 0.19747105444021643, "spectral_convergence_status": "ok", "amplitude_floor": 1.6784480256181157e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.831397782863286, "spectral_convergence": 0.20349368640158352, "spectral_convergence_status": "ok", "amplitude_floor": 1.5558256811894896e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.01876573628214e-07, "output_power": 5.353601958379323e-06, "delta_db": 10.280491537995896, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0014282687361772438, "output_power": 0.0013532135285844163, "delta_db": -0.23443598947094568, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.002893798215697645, "output_power": 0.0028780808194018943, "delta_db": -0.02365259324336604, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0011796153749935407, "output_power": 0.00100354447294519, "delta_db": -0.7020380108198132, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.624359886340766e-05, "output_power": 1.6636905436873523e-05, "delta_db": 0.10390292092516956, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.5152799044228294e-05, "output_power": 2.4910839502558182e-05, "delta_db": -0.0419795744090715, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2062863831028078e-05, "output_power": 1.2750813712490663e-05, "delta_db": 0.24087475401557618, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.6610536258399766, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.20910152382681807, "pitch": null, "output_rms_dbfs": -22.761757853758727, "output_peak": 0.6323744744473384, "reference_rms_dbfs": -22.552656329931906, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.463008213978031}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 97768, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0003314896640837282, "log_rms_mae_db": 0.7329199767508349, "rms_envelope_nrmse": 0.0753054782150965, "envelope_correlation": 0.9962000110275632, "rms_gain_error_db": -0.20910151680011235, "reference_mean_power": 0.005567487969490699, "output_mean_power": 0.005305778744598962}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 4.765376195527077e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0029556164553593994, "output_power": 0.002741433443382719, "reference_active": true, "delta_db": -0.3267036929198559}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00036953756834478597, "output_power": 0.00030700837001505744, "reference_active": true, "delta_db": -0.8050838083648697}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 0.00011202447087610656, "output_power": 5.84361087826885e-05, "reference_active": true, "delta_db": -2.8263161241541903}], "active_band_count": 3, "active_band_mae_db": 1.3193678751463054}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.0003156446105274747, "log_rms_mae_db": 0.4150475376509492, "rms_envelope_nrmse": 0.04648627504075717, "envelope_correlation": 0.9987432844013245, "rms_gain_error_db": -0.20910154083239693, "reference_mean_power": 0.005608881493358216, "output_mean_power": 0.005345226466017604}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 4.372836941600517e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0027064910584040595, "output_power": 0.002486254387037753, "reference_active": true, "delta_db": -0.36861034171768414}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00018117557189089236, "output_power": 0.00014927783729646354, "reference_active": true, "delta_db": -0.8410430637966444}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.701057462757455e-06, "output_power": 5.276923222505038e-06, "reference_active": true, "delta_db": -2.644383016899054}], "active_band_count": 3, "active_band_mae_db": 1.2846788074711275}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0002506339510784735, "log_rms_mae_db": 1.0231121319461005, "rms_envelope_nrmse": 0.07818127965489556, "envelope_correlation": 0.9957380122857705, "rms_gain_error_db": -0.11562854477378993, "reference_mean_power": 0.0041004048785232925, "output_mean_power": 0.003992674325278741}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 3.4168869077487306e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0021098794264420863, "output_power": 0.0020309150489290196, "reference_active": true, "delta_db": -0.1656587962597562}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00027960522877585594, "output_power": 0.00024330669497410045, "reference_active": true, "delta_db": -0.6039122929719098}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.021566680060571e-05, "output_power": 5.1442511537632646e-05, "reference_active": true, "delta_db": -2.43959799765642}], "active_band_count": 3, "active_band_mae_db": 1.0697230289626953}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00024415679244648423, "log_rms_mae_db": 0.6829363268491769, "rms_envelope_nrmse": 0.04785665745882685, "envelope_correlation": 0.9983908759206664, "rms_gain_error_db": -0.11562854939088373, "reference_mean_power": 0.004130891145990147, "output_mean_power": 0.004022359618185202}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 3.1086003931775263e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0019093077513610485, "output_power": 0.0018258788897756314, "reference_active": true, "delta_db": -0.19403968221635143}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00014045819894614964, "output_power": 0.00012060691620077579, "reference_active": true, "delta_db": -0.6617488216146634}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.796438388581124e-06, "output_power": 4.712524931252236e-06, "reference_active": true, "delta_db": -2.186425904024202}], "active_band_count": 3, "active_band_mae_db": 1.0140714692850723}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.00019827664142914133, "log_rms_mae_db": 1.1015587945090999, "rms_envelope_nrmse": 0.13393561834038847, "envelope_correlation": 0.9911259189095477, "rms_gain_error_db": -0.5402753801327131, "reference_mean_power": 0.0008784725402011367, "output_mean_power": 0.000775712254919085}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.1250771844458692e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007015897284632315, "output_power": 0.0006143901851069913, "reference_active": true, "delta_db": -0.5763895295282782}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.449911857407873e-05, "output_power": 6.40780174280167e-05, "reference_active": true, "delta_db": -1.2014311254182939}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6127775103534605e-05, "output_power": 1.1895206428227461e-05, "reference_active": true, "delta_db": -3.4173044604978875}], "active_band_count": 3, "active_band_mae_db": 1.7317083718148198}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00017853730341036803, "log_rms_mae_db": 0.6981698471999805, "rms_envelope_nrmse": 0.09492322189965229, "envelope_correlation": 0.996622063762497, "rms_gain_error_db": -0.5402753885978664, "reference_mean_power": 0.0008850039267330396, "output_mean_power": 0.000781479623851444}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.078630941288297e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006783838060260436, "output_power": 0.0005874972390696767, "reference_active": true, "delta_db": -0.6246964216210122}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3933140159486266e-05, "output_power": 2.62951551635702e-05, "reference_active": true, "delta_db": -1.1074831308548128}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.944075796645493e-06, "output_power": 8.682955363736324e-07, "reference_active": true, "delta_db": -3.500456249600746}], "active_band_count": 3, "active_band_mae_db": 1.7442119340255235}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 2.2340226127796077e-05, "log_rms_mae_db": 2.1702079485878967, "rms_envelope_nrmse": 0.2024642178173923, "envelope_correlation": 0.9707015098925312, "rms_gain_error_db": -0.0921923861667766, "reference_mean_power": 1.7310253593278313e-05, "output_mean_power": 1.6946662940482797e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.3633964732936534e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.958677073783288e-06, "output_power": 7.726686152027698e-06, "reference_active": true, "delta_db": -0.1284761127835492}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3383871013961803e-06, "output_power": 1.3142835819828146e-06, "reference_active": true, "delta_db": -0.07892659765036003}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.535118084866941e-07, "output_power": 5.898113308069827e-07, "reference_active": true, "delta_db": 1.141245118325824}], "active_band_count": 3, "active_band_mae_db": 0.4495492762532445}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 1.6591025056474894e-05, "log_rms_mae_db": 1.325564431247819, "rms_envelope_nrmse": 0.11684480722902478, "envelope_correlation": 0.9897297422064548, "rms_gain_error_db": -0.09219262746731674, "reference_mean_power": 1.743895029874837e-05, "output_mean_power": 1.7072655506518703e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.2324948655964946e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.384237970170313e-06, "output_power": 7.13539523894247e-06, "reference_active": true, "delta_db": -0.14887649893188223}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2197399674362034e-07, "output_power": 4.325953820634459e-07, "reference_active": true, "delta_db": 0.10796189747475024}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.206308596249792e-08, "output_power": 4.129077551077325e-08, "reference_active": true, "delta_db": 1.0984772034789352}], "active_band_count": 3, "active_band_mae_db": 0.4517718666285226}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.825466716872371, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "5a793439bfbc7a89a4b95bdaedc397cc37f0554ae16b2dae5f2268fc912bd316", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9935321514349339, "standard_deviation": 0.0013393757156192022, "minimum": 0.9911259189095477, "maximum": 0.9955344822722852, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.122058670133173, "standard_deviation": 0.02691112120672357, "minimum": 1.082201211655796, "maximum": 1.1522317626488592, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8356868704911024, "standard_deviation": 0.47500501519756216, "minimum": 0.2868104895620607, "maximum": 1.7317083718148198, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10650293479088677, "standard_deviation": 0.013413798086070428, "minimum": 0.08919343024513497, "maximum": 0.13393561834038847, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978303987222706, "standard_deviation": 0.0006004737715161736, "minimum": 0.996622063762497, "maximum": 0.9987352897308014, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7083959259728188, "standard_deviation": 0.022715779710435098, "minimum": 0.6883944991594158, "maximum": 0.7558150768434166, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8430984019418758, "standard_deviation": 0.5693535085292651, "minimum": 0.2949298735364191, "maximum": 1.7442119340255235, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06432155833584526, "standard_deviation": 0.01318329280422967, "minimum": 0.0509273170253824, "maximum": 0.09492322189965229, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9699263556974478, "standard_deviation": 0.0037508827107236345, "minimum": 0.9631453575094822, "maximum": 0.9745234810914578, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 2.187964174793386, "standard_deviation": 0.03393789945587972, "minimum": 2.1509208630216707, "maximum": 2.2388938733028234, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.4791775823935136, "standard_deviation": 0.19541472599088774, "minimum": 0.17156530018633495, "maximum": 0.6830312224112455, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.20575997772955595, "standard_deviation": 0.01181686179001798, "minimum": 0.19343479043865988, "maximum": 0.22722725088589724, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9892177530519771, "standard_deviation": 0.002092446573003735, "minimum": 0.9858808682348117, "maximum": 0.9917342101770703, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.371556849712977, "standard_deviation": 0.04099749912957463, "minimum": 1.325564431247819, "maximum": 1.4274349683859524, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.5339170970065086, "standard_deviation": 0.20264064395421036, "minimum": 0.2407714271911486, "maximum": 0.8337527324617607, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.11957951190012982, "standard_deviation": 0.010471716786658168, "minimum": 0.10918758042004507, "maximum": 0.13616058195742936, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9960658957294262, "standard_deviation": 0.0006201469117860837, "minimum": 0.994674252505028, "maximum": 0.9965243491149333, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.975487506227102, "standard_deviation": 0.05166810394099251, "minimum": 0.8843174960727679, "maximum": 1.0392922008764611, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6311880634077207, "standard_deviation": 0.4036828649526825, "minimum": 0.18277302554899152, "maximum": 1.1218515493839254, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07505479658110506, "standard_deviation": 0.00581380616736372, "minimum": 0.07002858276664893, "maximum": 0.08795310898990853, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9986530045704235, "standard_deviation": 0.00021487758651698256, "minimum": 0.998377080321482, "maximum": 0.9989164237373345, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.6340295156925757, "standard_deviation": 0.0379567511236327, "minimum": 0.5744769622241496, "maximum": 0.6829363268491769, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6612903164953736, "standard_deviation": 0.36698812437169315, "minimum": 0.1259955483773222, "maximum": 1.0289277958658387, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04357859448562483, "standard_deviation": 0.004384929893751429, "minimum": 0.038222836553449074, "maximum": 0.04974399350315663, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.5841699103841183, "standard_deviation": 0.07874892544335835, "minimum": 1.4180047591831204, "maximum": 1.6610536258399766, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.458410945247468, "standard_deviation": 0.0067579027255940255, "minimum": 5.44950947309304, "maximum": 5.465133564344508, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.6685049845206981, "standard_deviation": 0.0316442330598047, "minimum": 0.6323744744473384, "maximum": 0.7147074700648599, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.0678687513909119, "standard_deviation": 0.09191033940067578, "minimum": -0.20910152382681807, "maximum": 0.04235999214024368, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9966098496225124, "standard_deviation": 0.000412358531706742, "minimum": 0.9959429862678673, "maximum": 0.9971193639937821, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.716039202388861, "standard_deviation": 0.026618623643612203, "minimum": 0.6588848381762011, "maximum": 0.7438497443595384, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.6451863551444005, "standard_deviation": 0.4545451700215977, "minimum": 0.1917517102854328, "maximum": 1.3193678751463054, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.06890184800934154, "standard_deviation": 0.005093145367793442, "minimum": 0.06297575358625382, "maximum": 0.07637142014180608, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9989138753975437, "standard_deviation": 0.0002692148513772679, "minimum": 0.9983856674923767, "maximum": 0.9992193470090563, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4026483233462896, "standard_deviation": 0.017848461674974708, "minimum": 0.37147948811592674, "maximum": 0.430702463847449, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6517599458480096, "standard_deviation": 0.4405227754792657, "minimum": 0.14295414700356748, "maximum": 1.2846788074711275, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03897422190644466, "standard_deviation": 0.006246940437589646, "minimum": 0.0318885037397525, "maximum": 0.0491626464936751, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_falset10_BASIC5000_1205", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 2.6767418384552, "predicted_mos": 2.6767418384552, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 97768, "input_sample_rate": 24000, "input_seconds": 4.073666666666667, "input_float32_sha256": "d3bfd6f1aa0c24b3c85a3d829f6b9ce5fed5fe1aa8f02732a2e6f63d7c87e339", "internal_samples": 65179, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.460046700201929}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7214466977415974, "全帯域_10ms_rms_envelope_nrmse": 0.06956702948179742, "全帯域_10ms_envelope_correlation": 0.996535661500091, "全帯域_10ms_modulation_mae_db": 1.013642823508891, "全帯域_40ms_log_rms_mae_db": 0.42987543316445836, "全帯域_40ms_rms_envelope_nrmse": 0.03766123913627222, "全帯域_40ms_envelope_correlation": 0.999000646863232, "全帯域_40ms_modulation_mae_db": 1.1513107589562932, "300–1000 Hz_10ms_log_rms_mae_db": 0.8398380477193221, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07024973072846688, "300–1000 Hz_10ms_envelope_correlation": 0.9965068961977003, "300–1000 Hz_10ms_modulation_mae_db": 0.7673815107429264, "300–1000 Hz_40ms_log_rms_mae_db": 0.5492250413164246, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03320638148250582, "300–1000 Hz_40ms_envelope_correlation": 0.999179774838046, "300–1000 Hz_40ms_modulation_mae_db": 0.8939441771515155, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9332696380475295, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10548552296376905, "1000–3000 Hz_10ms_envelope_correlation": 0.994081512863601, "1000–3000 Hz_10ms_modulation_mae_db": 1.229269602837021, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6348444849989816, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06570074653069907, "1000–3000 Hz_40ms_envelope_correlation": 0.9981960762926388, "1000–3000 Hz_40ms_modulation_mae_db": 1.644872494353179, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4787860370609027, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16442581071628837, "3000–6000 Hz_10ms_envelope_correlation": 0.9814063990466501, "3000–6000 Hz_10ms_modulation_mae_db": 0.9093996015055357, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8282375343440372, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08957953040369043, "3000–6000 Hz_40ms_envelope_correlation": 0.9951883084720579, "3000–6000 Hz_40ms_modulation_mae_db": 0.9623123124759644, "mr_stft_db": 5.105108654818121, "band_mae_db": 1.6500427598935765, "rms_gain_error_db": -0.10014777458733666, "output_peak": 0.6497057101163096}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7193475338860197, "全帯域_10ms_rms_envelope_nrmse": 0.07333711758774784, "全帯域_10ms_envelope_correlation": 0.9960886881791806, "全帯域_10ms_modulation_mae_db": 0.7360270948602609, "全帯域_40ms_log_rms_mae_db": 0.44180331650786525, "全帯域_40ms_rms_envelope_nrmse": 0.0380121585275869, "全帯域_40ms_envelope_correlation": 0.9989211253952549, "全帯域_40ms_modulation_mae_db": 0.8604656613868408, "300–1000 Hz_10ms_log_rms_mae_db": 0.8606532410184552, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07861491085975163, "300–1000 Hz_10ms_envelope_correlation": 0.9956167331003349, "300–1000 Hz_10ms_modulation_mae_db": 0.6367857383547871, "300–1000 Hz_40ms_log_rms_mae_db": 0.5645281825077706, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04565918444531236, "300–1000 Hz_40ms_envelope_correlation": 0.9984403833580892, "300–1000 Hz_40ms_modulation_mae_db": 0.7870130499862577, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9269599132163158, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09703754825110746, "1000–3000 Hz_10ms_envelope_correlation": 0.9946128891842998, "1000–3000 Hz_10ms_modulation_mae_db": 0.8553916423203148, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6025914860528023, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04828468106688008, "1000–3000 Hz_40ms_envelope_correlation": 0.9988584525394868, "1000–3000 Hz_40ms_modulation_mae_db": 1.178054019374122, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5063242216818151, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17778430174256465, "3000–6000 Hz_10ms_envelope_correlation": 0.9782414444495798, "3000–6000 Hz_10ms_modulation_mae_db": 1.0295768882203826, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8663527983698205, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09673257248633348, "3000–6000 Hz_40ms_envelope_correlation": 0.994467035459009, "3000–6000 Hz_40ms_modulation_mae_db": 1.209996722633829, "mr_stft_db": 5.096063879730321, "band_mae_db": 1.7906825459047668, "rms_gain_error_db": -0.06721732556882913, "output_peak": 0.68047354825706}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7222408328794677, "全帯域_10ms_rms_envelope_nrmse": 0.07454317996511911, "全帯域_10ms_envelope_correlation": 0.9959972103509189, "全帯域_10ms_modulation_mae_db": 0.8112938716913319, "全帯域_40ms_log_rms_mae_db": 0.4268337574286462, "全帯域_40ms_rms_envelope_nrmse": 0.04278421428409011, "全帯域_40ms_envelope_correlation": 0.9986735085578647, "全帯域_40ms_modulation_mae_db": 0.9143284837093336, "300–1000 Hz_10ms_log_rms_mae_db": 0.8690490384983248, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07973197792078908, "300–1000 Hz_10ms_envelope_correlation": 0.9954934351991443, "300–1000 Hz_10ms_modulation_mae_db": 0.5717109910908545, "300–1000 Hz_40ms_log_rms_mae_db": 0.5623667696802233, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04407658760172566, "300–1000 Hz_40ms_envelope_correlation": 0.998546194930931, "300–1000 Hz_40ms_modulation_mae_db": 0.5645491933436181, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9954679833265027, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12293455183590193, "1000–3000 Hz_10ms_envelope_correlation": 0.9918207861622292, "1000–3000 Hz_10ms_modulation_mae_db": 1.0762074784861364, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6663366982058927, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08016377653947993, "1000–3000 Hz_40ms_envelope_correlation": 0.9970936120171673, "1000–3000 Hz_40ms_modulation_mae_db": 1.3740483348265284, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4931787252252933, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14319001419957536, "3000–6000 Hz_10ms_envelope_correlation": 0.9853960869676663, "3000–6000 Hz_10ms_modulation_mae_db": 0.11447130364306678, "3000–6000 Hz_40ms_log_rms_mae_db": 0.869368381887061, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08678504744977923, "3000–6000 Hz_40ms_envelope_correlation": 0.9942913509340602, "3000–6000 Hz_40ms_modulation_mae_db": 0.11121209043902024, "mr_stft_db": 5.098869653152496, "band_mae_db": 1.6429025901027623, "rms_gain_error_db": -0.10119297865894113, "output_peak": 0.634975219247882}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7187196212295993, "全帯域_10ms_rms_envelope_nrmse": 0.0741678916706126, "全帯域_10ms_envelope_correlation": 0.9959858651055581, "全帯域_10ms_modulation_mae_db": 0.5463457144023318, "全帯域_40ms_log_rms_mae_db": 0.4014365842486739, "全帯域_40ms_rms_envelope_nrmse": 0.04318678676552308, "全帯域_40ms_envelope_correlation": 0.9985733421188813, "全帯域_40ms_modulation_mae_db": 0.8374273615268965, "300–1000 Hz_10ms_log_rms_mae_db": 0.8292422083894412, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07792905481063941, "300–1000 Hz_10ms_envelope_correlation": 0.9957315303065924, "300–1000 Hz_10ms_modulation_mae_db": 0.13839487594166636, "300–1000 Hz_40ms_log_rms_mae_db": 0.5765278092872517, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.045112059000176, "300–1000 Hz_40ms_envelope_correlation": 0.9984928634813781, "300–1000 Hz_40ms_modulation_mae_db": 0.5288747678387592, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9597791262286257, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11774794764449008, "1000–3000 Hz_10ms_envelope_correlation": 0.9923838513596042, "1000–3000 Hz_10ms_modulation_mae_db": 0.9927281229066084, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5841306676170023, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07909207864124639, "1000–3000 Hz_40ms_envelope_correlation": 0.9969571353847526, "1000–3000 Hz_40ms_modulation_mae_db": 1.434622834336765, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4792574315103884, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14341917308032173, "3000–6000 Hz_10ms_envelope_correlation": 0.9864467132201108, "3000–6000 Hz_10ms_modulation_mae_db": 0.7971901909373337, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8873370647389148, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09014030732349466, "3000–6000 Hz_40ms_envelope_correlation": 0.9953529479282933, "3000–6000 Hz_40ms_modulation_mae_db": 0.8590990517567555, "mr_stft_db": 5.090516832074609, "band_mae_db": 1.696514979955673, "rms_gain_error_db": -0.04704750686222517, "output_peak": 0.6386636733444365}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7696451548179968, "全帯域_10ms_rms_envelope_nrmse": 0.07184588905866053, "全帯域_10ms_envelope_correlation": 0.9962338995288422, "全帯域_10ms_modulation_mae_db": 0.343616180703124, "全帯域_40ms_log_rms_mae_db": 0.45733073165436183, "全帯域_40ms_rms_envelope_nrmse": 0.04326171800164286, "全帯域_40ms_envelope_correlation": 0.9985648118382662, "全帯域_40ms_modulation_mae_db": 0.5736425108994592, "300–1000 Hz_10ms_log_rms_mae_db": 0.8748704767297779, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08790249738558029, "300–1000 Hz_10ms_envelope_correlation": 0.9945803800820566, "300–1000 Hz_10ms_modulation_mae_db": 0.161923770132177, "300–1000 Hz_40ms_log_rms_mae_db": 0.5902395627490107, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.058282484415302066, "300–1000 Hz_40ms_envelope_correlation": 0.9974885639255763, "300–1000 Hz_40ms_modulation_mae_db": 0.31457726032895644, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9871637798302754, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11828314220081193, "1000–3000 Hz_10ms_envelope_correlation": 0.9923377867634474, "1000–3000 Hz_10ms_modulation_mae_db": 1.541425230945247, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6585770289696107, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07831667391159657, "1000–3000 Hz_40ms_envelope_correlation": 0.9970648817839601, "1000–3000 Hz_40ms_modulation_mae_db": 1.7992687398313818, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4737200286179164, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14575454159806317, "3000–6000 Hz_10ms_envelope_correlation": 0.9850787675328274, "3000–6000 Hz_10ms_modulation_mae_db": 0.3203115437074568, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8552285173301986, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07805112209026577, "3000–6000 Hz_40ms_envelope_correlation": 0.9954321998335038, "3000–6000 Hz_40ms_modulation_mae_db": 0.30751592822438556, "mr_stft_db": 5.105347180473479, "band_mae_db": 1.873207368055473, "rms_gain_error_db": -0.04224052823020002, "output_peak": 0.7004376269221061}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7220234727015312, "全帯域_10ms_rms_envelope_nrmse": 0.07392588083073526, "全帯域_10ms_envelope_correlation": 0.9960495176331577, "全帯域_10ms_modulation_mae_db": 0.6833627411059421, "全帯域_40ms_log_rms_mae_db": 0.445899924195928, "全帯域_40ms_rms_envelope_nrmse": 0.04421254499977467, "全帯域_40ms_envelope_correlation": 0.9985504939497951, "全帯域_40ms_modulation_mae_db": 0.7750423383245786, "300–1000 Hz_10ms_log_rms_mae_db": 0.9401417563033504, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0858686977033125, "300–1000 Hz_10ms_envelope_correlation": 0.9948008874742884, "300–1000 Hz_10ms_modulation_mae_db": 0.8088960126693658, "300–1000 Hz_40ms_log_rms_mae_db": 0.6623729389371176, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.055876725440973996, "300–1000 Hz_40ms_envelope_correlation": 0.9977053979351581, "300–1000 Hz_40ms_modulation_mae_db": 1.069081251920584, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9812026909743794, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11853228379211721, "1000–3000 Hz_10ms_envelope_correlation": 0.9916997104612845, "1000–3000 Hz_10ms_modulation_mae_db": 0.6296545915046866, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6062221010780199, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06123334452105219, "1000–3000 Hz_40ms_envelope_correlation": 0.9978057434027796, "1000–3000 Hz_40ms_modulation_mae_db": 0.41156865501383955, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3654815476255682, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14962477990928602, "3000–6000 Hz_10ms_envelope_correlation": 0.9840241391312958, "3000–6000 Hz_10ms_modulation_mae_db": 0.15725247452828808, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8420780688283158, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09788787045893939, "3000–6000 Hz_40ms_envelope_correlation": 0.9926800932009855, "3000–6000 Hz_40ms_modulation_mae_db": 0.22171525343798537, "mr_stft_db": 5.100623900379539, "band_mae_db": 1.6835117803551203, "rms_gain_error_db": -0.0820807454164852, "output_peak": 0.6185852330308689}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6520058184699308, "全帯域_10ms_rms_envelope_nrmse": 0.062460411218700405, "全帯域_10ms_envelope_correlation": 0.9972028489796528, "全帯域_10ms_modulation_mae_db": 0.7280984246991679, "全帯域_40ms_log_rms_mae_db": 0.3381487672457596, "全帯域_40ms_rms_envelope_nrmse": 0.03260143342587604, "全帯域_40ms_envelope_correlation": 0.9992485919547625, "全帯域_40ms_modulation_mae_db": 0.7114035577587082, "300–1000 Hz_10ms_log_rms_mae_db": 0.8676419503224365, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06409163434904074, "300–1000 Hz_10ms_envelope_correlation": 0.9971201931995861, "300–1000 Hz_10ms_modulation_mae_db": 0.6640673061633212, "300–1000 Hz_40ms_log_rms_mae_db": 0.5708299762906378, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.036019467467541866, "300–1000 Hz_40ms_envelope_correlation": 0.9990718957434156, "300–1000 Hz_40ms_modulation_mae_db": 0.6199333530199872, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9566696786134852, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10623601695871508, "1000–3000 Hz_10ms_envelope_correlation": 0.9934383508236888, "1000–3000 Hz_10ms_modulation_mae_db": 0.8626413988791111, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6113527071511228, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05940312484052707, "1000–3000 Hz_40ms_envelope_correlation": 0.9980466439277875, "1000–3000 Hz_40ms_modulation_mae_db": 1.0505824895489768, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4823313451732103, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16179646382590274, "3000–6000 Hz_10ms_envelope_correlation": 0.9819167305672852, "3000–6000 Hz_10ms_modulation_mae_db": 0.7788185829561319, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8647495339422598, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09819737214545972, "3000–6000 Hz_40ms_envelope_correlation": 0.9936989790808275, "3000–6000 Hz_40ms_modulation_mae_db": 0.8713930597478292, "mr_stft_db": 5.073223592126057, "band_mae_db": 1.7438658795480821, "rms_gain_error_db": -0.08479069320597254, "output_peak": 0.673815489460833}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7545834087584472, "全帯域_10ms_rms_envelope_nrmse": 0.07036572714059536, "全帯域_10ms_envelope_correlation": 0.9964378520411733, "全帯域_10ms_modulation_mae_db": 0.10439683010179467, "全帯域_40ms_log_rms_mae_db": 0.4397835756986645, "全帯域_40ms_rms_envelope_nrmse": 0.04068856433640584, "全帯域_40ms_envelope_correlation": 0.9987970421837455, "全帯域_40ms_modulation_mae_db": 0.17085399129887602, "300–1000 Hz_10ms_log_rms_mae_db": 0.9221307591953574, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07274402172973721, "300–1000 Hz_10ms_envelope_correlation": 0.9962672551261688, "300–1000 Hz_10ms_modulation_mae_db": 0.16087918308122576, "300–1000 Hz_40ms_log_rms_mae_db": 0.5943515765373545, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04161156198739886, "300–1000 Hz_40ms_envelope_correlation": 0.9987102114761778, "300–1000 Hz_40ms_modulation_mae_db": 0.3132810047438553, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9647306612879178, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13119507395941202, "1000–3000 Hz_10ms_envelope_correlation": 0.9910411101643135, "1000–3000 Hz_10ms_modulation_mae_db": 0.5556093792142687, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6106218122816307, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08679411778353457, "1000–3000 Hz_40ms_envelope_correlation": 0.9969874918453631, "1000–3000 Hz_40ms_modulation_mae_db": 0.45170935407986357, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5195975144377962, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16762487304061216, "3000–6000 Hz_10ms_envelope_correlation": 0.9826189031589665, "3000–6000 Hz_10ms_modulation_mae_db": 1.3787216075117865, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9310411393053027, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1062199303468851, "3000–6000 Hz_40ms_envelope_correlation": 0.9951246123261364, "3000–6000 Hz_40ms_modulation_mae_db": 1.3305256975779967, "mr_stft_db": 5.101799852492275, "band_mae_db": 1.6553631970446225, "rms_gain_error_db": -0.08233251718525168, "output_peak": 0.7101368140264904}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 97768, "output_samples": 97768, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.5566741215822555, "spectral_convergence": 0.18022725671937329, "spectral_convergence_status": "ok", "amplitude_floor": 1.7496801023785185e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.097724005105989, "spectral_convergence": 0.20117415827986487, "spectral_convergence_status": "ok", "amplitude_floor": 1.6784480256181157e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.660927837766118, "spectral_convergence": 0.20462006408112388, "spectral_convergence_status": "ok", "amplitude_floor": 1.5558256811894896e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.01876573628214e-07, "output_power": 5.074733225588817e-06, "delta_db": 10.048162923434031, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0014282687361772438, "output_power": 0.0013896951724873682, "delta_db": -0.11890381020627097, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.002893798215697645, "output_power": 0.0029260064146663088, "delta_db": 0.04807029369846748, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0011796153749935407, "output_power": 0.0010576986865262759, "delta_db": -0.4737845943214785, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.624359886340766e-05, "output_power": 1.5036433929910338e-05, "delta_db": -0.33537405685353455, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.5152799044228294e-05, "output_power": 2.452491767119016e-05, "delta_db": -0.10978762923202198, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2062863831028078e-05, "output_power": 1.096046108036498e-05, "delta_db": -0.416216011509229, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.6500427598935765, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.10014777458733666, "pitch": null, "output_rms_dbfs": -22.65280410451924, "output_peak": 0.6497057101163096, "reference_rms_dbfs": -22.552656329931906, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.105108654818121}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 97768, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0003314896640837282, "log_rms_mae_db": 0.7214466977415974, "rms_envelope_nrmse": 0.06956702948179742, "envelope_correlation": 0.996535661500091, "rms_gain_error_db": -0.10014771424733798, "reference_mean_power": 0.005567487969490699, "output_mean_power": 0.00544057142063216}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 4.765376195527077e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0029556164553593994, "output_power": 0.0028528023520679314, "reference_active": true, "delta_db": -0.15376391925877286}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00036953756834478597, "output_power": 0.00032974166742921247, "reference_active": true, "delta_db": -0.49484766973399597}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 0.00011202447087610656, "output_power": 6.457749777696525e-05, "reference_active": true, "delta_db": -2.3923168815339038}], "active_band_count": 3, "active_band_mae_db": 1.013642823508891}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.0003156446105274747, "log_rms_mae_db": 0.42987543316445836, "rms_envelope_nrmse": 0.03766123913627222, "envelope_correlation": 0.999000646863232, "rms_gain_error_db": -0.10014772551999938, "reference_mean_power": 0.005608881493358216, "output_mean_power": 0.00548102132281068}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 4.372836941600517e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0027064910584040595, "output_power": 0.0025923289328644208, "reference_active": true, "delta_db": -0.187164896020785}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00018117557189089236, "output_power": 0.00015818219667317613, "reference_active": true, "delta_db": -0.589420385812319}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.701057462757455e-06, "output_power": 5.237021749803838e-06, "reference_active": true, "delta_db": -2.677346995035776}], "active_band_count": 3, "active_band_mae_db": 1.1513107589562932}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0002506339510784735, "log_rms_mae_db": 0.8398380477193221, "rms_envelope_nrmse": 0.07024973072846688, "envelope_correlation": 0.9965068961977003, "rms_gain_error_db": -0.027863750052239143, "reference_mean_power": 0.0041004048785232925, "output_mean_power": 0.004074181445085191}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 3.4168869077487306e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0021098794264420863, "output_power": 0.0020942539053648086, "reference_active": true, "delta_db": -0.032283033352074865}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00027960522877585594, "output_power": 0.000264222001096183, "reference_active": true, "delta_db": -0.2457631131725546}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.021566680060571e-05, "output_power": 5.660725881518074e-05, "reference_active": true, "delta_db": -2.0240983857041495}], "active_band_count": 3, "active_band_mae_db": 0.7673815107429264}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00024415679244648423, "log_rms_mae_db": 0.5492250413164246, "rms_envelope_nrmse": 0.03320638148250582, "envelope_correlation": 0.999179774838046, "rms_gain_error_db": -0.0278637545221176, "reference_mean_power": 0.004130891145990147, "output_mean_power": 0.004104472738652815}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 3.1086003931775263e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0019093077513610485, "output_power": 0.0018827242509195303, "reference_active": true, "delta_db": -0.060892190139452414}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00014045819894614964, "output_power": 0.00012969033058779576, "reference_active": true, "delta_db": -0.3463949799128424}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.796438388581124e-06, "output_power": 4.617870131581247e-06, "reference_active": true, "delta_db": -2.274545361402252}], "active_band_count": 3, "active_band_mae_db": 0.8939441771515155}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.00019827664142914133, "log_rms_mae_db": 0.9332696380475295, "rms_envelope_nrmse": 0.10548552296376905, "envelope_correlation": 0.994081512863601, "rms_gain_error_db": -0.3349998755423417, "reference_mean_power": 0.0008784725402011367, "output_mean_power": 0.0008132577358581749}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.1250771844458692e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007015897284632315, "output_power": 0.000642755555554574, "reference_active": true, "delta_db": -0.3803738308458929}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.449911857407873e-05, "output_power": 6.701553293682397e-05, "reference_active": true, "delta_db": -1.0067670312757864}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6127775103534605e-05, "output_power": 1.538280853514658e-05, "reference_active": true, "delta_db": -2.3006679463893835}], "active_band_count": 3, "active_band_mae_db": 1.229269602837021}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00017853730341036803, "log_rms_mae_db": 0.6348444849989816, "rms_envelope_nrmse": 0.06570074653069907, "envelope_correlation": 0.9981960762926388, "rms_gain_error_db": -0.3349998776655303, "reference_mean_power": 0.0008850039267330396, "output_mean_power": 0.0008193042541362163}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.078630941288297e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006783838060260436, "output_power": 0.0006169754233144433, "reference_active": true, "delta_db": -0.4120760752284605}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3933140159486266e-05, "output_power": 2.6771159820485234e-05, "reference_active": true, "delta_db": -1.0295686419205623}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.944075796645493e-06, "output_power": 8.697930173073412e-07, "reference_active": true, "delta_db": -3.4929727659105136}], "active_band_count": 3, "active_band_mae_db": 1.644872494353179}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 2.2340226127796077e-05, "log_rms_mae_db": 1.4787860370609027, "rms_envelope_nrmse": 0.16442581071628837, "envelope_correlation": 0.9814063990466501, "rms_gain_error_db": -0.39439842868841324, "reference_mean_power": 1.7310253593278313e-05, "output_mean_power": 1.580751444763617e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.3633964732936534e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.958677073783288e-06, "output_power": 7.2053288373762696e-06, "reference_active": true, "delta_db": -0.43187077434180604}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3383871013961803e-06, "output_power": 9.220217196876754e-07, "reference_active": true, "delta_db": -1.618405908232894}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.535118084866941e-07, "output_power": 3.879684300863904e-07, "reference_active": true, "delta_db": -0.6779221219419068}], "active_band_count": 3, "active_band_mae_db": 0.9093996015055357}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 1.6591025056474894e-05, "log_rms_mae_db": 0.8282375343440372, "rms_envelope_nrmse": 0.08957953040369043, "envelope_correlation": 0.9951883084720579, "rms_gain_error_db": -0.39439853892307075, "reference_mean_power": 1.743895029874837e-05, "output_mean_power": 1.592503832000602e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.2324948655964946e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.384237970170313e-06, "output_power": 6.5630132318169115e-06, "reference_active": true, "delta_db": -0.5120240430637818}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2197399674362034e-07, "output_power": 2.914697449214004e-07, "reference_active": true, "delta_db": -1.6069220841203558}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.206308596249792e-08, "output_power": 2.6866199685894228e-08, "reference_active": true, "delta_db": -0.7679908102437555}], "active_band_count": 3, "active_band_mae_db": 0.9623123124759644}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8290773857728988, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "e4d50ef914418d16ec12e855d2ee7d4bff8fa81562a122a27af546bf76a3223e", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9926769997228085, "standard_deviation": 0.0012458681811053018, "minimum": 0.9910411101643135, "maximum": 0.9946128891842998, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.963155433940629, "standard_deviation": 0.024510718764326127, "minimum": 0.9269599132163158, "maximum": 0.9954679833265027, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.9678659308866742, "standard_deviation": 0.32020600782469205, "minimum": 0.5556093792142687, "maximum": 1.541425230945247, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1146815109507906, "standard_deviation": 0.010988407292620208, "minimum": 0.09703754825110746, "maximum": 0.13119507395941202, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.997626254649242, "standard_deviation": 0.0007077668988019467, "minimum": 0.9969571353847526, "maximum": 0.9988584525394868, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6218346232943829, "standard_deviation": 0.02871269181595005, "minimum": 0.5841306676170023, "maximum": 0.6663366982058927, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.1680908651705821, "standard_deviation": 0.5125008443140076, "minimum": 0.41156865501383955, "maximum": 1.7992687398313818, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.069873567979377, "standard_deviation": 0.01318135313012762, "minimum": 0.04828468106688008, "maximum": 0.08679411778353457, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9831411480092977, "standard_deviation": 0.0026547515487980178, "minimum": 0.9782414444495798, "maximum": 0.9864467132201108, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.4748346064166113, "standard_deviation": 0.046877546448911254, "minimum": 1.3654815476255682, "maximum": 1.5195975144377962, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6857177741262478, "standard_deviation": 0.44860747076678437, "minimum": 0.11447130364306678, "maximum": 1.3787216075117865, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15670249476407677, "standard_deviation": 0.01297428530839575, "minimum": 0.14319001419957536, "maximum": 0.17778430174256465, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9945294409043592, "standard_deviation": 0.0009600452398245283, "minimum": 0.9926800932009855, "maximum": 0.9954321998335038, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8680491298432388, "standard_deviation": 0.03112038890636447, "minimum": 0.8282375343440372, "maximum": 0.9310411393053027, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7342212645367208, "standard_deviation": 0.4631040671605161, "minimum": 0.11121209043902024, "maximum": 1.3305256975779967, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09294921908810597, "standard_deviation": 0.008631785292914867, "minimum": 0.07805112209026577, "maximum": 0.1062199303468851, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.995764663835734, "standard_deviation": 0.0008509579418243107, "minimum": 0.9945803800820566, "maximum": 0.9971201931995861, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8754459347720582, "standard_deviation": 0.03796371482409482, "minimum": 0.8292422083894412, "maximum": 0.9401417563033504, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4887549235220405, "standard_deviation": 0.28703549352375224, "minimum": 0.13839487594166636, "maximum": 0.8088960126693658, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07714156568591471, "standard_deviation": 0.007915609305919453, "minimum": 0.06409163434904074, "maximum": 0.08790249738558029, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9984544107110965, "standard_deviation": 0.0005948414902936627, "minimum": 0.9974885639255763, "maximum": 0.999179774838046, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5838052321632239, "standard_deviation": 0.034997613392473315, "minimum": 0.5492250413164246, "maximum": 0.6623729389371176, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6364067572916917, "standard_deviation": 0.26758109176874445, "minimum": 0.3132810047438553, "maximum": 1.069081251920584, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04498055648011708, "standard_deviation": 0.00867875246494942, "minimum": 0.03320638148250582, "maximum": 0.058282484415302066, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.7170113876075095, "standard_deviation": 0.0809457705488293, "minimum": 1.6429025901027623, "maximum": 1.873207368055473, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.096444193155862, "standard_deviation": 0.010561699907466254, "minimum": 5.073223592126057, "maximum": 5.105347180473479, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.6633491643007483, "standard_deviation": 0.0328890653151925, "minimum": 0.6185852330308689, "maximum": 0.7101368140264904, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.0758812587144052, "standard_deviation": 0.022126664858373148, "minimum": -0.10119297865894113, "maximum": -0.04224052823020002, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9963164429148218, "standard_deviation": 0.00041224793681526325, "minimum": 0.9959858651055581, "maximum": 0.9972028489796528, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7225015675605738, "standard_deviation": 0.03432423830820362, "minimum": 0.6520058184699308, "maximum": 0.7696451548179968, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.6208479601341055, "standard_deviation": 0.28494717727158797, "minimum": 0.10439683010179467, "maximum": 1.013642823508891, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07127664086924607, "standard_deviation": 0.004001716224888648, "minimum": 0.062460411218700405, "maximum": 0.07454317996511911, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9987911953577253, "standard_deviation": 0.0002508541016964887, "minimum": 0.9985504939497951, "maximum": 0.9992485919547625, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4226390112680447, "standard_deviation": 0.037917011188182824, "minimum": 0.3381487672457596, "maximum": 0.45733073165436183, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7493093329826233, "standard_deviation": 0.28698567235336186, "minimum": 0.17085399129887602, "maximum": 1.1513107589562932, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.04030108243464646, "standard_deviation": 0.003967741675070801, "minimum": 0.03260143342587604, "maximum": 0.04421254499977467, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_falset10_BASIC5000_1205", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 2.7450764179229736, "predicted_mos": 2.7450764179229736, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 97768, "input_sample_rate": 24000, "input_seconds": 4.073666666666667, "input_float32_sha256": "77a70fd644f6aef6a1cf2cf46f0696946101ba4bd4997bcc145c80e05ba6b827", "internal_samples": 65179, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.77870270004496}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7166218829079514, "全帯域_10ms_rms_envelope_nrmse": 0.06659532769275638, "全帯域_10ms_envelope_correlation": 0.9967659722592329, "全帯域_10ms_modulation_mae_db": 1.1513641163757586, "全帯域_40ms_log_rms_mae_db": 0.38829432334784714, "全帯域_40ms_rms_envelope_nrmse": 0.03847993239453796, "全帯域_40ms_envelope_correlation": 0.9988621858203995, "全帯域_40ms_modulation_mae_db": 1.27001053549917, "300–1000 Hz_10ms_log_rms_mae_db": 0.900927477181492, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06805375778184357, "300–1000 Hz_10ms_envelope_correlation": 0.9967190123793892, "300–1000 Hz_10ms_modulation_mae_db": 0.8926739621324744, "300–1000 Hz_40ms_log_rms_mae_db": 0.5724125651821653, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04053686104671744, "300–1000 Hz_40ms_envelope_correlation": 0.998766909950023, "300–1000 Hz_40ms_modulation_mae_db": 0.9484533817155573, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9736034359846577, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11536342814569951, "1000–3000 Hz_10ms_envelope_correlation": 0.9921324062992595, "1000–3000 Hz_10ms_modulation_mae_db": 1.1660548768578636, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5964063979138713, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05767830606040418, "1000–3000 Hz_40ms_envelope_correlation": 0.9979724711571099, "1000–3000 Hz_40ms_modulation_mae_db": 1.5081960307343907, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7645533714102024, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17052615301716403, "3000–6000 Hz_10ms_envelope_correlation": 0.9799306976192607, "3000–6000 Hz_10ms_modulation_mae_db": 0.414040799803218, "3000–6000 Hz_40ms_log_rms_mae_db": 1.123379009416406, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10350977102768413, "3000–6000 Hz_40ms_envelope_correlation": 0.9931231639186632, "3000–6000 Hz_40ms_modulation_mae_db": 0.44656237830279616, "mr_stft_db": 5.197719793380531, "band_mae_db": 1.4167518592745914, "rms_gain_error_db": -0.03259324509383696, "output_peak": 0.662920587937375}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7051870065668917, "全帯域_10ms_rms_envelope_nrmse": 0.07799908587641022, "全帯域_10ms_envelope_correlation": 0.9955869604283647, "全帯域_10ms_modulation_mae_db": 0.7128926401806615, "全帯域_40ms_log_rms_mae_db": 0.3913089447660508, "全帯域_40ms_rms_envelope_nrmse": 0.04260052947673084, "全帯域_40ms_envelope_correlation": 0.998660273000472, "全帯域_40ms_modulation_mae_db": 0.6240614801719402, "300–1000 Hz_10ms_log_rms_mae_db": 0.9012267107746094, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08934517501663175, "300–1000 Hz_10ms_envelope_correlation": 0.9943526655409606, "300–1000 Hz_10ms_modulation_mae_db": 0.5164599279004464, "300–1000 Hz_40ms_log_rms_mae_db": 0.6028936007989769, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.051454904876428495, "300–1000 Hz_40ms_envelope_correlation": 0.9980583837351373, "300–1000 Hz_40ms_modulation_mae_db": 0.409666583591048, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9763165407366362, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10085246671844625, "1000–3000 Hz_10ms_envelope_correlation": 0.9940135644472553, "1000–3000 Hz_10ms_modulation_mae_db": 1.170210378861892, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5792747593465174, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04990235711945015, "1000–3000 Hz_40ms_envelope_correlation": 0.9985526120095005, "1000–3000 Hz_40ms_modulation_mae_db": 1.8009913012668104, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7041274201670307, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15175033258671763, "3000–6000 Hz_10ms_envelope_correlation": 0.9836713331894688, "3000–6000 Hz_10ms_modulation_mae_db": 0.2712826592180542, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0420367214305557, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08204081907261312, "3000–6000 Hz_40ms_envelope_correlation": 0.9948480862120023, "3000–6000 Hz_40ms_modulation_mae_db": 0.4467348059721292, "mr_stft_db": 5.191297210477768, "band_mae_db": 1.544637152143317, "rms_gain_error_db": -0.08581601148676059, "output_peak": 0.65482640240471}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7141807432375397, "全帯域_10ms_rms_envelope_nrmse": 0.06105001813130224, "全帯域_10ms_envelope_correlation": 0.9972857746768639, "全帯域_10ms_modulation_mae_db": 0.2805194547075868, "全帯域_40ms_log_rms_mae_db": 0.393158595814777, "全帯域_40ms_rms_envelope_nrmse": 0.03572490845970822, "全帯域_40ms_envelope_correlation": 0.9990308459731604, "全帯域_40ms_modulation_mae_db": 0.34376095205928653, "300–1000 Hz_10ms_log_rms_mae_db": 0.8266234768213024, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06859723732731146, "300–1000 Hz_10ms_envelope_correlation": 0.9966634680053191, "300–1000 Hz_10ms_modulation_mae_db": 0.3374969715398703, "300–1000 Hz_40ms_log_rms_mae_db": 0.5337420796284871, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04033910804143092, "300–1000 Hz_40ms_envelope_correlation": 0.9987806032200524, "300–1000 Hz_40ms_modulation_mae_db": 0.5212427884261023, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9755026791052767, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08924563478641204, "1000–3000 Hz_10ms_envelope_correlation": 0.9953413624492795, "1000–3000 Hz_10ms_modulation_mae_db": 0.458319858999038, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6283692768639297, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05631839258022708, "1000–3000 Hz_40ms_envelope_correlation": 0.9981518529869063, "1000–3000 Hz_40ms_modulation_mae_db": 0.25478555917122453, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7139070717483145, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1530055799504701, "3000–6000 Hz_10ms_envelope_correlation": 0.9833205712527683, "3000–6000 Hz_10ms_modulation_mae_db": 0.8015440048206944, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0406115323401897, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08018479903398146, "3000–6000 Hz_40ms_envelope_correlation": 0.995233933018194, "3000–6000 Hz_40ms_modulation_mae_db": 0.7598512355409656, "mr_stft_db": 5.195115505124469, "band_mae_db": 1.5306089672116616, "rms_gain_error_db": -0.04371767129485485, "output_peak": 0.6173369008218761}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6958276334356993, "全帯域_10ms_rms_envelope_nrmse": 0.07403093020451199, "全帯域_10ms_envelope_correlation": 0.9960252094205458, "全帯域_10ms_modulation_mae_db": 1.0894899940897314, "全帯域_40ms_log_rms_mae_db": 0.40040945192331834, "全帯域_40ms_rms_envelope_nrmse": 0.048239131323037955, "全帯域_40ms_envelope_correlation": 0.9982556367815089, "全帯域_40ms_modulation_mae_db": 1.0300734511892446, "300–1000 Hz_10ms_log_rms_mae_db": 0.8775952645681252, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08350189782695203, "300–1000 Hz_10ms_envelope_correlation": 0.995057097660219, "300–1000 Hz_10ms_modulation_mae_db": 1.1005173059293758, "300–1000 Hz_40ms_log_rms_mae_db": 0.5522964118948516, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05735295300846959, "300–1000 Hz_40ms_envelope_correlation": 0.997548068838119, "300–1000 Hz_40ms_modulation_mae_db": 1.072088121509677, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0273104322915643, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1199034847704922, "1000–3000 Hz_10ms_envelope_correlation": 0.9916561997914504, "1000–3000 Hz_10ms_modulation_mae_db": 1.3280138151539214, "1000–3000 Hz_40ms_log_rms_mae_db": 0.648441584404053, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07251527656579439, "1000–3000 Hz_40ms_envelope_correlation": 0.9970814522408318, "1000–3000 Hz_40ms_modulation_mae_db": 1.050822370302894, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7371131751606836, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17915376651358067, "3000–6000 Hz_10ms_envelope_correlation": 0.9774352364315213, "3000–6000 Hz_10ms_modulation_mae_db": 1.0862236302932509, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0444097043277742, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10264871861319994, "3000–6000 Hz_40ms_envelope_correlation": 0.9928311532756157, "3000–6000 Hz_40ms_modulation_mae_db": 1.013091983654789, "mr_stft_db": 5.1817579299887555, "band_mae_db": 1.534505480484921, "rms_gain_error_db": -0.07944360718929316, "output_peak": 0.6305536600851995}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7413990938214792, "全帯域_10ms_rms_envelope_nrmse": 0.07972784215779381, "全帯域_10ms_envelope_correlation": 0.9953613670077953, "全帯域_10ms_modulation_mae_db": 0.7700439347019025, "全帯域_40ms_log_rms_mae_db": 0.43110231931852905, "全帯域_40ms_rms_envelope_nrmse": 0.04943116406765881, "全帯域_40ms_envelope_correlation": 0.9981128451558666, "全帯域_40ms_modulation_mae_db": 0.7162833076478649, "300–1000 Hz_10ms_log_rms_mae_db": 0.9112948613491084, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09035800054845354, "300–1000 Hz_10ms_envelope_correlation": 0.9942233431157633, "300–1000 Hz_10ms_modulation_mae_db": 0.8759151578635914, "300–1000 Hz_40ms_log_rms_mae_db": 0.6163607591870763, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.060703213411132925, "300–1000 Hz_40ms_envelope_correlation": 0.997236424261438, "300–1000 Hz_40ms_modulation_mae_db": 0.8011873663071901, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9913767572053545, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09520158371210667, "1000–3000 Hz_10ms_envelope_correlation": 0.9946367457375429, "1000–3000 Hz_10ms_modulation_mae_db": 0.5579524363802011, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6187795308069922, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0480776526535497, "1000–3000 Hz_40ms_envelope_correlation": 0.998609993145763, "1000–3000 Hz_40ms_modulation_mae_db": 0.41348611660255147, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7024300694744028, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16606469484175196, "3000–6000 Hz_10ms_envelope_correlation": 0.9803083747659656, "3000–6000 Hz_10ms_modulation_mae_db": 0.35501747902312647, "3000–6000 Hz_40ms_log_rms_mae_db": 1.013609227729809, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08375561396886425, "3000–6000 Hz_40ms_envelope_correlation": 0.9948220265578791, "3000–6000 Hz_40ms_modulation_mae_db": 0.2906213527962997, "mr_stft_db": 5.187997012040433, "band_mae_db": 1.5133024574585452, "rms_gain_error_db": 0.0013783153592227548, "output_peak": 0.6497247105823128}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.724397077496606, "全帯域_10ms_rms_envelope_nrmse": 0.06180177977613192, "全帯域_10ms_envelope_correlation": 0.9972167538813697, "全帯域_10ms_modulation_mae_db": 0.4794890648626424, "全帯域_40ms_log_rms_mae_db": 0.4279344947043237, "全帯域_40ms_rms_envelope_nrmse": 0.03718759471374069, "全帯域_40ms_envelope_correlation": 0.9989472510430237, "全帯域_40ms_modulation_mae_db": 0.6021045909632702, "300–1000 Hz_10ms_log_rms_mae_db": 0.8342738558809737, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07156732856731161, "300–1000 Hz_10ms_envelope_correlation": 0.9963805348242846, "300–1000 Hz_10ms_modulation_mae_db": 0.4951032716373101, "300–1000 Hz_40ms_log_rms_mae_db": 0.5318346417159768, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.045388745015765404, "300–1000 Hz_40ms_envelope_correlation": 0.9984801776309373, "300–1000 Hz_40ms_modulation_mae_db": 0.749804785891517, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9572462450704124, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07596361452405352, "1000–3000 Hz_10ms_envelope_correlation": 0.9965909995864498, "1000–3000 Hz_10ms_modulation_mae_db": 0.22737539801444617, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5948178948298068, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04563987832315719, "1000–3000 Hz_40ms_envelope_correlation": 0.9987362436352288, "1000–3000 Hz_40ms_modulation_mae_db": 0.2863722154876755, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6697705108489826, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15527879516880919, "3000–6000 Hz_10ms_envelope_correlation": 0.982928795760648, "3000–6000 Hz_10ms_modulation_mae_db": 0.10665151778786773, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0193574199549886, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09746902655306615, "3000–6000 Hz_40ms_envelope_correlation": 0.9927334456960003, "3000–6000 Hz_40ms_modulation_mae_db": 0.03435068008241871, "mr_stft_db": 5.1782759230101565, "band_mae_db": 1.4891693928696061, "rms_gain_error_db": -0.037624327012612195, "output_peak": 0.6480864879050523}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7582707346864649, "全帯域_10ms_rms_envelope_nrmse": 0.07683670433354224, "全帯域_10ms_envelope_correlation": 0.9957012441265866, "全帯域_10ms_modulation_mae_db": 0.7976476786298906, "全帯域_40ms_log_rms_mae_db": 0.44543004124587504, "全帯域_40ms_rms_envelope_nrmse": 0.045235508065793024, "全帯域_40ms_envelope_correlation": 0.998447907452499, "全帯域_40ms_modulation_mae_db": 1.0353892915029563, "300–1000 Hz_10ms_log_rms_mae_db": 0.8908229234336446, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08709645464462092, "300–1000 Hz_10ms_envelope_correlation": 0.9946164142791294, "300–1000 Hz_10ms_modulation_mae_db": 0.6031827020918691, "300–1000 Hz_40ms_log_rms_mae_db": 0.5851718467094417, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04956695373620883, "300–1000 Hz_40ms_envelope_correlation": 0.9981573628026145, "300–1000 Hz_40ms_modulation_mae_db": 0.8357664745597336, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0548346521890355, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09437040051108664, "1000–3000 Hz_10ms_envelope_correlation": 0.9948271698699731, "1000–3000 Hz_10ms_modulation_mae_db": 0.6602239580551236, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6690103355094157, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.052739738333229966, "1000–3000 Hz_40ms_envelope_correlation": 0.9984578210120294, "1000–3000 Hz_40ms_modulation_mae_db": 0.4611367528514114, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7191745031780057, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17579463218343228, "3000–6000 Hz_10ms_envelope_correlation": 0.9778725596217144, "3000–6000 Hz_10ms_modulation_mae_db": 0.3443214625274745, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0474136101860292, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10283994130129766, "3000–6000 Hz_40ms_envelope_correlation": 0.9919610042825444, "3000–6000 Hz_40ms_modulation_mae_db": 0.4509240140189797, "mr_stft_db": 5.1835756420547385, "band_mae_db": 1.592788255515775, "rms_gain_error_db": -0.05970238069033905, "output_peak": 0.647031150500004}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.680220752742915, "全帯域_10ms_rms_envelope_nrmse": 0.072745228008812, "全帯域_10ms_envelope_correlation": 0.996192369744747, "全帯域_10ms_modulation_mae_db": 0.49356519998520754, "全帯域_40ms_log_rms_mae_db": 0.3895210145238238, "全帯域_40ms_rms_envelope_nrmse": 0.042288658570175566, "全帯域_40ms_envelope_correlation": 0.9987061211620869, "全帯域_40ms_modulation_mae_db": 0.4554218038235371, "300–1000 Hz_10ms_log_rms_mae_db": 0.8560038522073027, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08330910516282446, "300–1000 Hz_10ms_envelope_correlation": 0.9951551080984449, "300–1000 Hz_10ms_modulation_mae_db": 0.6559000137157999, "300–1000 Hz_40ms_log_rms_mae_db": 0.5728968064231952, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05240074445082625, "300–1000 Hz_40ms_envelope_correlation": 0.9980569050195232, "300–1000 Hz_40ms_modulation_mae_db": 0.7344827013859064, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9867469082566831, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1128107326476475, "1000–3000 Hz_10ms_envelope_correlation": 0.9925038127832307, "1000–3000 Hz_10ms_modulation_mae_db": 0.8886786683242088, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6010361327557778, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.060295092188963825, "1000–3000 Hz_40ms_envelope_correlation": 0.997884570779631, "1000–3000 Hz_40ms_modulation_mae_db": 0.7456000500759146, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6959416822957158, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15505370979718527, "3000–6000 Hz_10ms_envelope_correlation": 0.9831328262790793, "3000–6000 Hz_10ms_modulation_mae_db": 0.06606980969784924, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9621241075192758, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08186743117453857, "3000–6000 Hz_40ms_envelope_correlation": 0.9949656515239502, "3000–6000 Hz_40ms_modulation_mae_db": 0.13761253076951208, "mr_stft_db": 5.187215809823992, "band_mae_db": 1.7682451764243243, "rms_gain_error_db": -0.10105206987571036, "output_peak": 0.7131557316506962}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 97768, "output_samples": 97768, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.716883632826408, "spectral_convergence": 0.179578979182409, "spectral_convergence_status": "ok", "amplitude_floor": 1.7496801023785185e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.199318069474117, "spectral_convergence": 0.1897972578031264, "spectral_convergence_status": "ok", "amplitude_floor": 1.6784480256181157e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.676957677841066, "spectral_convergence": 0.19227240779392352, "spectral_convergence_status": "ok", "amplitude_floor": 1.5558256811894896e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.01876573628214e-07, "output_power": 3.9229140821113e-06, "delta_db": 8.930118721622808, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0014282687361772438, "output_power": 0.001446042308401879, "delta_db": 0.05371069871231242, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.002893798215697645, "output_power": 0.0028800435998035485, "delta_db": -0.020691821059290356, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0011796153749935407, "output_power": 0.001133040760820226, "delta_db": -0.1749489070390669, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.624359886340766e-05, "output_power": 1.5032683162142722e-05, "delta_db": -0.3364575191632777, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.5152799044228294e-05, "output_power": 2.3605844335152056e-05, "delta_db": -0.27566782160514414, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2062863831028078e-05, "output_power": 1.2417014205962398e-05, "delta_db": 0.12566752572024317, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.4167518592745914, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.03259324509383696, "pitch": null, "output_rms_dbfs": -22.585249575025745, "output_peak": 0.662920587937375, "reference_rms_dbfs": -22.552656329931906, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.197719793380531}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 97768, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0003314896640837282, "log_rms_mae_db": 0.7166218829079514, "rms_envelope_nrmse": 0.06659532769275638, "envelope_correlation": 0.9967659722592329, "rms_gain_error_db": -0.03259310803857228, "reference_mean_power": 0.005567487969490699, "output_mean_power": 0.005525861256754996}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 4.765376195527077e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0029556164553593994, "output_power": 0.002895899922917288, "reference_active": true, "delta_db": -0.08864526473040879}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00036953756834478597, "output_power": 0.0003249242156059181, "reference_active": true, "delta_db": -0.558765175226308}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 0.00011202447087610656, "output_power": 5.870089330795261e-05, "reference_active": true, "delta_db": -2.806681909170559}], "active_band_count": 3, "active_band_mae_db": 1.1513641163757586}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.0003156446105274747, "log_rms_mae_db": 0.38829432334784714, "rms_envelope_nrmse": 0.03847993239453796, "envelope_correlation": 0.9988621858203995, "rms_gain_error_db": -0.03259311779442384, "reference_mean_power": 0.005608881493358216, "output_mean_power": 0.0055669452791093895}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 4.372836941600517e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0027064910584040595, "output_power": 0.002640240013362486, "reference_active": true, "delta_db": -0.10763188034992949}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00018117557189089236, "output_power": 0.0001547627515098622, "reference_active": true, "delta_db": -0.6843319847599867}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.701057462757455e-06, "output_power": 4.841860836790695e-06, "reference_active": true, "delta_db": -3.018067741387594}], "active_band_count": 3, "active_band_mae_db": 1.27001053549917}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0002506339510784735, "log_rms_mae_db": 0.900927477181492, "rms_envelope_nrmse": 0.06805375778184357, "envelope_correlation": 0.9967190123793892, "rms_gain_error_db": -0.021793353675203075, "reference_mean_power": 0.0041004048785232925, "output_mean_power": 0.004079880156444387}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 3.4168869077487306e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0021098794264420863, "output_power": 0.0020692366873805664, "reference_active": true, "delta_db": -0.08447467515322495}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00027960522877585594, "output_power": 0.00025508842582537116, "reference_active": true, "delta_db": -0.3985453496947493}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.021566680060571e-05, "output_power": 5.4422912182825695e-05, "reference_active": true, "delta_db": -2.195001861549449}], "active_band_count": 3, "active_band_mae_db": 0.8926739621324744}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00024415679244648423, "log_rms_mae_db": 0.5724125651821653, "rms_envelope_nrmse": 0.04053686104671744, "envelope_correlation": 0.998766909950023, "rms_gain_error_db": -0.021793373150719247, "reference_mean_power": 0.004130891145990147, "output_mean_power": 0.004110213805386098}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 3.1086003931775263e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0019093077513610485, "output_power": 0.0018693264868724102, "reference_active": true, "delta_db": -0.0919077607286424}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00014045819894614964, "output_power": 0.00012500717204227057, "reference_active": true, "delta_db": -0.5061216476628169}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.796438388581124e-06, "output_power": 4.646898404283645e-06, "reference_active": true, "delta_db": -2.2473307367552127}], "active_band_count": 3, "active_band_mae_db": 0.9484533817155573}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.00019827664142914133, "log_rms_mae_db": 0.9736034359846577, "rms_envelope_nrmse": 0.11536342814569951, "envelope_correlation": 0.9921324062992595, "rms_gain_error_db": -0.01696103010371895, "reference_mean_power": 0.0008784725402011367, "output_mean_power": 0.0008750484253066832}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.1250771844458692e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007015897284632315, "output_power": 0.0006926462805665895, "reference_active": true, "delta_db": -0.055717157205040856}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.449911857407873e-05, "output_power": 6.614535831216151e-05, "reference_active": true, "delta_db": -1.0635280537825123}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6127775103534605e-05, "output_power": 1.5108122141948313e-05, "reference_active": true, "delta_db": -2.3789194195860377}], "active_band_count": 3, "active_band_mae_db": 1.1660548768578636}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00017853730341036803, "log_rms_mae_db": 0.5964063979138713, "rms_envelope_nrmse": 0.05767830606040418, "envelope_correlation": 0.9979724711571099, "rms_gain_error_db": -0.016961040653095977, "reference_mean_power": 0.0008850039267330396, "output_mean_power": 0.0008815543516243892}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.078630941288297e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006783838060260436, "output_power": 0.0006626308029890484, "reference_active": true, "delta_db": -0.10203851568402028}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3933140159486266e-05, "output_power": 2.5698285337934047e-05, "reference_active": true, "delta_db": -1.207199040004224}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.944075796645493e-06, "output_power": 9.272100702494187e-07, "reference_active": true, "delta_db": -3.2153505365149275}], "active_band_count": 3, "active_band_mae_db": 1.5081960307343907}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 2.2340226127796077e-05, "log_rms_mae_db": 1.7645533714102024, "rms_envelope_nrmse": 0.17052615301716403, "envelope_correlation": 0.9799306976192607, "rms_gain_error_db": -0.39718692332947236, "reference_mean_power": 1.7310253593278313e-05, "output_mean_power": 1.5797368101520315e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.3633964732936534e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.958677073783288e-06, "output_power": 7.003131321922124e-06, "reference_active": true, "delta_db": -0.5554861313785178}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3383871013961803e-06, "output_power": 1.1808995546978409e-06, "reference_active": true, "delta_db": -0.5436878365798968}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.535118084866941e-07, "output_power": 4.388274199951406e-07, "reference_active": true, "delta_db": -0.14294843145123917}], "active_band_count": 3, "active_band_mae_db": 0.414040799803218}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 1.6591025056474894e-05, "log_rms_mae_db": 1.123379009416406, "rms_envelope_nrmse": 0.10350977102768413, "envelope_correlation": 0.9931231639186632, "rms_gain_error_db": -0.3971870966559343, "reference_mean_power": 1.743895029874837e-05, "output_mean_power": 1.5914816307813263e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.2324948655964946e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.384237970170313e-06, "output_power": 6.387825394238102e-06, "reference_active": true, "delta_db": -0.6295264759438902}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2197399674362034e-07, "output_power": 4.1594961692845515e-07, "reference_active": true, "delta_db": -0.062449606386149964}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.206308596249792e-08, "output_power": 3.722000478674497e-08, "reference_active": true, "delta_db": 0.6477110525783485}], "active_band_count": 3, "active_band_mae_db": 0.44656237830279616}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8474920660071702, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "cccac1128c7f5ed4e8cb96ecb7b1146996094ed103b7d3dd69eadea5c60d2a40", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9939627826205552, "standard_deviation": 0.0017242460865642428, "minimum": 0.9916561997914504, "maximum": 0.9965909995864498, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.9928672063549526, "standard_deviation": 0.032252080141836066, "minimum": 0.9572462450704124, "maximum": 1.0548346521890355, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8071036738308368, "standard_deviation": 0.3928066252263672, "minimum": 0.22737539801444617, "maximum": 1.3280138151539214, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10046391822699305, "standard_deviation": 0.014848880799937037, "minimum": 0.07596361452405352, "maximum": 0.1199034847704922, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9981808771208751, "standard_deviation": 0.0005409337476141712, "minimum": 0.9970814522408318, "maximum": 0.9987362436352288, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6170169890537955, "standard_deviation": 0.030284966056574162, "minimum": 0.5792747593465174, "maximum": 0.6690103355094157, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8151737995616091, "standard_deviation": 0.5846669424857103, "minimum": 0.25478555917122453, "maximum": 1.8009913012668104, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05539583672809706, "standard_deviation": 0.00852815856377568, "minimum": 0.04563987832315719, "maximum": 0.07251527656579439, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9810750493650533, "standard_deviation": 0.0025313855432066578, "minimum": 0.9774352364315213, "maximum": 0.9836713331894688, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.7133772255354172, "standard_deviation": 0.028352941987107284, "minimum": 1.6697705108489826, "maximum": 1.7645533714102024, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.43064392039644195, "standard_deviation": 0.34725033957387047, "minimum": 0.06606980969784924, "maximum": 1.0862236302932509, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16332845800738888, "standard_deviation": 0.010948078910168621, "minimum": 0.15175033258671763, "maximum": 0.17915376651358067, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9938148080606062, "standard_deviation": 0.001280200348608004, "minimum": 0.9919610042825444, "maximum": 0.995233933018194, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.0366176666131284, "standard_deviation": 0.044923284916749594, "minimum": 0.9621241075192758, "maximum": 1.123379009416406, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.4474686226422363, "standard_deviation": 0.31821023622160494, "minimum": 0.03435068008241871, "maximum": 1.013091983654789, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09178951509315567, "standard_deviation": 0.010706161747486526, "minimum": 0.08018479903398146, "maximum": 0.10350977102768413, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9953959554879388, "standard_deviation": 0.00103994878079913, "minimum": 0.9942233431157633, "maximum": 0.9967190123793892, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8748460527770698, "standard_deviation": 0.0322801631661072, "minimum": 0.8266234768213024, "maximum": 0.9112948613491084, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6846561641013422, "standard_deviation": 0.2521327641670304, "minimum": 0.3374969715398703, "maximum": 1.1005173059293758, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08022861960949366, "standard_deviation": 0.009347429876976019, "minimum": 0.06805375778184357, "maximum": 0.09035800054845354, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9981356044322306, "standard_deviation": 0.0005476774202484854, "minimum": 0.997236424261438, "maximum": 0.9987806032200524, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5709510889425213, "standard_deviation": 0.030596726458210446, "minimum": 0.5318346417159768, "maximum": 0.6163607591870763, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7590865254233414, "standard_deviation": 0.21408861270917504, "minimum": 0.409666583591048, "maximum": 1.072088121509677, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04971793544837248, "standard_deviation": 0.0073698572187841874, "minimum": 0.04033910804143092, "maximum": 0.060703213411132925, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.5487510926728427, "standard_deviation": 0.10204782178008583, "minimum": 1.4167518592745914, "maximum": 1.7682451764243243, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.1878693532376055, "standard_deviation": 0.0066499287061334315, "minimum": 5.1782759230101565, "maximum": 5.197719793380531, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.6529544539859032, "standard_deviation": 0.0281999021540156, "minimum": 0.6173369008218761, "maximum": 0.7131557316506962, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.05482137466052306, "standard_deviation": 0.03337995297698476, "minimum": -0.10105206987571036, "maximum": 0.0013783153592227548, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9962669564431883, "standard_deviation": 0.0007421633032537334, "minimum": 0.9953613670077953, "maximum": 0.9972857746768639, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7170131156119435, "standard_deviation": 0.02479033460851814, "minimum": 0.680220752742915, "maximum": 0.7582707346864649, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.7218765104416727, "standard_deviation": 0.30081202876004287, "minimum": 0.2805194547075868, "maximum": 1.1513641163757586, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.0713483645226576, "standard_deviation": 0.007304612807813401, "minimum": 0.06105001813130224, "maximum": 0.07972784215779381, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9986278832986272, "standard_deviation": 0.00033007913860502275, "minimum": 0.9981128451558666, "maximum": 0.9990308459731604, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4083948982055681, "standard_deviation": 0.022731737686082536, "minimum": 0.38829432334784714, "maximum": 0.44543004124587504, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7596381766071587, "standard_deviation": 0.32076534437796683, "minimum": 0.34376095205928653, "maximum": 1.27001053549917, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.04239842838392288, "standard_deviation": 0.005052840275405294, "minimum": 0.03572490845970822, "maximum": 0.04943116406765881, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_falset10_BASIC5000_1205", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 2.6407949924468994, "predicted_mos": 2.6407949924468994, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 97768, "input_sample_rate": 24000, "input_seconds": 4.073666666666667, "input_float32_sha256": "4af515f800390d5695457d8b55041254c8353d2e65f8c6b29b568804f0626c8e", "internal_samples": 65179, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.775183399673551}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6814483343439643, "全帯域_10ms_rms_envelope_nrmse": 0.059709478289225175, "全帯域_10ms_envelope_correlation": 0.9973982335515928, "全帯域_10ms_modulation_mae_db": 0.22505484969984593, "全帯域_40ms_log_rms_mae_db": 0.38494506568312287, "全帯域_40ms_rms_envelope_nrmse": 0.038851992863948324, "全帯域_40ms_envelope_correlation": 0.9988341453369697, "全帯域_40ms_modulation_mae_db": 0.21777656423122216, "300–1000 Hz_10ms_log_rms_mae_db": 0.8311129102030455, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06407126945275264, "300–1000 Hz_10ms_envelope_correlation": 0.9971198965994474, "300–1000 Hz_10ms_modulation_mae_db": 0.088812618004738, "300–1000 Hz_40ms_log_rms_mae_db": 0.5533002370363463, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04148338396500124, "300–1000 Hz_40ms_envelope_correlation": 0.9987295345115266, "300–1000 Hz_40ms_modulation_mae_db": 0.1722450904655978, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9966200806128103, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09824764734824905, "1000–3000 Hz_10ms_envelope_correlation": 0.9944283933859278, "1000–3000 Hz_10ms_modulation_mae_db": 0.5724619597072627, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5974277024122084, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06625821652157136, "1000–3000 Hz_40ms_envelope_correlation": 0.9975186236622068, "1000–3000 Hz_40ms_modulation_mae_db": 0.6417889245385483, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5885762870290983, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14586301865316506, "3000–6000 Hz_10ms_envelope_correlation": 0.9850021548792143, "3000–6000 Hz_10ms_modulation_mae_db": 0.4304178828617849, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9329616568345274, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07716827903784945, "3000–6000 Hz_40ms_envelope_correlation": 0.995484791599479, "3000–6000 Hz_40ms_modulation_mae_db": 0.4847885714910834, "mr_stft_db": 5.1355221522223315, "band_mae_db": 1.5283075197836056, "rms_gain_error_db": -0.0020757662754677534, "output_peak": 0.6924069911901438}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7625320228677758, "全帯域_10ms_rms_envelope_nrmse": 0.06639636299923246, "全帯域_10ms_envelope_correlation": 0.9967819883958742, "全帯域_10ms_modulation_mae_db": 0.4904364201629035, "全帯域_40ms_log_rms_mae_db": 0.4288891127670949, "全帯域_40ms_rms_envelope_nrmse": 0.035194570256131166, "全帯域_40ms_envelope_correlation": 0.9990537383797634, "全帯域_40ms_modulation_mae_db": 0.6131817084329719, "300–1000 Hz_10ms_log_rms_mae_db": 0.9615928933477591, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07567030726927267, "300–1000 Hz_10ms_envelope_correlation": 0.9959415165689821, "300–1000 Hz_10ms_modulation_mae_db": 0.4103655792223108, "300–1000 Hz_40ms_log_rms_mae_db": 0.5871656567835194, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04201525855176176, "300–1000 Hz_40ms_envelope_correlation": 0.9986744896361063, "300–1000 Hz_40ms_modulation_mae_db": 0.5458013913966978, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9787359124144743, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09835905657057378, "1000–3000 Hz_10ms_envelope_correlation": 0.9943120700142533, "1000–3000 Hz_10ms_modulation_mae_db": 0.4963242128568328, "1000–3000 Hz_40ms_log_rms_mae_db": 0.613828947656948, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.049750885816131366, "1000–3000 Hz_40ms_envelope_correlation": 0.9985771623871222, "1000–3000 Hz_40ms_modulation_mae_db": 0.48015963370694376, "3000–6000 Hz_10ms_log_rms_mae_db": 1.624537143529201, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14645668814548407, "3000–6000 Hz_10ms_envelope_correlation": 0.9847351697437228, "3000–6000 Hz_10ms_modulation_mae_db": 0.5712666234525817, "3000–6000 Hz_40ms_log_rms_mae_db": 0.918138977135277, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0828028241606766, "3000–6000 Hz_40ms_envelope_correlation": 0.9948905570061038, "3000–6000 Hz_40ms_modulation_mae_db": 0.44644976151346266, "mr_stft_db": 5.1448327165384855, "band_mae_db": 1.5393362439891298, "rms_gain_error_db": -0.03415191733568826, "output_peak": 0.666829520693782}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7279678333626342, "全帯域_10ms_rms_envelope_nrmse": 0.07378058062738793, "全帯域_10ms_envelope_correlation": 0.9960236018115648, "全帯域_10ms_modulation_mae_db": 0.474046554516338, "全帯域_40ms_log_rms_mae_db": 0.41590929202971516, "全帯域_40ms_rms_envelope_nrmse": 0.040823438572999464, "全帯域_40ms_envelope_correlation": 0.9987115749488656, "全帯域_40ms_modulation_mae_db": 0.44495856449249965, "300–1000 Hz_10ms_log_rms_mae_db": 0.92278160553382, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0843330076790133, "300–1000 Hz_10ms_envelope_correlation": 0.9949525996939935, "300–1000 Hz_10ms_modulation_mae_db": 0.44483215195224485, "300–1000 Hz_40ms_log_rms_mae_db": 0.6304823820638067, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04885334378208366, "300–1000 Hz_40ms_envelope_correlation": 0.9982111317519705, "300–1000 Hz_40ms_modulation_mae_db": 0.5078863835590387, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9412666046696893, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09586519187635743, "1000–3000 Hz_10ms_envelope_correlation": 0.9946556679073693, "1000–3000 Hz_10ms_modulation_mae_db": 0.19426823231297152, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5486705730903326, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.052020349740356894, "1000–3000 Hz_40ms_envelope_correlation": 0.9984027911945363, "1000–3000 Hz_40ms_modulation_mae_db": 0.26678638525153403, "3000–6000 Hz_10ms_log_rms_mae_db": 1.618221718332997, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14699374068718518, "3000–6000 Hz_10ms_envelope_correlation": 0.9855028722096785, "3000–6000 Hz_10ms_modulation_mae_db": 0.2725422130457586, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9202464179440152, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08727993795715684, "3000–6000 Hz_40ms_envelope_correlation": 0.9947877200977109, "3000–6000 Hz_40ms_modulation_mae_db": 0.4790814761998596, "mr_stft_db": 5.146891015121002, "band_mae_db": 1.5215710378135872, "rms_gain_error_db": -0.012583983076068905, "output_peak": 0.6644797122493227}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6874121889210189, "全帯域_10ms_rms_envelope_nrmse": 0.068635875295219, "全帯域_10ms_envelope_correlation": 0.9965612822467885, "全帯域_10ms_modulation_mae_db": 0.8007655362944748, "全帯域_40ms_log_rms_mae_db": 0.38532052471935174, "全帯域_40ms_rms_envelope_nrmse": 0.0414833008199751, "全帯域_40ms_envelope_correlation": 0.9986694354521014, "全帯域_40ms_modulation_mae_db": 0.9740647135058359, "300–1000 Hz_10ms_log_rms_mae_db": 0.8917391496018873, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07429740641357033, "300–1000 Hz_10ms_envelope_correlation": 0.9960990350026472, "300–1000 Hz_10ms_modulation_mae_db": 0.6869234535350589, "300–1000 Hz_40ms_log_rms_mae_db": 0.5771393294448148, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0462565495939177, "300–1000 Hz_40ms_envelope_correlation": 0.998396433510745, "300–1000 Hz_40ms_modulation_mae_db": 0.7717461447408898, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9643722992760857, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11335860386885564, "1000–3000 Hz_10ms_envelope_correlation": 0.9923887309821156, "1000–3000 Hz_10ms_modulation_mae_db": 0.9980092812770951, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6382213798990201, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0683302857114723, "1000–3000 Hz_40ms_envelope_correlation": 0.9971485698517091, "1000–3000 Hz_40ms_modulation_mae_db": 1.3889054687818252, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6232562243122688, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17209250409238777, "3000–6000 Hz_10ms_envelope_correlation": 0.9788346271898171, "3000–6000 Hz_10ms_modulation_mae_db": 0.2813186366392677, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9396565844107452, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09368167875578734, "3000–6000 Hz_40ms_envelope_correlation": 0.9934793934560309, "3000–6000 Hz_40ms_modulation_mae_db": 0.39615085612476325, "mr_stft_db": 5.144318553715933, "band_mae_db": 1.5983581979225594, "rms_gain_error_db": -0.005390120154969285, "output_peak": 0.6773046972262424}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7200302944590704, "全帯域_10ms_rms_envelope_nrmse": 0.06658848727114736, "全帯域_10ms_envelope_correlation": 0.9968642231940321, "全帯域_10ms_modulation_mae_db": 0.9924589894262242, "全帯域_40ms_log_rms_mae_db": 0.40606544611994144, "全帯域_40ms_rms_envelope_nrmse": 0.039093542767975005, "全帯域_40ms_envelope_correlation": 0.9989479111666325, "全帯域_40ms_modulation_mae_db": 1.1755828988826897, "300–1000 Hz_10ms_log_rms_mae_db": 0.8922852371540443, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0772438101279155, "300–1000 Hz_10ms_envelope_correlation": 0.9957971429214247, "300–1000 Hz_10ms_modulation_mae_db": 0.9040468871874398, "300–1000 Hz_40ms_log_rms_mae_db": 0.5715245475681544, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.046054916145903714, "300–1000 Hz_40ms_envelope_correlation": 0.9984571774027232, "300–1000 Hz_40ms_modulation_mae_db": 1.1727190460676906, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9759575380146073, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1076711645813188, "1000–3000 Hz_10ms_envelope_correlation": 0.993667938721661, "1000–3000 Hz_10ms_modulation_mae_db": 1.0623053129909599, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6018820094816748, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.061252789804354335, "1000–3000 Hz_40ms_envelope_correlation": 0.9984150499782916, "1000–3000 Hz_40ms_modulation_mae_db": 0.9711396788315217, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6158568865050187, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1468699069743064, "3000–6000 Hz_10ms_envelope_correlation": 0.984652133382042, "3000–6000 Hz_10ms_modulation_mae_db": 0.4707668330476327, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9132472285836538, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07570496978828865, "3000–6000 Hz_40ms_envelope_correlation": 0.9956715879636967, "3000–6000 Hz_40ms_modulation_mae_db": 0.5575327192461387, "mr_stft_db": 5.151683260894081, "band_mae_db": 1.6956869658457612, "rms_gain_error_db": -0.11832602139504551, "output_peak": 0.6328960278158575}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6903526482517949, "全帯域_10ms_rms_envelope_nrmse": 0.06311360915610688, "全帯域_10ms_envelope_correlation": 0.9970938601594151, "全帯域_10ms_modulation_mae_db": 0.6009371618056376, "全帯域_40ms_log_rms_mae_db": 0.37689632585964017, "全帯域_40ms_rms_envelope_nrmse": 0.03631214850316728, "全帯域_40ms_envelope_correlation": 0.9989836629522179, "全帯域_40ms_modulation_mae_db": 0.678256005620077, "300–1000 Hz_10ms_log_rms_mae_db": 0.8340831071896908, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06857589928884261, "300–1000 Hz_10ms_envelope_correlation": 0.9966865581983776, "300–1000 Hz_10ms_modulation_mae_db": 0.27891899420522465, "300–1000 Hz_40ms_log_rms_mae_db": 0.5785945385456273, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04187956389704536, "300–1000 Hz_40ms_envelope_correlation": 0.9986947675451106, "300–1000 Hz_40ms_modulation_mae_db": 0.37730558472483516, "1000–3000 Hz_10ms_log_rms_mae_db": 1.004241784768434, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10281976721882695, "1000–3000 Hz_10ms_envelope_correlation": 0.9937372124286697, "1000–3000 Hz_10ms_modulation_mae_db": 1.5599262514476413, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6301836216224217, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05955245302599505, "1000–3000 Hz_40ms_envelope_correlation": 0.9978486138325745, "1000–3000 Hz_40ms_modulation_mae_db": 1.6893592475998436, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5929971792637254, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1682887453125894, "3000–6000 Hz_10ms_envelope_correlation": 0.9797941436097232, "3000–6000 Hz_10ms_modulation_mae_db": 0.48784816819710625, "3000–6000 Hz_40ms_log_rms_mae_db": 0.902676331321166, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0892261392647761, "3000–6000 Hz_40ms_envelope_correlation": 0.9941835059573944, "3000–6000 Hz_40ms_modulation_mae_db": 0.21619774745663056, "mr_stft_db": 5.129472181089537, "band_mae_db": 1.5473684272741206, "rms_gain_error_db": 0.0009021250559918963, "output_peak": 0.6999496173281531}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7223110538240292, "全帯域_10ms_rms_envelope_nrmse": 0.06730428753921086, "全帯域_10ms_envelope_correlation": 0.996703987467527, "全帯域_10ms_modulation_mae_db": 0.22173425543453038, "全帯域_40ms_log_rms_mae_db": 0.398798502891485, "全帯域_40ms_rms_envelope_nrmse": 0.03643815418699353, "全帯域_40ms_envelope_correlation": 0.9989790120613854, "全帯域_40ms_modulation_mae_db": 0.38187911907826955, "300–1000 Hz_10ms_log_rms_mae_db": 0.8937490692907692, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07453970267466653, "300–1000 Hz_10ms_envelope_correlation": 0.9961537090620765, "300–1000 Hz_10ms_modulation_mae_db": 0.1664233590419041, "300–1000 Hz_40ms_log_rms_mae_db": 0.570794657867509, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04092053465413655, "300–1000 Hz_40ms_envelope_correlation": 0.9988116117925097, "300–1000 Hz_40ms_modulation_mae_db": 0.3674873691786666, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9851981010874031, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0934911041117174, "1000–3000 Hz_10ms_envelope_correlation": 0.9950271385944184, "1000–3000 Hz_10ms_modulation_mae_db": 0.7723598659099485, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6228035337266632, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04768911498391592, "1000–3000 Hz_40ms_envelope_correlation": 0.9988994639180393, "1000–3000 Hz_40ms_modulation_mae_db": 0.9477618693353592, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6605098736634782, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1602823692901956, "3000–6000 Hz_10ms_envelope_correlation": 0.9817271186660282, "3000–6000 Hz_10ms_modulation_mae_db": 0.1396290333109232, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9574151116321649, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08579292598709082, "3000–6000 Hz_40ms_envelope_correlation": 0.9943455110184481, "3000–6000 Hz_40ms_modulation_mae_db": 0.5467836634086675, "mr_stft_db": 5.136992525985072, "band_mae_db": 1.5769539696639066, "rms_gain_error_db": 0.015341794046763993, "output_peak": 0.6814809461147989}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7322218785454789, "全帯域_10ms_rms_envelope_nrmse": 0.06789929109538924, "全帯域_10ms_envelope_correlation": 0.9966621053783646, "全帯域_10ms_modulation_mae_db": 0.7253721075325604, "全帯域_40ms_log_rms_mae_db": 0.40322234434632404, "全帯域_40ms_rms_envelope_nrmse": 0.039727772445801925, "全帯域_40ms_envelope_correlation": 0.998821920622755, "全帯域_40ms_modulation_mae_db": 1.0816871512117892, "300–1000 Hz_10ms_log_rms_mae_db": 0.8879854881280188, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07145777282761001, "300–1000 Hz_10ms_envelope_correlation": 0.9963846629160329, "300–1000 Hz_10ms_modulation_mae_db": 0.29020707729784395, "300–1000 Hz_40ms_log_rms_mae_db": 0.5647822642532537, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04284138520865993, "300–1000 Hz_40ms_envelope_correlation": 0.9986238420653026, "300–1000 Hz_40ms_modulation_mae_db": 0.7502043045641568, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9633031555602513, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11335570278855828, "1000–3000 Hz_10ms_envelope_correlation": 0.9925944611221146, "1000–3000 Hz_10ms_modulation_mae_db": 1.6004215428408555, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6036603566520657, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07733242274327945, "1000–3000 Hz_40ms_envelope_correlation": 0.9966500097248354, "1000–3000 Hz_40ms_modulation_mae_db": 2.140971985972422, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6573922215725607, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1591554261769884, "3000–6000 Hz_10ms_envelope_correlation": 0.9821119649349005, "3000–6000 Hz_10ms_modulation_mae_db": 0.6197715307259043, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9620547683337747, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09004677622946103, "3000–6000 Hz_40ms_envelope_correlation": 0.9942577921620522, "3000–6000 Hz_40ms_modulation_mae_db": 0.556158355624433, "mr_stft_db": 5.155100753369424, "band_mae_db": 1.5659352843460794, "rms_gain_error_db": -0.06931827873632052, "output_peak": 0.6607056148504786}, "full_scale": {"sample_count": 97768, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 97768, "output_samples": 97768, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.677619093436316, "spectral_convergence": 0.16518182805760695, "spectral_convergence_status": "ok", "amplitude_floor": 1.7496801023785185e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.1117934588375, "spectral_convergence": 0.18009729243969747, "spectral_convergence_status": "ok", "amplitude_floor": 1.6784480256181157e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.617153904393176, "spectral_convergence": 0.1882031468972953, "spectral_convergence_status": "ok", "amplitude_floor": 1.5558256811894896e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.01876573628214e-07, "output_power": 5.052216696838752e-06, "delta_db": 10.028850454473544, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0014282687361772438, "output_power": 0.0014234279103465172, "delta_db": -0.014744527389127038, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.002893798215697645, "output_power": 0.002939406942878501, "delta_db": 0.06791471122972746, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0011796153749935407, "output_power": 0.001129975966833667, "delta_db": -0.18671217784497304, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.624359886340766e-05, "output_power": 1.6689414944961718e-05, "delta_db": 0.11758856531687996, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.5152799044228294e-05, "output_power": 2.5966519380676605e-05, "delta_db": 0.13827418501723188, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2062863831028078e-05, "output_power": 1.2469735084615016e-05, "delta_db": 0.14406801721375626, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.5283075197836056, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.0020757662754677534, "pitch": null, "output_rms_dbfs": -22.554732096207374, "output_peak": 0.6924069911901438, "reference_rms_dbfs": -22.552656329931906, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.1355221522223315}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 97768, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0003314896640837282, "log_rms_mae_db": 0.6814483343439643, "rms_envelope_nrmse": 0.059709478289225175, "envelope_correlation": 0.9973982335515928, "rms_gain_error_db": -0.0020757011795089876, "reference_mean_power": 0.005567487969490699, "output_mean_power": 0.005564827636334664}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 4.765376195527077e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0029556164553593994, "output_power": 0.0028958555244558387, "reference_active": true, "delta_db": -0.08871184905700248}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00036953756834478597, "output_power": 0.000387086161608999, "reference_active": true, "delta_db": 0.20149048790202126}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 0.00011202447087610656, "output_power": 0.00010252190799645075, "reference_active": true, "delta_db": -0.38496221214051407}], "active_band_count": 3, "active_band_mae_db": 0.22505484969984593}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.0003156446105274747, "log_rms_mae_db": 0.38494506568312287, "rms_envelope_nrmse": 0.038851992863948324, "envelope_correlation": 0.9988341453369697, "rms_gain_error_db": -0.002075680265193027, "reference_mean_power": 0.005608881493358216, "output_mean_power": 0.005606201407980932}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 4.372836941600517e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0027064910584040595, "output_power": 0.0026606348313200274, "reference_active": true, "delta_db": -0.07421324337801283}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00018117557189089236, "output_power": 0.00019454058674795525, "reference_active": true, "delta_db": 0.30910580536374155}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.701057462757455e-06, "output_power": 9.116287492103918e-06, "reference_active": true, "delta_db": -0.2700106439519121}], "active_band_count": 3, "active_band_mae_db": 0.21777656423122216}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.0002506339510784735, "log_rms_mae_db": 0.8311129102030455, "rms_envelope_nrmse": 0.06407126945275264, "envelope_correlation": 0.9971198965994474, "rms_gain_error_db": 0.03787224282810041, "reference_mean_power": 0.0041004048785232925, "output_mean_power": 0.004136318437377774}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 3.4168869077487306e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0021098794264420863, "output_power": 0.002106549265301733, "reference_active": true, "delta_db": -0.00686017012767713}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00027960522877585594, "output_power": 0.00029009330105336757, "reference_active": true, "delta_db": 0.15992411320493627}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.021566680060571e-05, "output_power": 8.816914033269605e-05, "reference_active": true, "delta_db": -0.09965357068160062}], "active_band_count": 3, "active_band_mae_db": 0.088812618004738}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00024415679244648423, "log_rms_mae_db": 0.5533002370363463, "rms_envelope_nrmse": 0.04148338396500124, "envelope_correlation": 0.9987295345115266, "rms_gain_error_db": 0.03787223493952589, "reference_mean_power": 0.004130891145990147, "output_mean_power": 0.004167071712458978}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 3.1086003931775263e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0019093077513610485, "output_power": 0.0019114011143020315, "reference_active": true, "delta_db": 0.004758991573696078}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00014045819894614964, "output_power": 0.00015072340572246622, "reference_active": true, "delta_db": 0.3063360352319396}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.796438388581124e-06, "output_power": 8.174482636595265e-06, "reference_active": true, "delta_db": 0.20564024459115776}], "active_band_count": 3, "active_band_mae_db": 0.1722450904655978}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 0.00019827664142914133, "log_rms_mae_db": 0.9966200806128103, "rms_envelope_nrmse": 0.09824764734824905, "envelope_correlation": 0.9944283933859278, "rms_gain_error_db": -0.17817934294273502, "reference_mean_power": 0.0008784725402011367, "output_mean_power": 0.0008431605070058376}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.1250771844458692e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007015897284632315, "output_power": 0.0006580102380890107, "reference_active": true, "delta_db": -0.27850571244959493}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.449911857407873e-05, "output_power": 7.939111633405499e-05, "reference_active": true, "delta_db": -0.27080270080128244}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6127775103534605e-05, "output_power": 1.9966166232625384e-05, "reference_active": true, "delta_db": -1.1680774658709105}], "active_band_count": 3, "active_band_mae_db": 0.5724619597072627}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 0.00017853730341036803, "log_rms_mae_db": 0.5974277024122084, "rms_envelope_nrmse": 0.06625821652157136, "envelope_correlation": 0.9975186236622068, "rms_gain_error_db": -0.1781793603693353, "reference_mean_power": 0.0008850039267330396, "output_mean_power": 0.0008494293474458686}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.078630941288297e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006783838060260436, "output_power": 0.0006339713309095957, "reference_active": true, "delta_db": -0.29405853245224983}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3933140159486266e-05, "output_power": 3.230983683642255e-05, "reference_active": true, "delta_db": -0.21289286095057774}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.944075796645493e-06, "output_power": 1.4023992001863968e-06, "reference_active": true, "delta_db": -1.4184153802128174}], "active_band_count": 3, "active_band_mae_db": 0.6417889245385483}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 813, "rms_floor": 2.2340226127796077e-05, "log_rms_mae_db": 1.5885762870290983, "rms_envelope_nrmse": 0.14586301865316506, "envelope_correlation": 0.9850021548792143, "rms_gain_error_db": 0.045892885759338586, "reference_mean_power": 1.7310253593278313e-05, "output_mean_power": 1.7494144879754748e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.3633964732936534e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.958677073783288e-06, "output_power": 8.370298264974242e-06, "reference_active": true, "delta_db": 0.21900050399706494}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3383871013961803e-06, "output_power": 1.075618687160479e-06, "reference_active": true, "delta_db": -0.9492340370319654}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.535118084866941e-07, "output_power": 4.6654174606488905e-07, "reference_active": true, "delta_db": 0.12301910755632432}], "active_band_count": 3, "active_band_mae_db": 0.4304178828617849}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 97680, "uncovered_tail_samples": 88, "metrics": {"frame_count": 807, "rms_floor": 1.6591025056474894e-05, "log_rms_mae_db": 0.9329616568345274, "rms_envelope_nrmse": 0.07716827903784945, "envelope_correlation": 0.995484791599479, "rms_gain_error_db": 0.04589277046747557, "reference_mean_power": 1.743895029874837e-05, "output_mean_power": 1.762420829563614e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 1.2324948655964946e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.384237970170313e-06, "output_power": 7.660169626168947e-06, "reference_active": true, "delta_db": 0.15932702566906876}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2197399674362034e-07, "output_power": 3.308471164334233e-07, "reference_active": true, "delta_db": -1.056583354933823}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.206308596249792e-08, "output_power": 3.387278088448388e-08, "reference_active": true, "delta_db": 0.23845533387035828}], "active_band_count": 3, "active_band_mae_db": 0.4847885714910834}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8322959482183662, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "bc2d157d9c53440a7402d7b7bc2507665a053ff93651410a3bfc53525f834c21", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9938514516445662, "standard_deviation": 0.000951715680685846, "minimum": 0.9923887309821156, "maximum": 0.9950271385944184, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.9762119345504694, "standard_deviation": 0.020061836259616325, "minimum": 0.9412666046696893, "maximum": 1.004241784768434, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.9070095824179459, "standard_deviation": 0.4994616238109506, "minimum": 0.19426823231297152, "maximum": 1.6004215428408555, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10289602979555718, "standard_deviation": 0.007762131867947459, "minimum": 0.0934911041117174, "maximum": 0.11335860386885564, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9979325355686643, "standard_deviation": 0.000778487121336565, "minimum": 0.9966500097248354, "maximum": 0.9988994639180393, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6070847655676668, "standard_deviation": 0.027619562338589213, "minimum": 0.5486705730903326, "maximum": 0.6382213798990201, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.0658591492522498, "standard_deviation": 0.6362046407798347, "minimum": 0.26678638525153403, "maximum": 2.140971985972422, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06027331479338459, "standard_deviation": 0.010214982236851869, "minimum": 0.04768911498391592, "maximum": 0.07733242274327945, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9827950230768908, "standard_deviation": 0.002555495672019775, "minimum": 0.9788346271898171, "maximum": 0.9855028722096785, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.6226684417760433, "standard_deviation": 0.026050450651858063, "minimum": 1.5885762870290983, "maximum": 1.6605098736634782, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.40919511516011997, "standard_deviation": 0.16419921156762327, "minimum": 0.1396290333109232, "maximum": 0.6197715307259043, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15575029991653772, "standard_deviation": 0.010664246318623316, "minimum": 0.14586301865316506, "maximum": 0.17209250409238777, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9946376074076145, "standard_deviation": 0.000722159635148591, "minimum": 0.9934793934560309, "maximum": 0.9956715879636967, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9307996345244156, "standard_deviation": 0.02117632328792036, "minimum": 0.902676331321166, "maximum": 0.9620547683337747, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.4603928938831299, "standard_deviation": 0.1139972847309097, "minimum": 0.21619774745663056, "maximum": 0.5575327192461387, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08521294139763586, "standard_deviation": 0.00628748038733229, "minimum": 0.07570496978828865, "maximum": 0.09368167875578734, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9961418901203727, "standard_deviation": 0.0006422601583111624, "minimum": 0.9949525996939935, "maximum": 0.9971198965994474, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8894161825561294, "standard_deviation": 0.042792185988879454, "minimum": 0.8311129102030455, "maximum": 0.9615928933477591, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4088162650558456, "standard_deviation": 0.2715023328684107, "minimum": 0.088812618004738, "maximum": 0.9040468871874398, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07377364696670545, "standard_deviation": 0.006029885097239545, "minimum": 0.06407126945275264, "maximum": 0.0843330076790133, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9985748735269994, "standard_deviation": 0.0002016581920617742, "minimum": 0.9982111317519705, "maximum": 0.9988116117925097, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.579222951695379, "standard_deviation": 0.02300985597096677, "minimum": 0.5533002370363463, "maximum": 0.6304823820638067, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5831744143371966, "standard_deviation": 0.31072541176916774, "minimum": 0.1722450904655978, "maximum": 1.1727190460676906, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.043788116974813746, "standard_deviation": 0.0028810907204059877, "minimum": 0.04092053465413655, "maximum": 0.04885334378208366, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.5716897058298436, "standard_deviation": 0.05628945706387333, "minimum": 1.5215710378135872, "maximum": 1.6956869658457612, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.143101644866983, "standard_deviation": 0.008593950254309542, "minimum": 5.129472181089537, "maximum": 5.155100753369424, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.6720066409335974, "standard_deviation": 0.020893015093551407, "minimum": 0.6328960278158575, "maximum": 0.6999496173281531, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.028200270983850542, "standard_deviation": 0.04478246723330458, "minimum": -0.11832602139504551, "maximum": 0.015341794046763993, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9967611602756449, "standard_deviation": 0.00040082622959966205, "minimum": 0.9960236018115648, "maximum": 0.9973982335515928, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7155345318219708, "standard_deviation": 0.02750276379227563, "minimum": 0.6814483343439643, "maximum": 0.7625320228677758, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.5663507343590644, "standard_deviation": 0.2705890414949982, "minimum": 0.22173425543453038, "maximum": 0.9924589894262242, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.06667849653411487, "standard_deviation": 0.004097320067341078, "minimum": 0.059709478289225175, "maximum": 0.07378058062738793, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9988751751150864, "standard_deviation": 0.00013801677013382615, "minimum": 0.9986694354521014, "maximum": 0.9990537383797634, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4000058268020844, "standard_deviation": 0.01737083217576543, "minimum": 0.37689632585964017, "maximum": 0.4288891127670949, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6959233406819194, "standard_deviation": 0.3492112289227794, "minimum": 0.21777656423122216, "maximum": 1.1755828988826897, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03849061505212398, "standard_deviation": 0.002275494648259629, "minimum": 0.035194570256131166, "maximum": 0.0414833008199751, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "language": "ja", "style": "normal", "speaker": "jvs_jvs066", "source_utterance_id": "VOICEACTRESS100_025", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 123603, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs066_parallel100_VOICEACTRESS100_025.wav", "source_file_sha256": "c7ebca7938b1e044488e290c866f97301681f0d657ca6975ddfd27da675b293d", "decoded_pcm_sha256": "8ab43acb74cca30ae1e3fdd9a76fb7288130fbce511cf398836458ff852c6981", "original_source_sha256": "c7ebca7938b1e044488e290c866f97301681f0d657ca6975ddfd27da675b293d", "corpus_entry_id": "jvs_jvs066_parallel100_VOICEACTRESS100_025"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 4.037968158721924, "predicted_mos": 4.037968158721924, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 123603, "input_sample_rate": 24000, "input_seconds": 5.150125, "input_float32_sha256": "b16e8ab8b4bb7462a49fba4f9742d19d2ab1d4618347217f69444eaf0188c80c", "internal_samples": 82402, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.769754900131375}, "waveform_sha256": "011365440c7ba9de5ad56aa29c7c1f296320e79cb6819422557cc09ed5ee2fa6"}, "rows": [{"case": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 2.743691921234131, "predicted_mos": 2.743691921234131, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 123603, "input_sample_rate": 24000, "input_seconds": 5.150125, "input_float32_sha256": "02a0ba5086b86cbd16c7f4258e8e397a89287bdd9df210bac7e15bc37921ce66", "internal_samples": 82402, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.460692800115794}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9391602958669921, "全帯域_10ms_rms_envelope_nrmse": 0.05044643573360221, "全帯域_10ms_envelope_correlation": 0.9974279432805426, "全帯域_10ms_modulation_mae_db": 0.42887741030680004, "全帯域_40ms_log_rms_mae_db": 0.6260002844552242, "全帯域_40ms_rms_envelope_nrmse": 0.0261765816797062, "全帯域_40ms_envelope_correlation": 0.9992771723517097, "全帯域_40ms_modulation_mae_db": 0.32416176862892027, "300–1000 Hz_10ms_log_rms_mae_db": 0.9188609985452109, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08170706998904544, "300–1000 Hz_10ms_envelope_correlation": 0.9939911280858043, "300–1000 Hz_10ms_modulation_mae_db": 0.4844192068167439, "300–1000 Hz_40ms_log_rms_mae_db": 0.6098419277655122, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04775923398827758, "300–1000 Hz_40ms_envelope_correlation": 0.9978237702948339, "300–1000 Hz_40ms_modulation_mae_db": 0.19858903491841762, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1191340874933735, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.096202551181614, "1000–3000 Hz_10ms_envelope_correlation": 0.9934465362390451, "1000–3000 Hz_10ms_modulation_mae_db": 1.5514452791588071, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6666041696097952, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05348534160985608, "1000–3000 Hz_40ms_envelope_correlation": 0.9980307304516327, "1000–3000 Hz_40ms_modulation_mae_db": 1.1590485693517174, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5189547295488266, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13497428981539508, "3000–6000 Hz_10ms_envelope_correlation": 0.9845350250156911, "3000–6000 Hz_10ms_modulation_mae_db": 0.451638299129649, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9092352522372343, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07806353759197684, "3000–6000 Hz_40ms_envelope_correlation": 0.9946863946190508, "3000–6000 Hz_40ms_modulation_mae_db": 0.39716769272469316, "mr_stft_db": 5.409974853309208, "band_mae_db": 0.13042859411034785, "rms_gain_error_db": -0.042940798074918844, "output_peak": 0.4922653919690344}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9184599124599466, "全帯域_10ms_rms_envelope_nrmse": 0.05244065449399799, "全帯域_10ms_envelope_correlation": 0.9972532677632561, "全帯域_10ms_modulation_mae_db": 0.49994391893360707, "全帯域_40ms_log_rms_mae_db": 0.639357582335908, "全帯域_40ms_rms_envelope_nrmse": 0.029281023265963175, "全帯域_40ms_envelope_correlation": 0.9991356361798595, "全帯域_40ms_modulation_mae_db": 0.6998089766356473, "300–1000 Hz_10ms_log_rms_mae_db": 0.9101695454202798, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07186036209911414, "300–1000 Hz_10ms_envelope_correlation": 0.9953790721394141, "300–1000 Hz_10ms_modulation_mae_db": 0.19524740158449383, "300–1000 Hz_40ms_log_rms_mae_db": 0.6482276971187082, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.039060053815127976, "300–1000 Hz_40ms_envelope_correlation": 0.9985734790758147, "300–1000 Hz_40ms_modulation_mae_db": 0.510851421563934, "1000–3000 Hz_10ms_log_rms_mae_db": 1.096546489062421, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09711852708774871, "1000–3000 Hz_10ms_envelope_correlation": 0.9932013823650045, "1000–3000 Hz_10ms_modulation_mae_db": 0.9226187135874618, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7028311570849937, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.052297754874343926, "1000–3000 Hz_40ms_envelope_correlation": 0.9979855043963438, "1000–3000 Hz_40ms_modulation_mae_db": 0.733167006409063, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4793621250127085, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.141884776545636, "3000–6000 Hz_10ms_envelope_correlation": 0.9847168784677712, "3000–6000 Hz_10ms_modulation_mae_db": 0.8697589138184295, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9273300975004439, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08861411985049723, "3000–6000 Hz_40ms_envelope_correlation": 0.9954350046224301, "3000–6000 Hz_40ms_modulation_mae_db": 1.0070556493672043, "mr_stft_db": 5.399291969504265, "band_mae_db": 0.17851077695849119, "rms_gain_error_db": -0.07316121078605164, "output_peak": 0.438219477539873}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9047532321453409, "全帯域_10ms_rms_envelope_nrmse": 0.05133536845123084, "全帯域_10ms_envelope_correlation": 0.9973561694923915, "全帯域_10ms_modulation_mae_db": 0.20401383572809903, "全帯域_40ms_log_rms_mae_db": 0.594636676607769, "全帯域_40ms_rms_envelope_nrmse": 0.027036200277959867, "全帯域_40ms_envelope_correlation": 0.9992550037753389, "全帯域_40ms_modulation_mae_db": 0.48147180277055474, "300–1000 Hz_10ms_log_rms_mae_db": 0.9774728993885337, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0707110024133352, "300–1000 Hz_10ms_envelope_correlation": 0.9955111624551192, "300–1000 Hz_10ms_modulation_mae_db": 0.42243992726063473, "300–1000 Hz_40ms_log_rms_mae_db": 0.6849734756036641, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03581446364471031, "300–1000 Hz_40ms_envelope_correlation": 0.998781397003584, "300–1000 Hz_40ms_modulation_mae_db": 0.5784297322919, "1000–3000 Hz_10ms_log_rms_mae_db": 1.066755681733455, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10468282804556173, "1000–3000 Hz_10ms_envelope_correlation": 0.9920611841434286, "1000–3000 Hz_10ms_modulation_mae_db": 0.9320728826929828, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6834920727278593, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.058974130016899884, "1000–3000 Hz_40ms_envelope_correlation": 0.9973711122062805, "1000–3000 Hz_40ms_modulation_mae_db": 1.2182260110914402, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5230665917983823, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.137940867095787, "3000–6000 Hz_10ms_envelope_correlation": 0.9846397054273034, "3000–6000 Hz_10ms_modulation_mae_db": 0.3315430793639149, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9079129102937712, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08560990130337942, "3000–6000 Hz_40ms_envelope_correlation": 0.9946110790139832, "3000–6000 Hz_40ms_modulation_mae_db": 0.40765367743290715, "mr_stft_db": 5.401186207873155, "band_mae_db": 0.21649405158673168, "rms_gain_error_db": -0.06268098947909678, "output_peak": 0.4800991516105175}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9258921149132003, "全帯域_10ms_rms_envelope_nrmse": 0.04782543324840094, "全帯域_10ms_envelope_correlation": 0.9977097980930592, "全帯域_10ms_modulation_mae_db": 0.745190266661858, "全帯域_40ms_log_rms_mae_db": 0.5934413498328736, "全帯域_40ms_rms_envelope_nrmse": 0.026792904594765833, "全帯域_40ms_envelope_correlation": 0.9992618452510985, "全帯域_40ms_modulation_mae_db": 0.8504734549739342, "300–1000 Hz_10ms_log_rms_mae_db": 0.9726721097788227, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0807231284697106, "300–1000 Hz_10ms_envelope_correlation": 0.9941893564159312, "300–1000 Hz_10ms_modulation_mae_db": 0.4683157568440792, "300–1000 Hz_40ms_log_rms_mae_db": 0.6485071426606759, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04328079147819143, "300–1000 Hz_40ms_envelope_correlation": 0.9982707540785666, "300–1000 Hz_40ms_modulation_mae_db": 1.1697263676860785, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1087270558005378, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08054424978600093, "1000–3000 Hz_10ms_envelope_correlation": 0.9955178946968464, "1000–3000 Hz_10ms_modulation_mae_db": 0.17047238290935587, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6763738873825283, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05063685402928737, "1000–3000 Hz_40ms_envelope_correlation": 0.9982928507898748, "1000–3000 Hz_40ms_modulation_mae_db": 0.17503139965792033, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5031205884709025, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14234448525933197, "3000–6000 Hz_10ms_envelope_correlation": 0.9837048426793313, "3000–6000 Hz_10ms_modulation_mae_db": 0.71479619697132, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9121001460848785, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08665240328622104, "3000–6000 Hz_40ms_envelope_correlation": 0.9946565945090129, "3000–6000 Hz_40ms_modulation_mae_db": 0.7883438587022177, "mr_stft_db": 5.3982116043354305, "band_mae_db": 0.20285386942824796, "rms_gain_error_db": -0.05750865267194159, "output_peak": 0.4626315004056094}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9710461353247843, "全帯域_10ms_rms_envelope_nrmse": 0.058382340524570316, "全帯域_10ms_envelope_correlation": 0.9966494163318693, "全帯域_10ms_modulation_mae_db": 0.555349291515724, "全帯域_40ms_log_rms_mae_db": 0.60668531681828, "全帯域_40ms_rms_envelope_nrmse": 0.03389013436554725, "全帯域_40ms_envelope_correlation": 0.9988978528528834, "全帯域_40ms_modulation_mae_db": 0.741133373394215, "300–1000 Hz_10ms_log_rms_mae_db": 0.9342996916271836, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07767193090471657, "300–1000 Hz_10ms_envelope_correlation": 0.9947122241326342, "300–1000 Hz_10ms_modulation_mae_db": 0.5003559719016856, "300–1000 Hz_40ms_log_rms_mae_db": 0.6154381546031317, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.049066812330856656, "300–1000 Hz_40ms_envelope_correlation": 0.9978627312543452, "300–1000 Hz_40ms_modulation_mae_db": 0.8493360802446194, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0969354331775893, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11624587427142292, "1000–3000 Hz_10ms_envelope_correlation": 0.9903766974979944, "1000–3000 Hz_10ms_modulation_mae_db": 0.8577361250795509, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6946449035072186, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06431859148311819, "1000–3000 Hz_40ms_envelope_correlation": 0.9971420101146095, "1000–3000 Hz_40ms_modulation_mae_db": 0.9199263230085308, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5060849171778512, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1332019756878042, "3000–6000 Hz_10ms_envelope_correlation": 0.9857579716254904, "3000–6000 Hz_10ms_modulation_mae_db": 0.6917540072563667, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9352402496744846, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0833312730860373, "3000–6000 Hz_40ms_envelope_correlation": 0.9949334449731857, "3000–6000 Hz_40ms_modulation_mae_db": 0.7801019980998832, "mr_stft_db": 5.4044578646643515, "band_mae_db": 0.24557354963724576, "rms_gain_error_db": -0.10595298121810176, "output_peak": 0.4513680585179606}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9327779141257242, "全帯域_10ms_rms_envelope_nrmse": 0.0567335397593424, "全帯域_10ms_envelope_correlation": 0.9969028109566344, "全帯域_10ms_modulation_mae_db": 0.29645010703945945, "全帯域_40ms_log_rms_mae_db": 0.5915697336410664, "全帯域_40ms_rms_envelope_nrmse": 0.03631474564469833, "全帯域_40ms_envelope_correlation": 0.9987791430843247, "全帯域_40ms_modulation_mae_db": 0.5662874475463037, "300–1000 Hz_10ms_log_rms_mae_db": 0.9581097415046688, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0818086728051294, "300–1000 Hz_10ms_envelope_correlation": 0.9941119173260716, "300–1000 Hz_10ms_modulation_mae_db": 0.42300198328220856, "300–1000 Hz_40ms_log_rms_mae_db": 0.6882417624144871, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.055854800954529556, "300–1000 Hz_40ms_envelope_correlation": 0.9971811420725044, "300–1000 Hz_40ms_modulation_mae_db": 0.6765482586849565, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1133465832599885, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10527934006487115, "1000–3000 Hz_10ms_envelope_correlation": 0.9926844941929774, "1000–3000 Hz_10ms_modulation_mae_db": 0.5595860345621203, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6920869828906001, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07044408404763879, "1000–3000 Hz_40ms_envelope_correlation": 0.997093003276514, "1000–3000 Hz_40ms_modulation_mae_db": 0.6380393316349657, "3000–6000 Hz_10ms_log_rms_mae_db": 1.50480324831791, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13873722393596918, "3000–6000 Hz_10ms_envelope_correlation": 0.9851165621241201, "3000–6000 Hz_10ms_modulation_mae_db": 0.6437184834190238, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8860506546256895, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0828233394537899, "3000–6000 Hz_40ms_envelope_correlation": 0.9959443326335353, "3000–6000 Hz_40ms_modulation_mae_db": 0.9948889341505393, "mr_stft_db": 5.395630665311302, "band_mae_db": 0.2117153850974054, "rms_gain_error_db": -0.1253778539520704, "output_peak": 0.4614110191027701}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9078770528711507, "全帯域_10ms_rms_envelope_nrmse": 0.050216767397239674, "全帯域_10ms_envelope_correlation": 0.9975505952993537, "全帯域_10ms_modulation_mae_db": 0.6450805690146807, "全帯域_40ms_log_rms_mae_db": 0.575948341726759, "全帯域_40ms_rms_envelope_nrmse": 0.029502440928398353, "全帯域_40ms_envelope_correlation": 0.999189896102923, "全帯域_40ms_modulation_mae_db": 0.7633556543527975, "300–1000 Hz_10ms_log_rms_mae_db": 1.0087398572389785, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0794778135936096, "300–1000 Hz_10ms_envelope_correlation": 0.9943846239794999, "300–1000 Hz_10ms_modulation_mae_db": 0.7316624137220348, "300–1000 Hz_40ms_log_rms_mae_db": 0.7198905959298105, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05074093710106785, "300–1000 Hz_40ms_envelope_correlation": 0.9976143535821376, "300–1000 Hz_40ms_modulation_mae_db": 0.8537847420647592, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1105056774130289, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09440222358329961, "1000–3000 Hz_10ms_envelope_correlation": 0.993927684947042, "1000–3000 Hz_10ms_modulation_mae_db": 1.1846711868024256, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6791136705201961, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0548332567727717, "1000–3000 Hz_40ms_envelope_correlation": 0.9981767692173965, "1000–3000 Hz_40ms_modulation_mae_db": 1.262094792171135, "3000–6000 Hz_10ms_log_rms_mae_db": 1.544767044769688, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14344432172208155, "3000–6000 Hz_10ms_envelope_correlation": 0.9830512137496044, "3000–6000 Hz_10ms_modulation_mae_db": 0.4286558990950072, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9469267186195427, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0907209027938213, "3000–6000 Hz_40ms_envelope_correlation": 0.9934576067200769, "3000–6000 Hz_40ms_modulation_mae_db": 0.4804359315748909, "mr_stft_db": 5.3970173761145555, "band_mae_db": 0.23847572567999284, "rms_gain_error_db": -0.10143860503225738, "output_peak": 0.49532978733127814}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9389057626156005, "全帯域_10ms_rms_envelope_nrmse": 0.05226430807163367, "全帯域_10ms_envelope_correlation": 0.9973035671072943, "全帯域_10ms_modulation_mae_db": 0.30236327053900586, "全帯域_40ms_log_rms_mae_db": 0.6623056928778522, "全帯域_40ms_rms_envelope_nrmse": 0.028726238140430828, "全帯域_40ms_envelope_correlation": 0.9992057157101425, "全帯域_40ms_modulation_mae_db": 0.5645618135975514, "300–1000 Hz_10ms_log_rms_mae_db": 1.0045016093667405, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07005524737451797, "300–1000 Hz_10ms_envelope_correlation": 0.9955979506402817, "300–1000 Hz_10ms_modulation_mae_db": 0.3870023513450209, "300–1000 Hz_40ms_log_rms_mae_db": 0.7133560477172146, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04062856063694493, "300–1000 Hz_40ms_envelope_correlation": 0.998431514024168, "300–1000 Hz_40ms_modulation_mae_db": 0.2640858462025366, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0887684147271184, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08223791125615182, "1000–3000 Hz_10ms_envelope_correlation": 0.995448116390832, "1000–3000 Hz_10ms_modulation_mae_db": 0.9918436132311131, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6456010149161364, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04963892222462629, "1000–3000 Hz_40ms_envelope_correlation": 0.9985311153829203, "1000–3000 Hz_40ms_modulation_mae_db": 0.9169420810144814, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5486052620392237, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1382002658229927, "3000–6000 Hz_10ms_envelope_correlation": 0.9844296733233208, "3000–6000 Hz_10ms_modulation_mae_db": 0.5233816126001082, "3000–6000 Hz_40ms_log_rms_mae_db": 0.931490746762839, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09019131640706304, "3000–6000 Hz_40ms_envelope_correlation": 0.9936283300245041, "3000–6000 Hz_40ms_modulation_mae_db": 0.37715950714669627, "mr_stft_db": 5.40873630749831, "band_mae_db": 0.1745661361233973, "rms_gain_error_db": -0.08424726312895635, "output_peak": 0.49400495584774706}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 123603, "output_samples": 123603, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.562232056272464, "spectral_convergence": 0.15513301727493634, "spectral_convergence_status": "ok", "amplitude_floor": 1.160899353957536e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.385407896334377, "spectral_convergence": 0.16016142761877897, "spectral_convergence_status": "ok", "amplitude_floor": 1.2404642078999559e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.282284607320784, "spectral_convergence": 0.1612361511841533, "spectral_convergence_status": "ok", "amplitude_floor": 9.929858096613076e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00012203000528970826, "output_power": 0.00012951969247282315, "delta_db": 0.2586917447520572, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0029769778563333666, "output_power": 0.0029336423008852652, "delta_db": -0.06368445051305857, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0005003734805512382, "output_power": 0.0005090324433245129, "delta_db": 0.07451178774795843, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0006045073176565132, "output_power": 0.0005907072964178456, "delta_db": -0.10029227134553068, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7994477693589156e-05, "output_power": 2.6784068901095312e-05, "delta_db": -0.19195815543722863, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.1130460027276325e-05, "output_power": 2.1092984452546128e-05, "delta_db": -0.007709195583474212, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 6.414014484484223e-06, "output_power": 6.741323861485891e-06, "delta_db": 0.2161525533931275, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.13042859411034785, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.042940798074918844, "pitch": null, "output_rms_dbfs": -23.74942837896333, "output_peak": 0.4922653919690344, "reference_rms_dbfs": -23.706487580888414, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.409974853309208}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 123603, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00019691446092710702, "log_rms_mae_db": 0.9391602958669921, "rms_envelope_nrmse": 0.05044643573360221, "envelope_correlation": 0.9974279432805426, "rms_gain_error_db": -0.042940831382124664, "reference_mean_power": 0.004263670396682444, "output_mean_power": 0.004221721118828817}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 2.431988683155927e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000639691813348002, "output_power": 0.000637684279473603, "reference_active": true, "delta_db": -0.013650820719185133}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00010753471412479325, "output_power": 0.00010372139934322024, "reference_active": true, "delta_db": -0.15680317532861898}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.642399701776048e-05, "output_power": 2.0435284492676307e-05, "reference_active": true, "delta_db": -1.116178234872596}], "active_band_count": 3, "active_band_mae_db": 0.42887741030680004}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00017338386226625632, "log_rms_mae_db": 0.6260002844552242, "rms_envelope_nrmse": 0.0261765816797062, "envelope_correlation": 0.9992771723517097, "rms_gain_error_db": -0.04294083701963948, "reference_mean_power": 0.004288676885881949, "output_mean_power": 0.004246481569388233}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 2.255466410477988e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0005603710082458684, "output_power": 0.0005593194555879336, "reference_active": true, "delta_db": -0.008157319648367942}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.355233098915975e-05, "output_power": 5.4921036435388437e-05, "reference_active": true, "delta_db": 0.10960345123550784}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6814737983602464e-06, "output_power": 1.3810762306204035e-06, "reference_active": true, "delta_db": -0.8547245350028849}], "active_band_count": 3, "active_band_mae_db": 0.32416176862892027}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00013036665176469016, "log_rms_mae_db": 0.9188609985452109, "rms_envelope_nrmse": 0.08170706998904544, "envelope_correlation": 0.9939911280858043, "rms_gain_error_db": -0.046275585231035365, "reference_mean_power": 0.0015158717741492514, "output_mean_power": 0.001499805382476592}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.1878952461837722e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003623244921434429, "output_power": 0.00034764185244527505, "reference_active": true, "delta_db": -0.17965636704219584}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.273788700032257e-05, "output_power": 4.738095045832696e-05, "reference_active": true, "delta_db": -0.465189569454879}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.188850333636066e-05, "output_power": 1.432083537673538e-05, "reference_active": true, "delta_db": 0.8084116839531568}], "active_band_count": 3, "active_band_mae_db": 0.4844192068167439}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00011772885872912533, "log_rms_mae_db": 0.6098419277655122, "rms_envelope_nrmse": 0.04775923398827758, "envelope_correlation": 0.9978237702948339, "rms_gain_error_db": -0.046275647308430284, "reference_mean_power": 0.0015247625061786474, "output_mean_power": 0.0015086018620280926}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.1128010899378388e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00031933130970672837, "output_power": 0.0003043669097586898, "reference_active": true, "delta_db": -0.20844067286829143}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.477735373946001e-05, "output_power": 2.3644318248284692e-05, "reference_active": true, "delta_db": -0.2032812493764877}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0783298014452697e-06, "output_power": 1.1250093349178972e-06, "reference_active": true, "delta_db": 0.1840451825104737}], "active_band_count": 3, "active_band_mae_db": 0.19858903491841762}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 8.162582163687071e-05, "log_rms_mae_db": 1.1191340874933735, "rms_envelope_nrmse": 0.096202551181614, "envelope_correlation": 0.9934465362390451, "rms_gain_error_db": -0.16830518478773607, "reference_mean_power": 0.00046194923691890866, "output_mean_power": 0.000444389445413752}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 4.3226252960933766e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021745730779534734, "output_power": 0.00021290776235535273, "reference_active": true, "delta_db": -0.09182511427254114}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.26315917085523e-05, "output_power": 5.695518054965896e-05, "reference_active": true, "delta_db": -0.4126021600278091}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.1826956188918756e-06, "output_power": 2.7624638685559637e-06, "reference_active": true, "delta_db": -4.149908563176071}], "active_band_count": 3, "active_band_mae_db": 1.5514452791588071}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 6.494685964088987e-05, "log_rms_mae_db": 0.6666041696097952, "rms_envelope_nrmse": 0.05348534160985608, "envelope_correlation": 0.9980307304516327, "rms_gain_error_db": -0.16830522528178127, "reference_mean_power": 0.00046465861059889405, "output_mean_power": 0.00044699582517480647}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 3.961591197471977e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00020060895095818542, "output_power": 0.00019481608171073854, "reference_active": true, "delta_db": -0.12725502638504463}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.46199225862701e-05, "output_power": 3.179310678193284e-05, "reference_active": true, "delta_db": -0.369931237205544}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.414804941169707e-07, "output_power": 3.7333936651497566e-07, "reference_active": true, "delta_db": -2.979959444464564}], "active_band_count": 3, "active_band_mae_db": 1.1590485693517174}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 1.8521534194293832e-05, "log_rms_mae_db": 1.5189547295488266, "rms_envelope_nrmse": 0.13497428981539508, "envelope_correlation": 0.9845350250156911, "rms_gain_error_db": -0.2153968105905464, "reference_mean_power": 1.6841903509300322e-05, "output_mean_power": 1.60269725761344e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.2347471453358591e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.252863490142334e-06, "output_power": 5.746033237318544e-06, "reference_active": true, "delta_db": -0.36710813658184177}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.067523918077283e-06, "output_power": 1.7536869777447846e-06, "reference_active": true, "delta_db": -0.7149846529949779}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.652671220760486e-07, "output_power": 2.824656465248921e-07, "reference_active": true, "delta_db": 0.2728221078121271}], "active_band_count": 3, "active_band_mae_db": 0.451638299129649}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 1.4385957620494375e-05, "log_rms_mae_db": 0.9092352522372343, "rms_envelope_nrmse": 0.07806353759197684, "envelope_correlation": 0.9946863946190508, "rms_gain_error_db": -0.21539722823837607, "reference_mean_power": 1.6940674573447337e-05, "output_mean_power": 1.6120962844244677e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.0973267407020894e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.499482122012401e-06, "output_power": 5.069605767991389e-06, "reference_active": true, "delta_db": -0.35347606319302116}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2679437871779227e-06, "output_power": 1.091670621087023e-06, "reference_active": true, "delta_db": -0.6500837724818355}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8893101287704897e-08, "output_power": 1.809293106964624e-08, "reference_active": true, "delta_db": -0.18794324249922295}], "active_band_count": 3, "active_band_mae_db": 0.39716769272469316}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9356666565711913, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "8fc797428b48922f88492ade10762947b6a9e1082be9756ffc277414cd7e8b87", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9933329988091464, "standard_deviation": 0.0017075105474199147, "minimum": 0.9903766974979944, "maximum": 0.9955178946968464, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.100089927833439, "standard_deviation": 0.01683263058129629, "minimum": 1.066755681733455, "maximum": 1.1191340874933735, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8963057772529772, "standard_deviation": 0.40798519414075435, "minimum": 0.17047238290935587, "maximum": 1.5514452791588071, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09708918815958387, "standard_deviation": 0.01191651167631828, "minimum": 0.08054424978600093, "maximum": 0.11624587427142292, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978278869794466, "standard_deviation": 0.0005500069345914335, "minimum": 0.997093003276514, "maximum": 0.9985311153829203, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.680093482329916, "standard_deviation": 0.018010423440909466, "minimum": 0.6456010149161364, "maximum": 0.7028311570849937, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8778094392924067, "standard_deviation": 0.36218926179556693, "minimum": 0.17503139965792033, "maximum": 1.262094792171135, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05682861688231779, "standard_deviation": 0.007287966508565054, "minimum": 0.04963892222462629, "maximum": 0.07044408404763879, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9844939840515791, "standard_deviation": 0.0008251696936891573, "minimum": 0.9830512137496044, "maximum": 0.9857579716254904, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5160955633919366, "standard_deviation": 0.022931978001425456, "minimum": 1.4793621250127085, "maximum": 1.5486052620392237, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5819058114567274, "standard_deviation": 0.1784730613992627, "minimum": 0.3315430793639149, "maximum": 0.8697589138184295, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1388410257356247, "standard_deviation": 0.00359982434772607, "minimum": 0.1332019756878042, "maximum": 0.14344432172208155, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9946690983894724, "standard_deviation": 0.0008313024600232409, "minimum": 0.9934576067200769, "maximum": 0.9959443326335353, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9195358469748605, "standard_deviation": 0.01934019037885047, "minimum": 0.8860506546256895, "maximum": 0.9469267186195427, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.654100906149879, "standard_deviation": 0.26944863036790745, "minimum": 0.37715950714669627, "maximum": 1.0070556493672043, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08575084922159826, "standard_deviation": 0.0042589332716179784, "minimum": 0.07806353759197684, "maximum": 0.0907209027938213, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9947346793968446, "standard_deviation": 0.0006681024860183992, "minimum": 0.9939911280858043, "maximum": 0.9955979506402817, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.9606033066088023, "standard_deviation": 0.03714548663265307, "minimum": 0.9101695454202798, "maximum": 1.0087398572389785, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4515556265946127, "standard_deviation": 0.1481920900218641, "minimum": 0.19524740158449383, "maximum": 0.7316624137220348, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07675190345614737, "standard_deviation": 0.005062990663936925, "minimum": 0.07005524737451797, "maximum": 0.0818086728051294, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9980673926732443, "standard_deviation": 0.0005387536615738269, "minimum": 0.9971811420725044, "maximum": 0.998781397003584, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.6660596004766506, "standard_deviation": 0.04197539421025659, "minimum": 0.6098419277655122, "maximum": 0.7198905959298105, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6376689354571503, "standard_deviation": 0.32250208939935865, "minimum": 0.19858903491841762, "maximum": 1.1697263676860785, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.045275706743713284, "standard_deviation": 0.006719390730128588, "minimum": 0.03581446364471031, "maximum": 0.055854800954529556, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.19982726107773252, "standard_deviation": 0.03765138661036497, "minimum": 0.13042859411034785, "maximum": 0.24557354963724576, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.401813356076322, "standard_deviation": 0.005378278120004117, "minimum": 5.395630665311302, "maximum": 5.409974853309208, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.47191616779059875, "standard_deviation": 0.021618177578230948, "minimum": 0.438219477539873, "maximum": 0.49532978733127814, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.08166354429292436, "standard_deviation": 0.02781105425544054, "minimum": -0.1253778539520704, "maximum": -0.042940798074918844, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9972691960405502, "standard_deviation": 0.00034348648888294834, "minimum": 0.9966494163318693, "maximum": 0.9977097980930592, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9298590525403425, "standard_deviation": 0.0211539903284968, "minimum": 0.9047532321453409, "maximum": 0.9710461353247843, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.45965858371740426, "standard_deviation": 0.18684210851777475, "minimum": 0.20401383572809903, "maximum": 0.745190266661858, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.052455605960002254, "standard_deviation": 0.0034888867062409473, "minimum": 0.04782543324840094, "maximum": 0.058382340524570316, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9991252831635351, "standard_deviation": 0.00018548618679675475, "minimum": 0.9987791430843247, "maximum": 0.9992771723517097, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6112431222869665, "standard_deviation": 0.028937857807359336, "minimum": 0.575948341726759, "maximum": 0.6623056928778522, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6239067864874905, "standard_deviation": 0.1720706962309612, "minimum": 0.32416176862892027, "maximum": 0.8504734549739342, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.02971503361218373, "standard_deviation": 0.0035943322533653656, "minimum": 0.0261765816797062, "maximum": 0.03631474564469833, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 2.7886664867401123, "predicted_mos": 2.7886664867401123, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 123603, "input_sample_rate": 24000, "input_seconds": 5.150125, "input_float32_sha256": "af69d70ff9904417c6722a3f20f21131e6a5099b57a35d4c6400d53115c705bb", "internal_samples": 82402, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.166768499650061}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9453190734496537, "全帯域_10ms_rms_envelope_nrmse": 0.05140549039289565, "全帯域_10ms_envelope_correlation": 0.9973252092133003, "全帯域_10ms_modulation_mae_db": 0.4042507475060126, "全帯域_40ms_log_rms_mae_db": 0.6232103258382695, "全帯域_40ms_rms_envelope_nrmse": 0.027117033642882392, "全帯域_40ms_envelope_correlation": 0.9992181172348634, "全帯域_40ms_modulation_mae_db": 0.3045016013283246, "300–1000 Hz_10ms_log_rms_mae_db": 0.9372790121606477, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08234283429440414, "300–1000 Hz_10ms_envelope_correlation": 0.9938959763254378, "300–1000 Hz_10ms_modulation_mae_db": 0.4461616368296439, "300–1000 Hz_40ms_log_rms_mae_db": 0.6461313392330345, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04907990184859698, "300–1000 Hz_40ms_envelope_correlation": 0.9976920430329003, "300–1000 Hz_40ms_modulation_mae_db": 0.17405517600656165, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1177511260020059, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09610064374888823, "1000–3000 Hz_10ms_envelope_correlation": 0.9934896014774113, "1000–3000 Hz_10ms_modulation_mae_db": 1.5003949805448535, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6746180547265492, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05488095283414144, "1000–3000 Hz_40ms_envelope_correlation": 0.9979564610663885, "1000–3000 Hz_40ms_modulation_mae_db": 1.1131503983922026, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4542200318319092, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1286753905317878, "3000–6000 Hz_10ms_envelope_correlation": 0.9863350508695387, "3000–6000 Hz_10ms_modulation_mae_db": 0.4123863911070747, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8739979231030076, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0748945739681093, "3000–6000 Hz_40ms_envelope_correlation": 0.9956216536278082, "3000–6000 Hz_40ms_modulation_mae_db": 0.5189600237664147, "mr_stft_db": 5.354658796166436, "band_mae_db": 0.12992681225635053, "rms_gain_error_db": -0.03871341736993073, "output_peak": 0.4835707224387603}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9203104511020608, "全帯域_10ms_rms_envelope_nrmse": 0.051315459134784934, "全帯域_10ms_envelope_correlation": 0.9973797545547318, "全帯域_10ms_modulation_mae_db": 0.49685319307454545, "全帯域_40ms_log_rms_mae_db": 0.6181939178489456, "全帯域_40ms_rms_envelope_nrmse": 0.02870941027896185, "全帯域_40ms_envelope_correlation": 0.9991799988756338, "全帯域_40ms_modulation_mae_db": 0.65429443533125, "300–1000 Hz_10ms_log_rms_mae_db": 0.9280324017961905, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07252403212000247, "300–1000 Hz_10ms_envelope_correlation": 0.995309561278347, "300–1000 Hz_10ms_modulation_mae_db": 0.22797870616113847, "300–1000 Hz_40ms_log_rms_mae_db": 0.6650410977530712, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0403701756023836, "300–1000 Hz_40ms_envelope_correlation": 0.9984934282497148, "300–1000 Hz_40ms_modulation_mae_db": 0.48750214413142395, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1010784701919625, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09658243076693267, "1000–3000 Hz_10ms_envelope_correlation": 0.9933155629675948, "1000–3000 Hz_10ms_modulation_mae_db": 0.9383945664196948, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7215249221000273, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05225123100910899, "1000–3000 Hz_40ms_envelope_correlation": 0.9980426899979944, "1000–3000 Hz_40ms_modulation_mae_db": 0.73878115236817, "3000–6000 Hz_10ms_log_rms_mae_db": 1.446728242147153, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1405778993676682, "3000–6000 Hz_10ms_envelope_correlation": 0.9858135508085225, "3000–6000 Hz_10ms_modulation_mae_db": 0.9827182304348505, "3000–6000 Hz_40ms_log_rms_mae_db": 0.911708589467705, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0915358049721515, "3000–6000 Hz_40ms_envelope_correlation": 0.9958494170264006, "3000–6000 Hz_40ms_modulation_mae_db": 1.0646690127729925, "mr_stft_db": 5.347621239992166, "band_mae_db": 0.2245502426875944, "rms_gain_error_db": -0.07704036283450463, "output_peak": 0.44079707599808804}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9100132932835815, "全帯域_10ms_rms_envelope_nrmse": 0.05098679478013098, "全帯域_10ms_envelope_correlation": 0.9973927494639736, "全帯域_10ms_modulation_mae_db": 0.22750984025029405, "全帯域_40ms_log_rms_mae_db": 0.6034187625403465, "全帯域_40ms_rms_envelope_nrmse": 0.02694155694817096, "全帯域_40ms_envelope_correlation": 0.9992603750908708, "全帯域_40ms_modulation_mae_db": 0.4435151722570881, "300–1000 Hz_10ms_log_rms_mae_db": 0.9678515842075316, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07118864713158161, "300–1000 Hz_10ms_envelope_correlation": 0.9954511524720735, "300–1000 Hz_10ms_modulation_mae_db": 0.4198676314802519, "300–1000 Hz_40ms_log_rms_mae_db": 0.6894395753531753, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03577200587869588, "300–1000 Hz_40ms_envelope_correlation": 0.9987854664522946, "300–1000 Hz_40ms_modulation_mae_db": 0.5008659273463265, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0384129120731924, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1046144442960327, "1000–3000 Hz_10ms_envelope_correlation": 0.9920877419036364, "1000–3000 Hz_10ms_modulation_mae_db": 0.9456831537129773, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6615282685310236, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05833834165085575, "1000–3000 Hz_40ms_envelope_correlation": 0.9974579300504544, "1000–3000 Hz_40ms_modulation_mae_db": 1.203527362950063, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4915545298680692, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1374133910047704, "3000–6000 Hz_10ms_envelope_correlation": 0.9851583830511352, "3000–6000 Hz_10ms_modulation_mae_db": 0.4497125573204605, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9155378699145852, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08997939084314299, "3000–6000 Hz_40ms_envelope_correlation": 0.9943368516729733, "3000–6000 Hz_40ms_modulation_mae_db": 0.4572824505018842, "mr_stft_db": 5.34326804311763, "band_mae_db": 0.2638643532708261, "rms_gain_error_db": -0.06237466147748728, "output_peak": 0.47573251982659115}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9270957257735073, "全帯域_10ms_rms_envelope_nrmse": 0.04752785781277997, "全帯域_10ms_envelope_correlation": 0.9977457937471664, "全帯域_10ms_modulation_mae_db": 0.7519471508768207, "全帯域_40ms_log_rms_mae_db": 0.5916595820717261, "全帯域_40ms_rms_envelope_nrmse": 0.026367588148068565, "全帯域_40ms_envelope_correlation": 0.9992943106329527, "全帯域_40ms_modulation_mae_db": 0.8272533020405889, "300–1000 Hz_10ms_log_rms_mae_db": 0.9727645569005828, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08160686402083295, "300–1000 Hz_10ms_envelope_correlation": 0.9940751212156727, "300–1000 Hz_10ms_modulation_mae_db": 0.5313251304388281, "300–1000 Hz_40ms_log_rms_mae_db": 0.6555835402554413, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04400007190556133, "300–1000 Hz_40ms_envelope_correlation": 0.9982249934708769, "300–1000 Hz_40ms_modulation_mae_db": 1.195048756440696, "1000–3000 Hz_10ms_log_rms_mae_db": 1.104839176756073, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08043275125628853, "1000–3000 Hz_10ms_envelope_correlation": 0.9955716577199435, "1000–3000 Hz_10ms_modulation_mae_db": 0.31277318658523584, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6915877247540955, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.051660451941213624, "1000–3000 Hz_40ms_envelope_correlation": 0.9982622448640904, "1000–3000 Hz_40ms_modulation_mae_db": 0.3152360673848513, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4589071507987093, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1400611026621583, "3000–6000 Hz_10ms_envelope_correlation": 0.9849362530940471, "3000–6000 Hz_10ms_modulation_mae_db": 0.9321604436870041, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8763189742439907, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08878876900484893, "3000–6000 Hz_40ms_envelope_correlation": 0.9951094177954725, "3000–6000 Hz_40ms_modulation_mae_db": 0.9504909421803727, "mr_stft_db": 5.347398715343746, "band_mae_db": 0.19898249783637983, "rms_gain_error_db": -0.06167645669537526, "output_peak": 0.4764182077530433}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9536872623220016, "全帯域_10ms_rms_envelope_nrmse": 0.05695045183366121, "全帯域_10ms_envelope_correlation": 0.9968108281057303, "全帯域_10ms_modulation_mae_db": 0.4995501846536006, "全帯域_40ms_log_rms_mae_db": 0.6027775230258862, "全帯域_40ms_rms_envelope_nrmse": 0.03339702941783151, "全帯域_40ms_envelope_correlation": 0.9989251900995655, "全帯域_40ms_modulation_mae_db": 0.6737966041972139, "300–1000 Hz_10ms_log_rms_mae_db": 0.9662683508507531, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07634521535352, "300–1000 Hz_10ms_envelope_correlation": 0.9948799350341931, "300–1000 Hz_10ms_modulation_mae_db": 0.4416524044639735, "300–1000 Hz_40ms_log_rms_mae_db": 0.6585257137745838, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.047857193669248385, "300–1000 Hz_40ms_envelope_correlation": 0.9979513235791045, "300–1000 Hz_40ms_modulation_mae_db": 0.8097969083143383, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0695901448582097, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11291287388104221, "1000–3000 Hz_10ms_envelope_correlation": 0.990956883165232, "1000–3000 Hz_10ms_modulation_mae_db": 0.7927500221899278, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6778793947040737, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06375903945011138, "1000–3000 Hz_40ms_envelope_correlation": 0.9972197688413209, "1000–3000 Hz_40ms_modulation_mae_db": 0.8486160325928452, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4642295678604393, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12690179989697298, "3000–6000 Hz_10ms_envelope_correlation": 0.9880219036396808, "3000–6000 Hz_10ms_modulation_mae_db": 0.9575040737388217, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9161390709795215, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08386409177390537, "3000–6000 Hz_40ms_envelope_correlation": 0.9958313496504536, "3000–6000 Hz_40ms_modulation_mae_db": 1.1075191016400114, "mr_stft_db": 5.354534306374556, "band_mae_db": 0.29403090815268973, "rms_gain_error_db": -0.10305487221510473, "output_peak": 0.4282552780997103}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9184106226930887, "全帯域_10ms_rms_envelope_nrmse": 0.055682781294397285, "全帯域_10ms_envelope_correlation": 0.9970141049248062, "全帯域_10ms_modulation_mae_db": 0.3244872296307722, "全帯域_40ms_log_rms_mae_db": 0.5689021683024363, "全帯域_40ms_rms_envelope_nrmse": 0.03536557943600201, "全帯域_40ms_envelope_correlation": 0.9988413380718995, "全帯域_40ms_modulation_mae_db": 0.5677065192689462, "300–1000 Hz_10ms_log_rms_mae_db": 0.9633496880239746, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08046631027446009, "300–1000 Hz_10ms_envelope_correlation": 0.9943028968830074, "300–1000 Hz_10ms_modulation_mae_db": 0.4225762681726404, "300–1000 Hz_40ms_log_rms_mae_db": 0.6849073186167023, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05425881002751638, "300–1000 Hz_40ms_envelope_correlation": 0.9973400866496164, "300–1000 Hz_40ms_modulation_mae_db": 0.667719193252673, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1080543344420444, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10670385895134041, "1000–3000 Hz_10ms_envelope_correlation": 0.9924712663901436, "1000–3000 Hz_10ms_modulation_mae_db": 0.5361104455260005, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6899741591713825, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07217512532265148, "1000–3000 Hz_40ms_envelope_correlation": 0.9969134208204621, "1000–3000 Hz_40ms_modulation_mae_db": 0.6419704129317448, "3000–6000 Hz_10ms_log_rms_mae_db": 1.487529876857715, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13706322330777282, "3000–6000 Hz_10ms_envelope_correlation": 0.9862978982935974, "3000–6000 Hz_10ms_modulation_mae_db": 0.726215998179572, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8997404325059349, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08640695942586635, "3000–6000 Hz_40ms_envelope_correlation": 0.9962770375677747, "3000–6000 Hz_40ms_modulation_mae_db": 1.0539297523295494, "mr_stft_db": 5.344896065201738, "band_mae_db": 0.22425589865848164, "rms_gain_error_db": -0.12206049129345051, "output_peak": 0.4605711021498379}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9053611612553101, "全帯域_10ms_rms_envelope_nrmse": 0.051182162193633064, "全帯域_10ms_envelope_correlation": 0.9974232091190671, "全帯域_10ms_modulation_mae_db": 0.6300294111027397, "全帯域_40ms_log_rms_mae_db": 0.5789374445317609, "全帯域_40ms_rms_envelope_nrmse": 0.028714066718059227, "全帯域_40ms_envelope_correlation": 0.9992100522932833, "全帯域_40ms_modulation_mae_db": 0.6888492661523252, "300–1000 Hz_10ms_log_rms_mae_db": 0.9893092323508798, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08005046301880113, "300–1000 Hz_10ms_envelope_correlation": 0.9942716536674475, "300–1000 Hz_10ms_modulation_mae_db": 0.7011048892391619, "300–1000 Hz_40ms_log_rms_mae_db": 0.7060058033457983, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04878832196431374, "300–1000 Hz_40ms_envelope_correlation": 0.9977625099510989, "300–1000 Hz_40ms_modulation_mae_db": 0.7564406842029229, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1007459680192497, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09251058516163421, "1000–3000 Hz_10ms_envelope_correlation": 0.9941450433320499, "1000–3000 Hz_10ms_modulation_mae_db": 1.130217155538461, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6708190198413855, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05189979509680987, "1000–3000 Hz_40ms_envelope_correlation": 0.9983812718629694, "1000–3000 Hz_40ms_modulation_mae_db": 1.2196960642862096, "3000–6000 Hz_10ms_log_rms_mae_db": 1.473776221584515, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13948720524981872, "3000–6000 Hz_10ms_envelope_correlation": 0.9845677135912945, "3000–6000 Hz_10ms_modulation_mae_db": 0.538983932885326, "3000–6000 Hz_40ms_log_rms_mae_db": 0.91816936983421, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09090241298070062, "3000–6000 Hz_40ms_envelope_correlation": 0.994081349636563, "3000–6000 Hz_40ms_modulation_mae_db": 0.4290143143979857, "mr_stft_db": 5.338270996586963, "band_mae_db": 0.2771934886414463, "rms_gain_error_db": -0.09000892627139297, "output_peak": 0.5112273953944388}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9545288525152595, "全帯域_10ms_rms_envelope_nrmse": 0.053296452505092975, "全帯域_10ms_envelope_correlation": 0.9971852507210274, "全帯域_10ms_modulation_mae_db": 0.27862031317240593, "全帯域_40ms_log_rms_mae_db": 0.6904487745802522, "全帯域_40ms_rms_envelope_nrmse": 0.029346076955449656, "全帯域_40ms_envelope_correlation": 0.999159597385746, "全帯域_40ms_modulation_mae_db": 0.5821279296992681, "300–1000 Hz_10ms_log_rms_mae_db": 1.0109366719238264, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07199823073866886, "300–1000 Hz_10ms_envelope_correlation": 0.9953513938369386, "300–1000 Hz_10ms_modulation_mae_db": 0.3997189065506735, "300–1000 Hz_40ms_log_rms_mae_db": 0.7360376390269147, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.042129415928231086, "300–1000 Hz_40ms_envelope_correlation": 0.9983110527397053, "300–1000 Hz_40ms_modulation_mae_db": 0.33356194380341525, "1000–3000 Hz_10ms_log_rms_mae_db": 1.05151319515861, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08266128882395257, "1000–3000 Hz_10ms_envelope_correlation": 0.9953818067639486, "1000–3000 Hz_10ms_modulation_mae_db": 0.7872528872476744, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6319963253733665, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0498008690613901, "1000–3000 Hz_40ms_envelope_correlation": 0.998511069683827, "1000–3000 Hz_40ms_modulation_mae_db": 0.7372795802995595, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4763134581083501, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1362087418362323, "3000–6000 Hz_10ms_envelope_correlation": 0.9854350781473814, "3000–6000 Hz_10ms_modulation_mae_db": 0.4088951505421068, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9241527966178658, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09464297871556267, "3000–6000 Hz_40ms_envelope_correlation": 0.993454580908798, "3000–6000 Hz_40ms_modulation_mae_db": 0.3578483253245046, "mr_stft_db": 5.355287922164476, "band_mae_db": 0.19105783185717798, "rms_gain_error_db": -0.08113661812445676, "output_peak": 0.49619347770008526}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 123603, "output_samples": 123603, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.520410206496407, "spectral_convergence": 0.15463854385721998, "spectral_convergence_status": "ok", "amplitude_floor": 1.160899353957536e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.324378075137762, "spectral_convergence": 0.16018269750426525, "spectral_convergence_status": "ok", "amplitude_floor": 1.2404642078999559e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.2191881068651345, "spectral_convergence": 0.16119672500178336, "spectral_convergence_status": "ok", "amplitude_floor": 9.929858096613076e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00012203000528970826, "output_power": 0.00012947441580812543, "delta_db": 0.2571733004933809, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0029769778563333666, "output_power": 0.0029394504830650434, "delta_db": -0.055094556276081244, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0005003734805512382, "output_power": 0.0005118407998720762, "delta_db": 0.09840617104386594, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0006045073176565132, "output_power": 0.0005873504298530469, "delta_db": -0.12504271504382272, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7994477693589156e-05, "output_power": 2.6563152988347166e-05, "delta_db": -0.2279274550212449, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.1130460027276325e-05, "output_power": 2.0509866128115148e-05, "delta_db": -0.12946126445752537, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 6.414014484484223e-06, "output_power": 6.438254776047817e-06, "delta_db": 0.0163822234585327, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.12992681225635053, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.03871341736993073, "pitch": null, "output_rms_dbfs": -23.745200998258348, "output_peak": 0.4835707224387603, "reference_rms_dbfs": -23.706487580888414, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.354658796166436}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 123603, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00019691446092710702, "log_rms_mae_db": 0.9453190734496537, "rms_envelope_nrmse": 0.05140549039289565, "envelope_correlation": 0.9973252092133003, "rms_gain_error_db": -0.03871343635635985, "reference_mean_power": 0.004263670396682444, "output_mean_power": 0.004225832516150769}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 2.431988683155927e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000639691813348002, "output_power": 0.0006375425771568044, "reference_active": true, "delta_db": -0.01461599070744039}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00010753471412479325, "output_power": 0.00010435496027468271, "reference_active": true, "delta_db": -0.1303558780657953}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.642399701776048e-05, "output_power": 2.0664289345889493e-05, "reference_active": true, "delta_db": -1.067780373744802}], "active_band_count": 3, "active_band_mae_db": 0.4042507475060126}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00017338386226625632, "log_rms_mae_db": 0.6232103258382695, "rms_envelope_nrmse": 0.027117033642882392, "envelope_correlation": 0.9992181172348634, "rms_gain_error_db": -0.0387133911917436, "reference_mean_power": 0.004288676885881949, "output_mean_power": 0.004250617129832324}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 2.255466410477988e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0005603710082458684, "output_power": 0.0005588684355962477, "reference_active": true, "delta_db": -0.011660764924137153}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.355233098915975e-05, "output_power": 5.529064703128911e-05, "reference_active": true, "delta_db": 0.13873292988824387}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6814737983602464e-06, "output_power": 1.4105191714877502e-06, "reference_active": true, "delta_db": -0.7631111091725927}], "active_band_count": 3, "active_band_mae_db": 0.3045016013283246}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00013036665176469016, "log_rms_mae_db": 0.9372790121606477, "rms_envelope_nrmse": 0.08234283429440414, "envelope_correlation": 0.9938959763254378, "rms_gain_error_db": -0.029693737051688457, "reference_mean_power": 0.0015158717741492514, "output_mean_power": 0.001505542752860364}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.1878952461837722e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003623244921434429, "output_power": 0.0003488246632574448, "reference_active": true, "delta_db": -0.1649050849304181}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.273788700032257e-05, "output_power": 4.864800932195514e-05, "reference_active": true, "delta_db": -0.35057651710139937}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.188850333636066e-05, "output_power": 1.4369032095419808e-05, "reference_active": true, "delta_db": 0.8230033084571141}], "active_band_count": 3, "active_band_mae_db": 0.4461616368296439}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00011772885872912533, "log_rms_mae_db": 0.6461313392330345, "rms_envelope_nrmse": 0.04907990184859698, "envelope_correlation": 0.9976920430329003, "rms_gain_error_db": -0.029693778766894705, "reference_mean_power": 0.0015247625061786474, "output_mean_power": 0.0015143728896522151}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.1128010899378388e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00031933130970672837, "output_power": 0.0003048969932506403, "reference_active": true, "delta_db": -0.20088360630147672}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.477735373946001e-05, "output_power": 2.4293909891575492e-05, "reference_active": true, "delta_db": -0.08557504864238058}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0783298014452697e-06, "output_power": 1.1384718459974448e-06, "reference_active": true, "delta_db": 0.23570687307582766}], "active_band_count": 3, "active_band_mae_db": 0.17405517600656165}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 8.162582163687071e-05, "log_rms_mae_db": 1.1177511260020059, "rms_envelope_nrmse": 0.09610064374888823, "envelope_correlation": 0.9934896014774113, "rms_gain_error_db": -0.1831732924212731, "reference_mean_power": 0.00046194923691890866, "output_mean_power": 0.0004428706757027727}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 4.3226252960933766e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021745730779534734, "output_power": 0.00021281518289511283, "reference_active": true, "delta_db": -0.09371398353843978}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.26315917085523e-05, "output_power": 5.682692856236098e-05, "reference_active": true, "delta_db": -0.4223926542276845}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.1826956188918756e-06, "output_power": 2.8693242735621174e-06, "reference_active": true, "delta_db": -3.9850783038684363}], "active_band_count": 3, "active_band_mae_db": 1.5003949805448535}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 6.494685964088987e-05, "log_rms_mae_db": 0.6746180547265492, "rms_envelope_nrmse": 0.05488095283414144, "envelope_correlation": 0.9979564610663885, "rms_gain_error_db": -0.1831732998746553, "reference_mean_power": 0.00046465861059889405, "output_mean_power": 0.00044546815114666037}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 3.961591197471977e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00020060895095818542, "output_power": 0.0001947248960187375, "reference_active": true, "delta_db": -0.12928826272483857}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.46199225862701e-05, "output_power": 3.15755221347941e-05, "reference_active": true, "delta_db": -0.39975551605793813}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.414804941169707e-07, "output_power": 3.882030909755245e-07, "reference_active": true, "delta_db": -2.810407416393831}], "active_band_count": 3, "active_band_mae_db": 1.1131503983922026}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 1.8521534194293832e-05, "log_rms_mae_db": 1.4542200318319092, "rms_envelope_nrmse": 0.1286753905317878, "envelope_correlation": 0.9863350508695387, "rms_gain_error_db": -0.2946291240428153, "reference_mean_power": 1.6841903509300322e-05, "output_mean_power": 1.573722892628188e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.2347471453358591e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.252863490142334e-06, "output_power": 5.774346339978655e-06, "reference_active": true, "delta_db": -0.3457611854244035}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.067523918077283e-06, "output_power": 1.7493136071392758e-06, "reference_active": true, "delta_db": -0.7258286803485131}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.652671220760486e-07, "output_power": 2.5534449243724666e-07, "reference_active": true, "delta_db": -0.16556930754830754}], "active_band_count": 3, "active_band_mae_db": 0.4123863911070747}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 1.4385957620494375e-05, "log_rms_mae_db": 0.8739979231030076, "rms_envelope_nrmse": 0.0748945739681093, "envelope_correlation": 0.9956216536278082, "rms_gain_error_db": -0.2946294068752887, "reference_mean_power": 1.6940674573447337e-05, "output_mean_power": 1.582952048256289e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.0973267407020894e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.499482122012401e-06, "output_power": 5.126869289782936e-06, "reference_active": true, "delta_db": -0.30469549373634625}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2679437871779227e-06, "output_power": 1.0722948967515512e-06, "reference_active": true, "delta_db": -0.7278576092242345}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8893101287704897e-08, "output_power": 1.674443724079962e-08, "reference_active": true, "delta_db": -0.5243269683386633}], "active_band_count": 3, "active_band_mae_db": 0.5189600237664147}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9340072355373221, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "9d8f3ece0baeac29bfc54caada7b68e9408b651e8c00a0600e7299f6855a2404", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.993427445464995, "standard_deviation": 0.0015928978164489837, "minimum": 0.990956883165232, "maximum": 0.9955716577199435, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.0864981659376682, "standard_deviation": 0.029314586140113022, "minimum": 1.0384129120731924, "maximum": 1.1177511260020059, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8679470497206032, "standard_deviation": 0.3606108783481714, "minimum": 0.31277318658523584, "maximum": 1.5003949805448535, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09656485961076394, "standard_deviation": 0.01137076350508473, "minimum": 0.08043275125628853, "maximum": 0.11291287388104221, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978431071484384, "standard_deviation": 0.0005813018355676356, "minimum": 0.9969134208204621, "maximum": 0.998511069683827, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.677490983650238, "standard_deviation": 0.025831949781952395, "minimum": 0.6319963253733665, "maximum": 0.7215249221000273, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8522821339007058, "standard_deviation": 0.312864520330075, "minimum": 0.3152360673848513, "maximum": 1.2196960642862096, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05684572579578533, "standard_deviation": 0.007662164134777668, "minimum": 0.0498008690613901, "maximum": 0.07217512532265148, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9858207289368996, "standard_deviation": 0.0010874092947271109, "minimum": 0.9845677135912945, "maximum": 0.9880219036396808, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.4691573848821076, "standard_deviation": 0.0158891932760852, "minimum": 1.446728242147153, "maximum": 1.4915545298680692, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6760720972369021, "standard_deviation": 0.25418692193264103, "minimum": 0.4088951505421068, "maximum": 0.9827182304348505, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.13579859423214768, "standard_deviation": 0.005194566442875691, "minimum": 0.12690179989697298, "maximum": 0.1405778993676682, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9950702072357804, "standard_deviation": 0.001005305488479932, "minimum": 0.993454580908798, "maximum": 0.9962770375677747, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9044706283333526, "standard_deviation": 0.01938166984941553, "minimum": 0.8739979231030076, "maximum": 0.9241527966178658, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7424642403642144, "standard_deviation": 0.3283791117448957, "minimum": 0.3578483253245046, "maximum": 1.1075191016400114, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08762687271053596, "standard_deviation": 0.006093053932725452, "minimum": 0.0748945739681093, "maximum": 0.09464297871556267, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9946922113391397, "standard_deviation": 0.0006290695237849518, "minimum": 0.9938959763254378, "maximum": 0.9954511524720735, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.9669739372767984, "standard_deviation": 0.026397385643133348, "minimum": 0.9280324017961905, "maximum": 1.0109366719238264, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.448798196667039, "standard_deviation": 0.13267681838106068, "minimum": 0.22797870616113847, "maximum": 0.7011048892391619, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.0770653246190339, "standard_deviation": 0.004633852405410471, "minimum": 0.07118864713158161, "maximum": 0.08234283429440414, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.998070113015664, "standard_deviation": 0.0004717099919088197, "minimum": 0.9973400866496164, "maximum": 0.9987854664522946, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.6802090034198403, "standard_deviation": 0.03013664145833799, "minimum": 0.6461313392330345, "maximum": 0.7360376390269147, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6156238416872948, "standard_deviation": 0.31625172376007565, "minimum": 0.17405517600656165, "maximum": 1.195048756440696, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.045281987103068425, "standard_deviation": 0.005856391208891495, "minimum": 0.03577200587869588, "maximum": 0.05425881002751638, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.22548275417011832, "standard_deviation": 0.05327375160789064, "minimum": 0.12992681225635053, "maximum": 0.29403090815268973, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.348242010618463, "standard_deviation": 0.006174444098786957, "minimum": 5.338270996586963, "maximum": 5.355287922164476, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.47159572242006936, "standard_deviation": 0.027536941779557268, "minimum": 0.4282552780997103, "maximum": 0.5112273953944388, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07950822578521285, "standard_deviation": 0.026076519230449915, "minimum": -0.12206049129345051, "maximum": -0.03871341736993073, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9972846124812254, "standard_deviation": 0.0002832993459356442, "minimum": 0.9968108281057303, "maximum": 0.9977457937471664, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.929340805299308, "standard_deviation": 0.019409590284924064, "minimum": 0.9053611612553101, "maximum": 0.9545288525152595, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4516560087833989, "standard_deviation": 0.17925659670526603, "minimum": 0.22750984025029405, "maximum": 0.7519471508768207, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05229343124342201, "standard_deviation": 0.002965982431016489, "minimum": 0.04752785781277997, "maximum": 0.05695045183366121, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9991361224606019, "standard_deviation": 0.00016323405011935761, "minimum": 0.9988413380718995, "maximum": 0.9992943106329527, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6096935623424529, "standard_deviation": 0.037414032909769974, "minimum": 0.5689021683024363, "maximum": 0.6904487745802522, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5927556037843756, "standard_deviation": 0.16065994006717607, "minimum": 0.3045016013283246, "maximum": 0.8272533020405889, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.02949479269317827, "standard_deviation": 0.0032269893648986595, "minimum": 0.026367588148068565, "maximum": 0.03536557943600201, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 2.5022644996643066, "predicted_mos": 2.5022644996643066, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 123603, "input_sample_rate": 24000, "input_seconds": 5.150125, "input_float32_sha256": "9995cf3397625685e52dddc5e09c2cbea1c2f76a89dbb42712eb8fc498febf69", "internal_samples": 82402, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.188576400279999}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8879673483852615, "全帯域_10ms_rms_envelope_nrmse": 0.051912744017204054, "全帯域_10ms_envelope_correlation": 0.9973069132836085, "全帯域_10ms_modulation_mae_db": 0.3532720108367056, "全帯域_40ms_log_rms_mae_db": 0.5625751198546887, "全帯域_40ms_rms_envelope_nrmse": 0.02790368155055087, "全帯域_40ms_envelope_correlation": 0.9992153389626779, "全帯域_40ms_modulation_mae_db": 0.26614595234609983, "300–1000 Hz_10ms_log_rms_mae_db": 1.0294141179552874, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07174708222964656, "300–1000 Hz_10ms_envelope_correlation": 0.9954243059668844, "300–1000 Hz_10ms_modulation_mae_db": 0.2787117762526697, "300–1000 Hz_40ms_log_rms_mae_db": 0.7238034904674601, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03879158617391739, "300–1000 Hz_40ms_envelope_correlation": 0.9986202313754509, "300–1000 Hz_40ms_modulation_mae_db": 0.673482258089949, "1000–3000 Hz_10ms_log_rms_mae_db": 1.280157516036112, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10007703721747582, "1000–3000 Hz_10ms_envelope_correlation": 0.9930557699625504, "1000–3000 Hz_10ms_modulation_mae_db": 0.5128636214419664, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7981079111984393, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05781592845508249, "1000–3000 Hz_40ms_envelope_correlation": 0.9978419969538663, "1000–3000 Hz_40ms_modulation_mae_db": 0.778158410460147, "3000–6000 Hz_10ms_log_rms_mae_db": 1.901022646178256, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17965193949553335, "3000–6000 Hz_10ms_envelope_correlation": 0.9727032785609125, "3000–6000 Hz_10ms_modulation_mae_db": 0.8679414229277537, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1822439313676139, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10710289933069216, "3000–6000 Hz_40ms_envelope_correlation": 0.9905493880136367, "3000–6000 Hz_40ms_modulation_mae_db": 0.7068202104995235, "mr_stft_db": 5.648746415783361, "band_mae_db": 0.20717625544110393, "rms_gain_error_db": -0.06807277069880668, "output_peak": 0.4548305970342536}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8812645295212232, "全帯域_10ms_rms_envelope_nrmse": 0.046059875396349675, "全帯域_10ms_envelope_correlation": 0.998057415473142, "全帯域_10ms_modulation_mae_db": 0.47236879257394904, "全帯域_40ms_log_rms_mae_db": 0.5636923013874725, "全帯域_40ms_rms_envelope_nrmse": 0.028034263279690323, "全帯域_40ms_envelope_correlation": 0.9993916315571401, "全帯域_40ms_modulation_mae_db": 0.7727129308655009, "300–1000 Hz_10ms_log_rms_mae_db": 1.0101529529338513, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06356017585410559, "300–1000 Hz_10ms_envelope_correlation": 0.9964956255824595, "300–1000 Hz_10ms_modulation_mae_db": 0.4514117373018635, "300–1000 Hz_40ms_log_rms_mae_db": 0.7195906098113509, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03468866469797418, "300–1000 Hz_40ms_envelope_correlation": 0.9989875780088031, "300–1000 Hz_40ms_modulation_mae_db": 0.8201246249704021, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2406415307359437, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11697381717562357, "1000–3000 Hz_10ms_envelope_correlation": 0.990394518242079, "1000–3000 Hz_10ms_modulation_mae_db": 0.90357108271323, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7514857495705344, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06680115469865244, "1000–3000 Hz_40ms_envelope_correlation": 0.9970563236511528, "1000–3000 Hz_40ms_modulation_mae_db": 1.0435687936436706, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8735087635544776, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16356787574221102, "3000–6000 Hz_10ms_envelope_correlation": 0.9770822256837646, "3000–6000 Hz_10ms_modulation_mae_db": 0.548053064109035, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1381028091882548, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08904235003081355, "3000–6000 Hz_40ms_envelope_correlation": 0.9930447627682379, "3000–6000 Hz_40ms_modulation_mae_db": 0.8741146372131846, "mr_stft_db": 5.639090232126691, "band_mae_db": 0.22787541839194908, "rms_gain_error_db": -0.13422211786023447, "output_peak": 0.43781785969973974}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8954175363261163, "全帯域_10ms_rms_envelope_nrmse": 0.05411624074939069, "全帯域_10ms_envelope_correlation": 0.9970504829991522, "全帯域_10ms_modulation_mae_db": 0.5141341133844993, "全帯域_40ms_log_rms_mae_db": 0.5746873602826706, "全帯域_40ms_rms_envelope_nrmse": 0.02799345340241826, "全帯域_40ms_envelope_correlation": 0.9991908649016052, "全帯域_40ms_modulation_mae_db": 0.3389535772939715, "300–1000 Hz_10ms_log_rms_mae_db": 1.0086227865874868, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06783299409891576, "300–1000 Hz_10ms_envelope_correlation": 0.99586895583722, "300–1000 Hz_10ms_modulation_mae_db": 0.555093102827345, "300–1000 Hz_40ms_log_rms_mae_db": 0.7322792935047364, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03600818356133227, "300–1000 Hz_40ms_envelope_correlation": 0.9987602354908932, "300–1000 Hz_40ms_modulation_mae_db": 0.7382967439131108, "1000–3000 Hz_10ms_log_rms_mae_db": 1.314781299793113, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10207132164409007, "1000–3000 Hz_10ms_envelope_correlation": 0.9929470336502791, "1000–3000 Hz_10ms_modulation_mae_db": 1.3520762557048833, "1000–3000 Hz_40ms_log_rms_mae_db": 0.833052752522741, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06285389543099737, "1000–3000 Hz_40ms_envelope_correlation": 0.9975665502490686, "1000–3000 Hz_40ms_modulation_mae_db": 1.5218737597394985, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8582486484698573, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16340617334874746, "3000–6000 Hz_10ms_envelope_correlation": 0.977400598634092, "3000–6000 Hz_10ms_modulation_mae_db": 0.5633439426605352, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1281708964259254, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08642458909502808, "3000–6000 Hz_40ms_envelope_correlation": 0.9939894668669199, "3000–6000 Hz_40ms_modulation_mae_db": 0.911313138335419, "mr_stft_db": 5.6562789515344045, "band_mae_db": 0.2267362772314084, "rms_gain_error_db": -0.05865493248278283, "output_peak": 0.44654067259335023}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9009163531283892, "全帯域_10ms_rms_envelope_nrmse": 0.04656913671798033, "全帯域_10ms_envelope_correlation": 0.997919711844793, "全帯域_10ms_modulation_mae_db": 0.32108185569341746, "全帯域_40ms_log_rms_mae_db": 0.5616086058791324, "全帯域_40ms_rms_envelope_nrmse": 0.023667936896394594, "全帯域_40ms_envelope_correlation": 0.9995406713346567, "全帯域_40ms_modulation_mae_db": 0.6396320706164995, "300–1000 Hz_10ms_log_rms_mae_db": 1.0329518215753495, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06850144972469176, "300–1000 Hz_10ms_envelope_correlation": 0.9957807322995859, "300–1000 Hz_10ms_modulation_mae_db": 0.28113413694923256, "300–1000 Hz_40ms_log_rms_mae_db": 0.7313341395893961, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03430677933481357, "300–1000 Hz_40ms_envelope_correlation": 0.998867164026945, "300–1000 Hz_40ms_modulation_mae_db": 0.8853548127606912, "1000–3000 Hz_10ms_log_rms_mae_db": 1.293122734016407, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09719423354903542, "1000–3000 Hz_10ms_envelope_correlation": 0.9933429795961884, "1000–3000 Hz_10ms_modulation_mae_db": 0.5132681879606958, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8299161365620245, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.053141217279299276, "1000–3000 Hz_40ms_envelope_correlation": 0.998113949089351, "1000–3000 Hz_40ms_modulation_mae_db": 0.41801787354721115, "3000–6000 Hz_10ms_log_rms_mae_db": 1.9248331999703843, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18588803881217741, "3000–6000 Hz_10ms_envelope_correlation": 0.9703533713545223, "3000–6000 Hz_10ms_modulation_mae_db": 0.6277697254979757, "3000–6000 Hz_40ms_log_rms_mae_db": 1.193095479028393, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10293356302354252, "3000–6000 Hz_40ms_envelope_correlation": 0.9909130028411546, "3000–6000 Hz_40ms_modulation_mae_db": 0.6416511936808381, "mr_stft_db": 5.645083682636237, "band_mae_db": 0.18354491114287588, "rms_gain_error_db": -0.10429918272961794, "output_peak": 0.49075955300555124}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9132469858821508, "全帯域_10ms_rms_envelope_nrmse": 0.0480650283747901, "全帯域_10ms_envelope_correlation": 0.9977495963600509, "全帯域_10ms_modulation_mae_db": 0.6579824992401613, "全帯域_40ms_log_rms_mae_db": 0.5827214761389926, "全帯域_40ms_rms_envelope_nrmse": 0.026462324521538967, "全帯域_40ms_envelope_correlation": 0.9993508317142274, "全帯域_40ms_modulation_mae_db": 0.6639222742513898, "300–1000 Hz_10ms_log_rms_mae_db": 0.9966274152901051, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06316290014406561, "300–1000 Hz_10ms_envelope_correlation": 0.9964312425051205, "300–1000 Hz_10ms_modulation_mae_db": 0.43710788259598116, "300–1000 Hz_40ms_log_rms_mae_db": 0.7209726440389541, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03069527690373303, "300–1000 Hz_40ms_envelope_correlation": 0.9991066301565016, "300–1000 Hz_40ms_modulation_mae_db": 0.6658808496597776, "1000–3000 Hz_10ms_log_rms_mae_db": 1.298376052121487, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10238339341336544, "1000–3000 Hz_10ms_envelope_correlation": 0.9933746221217283, "1000–3000 Hz_10ms_modulation_mae_db": 1.0676848083873067, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8105053544918367, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07235815024686876, "1000–3000 Hz_40ms_envelope_correlation": 0.9971153817394067, "1000–3000 Hz_40ms_modulation_mae_db": 1.1097476208688477, "3000–6000 Hz_10ms_log_rms_mae_db": 1.903274635439276, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17583834245680716, "3000–6000 Hz_10ms_envelope_correlation": 0.973473009312026, "3000–6000 Hz_10ms_modulation_mae_db": 0.7892328310430684, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1535447550911846, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09619245684109891, "3000–6000 Hz_40ms_envelope_correlation": 0.9919716500128535, "3000–6000 Hz_40ms_modulation_mae_db": 0.6553203872024108, "mr_stft_db": 5.645934275955514, "band_mae_db": 0.17833035801415728, "rms_gain_error_db": -0.08782377395388825, "output_peak": 0.4965482252549252}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8894167799612109, "全帯域_10ms_rms_envelope_nrmse": 0.048503653472801604, "全帯域_10ms_envelope_correlation": 0.9976252766844376, "全帯域_10ms_modulation_mae_db": 0.6770956366426732, "全帯域_40ms_log_rms_mae_db": 0.5523055993881423, "全帯域_40ms_rms_envelope_nrmse": 0.023814018853254036, "全帯域_40ms_envelope_correlation": 0.9994127807569343, "全帯域_40ms_modulation_mae_db": 0.7808007280189608, "300–1000 Hz_10ms_log_rms_mae_db": 1.0607728512492465, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07756594306344931, "300–1000 Hz_10ms_envelope_correlation": 0.9946397596016101, "300–1000 Hz_10ms_modulation_mae_db": 0.4647027681868378, "300–1000 Hz_40ms_log_rms_mae_db": 0.7747766143931998, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04312352097960366, "300–1000 Hz_40ms_envelope_correlation": 0.9982867738763376, "300–1000 Hz_40ms_modulation_mae_db": 1.0148787566912227, "1000–3000 Hz_10ms_log_rms_mae_db": 1.260928365337199, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10188713162174493, "1000–3000 Hz_10ms_envelope_correlation": 0.9927384025223007, "1000–3000 Hz_10ms_modulation_mae_db": 1.1819443746875753, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7804233320677362, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.059531536293450635, "1000–3000 Hz_40ms_envelope_correlation": 0.9976224918786174, "1000–3000 Hz_40ms_modulation_mae_db": 1.2077971320489742, "3000–6000 Hz_10ms_log_rms_mae_db": 1.9244907334415486, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17524276274959671, "3000–6000 Hz_10ms_envelope_correlation": 0.9737939218479519, "3000–6000 Hz_10ms_modulation_mae_db": 0.5271830169052812, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2077869346696595, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10637409331625482, "3000–6000 Hz_40ms_envelope_correlation": 0.9901589565971163, "3000–6000 Hz_40ms_modulation_mae_db": 0.6969956281321421, "mr_stft_db": 5.660560081676752, "band_mae_db": 0.24519960535967705, "rms_gain_error_db": -0.046616135652429586, "output_peak": 0.4678901260042874}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9119204532507234, "全帯域_10ms_rms_envelope_nrmse": 0.05589062128381858, "全帯域_10ms_envelope_correlation": 0.9971023575521373, "全帯域_10ms_modulation_mae_db": 0.3541460041002609, "全帯域_40ms_log_rms_mae_db": 0.5657819296928841, "全帯域_40ms_rms_envelope_nrmse": 0.03776509822436142, "全帯域_40ms_envelope_correlation": 0.9987737892685855, "全帯域_40ms_modulation_mae_db": 0.6604674667774945, "300–1000 Hz_10ms_log_rms_mae_db": 1.0643335247204437, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08472436697866233, "300–1000 Hz_10ms_envelope_correlation": 0.9937231688286834, "300–1000 Hz_10ms_modulation_mae_db": 0.2962815093138061, "300–1000 Hz_40ms_log_rms_mae_db": 0.7705822777653323, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.057811365194055477, "300–1000 Hz_40ms_envelope_correlation": 0.9970134568766204, "300–1000 Hz_40ms_modulation_mae_db": 0.8945605267587124, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2970164227659133, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09237007096724116, "1000–3000 Hz_10ms_envelope_correlation": 0.9941105567702744, "1000–3000 Hz_10ms_modulation_mae_db": 0.8552891992379962, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7855019367939862, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.054010270209604104, "1000–3000 Hz_40ms_envelope_correlation": 0.9981358238079755, "1000–3000 Hz_40ms_modulation_mae_db": 1.055913201255844, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8861257398275726, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18136414895935118, "3000–6000 Hz_10ms_envelope_correlation": 0.9716097188686743, "3000–6000 Hz_10ms_modulation_mae_db": 0.9551296454867529, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1324216944044219, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1066353404645136, "3000–6000 Hz_40ms_envelope_correlation": 0.9896450274990157, "3000–6000 Hz_40ms_modulation_mae_db": 0.5594779642774794, "mr_stft_db": 5.642089313996718, "band_mae_db": 0.1936400741358953, "rms_gain_error_db": -0.15091483194511554, "output_peak": 0.4314398564447021}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9590551223729232, "全帯域_10ms_rms_envelope_nrmse": 0.05870283975739894, "全帯域_10ms_envelope_correlation": 0.9966983707647769, "全帯域_10ms_modulation_mae_db": 0.5738206937354627, "全帯域_40ms_log_rms_mae_db": 0.6133643229152228, "全帯域_40ms_rms_envelope_nrmse": 0.03731824355313548, "全帯域_40ms_envelope_correlation": 0.9987294801280281, "全帯域_40ms_modulation_mae_db": 0.6330753335237108, "300–1000 Hz_10ms_log_rms_mae_db": 1.0875486907949, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08424867885544349, "300–1000 Hz_10ms_envelope_correlation": 0.993929260744021, "300–1000 Hz_10ms_modulation_mae_db": 0.9646768768616761, "300–1000 Hz_40ms_log_rms_mae_db": 0.8347849429163972, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.058268301091559865, "300–1000 Hz_40ms_envelope_correlation": 0.997108842308382, "300–1000 Hz_40ms_modulation_mae_db": 1.3795193053503445, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2634868214008943, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08519439803297126, "1000–3000 Hz_10ms_envelope_correlation": 0.9951303541306505, "1000–3000 Hz_10ms_modulation_mae_db": 0.7210490089915801, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7738006089996385, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04888557806651758, "1000–3000 Hz_40ms_envelope_correlation": 0.9986188608487343, "1000–3000 Hz_40ms_modulation_mae_db": 0.7890689215021401, "3000–6000 Hz_10ms_log_rms_mae_db": 1.9030674314295797, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17589318512024263, "3000–6000 Hz_10ms_envelope_correlation": 0.9735287970578423, "3000–6000 Hz_10ms_modulation_mae_db": 0.5750884743569504, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2023207455640152, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10343280689472338, "3000–6000 Hz_40ms_envelope_correlation": 0.9906783874784598, "3000–6000 Hz_40ms_modulation_mae_db": 0.8601285051327455, "mr_stft_db": 5.6492244019668005, "band_mae_db": 0.2893121107517286, "rms_gain_error_db": -0.13589185634089312, "output_peak": 0.4726805731546282}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 123603, "output_samples": 123603, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.862595273104077, "spectral_convergence": 0.15234824367092173, "spectral_convergence_status": "ok", "amplitude_floor": 1.160899353957536e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.673001493719967, "spectral_convergence": 0.15354523293072456, "spectral_convergence_status": "ok", "amplitude_floor": 1.2404642078999559e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.410642480526039, "spectral_convergence": 0.1507851167201982, "spectral_convergence_status": "ok", "amplitude_floor": 9.929858096613076e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00012203000528970826, "output_power": 0.00012693466508249772, "delta_db": 0.17113611368355364, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0029769778563333666, "output_power": 0.0029462067689098688, "delta_db": -0.0451238127421468, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0005003734805512382, "output_power": 0.0004945893644726386, "delta_db": -0.05049511159255702, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0006045073176565132, "output_power": 0.000575070017432455, "delta_db": -0.21680837162578032, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7994477693589156e-05, "output_power": 2.455107156736582e-05, "delta_db": -0.5700191677648356, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.1130460027276325e-05, "output_power": 1.938547362981905e-05, "delta_db": -0.3743253585520856, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 6.414014484484223e-06, "output_power": 6.447072017455096e-06, "delta_db": 0.022325852126768662, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.20717625544110393, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.06807277069880668, "pitch": null, "output_rms_dbfs": -23.774560351587223, "output_peak": 0.4548305970342536, "reference_rms_dbfs": -23.706487580888414, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.648746415783361}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 123603, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00019691446092710702, "log_rms_mae_db": 0.8879673483852615, "rms_envelope_nrmse": 0.051912744017204054, "envelope_correlation": 0.9973069132836085, "rms_gain_error_db": -0.06807269841119967, "reference_mean_power": 0.004263670396682444, "output_mean_power": 0.0041973613032774285}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 2.431988683155927e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000639691813348002, "output_power": 0.0006172266192552354, "reference_active": true, "delta_db": -0.1552614503686612}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00010753471412479325, "output_power": 9.619677006149974e-05, "reference_active": true, "delta_db": -0.48388194645223864}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.642399701776048e-05, "output_power": 2.911157988526903e-05, "reference_active": true, "delta_db": 0.42067263568921714}], "active_band_count": 3, "active_band_mae_db": 0.3532720108367056}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00017338386226625632, "log_rms_mae_db": 0.5625751198546887, "rms_envelope_nrmse": 0.02790368155055087, "envelope_correlation": 0.9992153389626779, "rms_gain_error_db": -0.06807265497051199, "reference_mean_power": 0.004288676885881949, "output_mean_power": 0.004221978930905575}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 2.255466410477988e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0005603710082458684, "output_power": 0.0005433559536290931, "reference_active": true, "delta_db": -0.13391228176324838}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.355233098915975e-05, "output_power": 4.75014357002135e-05, "reference_active": true, "delta_db": -0.5207164315840451}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6814737983602464e-06, "output_power": 1.7380850284848002e-06, "reference_active": true, "delta_db": 0.14380914369100609}], "active_band_count": 3, "active_band_mae_db": 0.26614595234609983}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00013036665176469016, "log_rms_mae_db": 1.0294141179552874, "rms_envelope_nrmse": 0.07174708222964656, "envelope_correlation": 0.9954243059668844, "rms_gain_error_db": -0.05056156731334813, "reference_mean_power": 0.0015158717741492514, "output_mean_power": 0.001498325978893565}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.1878952461837722e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003623244921434429, "output_power": 0.00033966750601066516, "reference_active": true, "delta_db": -0.28043689681997463}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.273788700032257e-05, "output_power": 4.991525378905215e-05, "reference_active": true, "delta_db": -0.23889441753444007}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.188850333636066e-05, "output_power": 1.2788145986684345e-05, "reference_active": true, "delta_db": 0.31680401440359446}], "active_band_count": 3, "active_band_mae_db": 0.2787117762526697}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00011772885872912533, "log_rms_mae_db": 0.7238034904674601, "rms_envelope_nrmse": 0.03879158617391739, "envelope_correlation": 0.9986202313754509, "rms_gain_error_db": -0.050561599006643865, "reference_mean_power": 0.0015247625061786474, "output_mean_power": 0.001507113792167779}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.1128010899378388e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00031933130970672837, "output_power": 0.00030048656805743484, "reference_active": true, "delta_db": -0.2641643868030859}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.477735373946001e-05, "output_power": 2.3054954507087763e-05, "reference_active": true, "delta_db": -0.31290651589806734}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0783298014452697e-06, "output_power": 7.734175464957309e-07, "reference_active": true, "delta_db": -1.443375871568694}], "active_band_count": 3, "active_band_mae_db": 0.673482258089949}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 8.162582163687071e-05, "log_rms_mae_db": 1.280157516036112, "rms_envelope_nrmse": 0.10007703721747582, "envelope_correlation": 0.9930557699625504, "rms_gain_error_db": -0.21312484861692946, "reference_mean_power": 0.00046194923691890866, "output_mean_power": 0.0004398268814802124}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 4.3226252960933766e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021745730779534734, "output_power": 0.00020506599484161926, "reference_active": true, "delta_db": -0.2548035773106467}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.26315917085523e-05, "output_power": 5.082890700553299e-05, "reference_active": true, "delta_db": -0.9068267793330859}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.1826956188918756e-06, "output_power": 6.58554030317079e-06, "reference_active": true, "delta_db": -0.37696050768216666}], "active_band_count": 3, "active_band_mae_db": 0.5128636214419664}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 6.494685964088987e-05, "log_rms_mae_db": 0.7981079111984393, "rms_envelope_nrmse": 0.05781592845508249, "envelope_correlation": 0.9978419969538663, "rms_gain_error_db": -0.21312485674005455, "reference_mean_power": 0.00046465861059889405, "output_mean_power": 0.0004424065047351924}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 3.961591197471977e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00020060895095818542, "output_power": 0.0001885086880795296, "reference_active": true, "delta_db": -0.2701893589786416}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.46199225862701e-05, "output_power": 2.8869820471299392e-05, "reference_active": true, "delta_db": -0.7888200921007442}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.414804941169707e-07, "output_power": 5.527810578395691e-07, "reference_active": true, "delta_db": -1.275465780301055}], "active_band_count": 3, "active_band_mae_db": 0.778158410460147}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 1.8521534194293832e-05, "log_rms_mae_db": 1.901022646178256, "rms_envelope_nrmse": 0.17965193949553335, "envelope_correlation": 0.9727032785609125, "rms_gain_error_db": -0.3520449399515135, "reference_mean_power": 1.6841903509300322e-05, "output_mean_power": 1.5530544447549648e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.2347471453358591e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.252863490142334e-06, "output_power": 5.356978872233445e-06, "reference_active": true, "delta_db": -0.6715901392003092}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.067523918077283e-06, "output_power": 1.5096432350233952e-06, "reference_active": true, "delta_db": -1.3657621717842523}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.652671220760486e-07, "output_power": 3.0222516368395793e-07, "reference_active": true, "delta_db": 0.5664719577986995}], "active_band_count": 3, "active_band_mae_db": 0.8679414229277537}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 1.4385957620494375e-05, "log_rms_mae_db": 1.1822439313676139, "rms_envelope_nrmse": 0.10710289933069216, "envelope_correlation": 0.9905493880136367, "rms_gain_error_db": -0.3520454969237122, "reference_mean_power": 1.6940674573447337e-05, "output_mean_power": 1.5621622909040123e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.0973267407020894e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.499482122012401e-06, "output_power": 4.648630802789772e-06, "reference_active": true, "delta_db": -0.7299673895020429}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2679437871779227e-06, "output_power": 9.721044123475013e-07, "reference_active": true, "delta_db": -1.1538708564663305}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8893101287704897e-08, "output_power": 1.995103779852935e-08, "reference_active": true, "delta_db": 0.236622385530197}], "active_band_count": 3, "active_band_mae_db": 0.7068202104995235}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9166000551542496, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "438c50fe280d3a4ffcc230a553b1c5e3d33f8026b0f37f8f0f7476bd50870a83", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9931367796245063, "standard_deviation": 0.0013492292311937791, "minimum": 0.990394518242079, "maximum": 0.9951303541306505, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.2810638427758838, "standard_deviation": 0.02445303088820888, "minimum": 1.2406415307359437, "maximum": 1.314781299793113, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8884683173906542, "standard_deviation": 0.30340714378284167, "minimum": 0.5128636214419664, "maximum": 1.3520762557048833, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09976892545269346, "standard_deviation": 0.009153574133913767, "minimum": 0.08519439803297126, "maximum": 0.11697381717562357, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9977589222772716, "standard_deviation": 0.0005315615881443954, "minimum": 0.9970563236511528, "maximum": 0.9986188608487343, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7953492227758672, "standard_deviation": 0.028187749787121866, "minimum": 0.7514857495705344, "maximum": 0.833052752522741, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.9905182141332917, "standard_deviation": 0.3304305648832842, "minimum": 0.41801787354721115, "maximum": 1.5218737597394985, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05942471633505908, "standard_deviation": 0.007708218773064386, "minimum": 0.04888557806651758, "maximum": 0.07235815024686876, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9737431151649732, "standard_deviation": 0.002442812142539033, "minimum": 0.9703533713545223, "maximum": 0.977400598634092, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.8968214747888692, "standard_deviation": 0.02328179516124528, "minimum": 1.8582486484698573, "maximum": 1.9248331999703843, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6817177653734191, "standard_deviation": 0.16519797457549326, "minimum": 0.5271830169052812, "maximum": 0.9551296454867529, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17510655833558336, "standard_deviation": 0.007993491081969291, "minimum": 0.16340617334874746, "maximum": 0.18588803881217741, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9913688302596744, "standard_deviation": 0.001503859005383988, "minimum": 0.9896450274990157, "maximum": 0.9939894668669199, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.1672109057174336, "standard_deviation": 0.032827633135662754, "minimum": 1.1281708964259254, "maximum": 1.2077869346696595, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7382277080592179, "standard_deviation": 0.1276839072627609, "minimum": 0.5594779642774794, "maximum": 0.911313138335419, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09976726237458339, "standard_deviation": 0.008228208165907079, "minimum": 0.08642458909502808, "maximum": 0.10710289933069216, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9952866314206981, "standard_deviation": 0.0010743308006037383, "minimum": 0.9937231688286834, "maximum": 0.9964956255824595, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0363030201383339, "standard_deviation": 0.03183318809975979, "minimum": 0.9966274152901051, "maximum": 1.0875486907949, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4661399737861765, "standard_deviation": 0.22542719400234051, "minimum": 0.2787117762526697, "maximum": 0.9646768768616761, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07266794886862256, "standard_deviation": 0.008605171621536963, "minimum": 0.06316290014406561, "maximum": 0.08472436697866233, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9983438640149918, "standard_deviation": 0.0008296546589999628, "minimum": 0.9970134568766204, "maximum": 0.9991066301565016, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7510155015608534, "standard_deviation": 0.04023814941384645, "minimum": 0.7195906098113509, "maximum": 0.8347849429163972, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8840122347742763, "standard_deviation": 0.2329884042936133, "minimum": 0.6658808496597776, "maximum": 1.3795193053503445, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.041711709742123675, "standard_deviation": 0.010703057739423377, "minimum": 0.03069527690373303, "maximum": 0.058268301091559865, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.21897687630859944, "standard_deviation": 0.03676730084329356, "minimum": 0.17833035801415728, "maximum": 0.2893121107517286, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.64837591945956, "standard_deviation": 0.007114519949600554, "minimum": 5.639090232126691, "maximum": 5.660560081676752, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.46231343289892973, "standard_deviation": 0.02383803530230624, "minimum": 0.4314398564447021, "maximum": 0.4965482252549252, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.09831195020797105, "standard_deviation": 0.0392323585868935, "minimum": -0.15091483194511554, "maximum": -0.046616135652429586, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9974387656202623, "standard_deviation": 0.0004743329752824016, "minimum": 0.9966983707647769, "maximum": 0.998057415473142, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9049006386034998, "standard_deviation": 0.024618816935365294, "minimum": 0.8812645295212232, "maximum": 0.9590551223729232, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4904877007758912, "standard_deviation": 0.13980824050223617, "minimum": 0.32108185569341746, "maximum": 0.6770956366426732, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.051227517471216746, "standard_deviation": 0.004663919967910549, "minimum": 0.046059875396349675, "maximum": 0.05870283975739894, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9992006735779819, "standard_deviation": 0.00029860750878529476, "minimum": 0.9987294801280281, "maximum": 0.9995406713346567, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5720920894424008, "standard_deviation": 0.018994256387389965, "minimum": 0.5523055993881423, "maximum": 0.6133643229152228, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5944637917117035, "standard_deviation": 0.18984364741927073, "minimum": 0.26614595234609983, "maximum": 0.7808007280189608, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.029119877535167992, "standard_deviation": 0.005487882099191137, "minimum": 0.023667936896394594, "maximum": 0.03776509822436142, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 2.1297214031219482, "predicted_mos": 2.1297214031219482, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 123603, "input_sample_rate": 24000, "input_seconds": 5.150125, "input_float32_sha256": "ee017b18eb84906e4bc3974dd165ba11d6f891a05230130cc3b351c95896fcd3", "internal_samples": 82402, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.352894600015134}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9453689543627033, "全帯域_10ms_rms_envelope_nrmse": 0.05146429478798835, "全帯域_10ms_envelope_correlation": 0.9973203022881211, "全帯域_10ms_modulation_mae_db": 0.2826798285046091, "全帯域_40ms_log_rms_mae_db": 0.6253129820287937, "全帯域_40ms_rms_envelope_nrmse": 0.027231044255383856, "全帯域_40ms_envelope_correlation": 0.9992168121409618, "全帯域_40ms_modulation_mae_db": 0.3294299926344321, "300–1000 Hz_10ms_log_rms_mae_db": 0.9716841377242538, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0715487759915713, "300–1000 Hz_10ms_envelope_correlation": 0.9954348015778278, "300–1000 Hz_10ms_modulation_mae_db": 0.4331524653469269, "300–1000 Hz_40ms_log_rms_mae_db": 0.7004409984071094, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043817452961182446, "300–1000 Hz_40ms_envelope_correlation": 0.998172867845889, "300–1000 Hz_40ms_modulation_mae_db": 0.7025078941933726, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0132727075974672, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0874570366224741, "1000–3000 Hz_10ms_envelope_correlation": 0.9946615900928504, "1000–3000 Hz_10ms_modulation_mae_db": 0.47438956070699784, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6467732267986884, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05380901399533268, "1000–3000 Hz_40ms_envelope_correlation": 0.9980452395313592, "1000–3000 Hz_40ms_modulation_mae_db": 0.7126398009904555, "3000–6000 Hz_10ms_log_rms_mae_db": 1.466846615671246, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13010866474487878, "3000–6000 Hz_10ms_envelope_correlation": 0.9881286686574376, "3000–6000 Hz_10ms_modulation_mae_db": 1.016022222013677, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9311953551538141, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08969845108631129, "3000–6000 Hz_40ms_envelope_correlation": 0.9958141700019122, "3000–6000 Hz_40ms_modulation_mae_db": 1.2352002492547616, "mr_stft_db": 5.354102828020093, "band_mae_db": 0.20962475297308503, "rms_gain_error_db": -0.043934182407403585, "output_peak": 0.48314041431471766}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9650975996553254, "全帯域_10ms_rms_envelope_nrmse": 0.05606864773526522, "全帯域_10ms_envelope_correlation": 0.9968213281486106, "全帯域_10ms_modulation_mae_db": 0.3596580242380609, "全帯域_40ms_log_rms_mae_db": 0.6246061665569351, "全帯域_40ms_rms_envelope_nrmse": 0.03247327909694413, "全帯域_40ms_envelope_correlation": 0.9988834370754619, "全帯域_40ms_modulation_mae_db": 0.5318231711897774, "300–1000 Hz_10ms_log_rms_mae_db": 0.9392729745921808, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0661673090722026, "300–1000 Hz_10ms_envelope_correlation": 0.9961012197746062, "300–1000 Hz_10ms_modulation_mae_db": 0.5955321098162435, "300–1000 Hz_40ms_log_rms_mae_db": 0.69764039609278, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03449987117889465, "300–1000 Hz_40ms_envelope_correlation": 0.9988805294916, "300–1000 Hz_40ms_modulation_mae_db": 0.9234854191782919, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0905657509604223, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07974797940219691, "1000–3000 Hz_10ms_envelope_correlation": 0.9954990561521918, "1000–3000 Hz_10ms_modulation_mae_db": 0.19370748023337014, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6537224622488867, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04891466673209322, "1000–3000 Hz_40ms_envelope_correlation": 0.9983045352162502, "1000–3000 Hz_40ms_modulation_mae_db": 0.22847426733033216, "3000–6000 Hz_10ms_log_rms_mae_db": 1.398488895357961, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13773088129136876, "3000–6000 Hz_10ms_envelope_correlation": 0.9841257674413781, "3000–6000 Hz_10ms_modulation_mae_db": 0.28234445731254854, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8313516826606018, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07263720290572377, "3000–6000 Hz_40ms_envelope_correlation": 0.9958480430950893, "3000–6000 Hz_40ms_modulation_mae_db": 0.5668598325737423, "mr_stft_db": 5.354985246030592, "band_mae_db": 0.16333834736752156, "rms_gain_error_db": -0.05203596259693731, "output_peak": 0.47949919930356677}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9453116372445047, "全帯域_10ms_rms_envelope_nrmse": 0.05535356015411395, "全帯域_10ms_envelope_correlation": 0.9969059038312648, "全帯域_10ms_modulation_mae_db": 0.7632487133859046, "全帯域_40ms_log_rms_mae_db": 0.5959354499602197, "全帯域_40ms_rms_envelope_nrmse": 0.031497964118920654, "全帯域_40ms_envelope_correlation": 0.9989598215249549, "全帯域_40ms_modulation_mae_db": 0.8579992082776081, "300–1000 Hz_10ms_log_rms_mae_db": 0.9869419288874914, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08026196711940908, "300–1000 Hz_10ms_envelope_correlation": 0.9942694804959478, "300–1000 Hz_10ms_modulation_mae_db": 0.9324830862373804, "300–1000 Hz_40ms_log_rms_mae_db": 0.7534203434847451, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04908184867183139, "300–1000 Hz_40ms_envelope_correlation": 0.9977323295735561, "300–1000 Hz_40ms_modulation_mae_db": 1.1057069968781377, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0095423079625534, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08895864284388726, "1000–3000 Hz_10ms_envelope_correlation": 0.9946598112139643, "1000–3000 Hz_10ms_modulation_mae_db": 0.37596895765067107, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6373848989104388, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.053806805668684225, "1000–3000 Hz_40ms_envelope_correlation": 0.9982789493926802, "1000–3000 Hz_40ms_modulation_mae_db": 0.5748725893325156, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4397196844519393, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14422793416289642, "3000–6000 Hz_10ms_envelope_correlation": 0.9837022214016181, "3000–6000 Hz_10ms_modulation_mae_db": 0.5809381230213323, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8773227157441649, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09067554043809935, "3000–6000 Hz_40ms_envelope_correlation": 0.9945972781206704, "3000–6000 Hz_40ms_modulation_mae_db": 0.8730559937353806, "mr_stft_db": 5.336499329274878, "band_mae_db": 0.30479914737585895, "rms_gain_error_db": -0.054548406469083585, "output_peak": 0.44697873306902003}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8991003453250496, "全帯域_10ms_rms_envelope_nrmse": 0.051726268515124414, "全帯域_10ms_envelope_correlation": 0.9972835447746443, "全帯域_10ms_modulation_mae_db": 0.7848166792667522, "全帯域_40ms_log_rms_mae_db": 0.5641203520511843, "全帯域_40ms_rms_envelope_nrmse": 0.02891450278234509, "全帯域_40ms_envelope_correlation": 0.9991031497085737, "全帯域_40ms_modulation_mae_db": 0.7457976716022481, "300–1000 Hz_10ms_log_rms_mae_db": 0.9541288783963117, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0704798690070207, "300–1000 Hz_10ms_envelope_correlation": 0.995532947511664, "300–1000 Hz_10ms_modulation_mae_db": 0.8297010295065564, "300–1000 Hz_40ms_log_rms_mae_db": 0.6961257221911495, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03909413992264583, "300–1000 Hz_40ms_envelope_correlation": 0.9985231404333981, "300–1000 Hz_40ms_modulation_mae_db": 0.7697150437340694, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0217288944514475, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08301722582136323, "1000–3000 Hz_10ms_envelope_correlation": 0.9950581177350402, "1000–3000 Hz_10ms_modulation_mae_db": 0.4770320775990089, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6192937598820214, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04115566313919641, "1000–3000 Hz_40ms_envelope_correlation": 0.9987835463345869, "1000–3000 Hz_40ms_modulation_mae_db": 0.5503724407739325, "3000–6000 Hz_10ms_log_rms_mae_db": 1.423706983556167, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12906457523012438, "3000–6000 Hz_10ms_envelope_correlation": 0.9863582319966371, "3000–6000 Hz_10ms_modulation_mae_db": 0.6408736262335489, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8506374199452422, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0774387341998181, "3000–6000 Hz_40ms_envelope_correlation": 0.995396184781197, "3000–6000 Hz_40ms_modulation_mae_db": 0.8666610652961962, "mr_stft_db": 5.348596765567673, "band_mae_db": 0.23983758121498008, "rms_gain_error_db": -0.02912190664798963, "output_peak": 0.4683589884526604}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9537774923139176, "全帯域_10ms_rms_envelope_nrmse": 0.052089650889651264, "全帯域_10ms_envelope_correlation": 0.9973995352326874, "全帯域_10ms_modulation_mae_db": 0.4890961731360319, "全帯域_40ms_log_rms_mae_db": 0.6213559850470858, "全帯域_40ms_rms_envelope_nrmse": 0.030785348541439505, "全帯域_40ms_envelope_correlation": 0.9991603615792803, "全帯域_40ms_modulation_mae_db": 0.6878528146196151, "300–1000 Hz_10ms_log_rms_mae_db": 0.8975454493736428, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07477990713006892, "300–1000 Hz_10ms_envelope_correlation": 0.995116699724113, "300–1000 Hz_10ms_modulation_mae_db": 0.37845378325429646, "300–1000 Hz_40ms_log_rms_mae_db": 0.6614239989908235, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04345272543642497, "300–1000 Hz_40ms_envelope_correlation": 0.9983819083418302, "300–1000 Hz_40ms_modulation_mae_db": 0.9321088883347165, "1000–3000 Hz_10ms_log_rms_mae_db": 1.065836318079239, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09771454929863675, "1000–3000 Hz_10ms_envelope_correlation": 0.9937316491459279, "1000–3000 Hz_10ms_modulation_mae_db": 1.1957927959919739, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6698055184271173, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06695474605814208, "1000–3000 Hz_40ms_envelope_correlation": 0.9973381560913478, "1000–3000 Hz_40ms_modulation_mae_db": 1.3605093433857194, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4170970163634322, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12456683725412601, "3000–6000 Hz_10ms_envelope_correlation": 0.9870069068235418, "3000–6000 Hz_10ms_modulation_mae_db": 0.33372409102504214, "3000–6000 Hz_40ms_log_rms_mae_db": 0.908408372706123, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07694690438190814, "3000–6000 Hz_40ms_envelope_correlation": 0.9949871197825721, "3000–6000 Hz_40ms_modulation_mae_db": 0.5036758802758654, "mr_stft_db": 5.338970702417552, "band_mae_db": 0.16423911643334768, "rms_gain_error_db": -0.11462398091702235, "output_peak": 0.44190422368864996}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9213486126868374, "全帯域_10ms_rms_envelope_nrmse": 0.046424406063442475, "全帯域_10ms_envelope_correlation": 0.9978146772841672, "全帯域_10ms_modulation_mae_db": 0.3745862025148794, "全帯域_40ms_log_rms_mae_db": 0.6319717322461859, "全帯域_40ms_rms_envelope_nrmse": 0.025787550378527358, "全帯域_40ms_envelope_correlation": 0.9992867203190152, "全帯域_40ms_modulation_mae_db": 0.41443409539637127, "300–1000 Hz_10ms_log_rms_mae_db": 0.9883869951986252, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06972473837748153, "300–1000 Hz_10ms_envelope_correlation": 0.9956479385079035, "300–1000 Hz_10ms_modulation_mae_db": 0.47062804441413747, "300–1000 Hz_40ms_log_rms_mae_db": 0.7068625047394782, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04010458651224977, "300–1000 Hz_40ms_envelope_correlation": 0.9984704264984924, "300–1000 Hz_40ms_modulation_mae_db": 0.7824179056635133, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0299137104605827, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08687211803413206, "1000–3000 Hz_10ms_envelope_correlation": 0.9945421164541287, "1000–3000 Hz_10ms_modulation_mae_db": 0.6332205393178953, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6356734526308258, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04829308943856437, "1000–3000 Hz_40ms_envelope_correlation": 0.9982383487246498, "1000–3000 Hz_40ms_modulation_mae_db": 0.42574637401439636, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4389707198251558, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13187660124734854, "3000–6000 Hz_10ms_envelope_correlation": 0.9858477948033109, "3000–6000 Hz_10ms_modulation_mae_db": 0.9372770343161987, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8957136324495966, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08024351922899331, "3000–6000 Hz_40ms_envelope_correlation": 0.9951490811112457, "3000–6000 Hz_40ms_modulation_mae_db": 0.9842001900739316, "mr_stft_db": 5.347768037598879, "band_mae_db": 0.16215329141286866, "rms_gain_error_db": -0.030442390653827988, "output_peak": 0.4915273552639932}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9097015641164377, "全帯域_10ms_rms_envelope_nrmse": 0.04905723805169439, "全帯域_10ms_envelope_correlation": 0.9977461719430887, "全帯域_10ms_modulation_mae_db": 0.3842129215044525, "全帯域_40ms_log_rms_mae_db": 0.5629243491599606, "全帯域_40ms_rms_envelope_nrmse": 0.03140831475519063, "全帯域_40ms_envelope_correlation": 0.9991494234772115, "全帯域_40ms_modulation_mae_db": 0.5741800690573358, "300–1000 Hz_10ms_log_rms_mae_db": 0.9211926254569832, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0795935903564953, "300–1000 Hz_10ms_envelope_correlation": 0.9946290752499849, "300–1000 Hz_10ms_modulation_mae_db": 0.4210801764786581, "300–1000 Hz_40ms_log_rms_mae_db": 0.7191158008690149, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05696076985742319, "300–1000 Hz_40ms_envelope_correlation": 0.9972698072852089, "300–1000 Hz_40ms_modulation_mae_db": 0.9414370541269156, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0055218076001136, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08252674444163065, "1000–3000 Hz_10ms_envelope_correlation": 0.995210500941596, "1000–3000 Hz_10ms_modulation_mae_db": 0.25956613264329637, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6100026366189589, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.044245655186762704, "1000–3000 Hz_40ms_envelope_correlation": 0.9987038034650637, "1000–3000 Hz_40ms_modulation_mae_db": 0.33717312267244876, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4138807452020248, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12625393681330238, "3000–6000 Hz_10ms_envelope_correlation": 0.9870994977047467, "3000–6000 Hz_10ms_modulation_mae_db": 0.4888115828586502, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8209683100446769, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0721118327369076, "3000–6000 Hz_40ms_envelope_correlation": 0.9963021131007095, "3000–6000 Hz_40ms_modulation_mae_db": 0.5214270516634731, "mr_stft_db": 5.333914367473295, "band_mae_db": 0.1769336943371734, "rms_gain_error_db": -0.12632509628159708, "output_peak": 0.47189857700683563}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9678122544520695, "全帯域_10ms_rms_envelope_nrmse": 0.052032292744922104, "全帯域_10ms_envelope_correlation": 0.9972820557620694, "全帯域_10ms_modulation_mae_db": 0.35316271895308654, "全帯域_40ms_log_rms_mae_db": 0.6021725433815444, "全帯域_40ms_rms_envelope_nrmse": 0.028048899720560044, "全帯域_40ms_envelope_correlation": 0.9991925099597833, "全帯域_40ms_modulation_mae_db": 0.31487363770907445, "300–1000 Hz_10ms_log_rms_mae_db": 0.9484501819662097, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07026616639205258, "300–1000 Hz_10ms_envelope_correlation": 0.9955741131815944, "300–1000 Hz_10ms_modulation_mae_db": 0.35437130400884165, "300–1000 Hz_40ms_log_rms_mae_db": 0.7128085923752487, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03841974740411524, "300–1000 Hz_40ms_envelope_correlation": 0.9985872701875792, "300–1000 Hz_40ms_modulation_mae_db": 0.46979823780266655, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0410664766081614, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09229968087157941, "1000–3000 Hz_10ms_envelope_correlation": 0.9940661038715632, "1000–3000 Hz_10ms_modulation_mae_db": 0.42803825772388765, "1000–3000 Hz_40ms_log_rms_mae_db": 0.639918849170321, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.058266010697911, "1000–3000 Hz_40ms_envelope_correlation": 0.9977145705636017, "1000–3000 Hz_40ms_modulation_mae_db": 0.4833059504077359, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3762931068812359, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1346978010371498, "3000–6000 Hz_10ms_envelope_correlation": 0.9854768351227725, "3000–6000 Hz_10ms_modulation_mae_db": 0.653675725562075, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8435656308496032, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0874103814509583, "3000–6000 Hz_40ms_envelope_correlation": 0.9943561641062022, "3000–6000 Hz_40ms_modulation_mae_db": 0.6238319620302701, "mr_stft_db": 5.340997187234836, "band_mae_db": 0.21237594007135566, "rms_gain_error_db": -0.061817690331787904, "output_peak": 0.46998566129140673}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 123603, "output_samples": 123603, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.453048446348433, "spectral_convergence": 0.15402094224386198, "spectral_convergence_status": "ok", "amplitude_floor": 1.160899353957536e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.340121446539936, "spectral_convergence": 0.1625945558552367, "spectral_convergence_status": "ok", "amplitude_floor": 1.2404642078999559e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.26913859117191, "spectral_convergence": 0.1642590881597439, "spectral_convergence_status": "ok", "amplitude_floor": 9.929858096613076e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00012203000528970826, "output_power": 0.00013019173363785914, "delta_db": 0.2811678002257516, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0029769778563333666, "output_power": 0.0029350238642618627, "delta_db": -0.06163967459616167, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0005003734805512382, "output_power": 0.0005211972983371616, "delta_db": 0.17707871526577784, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0006045073176565132, "output_power": 0.0005779887263954527, "delta_db": -0.19482194793343718, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7994477693589156e-05, "output_power": 2.7025364622092606e-05, "delta_db": -0.15300806966224598, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.1130460027276325e-05, "output_power": 1.8873698665835046e-05, "delta_db": -0.49051935200535124, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 6.414014484484223e-06, "output_power": 6.2548394295729115e-06, "delta_db": -0.10913771112286963, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.20962475297308503, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.043934182407403585, "pitch": null, "output_rms_dbfs": -23.75042176329582, "output_peak": 0.48314041431471766, "reference_rms_dbfs": -23.706487580888414, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.354102828020093}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 123603, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00019691446092710702, "log_rms_mae_db": 0.9453689543627033, "rms_envelope_nrmse": 0.05146429478798835, "envelope_correlation": 0.9973203022881211, "rms_gain_error_db": -0.0439342295532156, "reference_mean_power": 0.004263670396682444, "output_mean_power": 0.00422075555960521}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 2.431988683155927e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000639691813348002, "output_power": 0.0006390324875734458, "reference_active": true, "delta_db": -0.004478550549719044}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00010753471412479325, "output_power": 0.00012354875988370226, "reference_active": true, "delta_db": 0.6028970564958848}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.642399701776048e-05, "output_power": 2.79296118083391e-05, "reference_active": true, "delta_db": 0.24066387846822343}], "active_band_count": 3, "active_band_mae_db": 0.2826798285046091}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00017338386226625632, "log_rms_mae_db": 0.6253129820287937, "rms_envelope_nrmse": 0.027231044255383856, "envelope_correlation": 0.9992168121409618, "rms_gain_error_db": -0.04393424084331587, "reference_mean_power": 0.004288676885881949, "output_mean_power": 0.004245510341621157}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 2.255466410477988e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0005603710082458684, "output_power": 0.0005677102748173027, "reference_active": true, "delta_db": 0.05651096235683295}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.355233098915975e-05, "output_power": 5.9184229711986325e-05, "reference_active": true, "delta_db": 0.43427620351638896}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6814737983602464e-06, "output_power": 1.4994770498755484e-06, "reference_active": true, "delta_db": -0.4975028120300744}], "active_band_count": 3, "active_band_mae_db": 0.3294299926344321}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00013036665176469016, "log_rms_mae_db": 0.9716841377242538, "rms_envelope_nrmse": 0.0715487759915713, "envelope_correlation": 0.9954348015778278, "rms_gain_error_db": 0.03854725131565799, "reference_mean_power": 0.0015158717741492514, "output_mean_power": 0.0015293862858471844}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.1878952461837722e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003623244921434429, "output_power": 0.0003612802379206308, "reference_active": true, "delta_db": -0.012534858954384432}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.273788700032257e-05, "output_power": 5.7699668586061376e-05, "reference_active": true, "delta_db": 0.39050593338439754}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.188850333636066e-05, "output_power": 9.671314886439952e-06, "reference_active": true, "delta_db": -0.8964166037019987}], "active_band_count": 3, "active_band_mae_db": 0.4331524653469269}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00011772885872912533, "log_rms_mae_db": 0.7004409984071094, "rms_envelope_nrmse": 0.043817452961182446, "envelope_correlation": 0.998172867845889, "rms_gain_error_db": 0.03854724772439997, "reference_mean_power": 0.0015247625061786474, "output_mean_power": 0.0015383562805000636}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.1128010899378388e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00031933130970672837, "output_power": 0.00032060645413869537, "reference_active": true, "delta_db": 0.01730758691415119}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.477735373946001e-05, "output_power": 2.6515554836505647e-05, "reference_active": true, "delta_db": 0.29445797957760583}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0783298014452697e-06, "output_power": 7.131416412877598e-07, "reference_active": true, "delta_db": -1.7957581160883607}], "active_band_count": 3, "active_band_mae_db": 0.7025078941933726}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 8.162582163687071e-05, "log_rms_mae_db": 1.0132727075974672, "rms_envelope_nrmse": 0.0874570366224741, "envelope_correlation": 0.9946615900928504, "rms_gain_error_db": -0.181469832144814, "reference_mean_power": 0.00046194923691890866, "output_mean_power": 0.0004430444196964065}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 4.3226252960933766e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021745730779534734, "output_power": 0.0002081705537444299, "reference_active": true, "delta_db": -0.18954709540044803}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.26315917085523e-05, "output_power": 5.6949692149436906e-05, "reference_active": true, "delta_db": -0.4130206815319869}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.1826956188918756e-06, "output_power": 5.94603378083205e-06, "reference_active": true, "delta_db": -0.8206009051885587}], "active_band_count": 3, "active_band_mae_db": 0.47438956070699784}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 6.494685964088987e-05, "log_rms_mae_db": 0.6467732267986884, "rms_envelope_nrmse": 0.05380901399533268, "envelope_correlation": 0.9980452395313592, "rms_gain_error_db": -0.181469826186588, "reference_mean_power": 0.00046465861059889405, "output_mean_power": 0.0004456429155402963}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 3.961591197471977e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00020060895095818542, "output_power": 0.00019188588987994857, "reference_active": true, "delta_db": -0.19307266337368292}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.46199225862701e-05, "output_power": 3.161984717247498e-05, "reference_active": true, "delta_db": -0.39366325877936814}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.414804941169707e-07, "output_power": 5.187777993982116e-07, "reference_active": true, "delta_db": -1.5511834808183158}], "active_band_count": 3, "active_band_mae_db": 0.7126398009904555}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 1.8521534194293832e-05, "log_rms_mae_db": 1.466846615671246, "rms_envelope_nrmse": 0.13010866474487878, "envelope_correlation": 0.9881286686574376, "rms_gain_error_db": -0.5506699226229608, "reference_mean_power": 1.6841903509300322e-05, "output_mean_power": 1.483625135799954e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.2347471453358591e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.252863490142334e-06, "output_power": 5.42124224371642e-06, "reference_active": true, "delta_db": -0.6198013364849889}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.067523918077283e-06, "output_power": 1.6293885399448833e-06, "reference_active": true, "delta_db": -1.034258849324477}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.652671220760486e-07, "output_power": 1.9243442994301868e-07, "reference_active": true, "delta_db": -1.3940064802315648}], "active_band_count": 3, "active_band_mae_db": 1.016022222013677}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 1.4385957620494375e-05, "log_rms_mae_db": 0.9311953551538141, "rms_envelope_nrmse": 0.08969845108631129, "envelope_correlation": 0.9958141700019122, "rms_gain_error_db": -0.5506701704216237, "reference_mean_power": 1.6940674573447337e-05, "output_mean_power": 1.4923259218666866e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.0973267407020894e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.499482122012401e-06, "output_power": 4.749490548864446e-06, "reference_active": true, "delta_db": -0.6367476676246004}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2679437871779227e-06, "output_power": 1.005680659587161e-06, "reference_active": true, "delta_db": -1.0063990180980806}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8893101287704897e-08, "output_power": 1.175054058041876e-08, "reference_active": true, "delta_db": -2.0624540620416036}], "active_band_count": 3, "active_band_mae_db": 1.2352002492547616}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.929028434460391, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "5d75a71179e0e2bfe80a736096cf271e44c50e10b88e528f24bc48321bf4f817", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9946786182009079, "standard_deviation": 0.0005844702313076005, "minimum": 0.9937316491459279, "maximum": 0.9954990561521918, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.0346809967149984, "standard_deviation": 0.029917851708812022, "minimum": 1.0055218076001136, "maximum": 1.0905657509604223, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5047144752333876, "standard_deviation": 0.31054483940134153, "minimum": 0.19370748023337014, "maximum": 1.1957927959919739, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08732424716698756, "standard_deviation": 0.005788818291350914, "minimum": 0.07974797940219691, "maximum": 0.09771454929863675, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9981758936649424, "standard_deviation": 0.0004796865105582526, "minimum": 0.9973381560913478, "maximum": 0.9987835463345869, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6390718505859072, "standard_deviation": 0.018783786132915953, "minimum": 0.6100026366189589, "maximum": 0.6698055184271173, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.584136736113442, "standard_deviation": 0.3470764607562345, "minimum": 0.22847426733033216, "maximum": 1.3605093433857194, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05193070636458584, "standard_deviation": 0.008197525392667314, "minimum": 0.04115566313919641, "maximum": 0.06695474605814208, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9859682404939303, "standard_deviation": 0.0015101395263091028, "minimum": 0.9837022214016181, "maximum": 0.9881286686574376, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.4218754709136454, "standard_deviation": 0.02764017491575018, "minimum": 1.3762931068812359, "maximum": 1.466846615671246, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6167083577928841, "standard_deviation": 0.2601326016043659, "minimum": 0.28234445731254854, "maximum": 1.016022222013677, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.13231590397264936, "standard_deviation": 0.006428990007054444, "minimum": 0.12456683725412601, "maximum": 0.14422793416289642, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9953062692624498, "standard_deviation": 0.0006636699427131087, "minimum": 0.9943561641062022, "maximum": 0.9963021131007095, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8698953899442278, "standard_deviation": 0.0394720236037856, "minimum": 0.8209683100446769, "maximum": 0.9311953551538141, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7718640281129526, "standard_deviation": 0.2611997501241348, "minimum": 0.5036758802758654, "maximum": 1.2352002492547616, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08089532080358998, "standard_deviation": 0.0074536933934635325, "minimum": 0.0721118327369076, "maximum": 0.09067554043809935, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9952882845029551, "standard_deviation": 0.0005922354519697005, "minimum": 0.9942694804959478, "maximum": 0.9961012197746062, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.9509503964494623, "standard_deviation": 0.03166139304801683, "minimum": 0.8975454493736428, "maximum": 0.9883869951986252, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5519252498828802, "standard_deviation": 0.21740080274917153, "minimum": 0.35437130400884165, "maximum": 0.9324830862373804, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07285279043078774, "standard_deviation": 0.0049648804606136155, "minimum": 0.0661673090722026, "maximum": 0.08026196711940908, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9982522849571942, "standard_deviation": 0.0005191449009054594, "minimum": 0.9972698072852089, "maximum": 0.9988805294916, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7059797946437937, "standard_deviation": 0.025782379064461975, "minimum": 0.6614239989908235, "maximum": 0.7534203434847451, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8283971799889605, "standard_deviation": 0.19253038341539047, "minimum": 0.46979823780266655, "maximum": 1.1057069968781377, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.043178892743095935, "standard_deviation": 0.007064794133707509, "minimum": 0.03449987117889465, "maximum": 0.05696076985742319, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.20416273389827388, "standard_deviation": 0.049662306023740395, "minimum": 0.16215329141286866, "maximum": 0.30479914737585895, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.344479307952224, "standard_deviation": 0.008004677203701781, "minimum": 5.333914367473295, "maximum": 5.354985246030592, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.4691616440488563, "standard_deviation": 0.01709786399198848, "minimum": 0.44190422368864996, "maximum": 0.4915273552639932, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06410620203820619, "standard_deviation": 0.03670262680890983, "minimum": -0.12632509628159708, "maximum": -0.02912190664798963, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9973216899080817, "standard_deviation": 0.00034960165899949045, "minimum": 0.9968213281486106, "maximum": 0.9978146772841672, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9384398075196057, "standard_deviation": 0.02554952354996304, "minimum": 0.8991003453250496, "maximum": 0.9678122544520695, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4739326576879722, "standard_deviation": 0.19373164465953857, "minimum": 0.2826798285046091, "maximum": 0.7848166792667522, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05177704486777527, "standard_deviation": 0.003105770502656715, "minimum": 0.046424406063442475, "maximum": 0.05606864773526522, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9991190294731553, "standard_deviation": 0.0001345979759172965, "minimum": 0.9988834370754619, "maximum": 0.9992867203190152, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6035499450539886, "standard_deviation": 0.027534022867287428, "minimum": 0.5629243491599606, "maximum": 0.6319717322461859, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5570488325608078, "standard_deviation": 0.19821880853848167, "minimum": 0.31487363770907445, "maximum": 0.8579992082776081, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.029518362956163908, "standard_deviation": 0.0023755384074616165, "minimum": 0.025787550378527358, "maximum": 0.03247327909694413, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 2.7230875492095947, "predicted_mos": 2.7230875492095947, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 123603, "input_sample_rate": 24000, "input_seconds": 5.150125, "input_float32_sha256": "822b5f078ca31d4b24d46f985d658aca9f4e97a5d014867dbe6b35b3f81813d5", "internal_samples": 82402, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.488882400095463}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9354465529290488, "全帯域_10ms_rms_envelope_nrmse": 0.050458205619044745, "全帯域_10ms_envelope_correlation": 0.9974267497969518, "全帯域_10ms_modulation_mae_db": 0.42769374325398957, "全帯域_40ms_log_rms_mae_db": 0.6132926136253475, "全帯域_40ms_rms_envelope_nrmse": 0.026179729667516038, "全帯域_40ms_envelope_correlation": 0.9992770358110484, "全帯域_40ms_modulation_mae_db": 0.3266921335140543, "300–1000 Hz_10ms_log_rms_mae_db": 0.924414373491081, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08177721241543383, "300–1000 Hz_10ms_envelope_correlation": 0.9939810528334616, "300–1000 Hz_10ms_modulation_mae_db": 0.485908590574956, "300–1000 Hz_40ms_log_rms_mae_db": 0.6138080248007913, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.047795657111108995, "300–1000 Hz_40ms_envelope_correlation": 0.9978205862775315, "300–1000 Hz_40ms_modulation_mae_db": 0.19964471836040787, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1236396936930078, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09623702107319151, "1000–3000 Hz_10ms_envelope_correlation": 0.9934414491676888, "1000–3000 Hz_10ms_modulation_mae_db": 1.5518446853363228, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6682085303187925, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.053487811101835925, "1000–3000 Hz_40ms_envelope_correlation": 0.9980298412833608, "1000–3000 Hz_40ms_modulation_mae_db": 1.1598352698882597, "3000–6000 Hz_10ms_log_rms_mae_db": 1.569717687219118, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1350913743302312, "3000–6000 Hz_10ms_envelope_correlation": 0.9845027096896843, "3000–6000 Hz_10ms_modulation_mae_db": 0.45350144099028, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9747352089873124, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0781295977130724, "3000–6000 Hz_40ms_envelope_correlation": 0.9946694699031071, "3000–6000 Hz_40ms_modulation_mae_db": 0.39604578500959725, "mr_stft_db": 5.427387477846616, "band_mae_db": 0.1285097259334471, "rms_gain_error_db": -0.042994647419429016, "output_peak": 0.49241787495895323}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9072484746789696, "全帯域_10ms_rms_envelope_nrmse": 0.05241581764646458, "全帯域_10ms_envelope_correlation": 0.9972560784951169, "全帯域_10ms_modulation_mae_db": 0.5002283661394936, "全帯域_40ms_log_rms_mae_db": 0.6244679615976269, "全帯域_40ms_rms_envelope_nrmse": 0.029279341775135897, "全帯域_40ms_envelope_correlation": 0.9991360112077301, "全帯域_40ms_modulation_mae_db": 0.6982477534842157, "300–1000 Hz_10ms_log_rms_mae_db": 0.9180629721045213, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07191190120817556, "300–1000 Hz_10ms_envelope_correlation": 0.995372913086742, "300–1000 Hz_10ms_modulation_mae_db": 0.1948136141754542, "300–1000 Hz_40ms_log_rms_mae_db": 0.655618257545973, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03909105235818676, "300–1000 Hz_40ms_envelope_correlation": 0.9985714099484195, "300–1000 Hz_40ms_modulation_mae_db": 0.5108375965403703, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1022076674478238, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09714931013022397, "1000–3000 Hz_10ms_envelope_correlation": 0.9931964282551167, "1000–3000 Hz_10ms_modulation_mae_db": 0.9224371318801564, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7042718440333439, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.052311481000544606, "1000–3000 Hz_40ms_envelope_correlation": 0.9979835760277338, "1000–3000 Hz_40ms_modulation_mae_db": 0.7329980293675581, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5249307825816107, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1419692265048634, "3000–6000 Hz_10ms_envelope_correlation": 0.9846845359528614, "3000–6000 Hz_10ms_modulation_mae_db": 0.8689133874326678, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9908817044769908, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.088622583384501, "3000–6000 Hz_40ms_envelope_correlation": 0.995419490824846, "3000–6000 Hz_40ms_modulation_mae_db": 1.0066296577371008, "mr_stft_db": 5.4164330438190555, "band_mae_db": 0.1760346837285681, "rms_gain_error_db": -0.07327531458692928, "output_peak": 0.43852369418671977}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9204096948227818, "全帯域_10ms_rms_envelope_nrmse": 0.051402689575841334, "全帯域_10ms_envelope_correlation": 0.9973491205606342, "全帯域_10ms_modulation_mae_db": 0.20348435327612066, "全帯域_40ms_log_rms_mae_db": 0.5970820766607663, "全帯域_40ms_rms_envelope_nrmse": 0.027064226345198047, "全帯域_40ms_envelope_correlation": 0.9992533818307903, "全帯域_40ms_modulation_mae_db": 0.48210791559720767, "300–1000 Hz_10ms_log_rms_mae_db": 0.9839574031555987, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07078512571389452, "300–1000 Hz_10ms_envelope_correlation": 0.995502249156267, "300–1000 Hz_10ms_modulation_mae_db": 0.4245978372760743, "300–1000 Hz_40ms_log_rms_mae_db": 0.6927792957019865, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035856231015028446, "300–1000 Hz_40ms_envelope_correlation": 0.998778766373936, "300–1000 Hz_40ms_modulation_mae_db": 0.5791871860845222, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0724470973362128, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10472312821295067, "1000–3000 Hz_10ms_envelope_correlation": 0.9920547090682621, "1000–3000 Hz_10ms_modulation_mae_db": 0.9324885739276344, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6872519636801074, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.058991459813326236, "1000–3000 Hz_40ms_envelope_correlation": 0.997368837718516, "1000–3000 Hz_40ms_modulation_mae_db": 1.2186194226446254, "3000–6000 Hz_10ms_log_rms_mae_db": 1.564751211065971, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1379920840830916, "3000–6000 Hz_10ms_envelope_correlation": 0.9846169651319262, "3000–6000 Hz_10ms_modulation_mae_db": 0.3305572925160521, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9653384492073757, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08556091418924656, "3000–6000 Hz_40ms_envelope_correlation": 0.9946065129413328, "3000–6000 Hz_40ms_modulation_mae_db": 0.4072230300241087, "mr_stft_db": 5.417692551708895, "band_mae_db": 0.21432178970355256, "rms_gain_error_db": -0.06270750232230209, "output_peak": 0.4800665086859654}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9223260775972372, "全帯域_10ms_rms_envelope_nrmse": 0.04779803404335547, "全帯域_10ms_envelope_correlation": 0.9977124577081569, "全帯域_10ms_modulation_mae_db": 0.7450236162791609, "全帯域_40ms_log_rms_mae_db": 0.5834071860785583, "全帯域_40ms_rms_envelope_nrmse": 0.026782998841837262, "全帯域_40ms_envelope_correlation": 0.9992623651505822, "全帯域_40ms_modulation_mae_db": 0.8503164021813115, "300–1000 Hz_10ms_log_rms_mae_db": 0.9804710728290362, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08080588411226543, "300–1000 Hz_10ms_envelope_correlation": 0.9941783008150856, "300–1000 Hz_10ms_modulation_mae_db": 0.46916911973971515, "300–1000 Hz_40ms_log_rms_mae_db": 0.6575686048104508, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043318679732888755, "300–1000 Hz_40ms_envelope_correlation": 0.9982683200001162, "300–1000 Hz_40ms_modulation_mae_db": 1.1707933253338012, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1146536590433698, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08058684775295892, "1000–3000 Hz_10ms_envelope_correlation": 0.9955126614941407, "1000–3000 Hz_10ms_modulation_mae_db": 0.17085673887147887, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6826314105610891, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05066267355562954, "1000–3000 Hz_40ms_envelope_correlation": 0.9982902430321648, "1000–3000 Hz_40ms_modulation_mae_db": 0.1753971824813206, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5483607849061582, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14242272185438082, "3000–6000 Hz_10ms_envelope_correlation": 0.9836764169166399, "3000–6000 Hz_10ms_modulation_mae_db": 0.7138045038322686, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9661936988903354, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08666478693172198, "3000–6000 Hz_40ms_envelope_correlation": 0.9946430538094807, "3000–6000 Hz_40ms_modulation_mae_db": 0.7880933754688687, "mr_stft_db": 5.415487982168025, "band_mae_db": 0.20182345242156408, "rms_gain_error_db": -0.0574489950025188, "output_peak": 0.4626356989471969}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9660828066632035, "全帯域_10ms_rms_envelope_nrmse": 0.05844570933095972, "全帯域_10ms_envelope_correlation": 0.9966419340524544, "全帯域_10ms_modulation_mae_db": 0.5550924293974658, "全帯域_40ms_log_rms_mae_db": 0.5998967020956562, "全帯域_40ms_rms_envelope_nrmse": 0.033931457788772316, "全帯域_40ms_envelope_correlation": 0.9988948596272517, "全帯域_40ms_modulation_mae_db": 0.7406452367798332, "300–1000 Hz_10ms_log_rms_mae_db": 0.9399177693562039, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07772880169980428, "300–1000 Hz_10ms_envelope_correlation": 0.9947043332604, "300–1000 Hz_10ms_modulation_mae_db": 0.5007848776299247, "300–1000 Hz_40ms_log_rms_mae_db": 0.6213075139005906, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.049084282285257234, "300–1000 Hz_40ms_envelope_correlation": 0.9978608272429305, "300–1000 Hz_40ms_modulation_mae_db": 0.8501588249970101, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1031847649449271, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1162882493708033, "1000–3000 Hz_10ms_envelope_correlation": 0.9903690867492223, "1000–3000 Hz_10ms_modulation_mae_db": 0.8578473989885129, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6992485276680956, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06433671397466965, "1000–3000 Hz_40ms_envelope_correlation": 0.9971394712866677, "1000–3000 Hz_40ms_modulation_mae_db": 0.9202547423684084, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5487447951065327, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13330281221269172, "3000–6000 Hz_10ms_envelope_correlation": 0.9857249877319006, "3000–6000 Hz_10ms_modulation_mae_db": 0.6901535680942019, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9880655377534447, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08336633619954482, "3000–6000 Hz_40ms_envelope_correlation": 0.9949155366759705, "3000–6000 Hz_40ms_modulation_mae_db": 0.7783417215724899, "mr_stft_db": 5.419918717444023, "band_mae_db": 0.24333812913990308, "rms_gain_error_db": -0.10596589492208522, "output_peak": 0.4512291815589746}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9327301705776027, "全帯域_10ms_rms_envelope_nrmse": 0.05676978584569391, "全帯域_10ms_envelope_correlation": 0.9968983107901948, "全帯域_10ms_modulation_mae_db": 0.29527711495447456, "全帯域_40ms_log_rms_mae_db": 0.5950770069429335, "全帯域_40ms_rms_envelope_nrmse": 0.03632178175322801, "全帯域_40ms_envelope_correlation": 0.998778278426174, "全帯域_40ms_modulation_mae_db": 0.5668446170369984, "300–1000 Hz_10ms_log_rms_mae_db": 0.9646459483868947, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08186344966798989, "300–1000 Hz_10ms_envelope_correlation": 0.9941043479458995, "300–1000 Hz_10ms_modulation_mae_db": 0.4230449516660591, "300–1000 Hz_40ms_log_rms_mae_db": 0.6978387683405294, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.055877709479888266, "300–1000 Hz_40ms_envelope_correlation": 0.9971790957345058, "300–1000 Hz_40ms_modulation_mae_db": 0.6765742423577326, "1000–3000 Hz_10ms_log_rms_mae_db": 1.118495646034264, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10529365066795039, "1000–3000 Hz_10ms_envelope_correlation": 0.9926811263174081, "1000–3000 Hz_10ms_modulation_mae_db": 0.5600085643552704, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6957580476665455, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07043315859492157, "1000–3000 Hz_40ms_envelope_correlation": 0.9970927836002506, "1000–3000 Hz_40ms_modulation_mae_db": 0.6385295993422053, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5381321790442164, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13878176460233851, "3000–6000 Hz_10ms_envelope_correlation": 0.9850938832577213, "3000–6000 Hz_10ms_modulation_mae_db": 0.6432777039412868, "3000–6000 Hz_40ms_log_rms_mae_db": 0.934326894051195, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08277739672388867, "3000–6000 Hz_40ms_envelope_correlation": 0.9959374424073665, "3000–6000 Hz_40ms_modulation_mae_db": 0.9948671098176062, "mr_stft_db": 5.411783415857546, "band_mae_db": 0.21076774908589663, "rms_gain_error_db": -0.12525740941650965, "output_peak": 0.46141902822347497}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9077967553694285, "全帯域_10ms_rms_envelope_nrmse": 0.05029463081940297, "全帯域_10ms_envelope_correlation": 0.9975425716195621, "全帯域_10ms_modulation_mae_db": 0.6453931420933611, "全帯域_40ms_log_rms_mae_db": 0.5698771908623341, "全帯域_40ms_rms_envelope_nrmse": 0.029549026794006516, "全帯域_40ms_envelope_correlation": 0.9991868831522482, "全帯域_40ms_modulation_mae_db": 0.7629359107032444, "300–1000 Hz_10ms_log_rms_mae_db": 1.0155457650753708, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.079517660194628, "300–1000 Hz_10ms_envelope_correlation": 0.9943791712859502, "300–1000 Hz_10ms_modulation_mae_db": 0.7322739798047849, "300–1000 Hz_40ms_log_rms_mae_db": 0.7275555069970734, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05075122110198917, "300–1000 Hz_40ms_envelope_correlation": 0.9976132889767444, "300–1000 Hz_40ms_modulation_mae_db": 0.854740229099173, "1000–3000 Hz_10ms_log_rms_mae_db": 1.116576688311378, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09444349753014475, "1000–3000 Hz_10ms_envelope_correlation": 0.9939217146694156, "1000–3000 Hz_10ms_modulation_mae_db": 1.1853548767566982, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6832257786498958, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05485223402257525, "1000–3000 Hz_40ms_envelope_correlation": 0.9981743081887777, "1000–3000 Hz_40ms_modulation_mae_db": 1.262805882807334, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5875816138482814, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14352432431535747, "3000–6000 Hz_10ms_envelope_correlation": 0.9830209901830101, "3000–6000 Hz_10ms_modulation_mae_db": 0.4301596621220347, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9944302626406148, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09072504529262226, "3000–6000 Hz_40ms_envelope_correlation": 0.9934441183148702, "3000–6000 Hz_40ms_modulation_mae_db": 0.48116460087628177, "mr_stft_db": 5.413595209145886, "band_mae_db": 0.2368390173347305, "rms_gain_error_db": -0.10144871526354689, "output_peak": 0.4955949491775624}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9393564238104312, "全帯域_10ms_rms_envelope_nrmse": 0.0522433906776904, "全帯域_10ms_envelope_correlation": 0.9973058784619987, "全帯域_10ms_modulation_mae_db": 0.30333541995240393, "全帯域_40ms_log_rms_mae_db": 0.6540031973557134, "全帯域_40ms_rms_envelope_nrmse": 0.028727160114821487, "全帯域_40ms_envelope_correlation": 0.9992056814916632, "全帯域_40ms_modulation_mae_db": 0.5648906499253311, "300–1000 Hz_10ms_log_rms_mae_db": 1.009749989166306, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07012577072649881, "300–1000 Hz_10ms_envelope_correlation": 0.9955896407995294, "300–1000 Hz_10ms_modulation_mae_db": 0.3882867202236289, "300–1000 Hz_40ms_log_rms_mae_db": 0.7187429698567362, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04065832985782057, "300–1000 Hz_40ms_envelope_correlation": 0.9984296524221461, "300–1000 Hz_40ms_modulation_mae_db": 0.2631816156454862, "1000–3000 Hz_10ms_log_rms_mae_db": 1.093404125831607, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08226337191494584, "1000–3000 Hz_10ms_envelope_correlation": 0.9954446631445533, "1000–3000 Hz_10ms_modulation_mae_db": 0.9923394489874209, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6478097864623175, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.049638509991676384, "1000–3000 Hz_40ms_envelope_correlation": 0.9985303249069963, "1000–3000 Hz_40ms_modulation_mae_db": 0.9175722694541614, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5876283852203181, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1382694516556027, "3000–6000 Hz_10ms_envelope_correlation": 0.9844032625416309, "3000–6000 Hz_10ms_modulation_mae_db": 0.5245824009724604, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9771384161752865, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09019430528876912, "3000–6000 Hz_40ms_envelope_correlation": 0.9936160076183296, "3000–6000 Hz_40ms_modulation_mae_db": 0.3773404233551148, "mr_stft_db": 5.424973741194999, "band_mae_db": 0.17324268477638446, "rms_gain_error_db": -0.08429434594243163, "output_peak": 0.4933742581165027}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 123603, "output_samples": 123603, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.57746215373628, "spectral_convergence": 0.15498934814932938, "spectral_convergence_status": "ok", "amplitude_floor": 1.160899353957536e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.4045422112747135, "spectral_convergence": 0.159949724077435, "spectral_convergence_status": "ok", "amplitude_floor": 1.2404642078999559e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.300158068528855, "spectral_convergence": 0.1610473640194452, "spectral_convergence_status": "ok", "amplitude_floor": 9.929858096613076e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00012203000528970826, "output_power": 0.00012919486835462704, "delta_db": 0.2477863364290167, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0029769778563333666, "output_power": 0.0029338095298578628, "delta_db": -0.06343689289476642, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0005003734805512382, "output_power": 0.0005090830131055435, "delta_db": 0.07494321576983942, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0006045073176565132, "output_power": 0.0005907443629042664, "delta_db": -0.10001976302249649, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7994477693589156e-05, "output_power": 2.6791106010297805e-05, "delta_db": -0.1908172622090407, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.1130460027276325e-05, "output_power": 2.1102564638091615e-05, "delta_db": -0.0057371289180696335, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 6.414014484484223e-06, "output_power": 6.742371599377599e-06, "delta_db": 0.21682748229090026, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.1285097259334471, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.042994647419429016, "pitch": null, "output_rms_dbfs": -23.749482228307844, "output_peak": 0.49241787495895323, "reference_rms_dbfs": -23.706487580888414, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.427387477846616}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 123603, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00019691446092710702, "log_rms_mae_db": 0.9354465529290488, "rms_envelope_nrmse": 0.050458205619044745, "envelope_correlation": 0.9974267497969518, "rms_gain_error_db": -0.042994697485386146, "reference_mean_power": 0.004263670396682444, "output_mean_power": 0.004221668756603431}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 2.431988683155927e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000639691813348002, "output_power": 0.0006377032014704139, "reference_active": true, "delta_db": -0.013521954489510539}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00010753471412479325, "output_power": 0.00010372642371062399, "reference_active": true, "delta_db": -0.15659280387166102}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.642399701776048e-05, "output_power": 2.0450402708099e-05, "reference_active": true, "delta_db": -1.1129664714007972}], "active_band_count": 3, "active_band_mae_db": 0.42769374325398957}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00017338386226625632, "log_rms_mae_db": 0.6132926136253475, "rms_envelope_nrmse": 0.026179729667516038, "envelope_correlation": 0.9992770358110484, "rms_gain_error_db": -0.04299472602732751, "reference_mean_power": 0.004288676885881949, "output_mean_power": 0.004246428877662291}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 2.255466410477988e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0005603710082458684, "output_power": 0.000559327915010482, "reference_active": true, "delta_db": -0.008091635311560803}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.355233098915975e-05, "output_power": 5.492218225883604e-05, "reference_active": true, "delta_db": 0.10969405761184359}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6814737983602464e-06, "output_power": 1.3786722479595562e-06, "reference_active": true, "delta_db": -0.8622907076187586}], "active_band_count": 3, "active_band_mae_db": 0.3266921335140543}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00013036665176469016, "log_rms_mae_db": 0.924414373491081, "rms_envelope_nrmse": 0.08177721241543383, "envelope_correlation": 0.9939810528334616, "rms_gain_error_db": -0.04593456808125323, "reference_mean_power": 0.0015158717741492514, "output_mean_power": 0.001499923154969458}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.1878952461837722e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003623244921434429, "output_power": 0.00034760342467172377, "reference_active": true, "delta_db": -0.18013645574100295}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.273788700032257e-05, "output_power": 4.7368196606472216e-05, "reference_active": true, "delta_db": -0.4663587467379615}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.188850333636066e-05, "output_power": 1.4330133651955055e-05, "reference_active": true, "delta_db": 0.8112305692459033}], "active_band_count": 3, "active_band_mae_db": 0.485908590574956}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00011772885872912533, "log_rms_mae_db": 0.6138080248007913, "rms_envelope_nrmse": 0.047795657111108995, "envelope_correlation": 0.9978205862775315, "rms_gain_error_db": -0.045934638324770787, "reference_mean_power": 0.0015247625061786474, "output_mean_power": 0.0015087203224292537}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.1128010899378388e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00031933130970672837, "output_power": 0.0003043381543563897, "reference_active": true, "delta_db": -0.20885099679327143}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.477735373946001e-05, "output_power": 2.3639061349660156e-05, "reference_active": true, "delta_db": -0.20424693418725204}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0783298014452697e-06, "output_power": 1.1254733873367597e-06, "reference_active": true, "delta_db": 0.1858362241007001}], "active_band_count": 3, "active_band_mae_db": 0.19964471836040787}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 8.162582163687071e-05, "log_rms_mae_db": 1.1236396936930078, "rms_envelope_nrmse": 0.09623702107319151, "envelope_correlation": 0.9934414491676888, "rms_gain_error_db": -0.16798155407867582, "reference_mean_power": 0.00046194923691890866, "output_mean_power": 0.00044442256198235094}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 4.3226252960933766e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021745730779534734, "output_power": 0.00021290091329318592, "reference_active": true, "delta_db": -0.09196482537170952}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.26315917085523e-05, "output_power": 5.6938972514468095e-05, "reference_active": true, "delta_db": -0.4138382305554055}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.1826956188918756e-06, "output_power": 2.762576815342102e-06, "reference_active": true, "delta_db": -4.149731000081854}], "active_band_count": 3, "active_band_mae_db": 1.5518446853363228}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 6.494685964088987e-05, "log_rms_mae_db": 0.6682085303187925, "rms_envelope_nrmse": 0.053487811101835925, "envelope_correlation": 0.9980298412833608, "rms_gain_error_db": -0.16798160260383543, "reference_mean_power": 0.00046465861059889405, "output_mean_power": 0.0004470291351480772}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 3.961591197471977e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00020060895095818542, "output_power": 0.0001948069877036369, "reference_active": true, "delta_db": -0.1274577596117648}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.46199225862701e-05, "output_power": 3.1784734425091786e-05, "reference_active": true, "delta_db": -0.3710750534561696}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.414804941169707e-07, "output_power": 3.732522471121244e-07, "reference_active": true, "delta_db": -2.9809729965968446}], "active_band_count": 3, "active_band_mae_db": 1.1598352698882597}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 1.8521534194293832e-05, "log_rms_mae_db": 1.569717687219118, "rms_envelope_nrmse": 0.1350913743302312, "envelope_correlation": 0.9845027096896843, "rms_gain_error_db": -0.2136724065823571, "reference_mean_power": 1.6841903509300322e-05, "output_mean_power": 1.603333748851029e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.2347471453358591e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.252863490142334e-06, "output_power": 5.744698197552382e-06, "reference_active": true, "delta_db": -0.3681172984606323}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.067523918077283e-06, "output_power": 1.7536449872578955e-06, "reference_active": true, "delta_db": -0.7150886422205838}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.652671220760486e-07, "output_power": 2.8275693403750373e-07, "reference_active": true, "delta_db": 0.27729838228962395}], "active_band_count": 3, "active_band_mae_db": 0.45350144099028}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 1.4385957620494375e-05, "log_rms_mae_db": 0.9747352089873124, "rms_envelope_nrmse": 0.0781295977130724, "envelope_correlation": 0.9946694699031071, "rms_gain_error_db": -0.21367304502019183, "reference_mean_power": 1.6940674573447337e-05, "output_mean_power": 1.6127364263788417e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.0973267407020894e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.499482122012401e-06, "output_power": 5.068329000365811e-06, "reference_active": true, "delta_db": -0.35456996081627995}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2679437871779227e-06, "output_power": 1.091739370550525e-06, "reference_active": true, "delta_db": -0.649810278151802}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8893101287704897e-08, "output_power": 1.8110379094940485e-08, "reference_active": true, "delta_db": -0.1837571160607097}], "active_band_count": 3, "active_band_mae_db": 0.39604578500959725}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9356528141673486, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "8d2df7c78b58e74ecde524aedbdc1792e175a04072490e0a04dc3fb2cdc99eff", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9933277298582259, "standard_deviation": 0.001708406528140969, "minimum": 0.9903690867492223, "maximum": 0.9955126614941407, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.105576167830324, "standard_deviation": 0.016730535394218763, "minimum": 1.0724470973362128, "maximum": 1.1236396936930078, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8966471773879369, "standard_deviation": 0.40801704929878124, "minimum": 0.17085673887147887, "maximum": 1.5518446853363228, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09712313458164618, "standard_deviation": 0.011916654173420246, "minimum": 0.08058684775295892, "maximum": 0.1162882493708033, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978261732555584, "standard_deviation": 0.0005499636753953001, "minimum": 0.9970927836002506, "maximum": 0.9985303249069963, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6835507361300235, "standard_deviation": 0.018331284856419147, "minimum": 0.6478097864623175, "maximum": 0.7042718440333439, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8782515497942341, "standard_deviation": 0.3623142998018911, "minimum": 0.1753971824813206, "maximum": 1.262805882807334, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0568392552568974, "standard_deviation": 0.007283250300269503, "minimum": 0.049638509991676384, "maximum": 0.07043315859492157, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9844654689256718, "standard_deviation": 0.0008251936637246282, "minimum": 0.9830209901830101, "maximum": 0.9857249877319006, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.558730929874026, "standard_deviation": 0.022672824516367627, "minimum": 1.5249307825816107, "maximum": 1.5876283852203181, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5818687449876565, "standard_deviation": 0.1777764713207372, "minimum": 0.3305572925160521, "maximum": 0.8689133874326678, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.13891921994481968, "standard_deviation": 0.0035912823710387612, "minimum": 0.13330281221269172, "maximum": 0.14352432431535747, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9946564540619129, "standard_deviation": 0.0008319864270542143, "minimum": 0.9934441183148702, "maximum": 0.9959374424073665, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9738887715228194, "standard_deviation": 0.019348068485476575, "minimum": 0.934326894051195, "maximum": 0.9944302626406148, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.653713212982646, "standard_deviation": 0.26934607256583243, "minimum": 0.3773404233551148, "maximum": 1.0066296577371008, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08575512071542085, "standard_deviation": 0.004246272207648916, "minimum": 0.0781295977130724, "maximum": 0.09072504529262226, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9947265011479169, "standard_deviation": 0.0006685874528513978, "minimum": 0.9939810528334616, "maximum": 0.9955896407995294, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.9670956616956266, "standard_deviation": 0.03703388420695669, "minimum": 0.9180629721045213, "maximum": 1.0155457650753708, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.45235996138632467, "standard_deviation": 0.14840605256723519, "minimum": 0.1948136141754542, "maximum": 0.7322739798047849, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07681447571733628, "standard_deviation": 0.005061373409333401, "minimum": 0.07012577072649881, "maximum": 0.08186344966798989, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9980652433720412, "standard_deviation": 0.0005385850786507291, "minimum": 0.9971790957345058, "maximum": 0.998778766373936, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.6731523677442663, "standard_deviation": 0.042749733222363424, "minimum": 0.6138080248007913, "maximum": 0.7275555069970734, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.638139717302313, "standard_deviation": 0.3228484021921436, "minimum": 0.19964471836040787, "maximum": 1.1707933253338012, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.045304145367771026, "standard_deviation": 0.006712028050679868, "minimum": 0.035856231015028446, "maximum": 0.055877709479888266, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1981096540155058, "standard_deviation": 0.0376681980673857, "minimum": 0.1285097259334471, "maximum": 0.24333812913990308, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.4184090173981305, "standard_deviation": 0.00542493096639814, "minimum": 5.411783415857546, "maximum": 5.427387477846616, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.47190764923191875, "standard_deviation": 0.021538031264272194, "minimum": 0.43852369418671977, "maximum": 0.4955949491775624, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.08167410310946907, "standard_deviation": 0.027776466004273706, "minimum": -0.12525740941650965, "maximum": -0.042994647419429016, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9972666376856336, "standard_deviation": 0.0003453579938639335, "minimum": 0.9966419340524544, "maximum": 0.9977124577081569, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9289246195560878, "standard_deviation": 0.019193964243284407, "minimum": 0.9072484746789696, "maximum": 0.9660828066632035, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4594410231683088, "standard_deviation": 0.1870022389631426, "minimum": 0.20348435327612066, "maximum": 0.7450236162791609, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.052478532944806644, "standard_deviation": 0.0035050357751355847, "minimum": 0.04779803404335547, "maximum": 0.05844570933095972, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.999124312087186, "standard_deviation": 0.00018597346061444272, "minimum": 0.998778278426174, "maximum": 0.9992770358110484, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.604637991902367, "standard_deviation": 0.026008510165413494, "minimum": 0.5698771908623341, "maximum": 0.6540031973557134, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6240850774027745, "standard_deviation": 0.1711002494751812, "minimum": 0.3266921335140543, "maximum": 0.8503164021813115, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.029729465385064446, "standard_deviation": 0.003600415618018779, "minimum": 0.026179729667516038, "maximum": 0.03632178175322801, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 2.391757011413574, "predicted_mos": 2.391757011413574, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 123603, "input_sample_rate": 24000, "input_seconds": 5.150125, "input_float32_sha256": "fc9965df51b709cc29d4d91dcc196ee70bdaaaaf4046597bbefd16ccdf203ac7", "internal_samples": 82402, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.2500956999138}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.945385182267317, "全帯域_10ms_rms_envelope_nrmse": 0.054900324341667986, "全帯域_10ms_envelope_correlation": 0.9969878557667318, "全帯域_10ms_modulation_mae_db": 0.3214606442233625, "全帯域_40ms_log_rms_mae_db": 0.5440810608247107, "全帯域_40ms_rms_envelope_nrmse": 0.02569502738724735, "全帯域_40ms_envelope_correlation": 0.999359325879324, "全帯域_40ms_modulation_mae_db": 0.4167893339238858, "300–1000 Hz_10ms_log_rms_mae_db": 0.9065386005188838, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06982707411929204, "300–1000 Hz_10ms_envelope_correlation": 0.9956331776343896, "300–1000 Hz_10ms_modulation_mae_db": 0.35060193239053766, "300–1000 Hz_40ms_log_rms_mae_db": 0.6219409129420845, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.034185545900556516, "300–1000 Hz_40ms_envelope_correlation": 0.9989123872502479, "300–1000 Hz_40ms_modulation_mae_db": 0.5695474168968799, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1379461171486207, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.110522074977248, "1000–3000 Hz_10ms_envelope_correlation": 0.991508506047322, "1000–3000 Hz_10ms_modulation_mae_db": 1.4523191896301733, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7112898880931132, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0591040477764599, "1000–3000 Hz_40ms_envelope_correlation": 0.9978742973686828, "1000–3000 Hz_40ms_modulation_mae_db": 1.664707229342163, "3000–6000 Hz_10ms_log_rms_mae_db": 1.529154687341723, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14865332745503118, "3000–6000 Hz_10ms_envelope_correlation": 0.9812670748255893, "3000–6000 Hz_10ms_modulation_mae_db": 0.4334155879987687, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9393857761885853, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0948901905656333, "3000–6000 Hz_40ms_envelope_correlation": 0.9920890452485491, "3000–6000 Hz_40ms_modulation_mae_db": 0.37197534012124195, "mr_stft_db": 5.380156401131248, "band_mae_db": 0.20757852743112554, "rms_gain_error_db": -0.07657427125231897, "output_peak": 0.4753866646363873}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9579182046124912, "全帯域_10ms_rms_envelope_nrmse": 0.051603149355910906, "全帯域_10ms_envelope_correlation": 0.9972993871107769, "全帯域_10ms_modulation_mae_db": 0.8260753808210977, "全帯域_40ms_log_rms_mae_db": 0.602064218198716, "全帯域_40ms_rms_envelope_nrmse": 0.02838475826235342, "全帯域_40ms_envelope_correlation": 0.9991383173834093, "全帯域_40ms_modulation_mae_db": 0.7383533535475348, "300–1000 Hz_10ms_log_rms_mae_db": 0.9068111043076359, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06700653548272309, "300–1000 Hz_10ms_envelope_correlation": 0.9959707884159097, "300–1000 Hz_10ms_modulation_mae_db": 0.5002694586368083, "300–1000 Hz_40ms_log_rms_mae_db": 0.6350336542974534, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03823080635630114, "300–1000 Hz_40ms_envelope_correlation": 0.9985900880269155, "300–1000 Hz_40ms_modulation_mae_db": 0.7776907173835453, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0924436135154516, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08957133559727312, "1000–3000 Hz_10ms_envelope_correlation": 0.9942860987054462, "1000–3000 Hz_10ms_modulation_mae_db": 0.6226783768577651, "1000–3000 Hz_40ms_log_rms_mae_db": 0.68014311505647, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0487370130226581, "1000–3000 Hz_40ms_envelope_correlation": 0.9983275111804538, "1000–3000 Hz_40ms_modulation_mae_db": 0.6232139722048183, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4886496787218995, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15102642199288624, "3000–6000 Hz_10ms_envelope_correlation": 0.9804698910923356, "3000–6000 Hz_10ms_modulation_mae_db": 0.449994675400515, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9144418643839016, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09094075199121224, "3000–6000 Hz_40ms_envelope_correlation": 0.9925370736032741, "3000–6000 Hz_40ms_modulation_mae_db": 0.5270645036824569, "mr_stft_db": 5.386982293562627, "band_mae_db": 0.14435682306677938, "rms_gain_error_db": -0.03585506931919942, "output_peak": 0.45933080934662673}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9527764557380064, "全帯域_10ms_rms_envelope_nrmse": 0.05842603709006677, "全帯域_10ms_envelope_correlation": 0.9967424456358361, "全帯域_10ms_modulation_mae_db": 0.5012186306134396, "全帯域_40ms_log_rms_mae_db": 0.6100318483350291, "全帯域_40ms_rms_envelope_nrmse": 0.03866639872264592, "全帯域_40ms_envelope_correlation": 0.9986273334467389, "全帯域_40ms_modulation_mae_db": 0.7475569672360519, "300–1000 Hz_10ms_log_rms_mae_db": 0.9871485291065267, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07848551922585763, "300–1000 Hz_10ms_envelope_correlation": 0.994598324073865, "300–1000 Hz_10ms_modulation_mae_db": 0.34342679157704853, "300–1000 Hz_40ms_log_rms_mae_db": 0.7426671232608467, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.056138615733852495, "300–1000 Hz_40ms_envelope_correlation": 0.9971368193442681, "300–1000 Hz_40ms_modulation_mae_db": 0.702683907737498, "1000–3000 Hz_10ms_log_rms_mae_db": 1.103438991442582, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10025574505590883, "1000–3000 Hz_10ms_envelope_correlation": 0.9934029406849749, "1000–3000 Hz_10ms_modulation_mae_db": 0.8216885037701287, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7079922186933149, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06768514931454095, "1000–3000 Hz_40ms_envelope_correlation": 0.9973169943164023, "1000–3000 Hz_40ms_modulation_mae_db": 1.0209114408396294, "3000–6000 Hz_10ms_log_rms_mae_db": 1.508870789273249, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13944297098425965, "3000–6000 Hz_10ms_envelope_correlation": 0.9835508197094377, "3000–6000 Hz_10ms_modulation_mae_db": 0.6224750820479912, "3000–6000 Hz_40ms_log_rms_mae_db": 0.882301353951206, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07243188859484119, "3000–6000 Hz_40ms_envelope_correlation": 0.9956599771415939, "3000–6000 Hz_40ms_modulation_mae_db": 0.7326047405814284, "mr_stft_db": 5.379315117923537, "band_mae_db": 0.2300486644243185, "rms_gain_error_db": -0.13173241082731396, "output_peak": 0.39613528173077917}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9299048470612703, "全帯域_10ms_rms_envelope_nrmse": 0.055656026330250664, "全帯域_10ms_envelope_correlation": 0.9970461933915006, "全帯域_10ms_modulation_mae_db": 0.5319012297352784, "全帯域_40ms_log_rms_mae_db": 0.5964234930449978, "全帯域_40ms_rms_envelope_nrmse": 0.032485685685440045, "全帯域_40ms_envelope_correlation": 0.999086013443042, "全帯域_40ms_modulation_mae_db": 0.9652500719537604, "300–1000 Hz_10ms_log_rms_mae_db": 0.9454876243361052, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0717125459927331, "300–1000 Hz_10ms_envelope_correlation": 0.995487852714883, "300–1000 Hz_10ms_modulation_mae_db": 0.414249237490125, "300–1000 Hz_40ms_log_rms_mae_db": 0.6805853863376825, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04024109623570077, "300–1000 Hz_40ms_envelope_correlation": 0.9985787933892616, "300–1000 Hz_40ms_modulation_mae_db": 1.2245132557321012, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0884856636753981, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09937990050245807, "1000–3000 Hz_10ms_envelope_correlation": 0.9931239473724459, "1000–3000 Hz_10ms_modulation_mae_db": 1.2699239288689006, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6647609628073032, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06284939068927808, "1000–3000 Hz_40ms_envelope_correlation": 0.997338242427434, "1000–3000 Hz_40ms_modulation_mae_db": 1.4380359978337285, "3000–6000 Hz_10ms_log_rms_mae_db": 1.500577782857249, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1365551594531711, "3000–6000 Hz_10ms_envelope_correlation": 0.9840650682594189, "3000–6000 Hz_10ms_modulation_mae_db": 0.3343507557410674, "3000–6000 Hz_40ms_log_rms_mae_db": 0.885239650298496, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0794095474899682, "3000–6000 Hz_40ms_envelope_correlation": 0.9943213297291426, "3000–6000 Hz_40ms_modulation_mae_db": 0.45360044830007845, "mr_stft_db": 5.384000857250541, "band_mae_db": 0.16797003924624962, "rms_gain_error_db": -0.1251334265562619, "output_peak": 0.45771752169211655}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8622781874291147, "全帯域_10ms_rms_envelope_nrmse": 0.04674854235477889, "全帯域_10ms_envelope_correlation": 0.9978178142138913, "全帯域_10ms_modulation_mae_db": 0.6333927700138493, "全帯域_40ms_log_rms_mae_db": 0.5409563732951446, "全帯域_40ms_rms_envelope_nrmse": 0.024792121961029843, "全帯域_40ms_envelope_correlation": 0.9993821370766501, "全帯域_40ms_modulation_mae_db": 0.638640013566402, "300–1000 Hz_10ms_log_rms_mae_db": 0.9178992193365366, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06512641716134648, "300–1000 Hz_10ms_envelope_correlation": 0.996197161881538, "300–1000 Hz_10ms_modulation_mae_db": 0.763283334474052, "300–1000 Hz_40ms_log_rms_mae_db": 0.6612751921014082, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.034595811870706636, "300–1000 Hz_40ms_envelope_correlation": 0.9988553414083378, "300–1000 Hz_40ms_modulation_mae_db": 0.9934357608130256, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0480741939973899, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08083302868459308, "1000–3000 Hz_10ms_envelope_correlation": 0.9954351906809303, "1000–3000 Hz_10ms_modulation_mae_db": 0.7489398079760675, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6458049464545659, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.046297144091758766, "1000–3000 Hz_40ms_envelope_correlation": 0.9985657946001116, "1000–3000 Hz_40ms_modulation_mae_db": 0.6861586550796758, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4534686927997584, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.136406032258876, "3000–6000 Hz_10ms_envelope_correlation": 0.9843353518067124, "3000–6000 Hz_10ms_modulation_mae_db": 0.8435295948510557, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8859367248769747, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0825482975652676, "3000–6000 Hz_40ms_envelope_correlation": 0.9941957544766289, "3000–6000 Hz_40ms_modulation_mae_db": 1.1327741103930788, "mr_stft_db": 5.3707267396523335, "band_mae_db": 0.13177216156943608, "rms_gain_error_db": -0.06173489051092719, "output_peak": 0.4333433635976794}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8813238789072352, "全帯域_10ms_rms_envelope_nrmse": 0.05014556688741818, "全帯域_10ms_envelope_correlation": 0.9975484552409615, "全帯域_10ms_modulation_mae_db": 0.7138677046995611, "全帯域_40ms_log_rms_mae_db": 0.5893199374785746, "全帯域_40ms_rms_envelope_nrmse": 0.02789609981250613, "全帯域_40ms_envelope_correlation": 0.9992842186037598, "全帯域_40ms_modulation_mae_db": 0.9160209179045292, "300–1000 Hz_10ms_log_rms_mae_db": 0.9724733487265619, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08156513288821657, "300–1000 Hz_10ms_envelope_correlation": 0.9940809824813218, "300–1000 Hz_10ms_modulation_mae_db": 0.8006670707550239, "300–1000 Hz_40ms_log_rms_mae_db": 0.7575743728975686, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04743023298094102, "300–1000 Hz_40ms_envelope_correlation": 0.9979361589224222, "300–1000 Hz_40ms_modulation_mae_db": 1.127479506866352, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0752084430763404, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09270340332938812, "1000–3000 Hz_10ms_envelope_correlation": 0.9940145848169506, "1000–3000 Hz_10ms_modulation_mae_db": 0.29520783077878593, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6733703474701546, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05155920830110257, "1000–3000 Hz_40ms_envelope_correlation": 0.9982947380238841, "1000–3000 Hz_40ms_modulation_mae_db": 0.5841691534039749, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5058393746740255, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14216518430077318, "3000–6000 Hz_10ms_envelope_correlation": 0.9844418018644977, "3000–6000 Hz_10ms_modulation_mae_db": 0.7792156368562658, "3000–6000 Hz_40ms_log_rms_mae_db": 0.916475836300348, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09107898961022273, "3000–6000 Hz_40ms_envelope_correlation": 0.9947486949704262, "3000–6000 Hz_40ms_modulation_mae_db": 0.8670485617806006, "mr_stft_db": 5.380544503035556, "band_mae_db": 0.18742675447758292, "rms_gain_error_db": -0.09899160586706734, "output_peak": 0.4282752149049229}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9230338739847794, "全帯域_10ms_rms_envelope_nrmse": 0.058912783213308936, "全帯域_10ms_envelope_correlation": 0.9965917252060119, "全帯域_10ms_modulation_mae_db": 0.20291433040386594, "全帯域_40ms_log_rms_mae_db": 0.6425906439239866, "全帯域_40ms_rms_envelope_nrmse": 0.03467607413609594, "全帯域_40ms_envelope_correlation": 0.9988504948675201, "全帯域_40ms_modulation_mae_db": 0.6052593444628046, "300–1000 Hz_10ms_log_rms_mae_db": 0.9496772613767016, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08569690717740618, "300–1000 Hz_10ms_envelope_correlation": 0.993393874460096, "300–1000 Hz_10ms_modulation_mae_db": 0.635838009112644, "300–1000 Hz_40ms_log_rms_mae_db": 0.694974125254777, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04652851074971581, "300–1000 Hz_40ms_envelope_correlation": 0.9979543989732407, "300–1000 Hz_40ms_modulation_mae_db": 0.471975941718358, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0984447615416595, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10822701661254024, "1000–3000 Hz_10ms_envelope_correlation": 0.9917388134397923, "1000–3000 Hz_10ms_modulation_mae_db": 0.884228701753436, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7038406358067597, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05938064167909434, "1000–3000 Hz_40ms_envelope_correlation": 0.9976673513523298, "1000–3000 Hz_40ms_modulation_mae_db": 1.0032668766448205, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5387729340675151, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1508821875906116, "3000–6000 Hz_10ms_envelope_correlation": 0.9804693653606572, "3000–6000 Hz_10ms_modulation_mae_db": 0.41335980604860456, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9180379297339026, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08557586422611417, "3000–6000 Hz_40ms_envelope_correlation": 0.9933825635648671, "3000–6000 Hz_40ms_modulation_mae_db": 0.4571345219838998, "mr_stft_db": 5.375429177627956, "band_mae_db": 0.2021362078890512, "rms_gain_error_db": -0.10957166052080693, "output_peak": 0.4109416431820912}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8862641870604354, "全帯域_10ms_rms_envelope_nrmse": 0.05021477099424673, "全帯域_10ms_envelope_correlation": 0.9974804290377373, "全帯域_10ms_modulation_mae_db": 0.05997749336278888, "全帯域_40ms_log_rms_mae_db": 0.5253343068967528, "全帯域_40ms_rms_envelope_nrmse": 0.025615967835605966, "全帯域_40ms_envelope_correlation": 0.9993467267700841, "全帯域_40ms_modulation_mae_db": 0.1262079538949999, "300–1000 Hz_10ms_log_rms_mae_db": 0.8714601586254775, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0732480569991619, "300–1000 Hz_10ms_envelope_correlation": 0.9952340031078681, "300–1000 Hz_10ms_modulation_mae_db": 0.17240091050856554, "300–1000 Hz_40ms_log_rms_mae_db": 0.6319744211795559, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03888352693603463, "300–1000 Hz_40ms_envelope_correlation": 0.9985840952291632, "300–1000 Hz_40ms_modulation_mae_db": 0.1047713334606254, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0729206961636004, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09401916768883666, "1000–3000 Hz_10ms_envelope_correlation": 0.9943478488964551, "1000–3000 Hz_10ms_modulation_mae_db": 1.0636990164282216, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6870566158961494, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06105349436643145, "1000–3000 Hz_40ms_envelope_correlation": 0.9980453057527628, "1000–3000 Hz_40ms_modulation_mae_db": 1.00117694762209, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4830860526265932, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14577801715107166, "3000–6000 Hz_10ms_envelope_correlation": 0.9826713478581627, "3000–6000 Hz_10ms_modulation_mae_db": 0.5924857747800932, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8878198320477663, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09017483945994112, "3000–6000 Hz_40ms_envelope_correlation": 0.9938680656769662, "3000–6000 Hz_40ms_modulation_mae_db": 0.8724273163247941, "mr_stft_db": 5.371056142229705, "band_mae_db": 0.2462978926526624, "rms_gain_error_db": -0.06666545770373722, "output_peak": 0.4600843986341876}, "full_scale": {"sample_count": 123603, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 123603, "output_samples": 123603, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.555645469166906, "spectral_convergence": 0.15664159282006487, "spectral_convergence_status": "ok", "amplitude_floor": 1.160899353957536e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.333121791293215, "spectral_convergence": 0.16111525983922065, "spectral_convergence_status": "ok", "amplitude_floor": 1.2404642078999559e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.25170194293362, "spectral_convergence": 0.1621102013431503, "spectral_convergence_status": "ok", "amplitude_floor": 9.929858096613076e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 0.00012203000528970826, "output_power": 0.00012981598074666655, "delta_db": 0.26861528645164356, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0029769778563333666, "output_power": 0.0029246145907517993, "delta_db": -0.07706961907519469, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0005003734805512382, "output_power": 0.0005104494012238631, "delta_db": 0.08658414384381884, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0006045073176565132, "output_power": 0.0005685417529426106, "delta_db": -0.26639198233577716, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7994477693589156e-05, "output_power": 2.4577591274232692e-05, "delta_db": -0.5653305144181029, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.1130460027276325e-05, "output_power": 2.048883579054021e-05, "delta_db": -0.1339167032567996, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 6.414014484484223e-06, "output_power": 6.495971047729401e-06, "delta_db": 0.05514144263654197, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.20757852743112554, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.07657427125231897, "pitch": null, "output_rms_dbfs": -23.783061852140733, "output_peak": 0.4753866646363873, "reference_rms_dbfs": -23.706487580888414, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.380156401131248}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 123603, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00019691446092710702, "log_rms_mae_db": 0.945385182267317, "rms_envelope_nrmse": 0.054900324341667986, "envelope_correlation": 0.9969878557667318, "rms_gain_error_db": -0.07657420381870127, "reference_mean_power": 0.004263670396682444, "output_mean_power": 0.004189152820855978}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 2.431988683155927e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000639691813348002, "output_power": 0.0006308293897997808, "reference_active": true, "delta_db": -0.06058874201085708}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00010753471412479325, "output_power": 0.0001007979253946528, "reference_active": true, "delta_db": -0.2809709126682598}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.642399701776048e-05, "output_power": 2.2893715622629262e-05, "reference_active": true, "delta_db": -0.6228222779909707}], "active_band_count": 3, "active_band_mae_db": 0.3214606442233625}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00017338386226625632, "log_rms_mae_db": 0.5440810608247107, "rms_envelope_nrmse": 0.02569502738724735, "envelope_correlation": 0.999359325879324, "rms_gain_error_db": -0.07657404449061117, "reference_mean_power": 0.004288676885881949, "output_mean_power": 0.004213722417971372}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 2.255466410477988e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0005603710082458684, "output_power": 0.0005540173295296574, "reference_active": true, "delta_db": -0.049523086574100095}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.355233098915975e-05, "output_power": 5.3277274181454144e-05, "reference_active": true, "delta_db": -0.022363822757210577}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6814737983602464e-06, "output_power": 1.2818641301922503e-06, "reference_active": true, "delta_db": -1.1784810924403468}], "active_band_count": 3, "active_band_mae_db": 0.4167893339238858}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 0.00013036665176469016, "log_rms_mae_db": 0.9065386005188838, "rms_envelope_nrmse": 0.06982707411929204, "envelope_correlation": 0.9956331776343896, "rms_gain_error_db": -0.05525556105395793, "reference_mean_power": 0.0015158717741492514, "output_mean_power": 0.001496707415082436}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.1878952461837722e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003623244921434429, "output_power": 0.00034352126425784006, "reference_active": true, "delta_db": -0.2314406671976166}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.273788700032257e-05, "output_power": 4.6739887293557544e-05, "reference_active": true, "delta_db": -0.5243506451500993}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.188850333636066e-05, "output_power": 1.1105183407196507e-05, "reference_active": true, "delta_db": -0.2960144848238971}], "active_band_count": 3, "active_band_mae_db": 0.35060193239053766}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 0.00011772885872912533, "log_rms_mae_db": 0.6219409129420845, "rms_envelope_nrmse": 0.034185545900556516, "envelope_correlation": 0.9989123872502479, "rms_gain_error_db": -0.055255579482291546, "reference_mean_power": 0.0015247625061786474, "output_mean_power": 0.0015054857399362557}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.1128010899378388e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00031933130970672837, "output_power": 0.0003018321346362463, "reference_active": true, "delta_db": -0.24476027035329628}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.477735373946001e-05, "output_power": 2.323062461665993e-05, "reference_active": true, "delta_db": -0.27994034069017526}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0783298014452697e-06, "output_power": 8.210270084257603e-07, "reference_active": true, "delta_db": -1.1839416396471683}], "active_band_count": 3, "active_band_mae_db": 0.5695474168968799}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 8.162582163687071e-05, "log_rms_mae_db": 1.1379461171486207, "rms_envelope_nrmse": 0.110522074977248, "envelope_correlation": 0.991508506047322, "rms_gain_error_db": -0.2533357711776377, "reference_mean_power": 0.00046194923691890866, "output_mean_power": 0.00043577335979890516}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 4.3226252960933766e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021745730779534734, "output_power": 0.00020779168070115902, "reference_active": true, "delta_db": -0.19745851157775482}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.26315917085523e-05, "output_power": 5.189683399451273e-05, "reference_active": true, "delta_db": -0.816525847329289}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.1826956188918756e-06, "output_power": 3.3265200216978738e-06, "reference_active": true, "delta_db": -3.3429732099834766}], "active_band_count": 3, "active_band_mae_db": 1.4523191896301733}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 6.494685964088987e-05, "log_rms_mae_db": 0.7112898880931132, "rms_envelope_nrmse": 0.0591040477764599, "envelope_correlation": 0.9978742973686828, "rms_gain_error_db": -0.25333579854382515, "reference_mean_power": 0.00046465861059889405, "output_mean_power": 0.0004383292068513415}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 3.961591197471977e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00020060895095818542, "output_power": 0.00019132312527015986, "reference_active": true, "delta_db": -0.20582840401022562}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.46199225862701e-05, "output_power": 2.8127837632952746e-05, "reference_active": true, "delta_db": -0.9018974596320888}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.414804941169707e-07, "output_power": 3.030122234707771e-07, "reference_active": true, "delta_db": -3.8863958243841745}], "active_band_count": 3, "active_band_mae_db": 1.664707229342163}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1029, "rms_floor": 1.8521534194293832e-05, "log_rms_mae_db": 1.529154687341723, "rms_envelope_nrmse": 0.14865332745503118, "envelope_correlation": 0.9812670748255893, "rms_gain_error_db": -0.2596553495312718, "reference_mean_power": 1.6841903509300322e-05, "output_mean_power": 1.5864472635071775e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.2347471453358591e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.252863490142334e-06, "output_power": 5.594681402818017e-06, "reference_active": true, "delta_db": -0.4830358740724675}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.067523918077283e-06, "output_power": 1.7442924392536755e-06, "reference_active": true, "delta_db": -0.7383124405549245}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.652671220760486e-07, "output_power": 2.7013028116617205e-07, "reference_active": true, "delta_db": 0.0788984493689143}], "active_band_count": 3, "active_band_mae_db": 0.4334155879987687}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 123600, "uncovered_tail_samples": 3, "metrics": {"frame_count": 1023, "rms_floor": 1.4385957620494375e-05, "log_rms_mae_db": 0.9393857761885853, "rms_envelope_nrmse": 0.0948901905656333, "envelope_correlation": 0.9920890452485491, "rms_gain_error_db": -0.25965593569010115, "reference_mean_power": 1.6940674573447337e-05, "output_mean_power": 1.5957509302222357e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.0973267407020894e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.499482122012401e-06, "output_power": 4.9231933866869014e-06, "reference_active": true, "delta_db": -0.4807489904226902}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2679437871779227e-06, "output_power": 1.1166843596100958e-06, "reference_active": true, "delta_db": -0.5516956661882241}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8893101287704897e-08, "output_power": 1.8533400743633663e-08, "reference_active": true, "delta_db": -0.08348136375281158}], "active_band_count": 3, "active_band_mae_db": 0.37197534012124195}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9285831361330695, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "70371c3b006b2da26c76d5874df7b7b4a1b5ba1a13877178bfc24667d66ec1cc", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9934822413305398, "standard_deviation": 0.0013396534104719933, "minimum": 0.991508506047322, "maximum": 0.9954351906809303, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.0896203100701303, "standard_deviation": 0.026257319438921914, "minimum": 1.0480741939973899, "maximum": 1.1379461171486207, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8948356695079348, "standard_deviation": 0.36652142061854365, "minimum": 0.29520783077878593, "maximum": 1.4523191896301733, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09693895905603075, "standard_deviation": 0.009776272504262851, "minimum": 0.08083302868459308, "maximum": 0.110522074977248, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9979287793777577, "standard_deviation": 0.00046392846177674093, "minimum": 0.9973169943164023, "maximum": 0.9985657946001116, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6842823412847289, "standard_deviation": 0.022927177537712395, "minimum": 0.6458049464545659, "maximum": 0.7112898880931132, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.0027050341213626, "standard_deviation": 0.386833562957302, "minimum": 0.5841691534039749, "maximum": 1.664707229342163, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.057083261155165516, "standard_deviation": 0.0074382016746543725, "minimum": 0.046297144091758766, "maximum": 0.06768514931454095, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9826588400971015, "standard_deviation": 0.0017023183281230036, "minimum": 0.9804693653606572, "maximum": 0.9844418018644977, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5010524990452516, "standard_deviation": 0.026826615693186267, "minimum": 1.4534686927997584, "maximum": 1.5387729340675151, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5586033642155452, "standard_deviation": 0.18280868064150668, "minimum": 0.3343507557410674, "maximum": 0.8435295948510557, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14386366264833506, "standard_deviation": 0.006078395810237999, "minimum": 0.136406032258876, "maximum": 0.15102642199288624, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9938503130514311, "standard_deviation": 0.0011630580098593358, "minimum": 0.9920890452485491, "maximum": 0.9956599771415939, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9037048709726476, "standard_deviation": 0.021125680195816465, "minimum": 0.882301353951206, "maximum": 0.9393857761885853, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6768286928959474, "standard_deviation": 0.2669673249735253, "minimum": 0.37197534012124195, "maximum": 1.1327741103930788, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08588129618790007, "standard_deviation": 0.007427565126812909, "minimum": 0.07243188859484119, "maximum": 0.0948901905656333, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9950745205962339, "standard_deviation": 0.0009717765621181585, "minimum": 0.993393874460096, "maximum": 0.996197161881538, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.9321869807918037, "standard_deviation": 0.03839687830306863, "minimum": 0.8714601586254775, "maximum": 0.9871485291065267, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4975920931181006, "standard_deviation": 0.22027053617876066, "minimum": 0.17240091050856554, "maximum": 0.8006670707550239, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07408352363084213, "standard_deviation": 0.00722073541120203, "minimum": 0.06512641716134648, "maximum": 0.08569690717740618, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9983185103179821, "standard_deviation": 0.0006009608642944007, "minimum": 0.9971368193442681, "maximum": 0.9989123872502479, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.678253148533922, "standard_deviation": 0.05098320639458834, "minimum": 0.6219409129420845, "maximum": 0.7575743728975686, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7465122300760482, "standard_deviation": 0.3695563737340432, "minimum": 0.1047713334606254, "maximum": 1.2245132557321012, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04202926834547613, "standard_deviation": 0.0074908430183526905, "minimum": 0.034185545900556516, "maximum": 0.056138615733852495, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1896983838446507, "standard_deviation": 0.03999041699782174, "minimum": 0.13177216156943608, "maximum": 0.2462978926526624, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.378526404051687, "standard_deviation": 0.005794773220741435, "minimum": 5.3707267396523335, "maximum": 5.386982293562627, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.4401518622155989, "standard_deviation": 0.027498800945144095, "minimum": 0.39613528173077917, "maximum": 0.4753866646363873, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.08828234906970411, "standard_deviation": 0.03353375493087512, "minimum": -0.13173241082731396, "maximum": -0.03585506931919942, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.997189288200431, "standard_deviation": 0.0004206681130446911, "minimum": 0.9965917252060119, "maximum": 0.9978178142138913, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9173606021325812, "standard_deviation": 0.036201475605898925, "minimum": 0.8622781874291147, "maximum": 0.9579182046124912, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4738510229841554, "standard_deviation": 0.26163311408433276, "minimum": 0.05997749336278888, "maximum": 0.8260753808210977, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05332590007095614, "standard_deviation": 0.004328577939882692, "minimum": 0.04674854235477889, "maximum": 0.058912783213308936, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.999134320933816, "standard_deviation": 0.00027244101592914126, "minimum": 0.9986273334467389, "maximum": 0.9993821370766501, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5813502352497391, "standard_deviation": 0.04044617340672696, "minimum": 0.5253343068967528, "maximum": 0.6425906439239866, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6442597445612461, "standard_deviation": 0.2720519664626046, "minimum": 0.1262079538949999, "maximum": 0.9652500719537604, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.029776516725365573, "standard_deviation": 0.004995156711889842, "minimum": 0.024792121961029843, "maximum": 0.03866639872264592, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs066_whisper10_BASIC5000_2372", "language": "ja", "style": "whisper", "speaker": "jvs_jvs066", "source_utterance_id": "BASIC5000_2372", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 96209, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs066_whisper10_BASIC5000_2372.wav", "source_file_sha256": "0cd67a512b6770abd7e169b447a819db8221646446c692f9abefdc6e57b89cb6", "decoded_pcm_sha256": "97a4254221777a4b1bec3289499f9287ccf298e1e1d1d3cf642fe2c3fb8e4de7", "original_source_sha256": "0cd67a512b6770abd7e169b447a819db8221646446c692f9abefdc6e57b89cb6", "corpus_entry_id": "jvs_jvs066_whisper10_BASIC5000_2372"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 1.9535846710205078, "predicted_mos": 1.9535846710205078, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 96209, "input_sample_rate": 24000, "input_seconds": 4.008708333333334, "input_float32_sha256": "df73104f031cf2d55449cafb23852f1a3d648078a8ec4bc76d6675d2276d5b95", "internal_samples": 64140, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.569401100277901}, "waveform_sha256": "ac55c4e22d12e84c044a290c548290ab0f68c5b92a37eeb980c21667b0ecbb9d"}, "rows": [{"case": "jvs_jvs066_whisper10_BASIC5000_2372", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 1.085850477218628, "predicted_mos": 1.085850477218628, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 96209, "input_sample_rate": 24000, "input_seconds": 4.008708333333334, "input_float32_sha256": "1872c211c92a1997e18e042e455b792b178ccfd6ab1d78b722672adebc6873d4", "internal_samples": 64140, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.042648499831557}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.712237387762556, "全帯域_10ms_rms_envelope_nrmse": 0.16282017505426682, "全帯域_10ms_envelope_correlation": 0.9753588778592562, "全帯域_10ms_modulation_mae_db": 0.17160346509366167, "全帯域_40ms_log_rms_mae_db": 0.9669612777638225, "全帯域_40ms_rms_envelope_nrmse": 0.08968946078840696, "全帯域_40ms_envelope_correlation": 0.9915072717572023, "全帯域_40ms_modulation_mae_db": 0.2430075583118312, "300–1000 Hz_10ms_log_rms_mae_db": 2.6047981493479018, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2607209041496645, "300–1000 Hz_10ms_envelope_correlation": 0.9515420010914665, "300–1000 Hz_10ms_modulation_mae_db": 0.4400996879351106, "300–1000 Hz_40ms_log_rms_mae_db": 1.9083886777915922, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.164066911792632, "300–1000 Hz_40ms_envelope_correlation": 0.9791720513217279, "300–1000 Hz_40ms_modulation_mae_db": 0.6052855528163205, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8751267341132154, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21081343655908485, "1000–3000 Hz_10ms_envelope_correlation": 0.966223133048443, "1000–3000 Hz_10ms_modulation_mae_db": 0.20603502434813947, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1682164489852567, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12628314603822782, "1000–3000 Hz_40ms_envelope_correlation": 0.9866439354863928, "1000–3000 Hz_40ms_modulation_mae_db": 0.4316832030729311, "3000–6000 Hz_10ms_log_rms_mae_db": 1.719334386856771, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17609358546154183, "3000–6000 Hz_10ms_envelope_correlation": 0.9776930390397746, "3000–6000 Hz_10ms_modulation_mae_db": 0.5966851184650526, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0296585872808357, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09472592161115757, "3000–6000 Hz_40ms_envelope_correlation": 0.9935995361063964, "3000–6000 Hz_40ms_modulation_mae_db": 0.6801609002706721, "mr_stft_db": 6.1477553286182385, "band_mae_db": 0.19990989778683427, "rms_gain_error_db": 0.013645286793610477, "output_peak": 0.05191181541768}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6420482390890272, "全帯域_10ms_rms_envelope_nrmse": 0.1534870835530218, "全帯域_10ms_envelope_correlation": 0.9781025747350219, "全帯域_10ms_modulation_mae_db": 0.3515165984971715, "全帯域_40ms_log_rms_mae_db": 0.9017933332766999, "全帯域_40ms_rms_envelope_nrmse": 0.08043414433967618, "全帯域_40ms_envelope_correlation": 0.99316786151191, "全帯域_40ms_modulation_mae_db": 0.26982451382161815, "300–1000 Hz_10ms_log_rms_mae_db": 2.575537280749481, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24298420707949006, "300–1000 Hz_10ms_envelope_correlation": 0.9581170742937918, "300–1000 Hz_10ms_modulation_mae_db": 0.27387535636990773, "300–1000 Hz_40ms_log_rms_mae_db": 1.8080312961928808, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15123790005200358, "300–1000 Hz_40ms_envelope_correlation": 0.9825610181417538, "300–1000 Hz_40ms_modulation_mae_db": 0.42595392701596907, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8483984073124617, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20268669026728922, "1000–3000 Hz_10ms_envelope_correlation": 0.9689068259045525, "1000–3000 Hz_10ms_modulation_mae_db": 0.4595698729077415, "1000–3000 Hz_40ms_log_rms_mae_db": 1.16463674745318, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11283919600151839, "1000–3000 Hz_40ms_envelope_correlation": 0.9893454078950927, "1000–3000 Hz_40ms_modulation_mae_db": 0.7737067897540383, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6796662848926582, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17960838586687275, "3000–6000 Hz_10ms_envelope_correlation": 0.9753508620191822, "3000–6000 Hz_10ms_modulation_mae_db": 0.5593186417748185, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0099500959442531, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08953231814710758, "3000–6000 Hz_40ms_envelope_correlation": 0.9933289872471748, "3000–6000 Hz_40ms_modulation_mae_db": 0.5746755416780651, "mr_stft_db": 6.149531788878289, "band_mae_db": 0.17571798531942973, "rms_gain_error_db": 0.0006615772081413661, "output_peak": 0.060182849782415934}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6814525941082112, "全帯域_10ms_rms_envelope_nrmse": 0.16589621025668824, "全帯域_10ms_envelope_correlation": 0.9742273306352053, "全帯域_10ms_modulation_mae_db": 0.37243388451187714, "全帯域_40ms_log_rms_mae_db": 0.8481941570381123, "全帯域_40ms_rms_envelope_nrmse": 0.08426969935090008, "全帯域_40ms_envelope_correlation": 0.9925017006184265, "全帯域_40ms_modulation_mae_db": 0.5415164804000056, "300–1000 Hz_10ms_log_rms_mae_db": 2.5415080699065515, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27351011582765516, "300–1000 Hz_10ms_envelope_correlation": 0.9431016807816063, "300–1000 Hz_10ms_modulation_mae_db": 0.8535352985703216, "300–1000 Hz_40ms_log_rms_mae_db": 1.6679253272828996, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1575743129348656, "300–1000 Hz_40ms_envelope_correlation": 0.9788109729913385, "300–1000 Hz_40ms_modulation_mae_db": 0.7316967539608049, "1000–3000 Hz_10ms_log_rms_mae_db": 1.907849502862913, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2150001110097768, "1000–3000 Hz_10ms_envelope_correlation": 0.9648828061558237, "1000–3000 Hz_10ms_modulation_mae_db": 0.2606017666907346, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1436168987489903, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.115788402533046, "1000–3000 Hz_40ms_envelope_correlation": 0.9887896773003155, "1000–3000 Hz_40ms_modulation_mae_db": 0.615516364181922, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6825718388691757, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1817483631477012, "3000–6000 Hz_10ms_envelope_correlation": 0.9742013304484064, "3000–6000 Hz_10ms_modulation_mae_db": 0.6371375532229772, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0358158616472821, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1003760936302598, "3000–6000 Hz_40ms_envelope_correlation": 0.9914326006778834, "3000–6000 Hz_40ms_modulation_mae_db": 0.7271664043409093, "mr_stft_db": 6.126476270582141, "band_mae_db": 0.4985849477852149, "rms_gain_error_db": -0.07289360462356875, "output_peak": 0.05170465076562936}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6414429066681628, "全帯域_10ms_rms_envelope_nrmse": 0.13029248056977, "全帯域_10ms_envelope_correlation": 0.9845147520058166, "全帯域_10ms_modulation_mae_db": 0.7800743835050467, "全帯域_40ms_log_rms_mae_db": 0.8957740112897911, "全帯域_40ms_rms_envelope_nrmse": 0.07017312811095945, "全帯域_40ms_envelope_correlation": 0.9955044293755216, "全帯域_40ms_modulation_mae_db": 0.7575709802263466, "300–1000 Hz_10ms_log_rms_mae_db": 2.582037989829301, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2400985039159039, "300–1000 Hz_10ms_envelope_correlation": 0.9568333417056224, "300–1000 Hz_10ms_modulation_mae_db": 0.4916911320992794, "300–1000 Hz_40ms_log_rms_mae_db": 1.8436132184306275, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14909426457653094, "300–1000 Hz_40ms_envelope_correlation": 0.9813929480983902, "300–1000 Hz_40ms_modulation_mae_db": 0.5979583374597648, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7973448543047406, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17496001260003718, "1000–3000 Hz_10ms_envelope_correlation": 0.9770783083151441, "1000–3000 Hz_10ms_modulation_mae_db": 0.633504453951843, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0957791847501823, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.100827455555531, "1000–3000 Hz_40ms_envelope_correlation": 0.992379456784541, "1000–3000 Hz_40ms_modulation_mae_db": 0.8087549017031214, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7029616378373902, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17185458432084524, "3000–6000 Hz_10ms_envelope_correlation": 0.9770080270088436, "3000–6000 Hz_10ms_modulation_mae_db": 0.7379398947663205, "3000–6000 Hz_40ms_log_rms_mae_db": 1.03375333127701, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10913919870139288, "3000–6000 Hz_40ms_envelope_correlation": 0.989997706812332, "3000–6000 Hz_40ms_modulation_mae_db": 1.0463696428936835, "mr_stft_db": 6.112935924297279, "band_mae_db": 0.4237689164716218, "rms_gain_error_db": -0.23085055456673403, "output_peak": 0.051937325724671704}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7092352620109152, "全帯域_10ms_rms_envelope_nrmse": 0.15000709970492665, "全帯域_10ms_envelope_correlation": 0.9790215235965916, "全帯域_10ms_modulation_mae_db": 0.3214235832927655, "全帯域_40ms_log_rms_mae_db": 0.8666139494793822, "全帯域_40ms_rms_envelope_nrmse": 0.08274946372701636, "全帯域_40ms_envelope_correlation": 0.9927523296059627, "全帯域_40ms_modulation_mae_db": 0.5213777988758659, "300–1000 Hz_10ms_log_rms_mae_db": 2.6174467854277816, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25488503991437256, "300–1000 Hz_10ms_envelope_correlation": 0.9530405402938099, "300–1000 Hz_10ms_modulation_mae_db": 0.7862814331153595, "300–1000 Hz_40ms_log_rms_mae_db": 1.8565058842672482, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15440804500024802, "300–1000 Hz_40ms_envelope_correlation": 0.9812454501005233, "300–1000 Hz_40ms_modulation_mae_db": 0.8046495501894558, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8026534016414768, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19115304139773975, "1000–3000 Hz_10ms_envelope_correlation": 0.9722740527632648, "1000–3000 Hz_10ms_modulation_mae_db": 0.5374054314980908, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1060502106709458, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10999936520661278, "1000–3000 Hz_40ms_envelope_correlation": 0.9898838694192449, "1000–3000 Hz_40ms_modulation_mae_db": 0.4108544049521479, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6785021552951367, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18923160263502084, "3000–6000 Hz_10ms_envelope_correlation": 0.974514529987796, "3000–6000 Hz_10ms_modulation_mae_db": 0.7599619498144893, "3000–6000 Hz_40ms_log_rms_mae_db": 1.039853609868785, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10566680600382752, "3000–6000 Hz_40ms_envelope_correlation": 0.9920971030467854, "3000–6000 Hz_40ms_modulation_mae_db": 0.5167376852665387, "mr_stft_db": 6.126409834343072, "band_mae_db": 0.6023648683356246, "rms_gain_error_db": -0.020954347018245945, "output_peak": 0.06519807947412244}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6342313936046662, "全帯域_10ms_rms_envelope_nrmse": 0.15647536019493163, "全帯域_10ms_envelope_correlation": 0.9772429161860093, "全帯域_10ms_modulation_mae_db": 0.7208946358928129, "全帯域_40ms_log_rms_mae_db": 0.9084300950027544, "全帯域_40ms_rms_envelope_nrmse": 0.08335343517882667, "全帯域_40ms_envelope_correlation": 0.9932690366053616, "全帯域_40ms_modulation_mae_db": 0.8920886130868105, "300–1000 Hz_10ms_log_rms_mae_db": 2.638942552152329, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26521578426502523, "300–1000 Hz_10ms_envelope_correlation": 0.9481790233399396, "300–1000 Hz_10ms_modulation_mae_db": 0.3401674645833303, "300–1000 Hz_40ms_log_rms_mae_db": 1.9589943764835382, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16212171533541375, "300–1000 Hz_40ms_envelope_correlation": 0.978530342844378, "300–1000 Hz_40ms_modulation_mae_db": 0.5644609519949014, "1000–3000 Hz_10ms_log_rms_mae_db": 1.9279800292259954, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18757915315020846, "1000–3000 Hz_10ms_envelope_correlation": 0.9734038861998487, "1000–3000 Hz_10ms_modulation_mae_db": 0.712750759125003, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2083234751741745, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10971259988427995, "1000–3000 Hz_40ms_envelope_correlation": 0.9906173330638905, "1000–3000 Hz_40ms_modulation_mae_db": 1.0295007498583442, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6782230924145054, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19097900095730422, "3000–6000 Hz_10ms_envelope_correlation": 0.9714891283329531, "3000–6000 Hz_10ms_modulation_mae_db": 0.36838331902898486, "3000–6000 Hz_40ms_log_rms_mae_db": 1.003480788697341, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10593143350396012, "3000–6000 Hz_40ms_envelope_correlation": 0.9904941272419105, "3000–6000 Hz_40ms_modulation_mae_db": 0.5280852569711227, "mr_stft_db": 6.12391704414345, "band_mae_db": 0.39410665799015604, "rms_gain_error_db": -0.23236491527146383, "output_peak": 0.05871388349566064}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6858953369282992, "全帯域_10ms_rms_envelope_nrmse": 0.1390201553472818, "全帯域_10ms_envelope_correlation": 0.9819413710556546, "全帯域_10ms_modulation_mae_db": 0.2677278846934083, "全帯域_40ms_log_rms_mae_db": 0.8738439597089724, "全帯域_40ms_rms_envelope_nrmse": 0.07248621697589916, "全帯域_40ms_envelope_correlation": 0.9945661901858857, "全帯域_40ms_modulation_mae_db": 0.610160617301767, "300–1000 Hz_10ms_log_rms_mae_db": 2.563404783962687, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.23279598578073016, "300–1000 Hz_10ms_envelope_correlation": 0.959727771000055, "300–1000 Hz_10ms_modulation_mae_db": 0.38114111201503204, "300–1000 Hz_40ms_log_rms_mae_db": 1.7498237507398156, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1588038608875158, "300–1000 Hz_40ms_envelope_correlation": 0.9790541191601562, "300–1000 Hz_40ms_modulation_mae_db": 0.5689175405997754, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8221581249254786, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17466662831784271, "1000–3000 Hz_10ms_envelope_correlation": 0.9768882555856555, "1000–3000 Hz_10ms_modulation_mae_db": 0.43787491035266957, "1000–3000 Hz_40ms_log_rms_mae_db": 1.135699162069209, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08674588618084396, "1000–3000 Hz_40ms_envelope_correlation": 0.9937158131667952, "1000–3000 Hz_40ms_modulation_mae_db": 0.8076856209132032, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6401683600921808, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1548966505120381, "3000–6000 Hz_10ms_envelope_correlation": 0.9814037472594183, "3000–6000 Hz_10ms_modulation_mae_db": 0.5572054791155842, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0119431620928083, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08382837258092406, "3000–6000 Hz_40ms_envelope_correlation": 0.9943311411693082, "3000–6000 Hz_40ms_modulation_mae_db": 0.8873632389062429, "mr_stft_db": 6.139670358835126, "band_mae_db": 0.36403571221068454, "rms_gain_error_db": -0.11836719734935609, "output_peak": 0.05743660011750735}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.689196783008319, "全帯域_10ms_rms_envelope_nrmse": 0.17211398966599079, "全帯域_10ms_envelope_correlation": 0.9728735593771625, "全帯域_10ms_modulation_mae_db": 0.43380949615702463, "全帯域_40ms_log_rms_mae_db": 0.8989543106800949, "全帯域_40ms_rms_envelope_nrmse": 0.09925228429005709, "全帯域_40ms_envelope_correlation": 0.9898316096785333, "全帯域_40ms_modulation_mae_db": 0.5833552186808576, "300–1000 Hz_10ms_log_rms_mae_db": 2.6871981434456513, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2395171962162964, "300–1000 Hz_10ms_envelope_correlation": 0.9573595642247299, "300–1000 Hz_10ms_modulation_mae_db": 0.5242715997113839, "300–1000 Hz_40ms_log_rms_mae_db": 1.8759586102149903, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14306864271769668, "300–1000 Hz_40ms_envelope_correlation": 0.9835115766373906, "300–1000 Hz_40ms_modulation_mae_db": 0.2772300774563456, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8604031846498597, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.22103368729379622, "1000–3000 Hz_10ms_envelope_correlation": 0.9643374546987019, "1000–3000 Hz_10ms_modulation_mae_db": 0.6873728727397966, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1556943106049273, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.13324138666783358, "1000–3000 Hz_40ms_envelope_correlation": 0.9859164657910044, "1000–3000 Hz_40ms_modulation_mae_db": 0.7958147483846899, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6805513594778796, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17204022829316856, "3000–6000 Hz_10ms_envelope_correlation": 0.9781425115766261, "3000–6000 Hz_10ms_modulation_mae_db": 0.3097836745613715, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0163273304967548, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09390977590741542, "3000–6000 Hz_40ms_envelope_correlation": 0.9932220397620848, "3000–6000 Hz_40ms_modulation_mae_db": 0.45648065690825107, "mr_stft_db": 6.126378765910847, "band_mae_db": 0.6146943487987624, "rms_gain_error_db": 0.09822750933986506, "output_peak": 0.06410355332840681}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 96209, "output_samples": 96209, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.4364791140139594, "spectral_convergence": 0.5939965878680474, "spectral_convergence_status": "ok", "amplitude_floor": 1.776300245720871e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.01280105012838, "spectral_convergence": 0.6073251057088024, "spectral_convergence_status": "ok", "amplitude_floor": 1.1913344769267054e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.993985821712375, "spectral_convergence": 0.624016211031098, "spectral_convergence_status": "ok", "amplitude_floor": 5.645485889979311e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0529488065388325e-06, "output_power": 1.0023976042467537e-06, "delta_db": -0.21367236662742042, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.178233710401702e-07, "output_power": 6.849545931575881e-07, "delta_db": 0.4479744952278719, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.652745613182611e-06, "output_power": 5.625251197426527e-06, "delta_db": -0.02117520850936739, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.2826510059132755e-05, "output_power": 1.2488873278031961e-05, "delta_db": -0.11585247149393052, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2385922939210616e-05, "output_power": 1.2934390569671553e-05, "delta_db": 0.1881759720297413, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.5916906482380547e-06, "output_power": 1.6448851489036476e-06, "delta_db": 0.14276914880309366, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.299457135974266e-06, "output_power": 2.1609780528022555e-06, "delta_db": -0.26974962181641465, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.19990989778683427, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.013645286793610477, "pitch": null, "output_rms_dbfs": -44.37210890355396, "output_peak": 0.05191181541768, "reference_rms_dbfs": -44.38575419034756, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.1477553286182385}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 96209, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.089458070502993e-05, "log_rms_mae_db": 1.712237387762556, "rms_envelope_nrmse": 0.16282017505426682, "envelope_correlation": 0.9753588778592562, "rms_gain_error_db": 0.013641861496225604, "reference_mean_power": 3.6506204511776254e-05, "output_mean_power": 3.662105643676844e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 2.0041859534078988e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.999428757782778e-06, "output_power": 7.93703789651427e-06, "reference_active": true, "delta_db": -0.03400521055625787}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3205374160249087e-06, "output_power": 3.1553525160099277e-06, "reference_active": true, "delta_db": -0.22160492586171054}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.233369046941817e-06, "output_power": 1.1619114170251277e-06, "reference_active": true, "delta_db": -0.2592002588630166}], "active_band_count": 3, "active_band_mae_db": 0.17160346509366167}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.7773650083170072e-05, "log_rms_mae_db": 0.9669612777638225, "rms_envelope_nrmse": 0.08968946078840696, "envelope_correlation": 0.9915072717572023, "rms_gain_error_db": 0.013622789149234957, "reference_mean_power": 3.678163866257165e-05, "output_mean_power": 3.6897195092119254e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.6475917872957343e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.744366291346524e-06, "output_power": 6.861438157247584e-06, "reference_active": true, "delta_db": 0.07474004258726837}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5635835823033082e-06, "output_power": 1.5161750004719332e-06, "reference_active": true, "delta_db": -0.13371770196807356}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.396664522501232e-08, "output_power": 8.335223107669854e-08, "reference_active": true, "delta_db": -0.5205649303801517}], "active_band_count": 3, "active_band_mae_db": 0.2430075583118312}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1737971097625835e-05, "log_rms_mae_db": 2.6047981493479018, "rms_envelope_nrmse": 0.2607209041496645, "envelope_correlation": 0.9515420010914665, "rms_gain_error_db": 0.35734644929529125, "reference_mean_power": 3.7178438627460445e-06, "output_mean_power": 4.036693653006579e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.0069118410394303e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5873171334916186e-06, "output_power": 1.6712955419857302e-06, "reference_active": true, "delta_db": 0.22389550694356494}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.351037742291938e-07, "output_power": 5.719750170719901e-07, "reference_active": true, "delta_db": -0.454676336885831}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7445146919256035e-07, "output_power": 2.3675155381706436e-07, "reference_active": true, "delta_db": -0.6417272199759358}], "active_band_count": 3, "active_band_mae_db": 0.4400996879351106}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 7.730313378567735e-06, "log_rms_mae_db": 1.9083886777915922, "rms_envelope_nrmse": 0.164066911792632, "envelope_correlation": 0.9791720513217279, "rms_gain_error_db": 0.3573333666003846, "reference_mean_power": 3.745927267695172e-06, "output_mean_power": 4.067173295442497e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.5331447910659217e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5569974188207908e-06, "output_power": 1.6312295014664468e-06, "reference_active": true, "delta_db": 0.20227174639674833}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5335281635338005e-07, "output_power": 3.066502603669038e-07, "reference_active": true, "delta_db": -0.6156521938390986}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.1249603669561348e-08, "output_power": 1.6887196719927637e-08, "reference_active": true, "delta_db": -0.9979327182131142}], "active_band_count": 3, "active_band_mae_db": 0.6052855528163205}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.066376004316646e-05, "log_rms_mae_db": 1.8751267341132154, "rms_envelope_nrmse": 0.21081343655908485, "envelope_correlation": 0.966223133048443, "rms_gain_error_db": -0.05399112608055998, "reference_mean_power": 1.9040046826256083e-05, "output_mean_power": 1.8804807825040444e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 1.3406247189798443e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.3392457188005514e-06, "output_power": 6.040442453667432e-06, "reference_active": true, "delta_db": -0.2096883478403464}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.391738535251293e-06, "output_power": 2.209717065181433e-06, "reference_active": true, "delta_db": -0.3437703119869768}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.54995852980617e-07, "output_power": 7.438406782424272e-07, "reference_active": true, "delta_db": -0.0646464132170952}], "active_band_count": 3, "active_band_mae_db": 0.20603502434813947}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.6710315888953048e-05, "log_rms_mae_db": 1.1682164489852567, "rms_envelope_nrmse": 0.12628314603822782, "envelope_correlation": 0.9866439354863928, "rms_gain_error_db": -0.053991275921297446, "reference_mean_power": 1.9183917331823965e-05, "output_mean_power": 1.89469001626777e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.1409929070898633e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.5949700460751985e-06, "output_power": 5.42198434475451e-06, "reference_active": true, "delta_db": -0.13639506498072002}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1687645280234336e-06, "output_power": 1.0785627747613344e-06, "reference_active": true, "delta_db": -0.3488159521614142}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.657756100862398e-08, "output_power": 6.355030961557019e-08, "reference_active": true, "delta_db": -0.8098385920766591}], "active_band_count": 3, "active_band_mae_db": 0.4316832030729311}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1530093504582296e-05, "log_rms_mae_db": 1.719334386856771, "rms_envelope_nrmse": 0.17609358546154183, "envelope_correlation": 0.9776930390397746, "rms_gain_error_db": 0.2983476825141041, "reference_mean_power": 5.108146850353514e-06, "output_mean_power": 5.4713959199265015e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.254259363144466e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7396247028720546e-06, "output_power": 1.8471449922974657e-06, "reference_active": true, "delta_db": 0.26045420807780206}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.118165550857846e-07, "output_power": 5.61294530336834e-07, "reference_active": true, "delta_db": 0.40076480802962583}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4689547511366827e-07, "output_power": 1.1327257785876511e-07, "reference_active": true, "delta_db": -1.1288363392877299}], "active_band_count": 3, "active_band_mae_db": 0.5966851184650526}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 9.091353933231884e-06, "log_rms_mae_db": 1.0296585872808357, "rms_envelope_nrmse": 0.09472592161115757, "envelope_correlation": 0.9935995361063964, "rms_gain_error_db": 0.29834722441607797, "reference_mean_power": 5.146742550240226e-06, "output_mean_power": 5.512735644633602e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.7984368001248054e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6090100968943592e-06, "output_power": 1.6963787828208847e-06, "reference_active": true, "delta_db": 0.22964062553166575}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.367924284305246e-07, "output_power": 2.570559154230391e-07, "reference_active": true, "delta_db": 0.35659790925530793}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2506680970493352e-08, "output_power": 8.947828573274468e-09, "reference_active": true, "delta_db": -1.4542441660250427}], "active_band_count": 3, "active_band_mae_db": 0.6801609002706721}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5996950054250156, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "b0315f840e1e957a623b7064fcd61da2ff3a254109f1597e7439af886c898302", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9704993403339293, "standard_deviation": 0.005155072264940714, "minimum": 0.9643374546987019, "maximum": 0.9770783083151441, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.8552392798795176, "standard_deviation": 0.04741824299253788, "minimum": 1.7973448543047406, "maximum": 1.9279800292259954, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.49188938645175234, "standard_deviation": 0.1883343800730561, "minimum": 0.20603502434813947, "maximum": 0.712750759125003, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1972365950744719, "standard_deviation": 0.017855785756130282, "minimum": 0.17466662831784271, "maximum": 0.22103368729379622, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9896614948634097, "standard_deviation": 0.0026397720464440065, "minimum": 0.9859164657910044, "maximum": 0.9937158131667952, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.1472520548071081, "standard_deviation": 0.03592940584885067, "minimum": 1.0957791847501823, "maximum": 1.2083234751741745, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7091895978525498, "standard_deviation": 0.20998935221893092, "minimum": 0.4108544049521479, "maximum": 1.0295007498583442, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1119296797584867, "standard_deviation": 0.014352959901470867, "minimum": 0.08674588618084396, "maximum": 0.13324138666783358, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.976225396959125, "standard_deviation": 0.003011361492145512, "minimum": 0.9714891283329531, "maximum": 0.9814037472594183, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.6827473894669622, "standard_deviation": 0.022718890207419136, "minimum": 1.6401683600921808, "maximum": 1.719334386856771, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5658019538436998, "standard_deviation": 0.1594667550432694, "minimum": 0.3097836745613715, "maximum": 0.7599619498144893, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1770565501493116, "standard_deviation": 0.011431809634529827, "minimum": 0.1548966505120381, "maximum": 0.19097900095730422, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9923129052579844, "standard_deviation": 0.0015619240585049144, "minimum": 0.989997706812332, "maximum": 0.9943311411693082, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.0225978459131337, "standard_deviation": 0.013758349977750894, "minimum": 1.003480788697341, "maximum": 1.039853609868785, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6771299159044357, "standard_deviation": 0.203600391322943, "minimum": 0.45648065690825107, "maximum": 1.0463696428936835, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09788874001075562, "standard_deviation": 0.008874540408108393, "minimum": 0.08382837258092406, "maximum": 0.10913919870139288, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9534876245913777, "standard_deviation": 0.005689481303508648, "minimum": 0.9431016807816063, "maximum": 0.959727771000055, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.6013592193527106, "standard_deviation": 0.04646695522445306, "minimum": 2.5415080699065515, "maximum": 2.6871981434456513, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5113828855499656, "standard_deviation": 0.20735067946618987, "minimum": 0.27387535636990773, "maximum": 0.8535352985703216, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.25121596714364225, "standard_deviation": 0.014463484486590135, "minimum": 0.23279598578073016, "maximum": 0.27351011582765516, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9805348099119573, "standard_deviation": 0.0018991399777031994, "minimum": 0.978530342844378, "maximum": 0.9835115766373906, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.833655142675449, "standard_deviation": 0.09169560148739124, "minimum": 1.6679253272828996, "maximum": 1.9589943764835382, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5720190864366672, "standard_deviation": 0.1646189228386174, "minimum": 0.2772300774563456, "maximum": 0.8046495501894558, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15504695666211327, "standard_deviation": 0.007027957723241884, "minimum": 0.14306864271769668, "maximum": 0.164066911792632, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.409147916837291, "standard_deviation": 0.16402365430112306, "minimum": 0.17571798531942973, "maximum": 0.6146943487987624, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.131634414451055, "standard_deviation": 0.012736293207484466, "minimum": 6.112935924297279, "maximum": 6.149531788878289, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.057648594763261785, "standard_deviation": 0.005439579045301895, "minimum": 0.05170465076562936, "maximum": 0.06519807947412244, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07036203068596897, "standard_deviation": 0.11788465323864707, "minimum": -0.23236491527146383, "maximum": 0.09822750933986506, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9779103631813398, "standard_deviation": 0.00391021159667677, "minimum": 0.9728735593771625, "maximum": 0.9845147520058166, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.6744674878975196, "standard_deviation": 0.03115004465015293, "minimum": 1.6342313936046662, "maximum": 1.712237387762556, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.42743549145547105, "standard_deviation": 0.21430852615947638, "minimum": 0.17160346509366167, "maximum": 0.7800743835050467, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.15376406929335973, "standard_deviation": 0.013916909494717532, "minimum": 0.13029248056977, "maximum": 0.17211398966599079, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9928875536673505, "standard_deviation": 0.0017444237971934386, "minimum": 0.9898316096785333, "maximum": 0.9955044293755216, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8950706367799537, "standard_deviation": 0.03558745950173792, "minimum": 0.8481941570381123, "maximum": 0.9669612777638225, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5523627225881378, "standard_deviation": 0.2198802936242107, "minimum": 0.2430075583118312, "maximum": 0.8920886130868105, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.08280097909521775, "standard_deviation": 0.009196431514582803, "minimum": 0.07017312811095945, "maximum": 0.09925228429005709, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_whisper10_BASIC5000_2372", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 1.0668725967407227, "predicted_mos": 1.0668725967407227, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 96209, "input_sample_rate": 24000, "input_seconds": 4.008708333333334, "input_float32_sha256": "db405ef0eb1300f1d99a599182c74be28b6ce24b6d5b4380597d322966a6b09e", "internal_samples": 64140, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 4.373734199907631}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7302289116966683, "全帯域_10ms_rms_envelope_nrmse": 0.16342565334053868, "全帯域_10ms_envelope_correlation": 0.9751231745986503, "全帯域_10ms_modulation_mae_db": 0.17547701091528636, "全帯域_40ms_log_rms_mae_db": 0.9732235256852914, "全帯域_40ms_rms_envelope_nrmse": 0.0896968234477192, "全帯域_40ms_envelope_correlation": 0.9914867889243907, "全帯域_40ms_modulation_mae_db": 0.2322732799133889, "300–1000 Hz_10ms_log_rms_mae_db": 2.4898696997813516, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26079179307914935, "300–1000 Hz_10ms_envelope_correlation": 0.9514601851235823, "300–1000 Hz_10ms_modulation_mae_db": 0.4133888418836153, "300–1000 Hz_40ms_log_rms_mae_db": 1.7345382473497013, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16120157139157631, "300–1000 Hz_40ms_envelope_correlation": 0.979892889535129, "300–1000 Hz_40ms_modulation_mae_db": 0.5885916736321332, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8990562089657743, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2107330227168611, "1000–3000 Hz_10ms_envelope_correlation": 0.9662081481679156, "1000–3000 Hz_10ms_modulation_mae_db": 0.2597583397209497, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1800569859242585, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12350518272950049, "1000–3000 Hz_40ms_envelope_correlation": 0.9872476315651516, "1000–3000 Hz_40ms_modulation_mae_db": 0.4100519975076824, "3000–6000 Hz_10ms_log_rms_mae_db": 1.746515482406632, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17458774121142165, "3000–6000 Hz_10ms_envelope_correlation": 0.9776368453901281, "3000–6000 Hz_10ms_modulation_mae_db": 0.6811762092209706, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9764492383724793, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09254345345612247, "3000–6000 Hz_40ms_envelope_correlation": 0.9935509642072667, "3000–6000 Hz_40ms_modulation_mae_db": 0.7738543757907284, "mr_stft_db": 6.140603224772815, "band_mae_db": 0.19366563763540917, "rms_gain_error_db": -0.0013881231941128944, "output_peak": 0.049345619907640734}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6797540882537418, "全帯域_10ms_rms_envelope_nrmse": 0.15215374018810052, "全帯域_10ms_envelope_correlation": 0.9784690899596928, "全帯域_10ms_modulation_mae_db": 0.33914426961834776, "全帯域_40ms_log_rms_mae_db": 0.9049209107339536, "全帯域_40ms_rms_envelope_nrmse": 0.07881613044297005, "全帯域_40ms_envelope_correlation": 0.9934354633371548, "全帯域_40ms_modulation_mae_db": 0.28597182635181945, "300–1000 Hz_10ms_log_rms_mae_db": 2.4854076913592733, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24246882019449903, "300–1000 Hz_10ms_envelope_correlation": 0.9583216187629896, "300–1000 Hz_10ms_modulation_mae_db": 0.30018286899808705, "300–1000 Hz_40ms_log_rms_mae_db": 1.6672103310811066, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15194084713544298, "300–1000 Hz_40ms_envelope_correlation": 0.9823796463536844, "300–1000 Hz_40ms_modulation_mae_db": 0.43662286747680484, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8988809782509184, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20021923389677088, "1000–3000 Hz_10ms_envelope_correlation": 0.9697141847846341, "1000–3000 Hz_10ms_modulation_mae_db": 0.40375920176420016, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1841085740906732, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10928997194183086, "1000–3000 Hz_40ms_envelope_correlation": 0.9900254658137261, "1000–3000 Hz_40ms_modulation_mae_db": 0.8336153900219699, "3000–6000 Hz_10ms_log_rms_mae_db": 1.669963336498953, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17791561898060965, "3000–6000 Hz_10ms_envelope_correlation": 0.9757275074299254, "3000–6000 Hz_10ms_modulation_mae_db": 0.5856406476098476, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9582762043833675, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0883704209165723, "3000–6000 Hz_40ms_envelope_correlation": 0.9934651080149578, "3000–6000 Hz_40ms_modulation_mae_db": 0.5973084707927253, "mr_stft_db": 6.144605627121099, "band_mae_db": 0.17153609491115995, "rms_gain_error_db": 0.002392495528135427, "output_peak": 0.06116942060987507}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6832357554851536, "全帯域_10ms_rms_envelope_nrmse": 0.16246835814951088, "全帯域_10ms_envelope_correlation": 0.9752911965341985, "全帯域_10ms_modulation_mae_db": 0.3846362403630584, "全帯域_40ms_log_rms_mae_db": 0.8558901464797463, "全帯域_40ms_rms_envelope_nrmse": 0.0808140720854829, "全帯域_40ms_envelope_correlation": 0.9931054192655842, "全帯域_40ms_modulation_mae_db": 0.5400022004934678, "300–1000 Hz_10ms_log_rms_mae_db": 2.4800703760643263, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2734528288794293, "300–1000 Hz_10ms_envelope_correlation": 0.94325574855513, "300–1000 Hz_10ms_modulation_mae_db": 0.8171643269766387, "300–1000 Hz_40ms_log_rms_mae_db": 1.579614689707704, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15921378638648245, "300–1000 Hz_40ms_envelope_correlation": 0.978361899032117, "300–1000 Hz_40ms_modulation_mae_db": 0.6753240867448822, "1000–3000 Hz_10ms_log_rms_mae_db": 1.9397813164815312, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21093141622724806, "1000–3000 Hz_10ms_envelope_correlation": 0.9662760767398141, "1000–3000 Hz_10ms_modulation_mae_db": 0.2911717174733888, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1682411551892709, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11030174153584084, "1000–3000 Hz_40ms_envelope_correlation": 0.989835457918644, "1000–3000 Hz_40ms_modulation_mae_db": 0.6354350480764603, "3000–6000 Hz_10ms_log_rms_mae_db": 1.701909969564117, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17694140612424225, "3000–6000 Hz_10ms_envelope_correlation": 0.9755279288559519, "3000–6000 Hz_10ms_modulation_mae_db": 0.6730531836619386, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9884184155197873, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09517144944857305, "3000–6000 Hz_40ms_envelope_correlation": 0.992326249412913, "3000–6000 Hz_40ms_modulation_mae_db": 0.7556414421465204, "mr_stft_db": 6.127981720891377, "band_mae_db": 0.5292422648241518, "rms_gain_error_db": -0.06832267347551077, "output_peak": 0.051976458509504275}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.660986386439392, "全帯域_10ms_rms_envelope_nrmse": 0.13066990957523106, "全帯域_10ms_envelope_correlation": 0.9845099635201979, "全帯域_10ms_modulation_mae_db": 0.7852496985839138, "全帯域_40ms_log_rms_mae_db": 0.9142383930988721, "全帯域_40ms_rms_envelope_nrmse": 0.0702482207290643, "全帯域_40ms_envelope_correlation": 0.9956270010167084, "全帯域_40ms_modulation_mae_db": 0.7897422072986519, "300–1000 Hz_10ms_log_rms_mae_db": 2.5282202157441116, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.23968755920583748, "300–1000 Hz_10ms_envelope_correlation": 0.9566880302418832, "300–1000 Hz_10ms_modulation_mae_db": 0.5361622635035294, "300–1000 Hz_40ms_log_rms_mae_db": 1.756610414548897, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1452028248343859, "300–1000 Hz_40ms_envelope_correlation": 0.982189334705295, "300–1000 Hz_40ms_modulation_mae_db": 0.7260333132921893, "1000–3000 Hz_10ms_log_rms_mae_db": 1.890422171003867, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17728513188635164, "1000–3000 Hz_10ms_envelope_correlation": 0.9764994629308346, "1000–3000 Hz_10ms_modulation_mae_db": 0.5971392046296439, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1679800418757702, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1020386573079344, "1000–3000 Hz_40ms_envelope_correlation": 0.9922723029003623, "1000–3000 Hz_40ms_modulation_mae_db": 0.8033564235659005, "3000–6000 Hz_10ms_log_rms_mae_db": 1.68327385300213, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17083640991767382, "3000–6000 Hz_10ms_envelope_correlation": 0.9772611766633635, "3000–6000 Hz_10ms_modulation_mae_db": 0.7389762368871917, "3000–6000 Hz_40ms_log_rms_mae_db": 0.946506301250987, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10684780922969679, "3000–6000 Hz_40ms_envelope_correlation": 0.99044690158713, "3000–6000 Hz_40ms_modulation_mae_db": 1.014027305586126, "mr_stft_db": 6.118158720745453, "band_mae_db": 0.448082733984581, "rms_gain_error_db": -0.24887628731000416, "output_peak": 0.05064461606794103}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7405244911093252, "全帯域_10ms_rms_envelope_nrmse": 0.15365238690018668, "全帯域_10ms_envelope_correlation": 0.9780342402588058, "全帯域_10ms_modulation_mae_db": 0.28032125806513125, "全帯域_40ms_log_rms_mae_db": 0.8892203521802289, "全帯域_40ms_rms_envelope_nrmse": 0.0851559227566562, "全帯域_40ms_envelope_correlation": 0.9923375645126065, "全帯域_40ms_modulation_mae_db": 0.5093387882908857, "300–1000 Hz_10ms_log_rms_mae_db": 2.514639668143277, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2596880901855065, "300–1000 Hz_10ms_envelope_correlation": 0.951200701605337, "300–1000 Hz_10ms_modulation_mae_db": 0.7453269005273682, "300–1000 Hz_40ms_log_rms_mae_db": 1.7296835246651237, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15857960101594804, "300–1000 Hz_40ms_envelope_correlation": 0.9801292403958713, "300–1000 Hz_40ms_modulation_mae_db": 0.8425697574795707, "1000–3000 Hz_10ms_log_rms_mae_db": 1.821953065532159, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19560424358462172, "1000–3000 Hz_10ms_envelope_correlation": 0.9711227572609734, "1000–3000 Hz_10ms_modulation_mae_db": 0.5274782772692674, "1000–3000 Hz_40ms_log_rms_mae_db": 1.128236972213578, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11116470615338547, "1000–3000 Hz_40ms_envelope_correlation": 0.9896887658839497, "1000–3000 Hz_40ms_modulation_mae_db": 0.33905635253747035, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7028196070932589, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1889832855522017, "3000–6000 Hz_10ms_envelope_correlation": 0.9742644112588292, "3000–6000 Hz_10ms_modulation_mae_db": 0.7022363149629065, "3000–6000 Hz_40ms_log_rms_mae_db": 1.037661440714077, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10610027851994715, "3000–6000 Hz_40ms_envelope_correlation": 0.9917558607069377, "3000–6000 Hz_40ms_modulation_mae_db": 0.40186635332708304, "mr_stft_db": 6.134562528665814, "band_mae_db": 0.6048469432217678, "rms_gain_error_db": -0.0017783497159265507, "output_peak": 0.06423854692505317}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.672885952042969, "全帯域_10ms_rms_envelope_nrmse": 0.15953855838767741, "全帯域_10ms_envelope_correlation": 0.9763252631347203, "全帯域_10ms_modulation_mae_db": 0.7235785755451665, "全帯域_40ms_log_rms_mae_db": 0.9215929546663504, "全帯域_40ms_rms_envelope_nrmse": 0.08662603022045157, "全帯域_40ms_envelope_correlation": 0.9926962854492966, "全帯域_40ms_modulation_mae_db": 0.8497251430754762, "300–1000 Hz_10ms_log_rms_mae_db": 2.547200162133809, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2717383590421998, "300–1000 Hz_10ms_envelope_correlation": 0.9456900888841658, "300–1000 Hz_10ms_modulation_mae_db": 0.23546787808562097, "300–1000 Hz_40ms_log_rms_mae_db": 1.8049948680970045, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1637318586415441, "300–1000 Hz_40ms_envelope_correlation": 0.978132249514482, "300–1000 Hz_40ms_modulation_mae_db": 0.45874819054370436, "1000–3000 Hz_10ms_log_rms_mae_db": 1.9487057084891368, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1893919282514213, "1000–3000 Hz_10ms_envelope_correlation": 0.9728674864700283, "1000–3000 Hz_10ms_modulation_mae_db": 0.6632399374881843, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2049762448676036, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11196033042380733, "1000–3000 Hz_40ms_envelope_correlation": 0.99018401522441, "1000–3000 Hz_40ms_modulation_mae_db": 0.9684446013746726, "3000–6000 Hz_10ms_log_rms_mae_db": 1.695747476273287, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1905404060403513, "3000–6000 Hz_10ms_envelope_correlation": 0.9715683559097817, "3000–6000 Hz_10ms_modulation_mae_db": 0.430916841040081, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9765122257410316, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10516597186438371, "3000–6000 Hz_40ms_envelope_correlation": 0.9906445441000868, "3000–6000 Hz_40ms_modulation_mae_db": 0.6111831983590482, "mr_stft_db": 6.122313319659178, "band_mae_db": 0.397077672880547, "rms_gain_error_db": -0.2383347284215398, "output_peak": 0.05838241767860852}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.71905530351796, "全帯域_10ms_rms_envelope_nrmse": 0.1415534275622436, "全帯域_10ms_envelope_correlation": 0.9812757272919858, "全帯域_10ms_modulation_mae_db": 0.29032117524089357, "全帯域_40ms_log_rms_mae_db": 0.8915175411264169, "全帯域_40ms_rms_envelope_nrmse": 0.07329976387225269, "全帯域_40ms_envelope_correlation": 0.9944587326291503, "全帯域_40ms_modulation_mae_db": 0.6489107211508469, "300–1000 Hz_10ms_log_rms_mae_db": 2.4886533338487054, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24080851828524655, "300–1000 Hz_10ms_envelope_correlation": 0.9572872602251532, "300–1000 Hz_10ms_modulation_mae_db": 0.3509490192740608, "300–1000 Hz_40ms_log_rms_mae_db": 1.6547299329230543, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16579554915704212, "300–1000 Hz_40ms_envelope_correlation": 0.9774066231633304, "300–1000 Hz_40ms_modulation_mae_db": 0.5258928751647849, "1000–3000 Hz_10ms_log_rms_mae_db": 1.857276087725891, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18006045593015418, "1000–3000 Hz_10ms_envelope_correlation": 0.9754072596474559, "1000–3000 Hz_10ms_modulation_mae_db": 0.4585606357005774, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1409437717822752, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08920038515076335, "1000–3000 Hz_40ms_envelope_correlation": 0.9933552209576851, "1000–3000 Hz_40ms_modulation_mae_db": 0.8380793600883046, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6739616116131224, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15896899928092692, "3000–6000 Hz_10ms_envelope_correlation": 0.9804694485245755, "3000–6000 Hz_10ms_modulation_mae_db": 0.5558358838350131, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0068484456884663, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0898005943797458, "3000–6000 Hz_40ms_envelope_correlation": 0.9935975515824049, "3000–6000 Hz_40ms_modulation_mae_db": 0.9084142885328933, "mr_stft_db": 6.13980613106984, "band_mae_db": 0.3388534114255007, "rms_gain_error_db": -0.12545947551773043, "output_peak": 0.057411808110804846}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6972348275111238, "全帯域_10ms_rms_envelope_nrmse": 0.17365680507288955, "全帯域_10ms_envelope_correlation": 0.9723740620059494, "全帯域_10ms_modulation_mae_db": 0.4458771818098846, "全帯域_40ms_log_rms_mae_db": 0.9048355666021319, "全帯域_40ms_rms_envelope_nrmse": 0.10105972163414632, "全帯域_40ms_envelope_correlation": 0.9894452674316899, "全帯域_40ms_modulation_mae_db": 0.6363554725973221, "300–1000 Hz_10ms_log_rms_mae_db": 2.572241347722956, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.23517503678815657, "300–1000 Hz_10ms_envelope_correlation": 0.9585581114688921, "300–1000 Hz_10ms_modulation_mae_db": 0.481463365892157, "300–1000 Hz_40ms_log_rms_mae_db": 1.7493447138728826, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13637925634113093, "300–1000 Hz_40ms_envelope_correlation": 0.9849027062654013, "300–1000 Hz_40ms_modulation_mae_db": 0.30004339606043146, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8571522788226644, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2232698706133649, "1000–3000 Hz_10ms_envelope_correlation": 0.9639816245681264, "1000–3000 Hz_10ms_modulation_mae_db": 0.6604524764086115, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1245388024602134, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.13568646747045998, "1000–3000 Hz_40ms_envelope_correlation": 0.9856712934259763, "1000–3000 Hz_40ms_modulation_mae_db": 0.8154893899257832, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6900562486815962, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17684012024136303, "3000–6000 Hz_10ms_envelope_correlation": 0.9769241510010984, "3000–6000 Hz_10ms_modulation_mae_db": 0.3726901626470154, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9887358604452782, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0973980931087329, "3000–6000 Hz_40ms_envelope_correlation": 0.9927150780352816, "3000–6000 Hz_40ms_modulation_mae_db": 0.368681259898955, "mr_stft_db": 6.127108713961154, "band_mae_db": 0.6247652983444837, "rms_gain_error_db": 0.09483590295092688, "output_peak": 0.06493254636297152}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 96209, "output_samples": 96209, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.430778637507146, "spectral_convergence": 0.5918250068430361, "spectral_convergence_status": "ok", "amplitude_floor": 1.776300245720871e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.013557790753144, "spectral_convergence": 0.6057109973280693, "spectral_convergence_status": "ok", "amplitude_floor": 1.1913344769267054e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.977473246058158, "spectral_convergence": 0.6241956617191957, "spectral_convergence_status": "ok", "amplitude_floor": 5.645485889979311e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0529488065388325e-06, "output_power": 9.566930448075183e-07, "delta_db": -0.4163464003855161, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.178233710401702e-07, "output_power": 6.748232794567745e-07, "delta_db": 0.3832572330225116, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.652745613182611e-06, "output_power": 5.662802971409456e-06, "delta_db": 0.007720096463666053, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.2826510059132755e-05, "output_power": 1.2495704073345093e-05, "delta_db": -0.11347774508275471, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2385922939210616e-05, "output_power": 1.2859346314565922e-05, "delta_db": 0.16290518788931577, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.5916906482380547e-06, "output_power": 1.5978489465651263e-06, "delta_db": 0.01677056029764851, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.299457135974266e-06, "output_power": 2.1682387129954184e-06, "delta_db": -0.25518224030645165, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.19366563763540917, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.0013881231941128944, "pitch": null, "output_rms_dbfs": -44.38714231354168, "output_peak": 0.049345619907640734, "reference_rms_dbfs": -44.38575419034756, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.140603224772815}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 96209, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.089458070502993e-05, "log_rms_mae_db": 1.7302289116966683, "rms_envelope_nrmse": 0.16342565334053868, "envelope_correlation": 0.9751231745986503, "rms_gain_error_db": -0.001387953287762017, "reference_mean_power": 3.6506204511776254e-05, "output_mean_power": 3.649453942899012e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 2.0041859534078988e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.999428757782778e-06, "output_power": 7.83406742350345e-06, "reference_active": true, "delta_db": -0.09071670005537513}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3205374160249087e-06, "output_power": 3.0988290161133907e-06, "reference_active": true, "delta_db": -0.3001076439798539}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.233369046941817e-06, "output_power": 1.1954526419621615e-06, "reference_active": true, "delta_db": -0.13560668871063009}], "active_band_count": 3, "active_band_mae_db": 0.17547701091528636}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.7773650083170072e-05, "log_rms_mae_db": 0.9732235256852914, "rms_envelope_nrmse": 0.0896968234477192, "envelope_correlation": 0.9914867889243907, "rms_gain_error_db": -0.001398296124759075, "reference_mean_power": 3.678163866257165e-05, "output_mean_power": 3.676979800004278e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.6475917872957343e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.744366291346524e-06, "output_power": 6.766685470837315e-06, "reference_active": true, "delta_db": 0.014348409703490701}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5635835823033082e-06, "output_power": 1.4940875207174617e-06, "reference_active": true, "delta_db": -0.19745063329162343}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.396664522501232e-08, "output_power": 8.403721325070907e-08, "reference_active": true, "delta_db": -0.4850207967450526}], "active_band_count": 3, "active_band_mae_db": 0.2322732799133889}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1737971097625835e-05, "log_rms_mae_db": 2.4898696997813516, "rms_envelope_nrmse": 0.26079179307914935, "envelope_correlation": 0.9514601851235823, "rms_gain_error_db": 0.35185137822832635, "reference_mean_power": 3.7178438627460445e-06, "output_mean_power": 4.031589307431344e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.0069118410394303e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5873171334916186e-06, "output_power": 1.6555641629163119e-06, "reference_active": true, "delta_db": 0.18282312848465115}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.351037742291938e-07, "output_power": 5.70385583692729e-07, "reference_active": true, "delta_db": -0.46676153294281275}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7445146919256035e-07, "output_power": 2.395561769247635e-07, "reference_active": true, "delta_db": -0.5905818642233819}], "active_band_count": 3, "active_band_mae_db": 0.4133888418836153}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 7.730313378567735e-06, "log_rms_mae_db": 1.7345382473497013, "rms_envelope_nrmse": 0.16120157139157631, "envelope_correlation": 0.979892889535129, "rms_gain_error_db": 0.35184139996192193, "reference_mean_power": 3.745927267695172e-06, "output_mean_power": 4.062033312389729e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.5331447910659217e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5569974188207908e-06, "output_power": 1.6184172945360263e-06, "reference_active": true, "delta_db": 0.16802618094521635}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5335281635338005e-07, "output_power": 3.0998736021700766e-07, "reference_active": true, "delta_db": -0.5686457138308263}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.1249603669561348e-08, "output_power": 1.676642697511303e-08, "reference_active": true, "delta_db": -1.029103126120357}], "active_band_count": 3, "active_band_mae_db": 0.5885916736321332}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.066376004316646e-05, "log_rms_mae_db": 1.8990562089657743, "rms_envelope_nrmse": 0.2107330227168611, "envelope_correlation": 0.9662081481679156, "rms_gain_error_db": -0.06882250972271543, "reference_mean_power": 1.9040046826256083e-05, "output_mean_power": 1.8740697954633704e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 1.3406247189798443e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.3392457188005514e-06, "output_power": 6.00410238653032e-06, "reference_active": true, "delta_db": -0.23589496457630868}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.391738535251293e-06, "output_power": 2.172353580149639e-06, "reference_active": true, "delta_db": -0.4178318684260185}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.54995852980617e-07, "output_power": 7.771402178838753e-07, "reference_active": true, "delta_db": 0.12554818616052182}], "active_band_count": 3, "active_band_mae_db": 0.2597583397209497}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.6710315888953048e-05, "log_rms_mae_db": 1.1800569859242585, "rms_envelope_nrmse": 0.12350518272950049, "envelope_correlation": 0.9872476315651516, "rms_gain_error_db": -0.06882222156683918, "reference_mean_power": 1.9183917331823965e-05, "output_mean_power": 1.8882307771474382e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.1409929070898633e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.5949700460751985e-06, "output_power": 5.3862873931775575e-06, "reference_active": true, "delta_db": -0.1650824367203971}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1687645280234336e-06, "output_power": 1.0575589388933739e-06, "reference_active": true, "delta_db": -0.4342244188011319}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.657756100862398e-08, "output_power": 6.622418408460954e-08, "reference_active": true, "delta_db": -0.6308491370015183}], "active_band_count": 3, "active_band_mae_db": 0.4100519975076824}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1530093504582296e-05, "log_rms_mae_db": 1.746515482406632, "rms_envelope_nrmse": 0.17458774121142165, "envelope_correlation": 0.9776368453901281, "rms_gain_error_db": 0.24273084037190085, "reference_mean_power": 5.108146850353514e-06, "output_mean_power": 5.401774595135451e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.254259363144466e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7396247028720546e-06, "output_power": 1.8373454759998107e-06, "reference_active": true, "delta_db": 0.2373525828997019}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.118165550857846e-07, "output_power": 5.71304598053489e-07, "reference_active": true, "delta_db": 0.47753390068907386}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4689547511366827e-07, "output_power": 1.0817930919518047e-07, "reference_active": true, "delta_db": -1.3286421440741358}], "active_band_count": 3, "active_band_mae_db": 0.6811762092209706}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 9.091353933231884e-06, "log_rms_mae_db": 0.9764492383724793, "rms_envelope_nrmse": 0.09254345345612247, "envelope_correlation": 0.9935509642072667, "rms_gain_error_db": 0.24273121929512842, "reference_mean_power": 5.146742550240226e-06, "output_mean_power": 5.442589337336548e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.7984368001248054e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6090100968943592e-06, "output_power": 1.6921882966396155e-06, "reference_active": true, "delta_db": 0.21889917694837185}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.367924284305246e-07, "output_power": 2.630765156960862e-07, "reference_active": true, "delta_db": 0.45714269767984506}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2506680970493352e-08, "output_power": 8.562290263273011e-09, "reference_active": true, "delta_db": -1.6455212527439684}], "active_band_count": 3, "active_band_mae_db": 0.7738543757907284}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.6112430974799958, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "c24b0d4d711b18b60f4b39691b7e99aa366d9651260b76f2c206fc1b189c4c09", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9702596250712228, "standard_deviation": 0.004550880202567597, "minimum": 0.9639816245681264, "maximum": 0.9764994629308346, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.8891534769089926, "standard_deviation": 0.04286204498907228, "minimum": 1.821953065532159, "maximum": 1.9487057084891368, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4826949738068529, "standard_deviation": 0.1569770059583149, "minimum": 0.2597583397209497, "maximum": 0.6632399374881843, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.19843691288834925, "standard_deviation": 0.016044968773105257, "minimum": 0.17728513188635164, "maximum": 0.2232698706133649, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9897850192112381, "standard_deviation": 0.002464688265328937, "minimum": 0.9856712934259763, "maximum": 0.9933552209576851, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.1623853185504553, "standard_deviation": 0.028590644526139065, "minimum": 1.1245388024602134, "maximum": 1.2049762448676036, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7054410703872804, "standard_deviation": 0.22401651324723595, "minimum": 0.33905635253747035, "maximum": 0.9684446013746726, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.11164343033919033, "standard_deviation": 0.013744501468687118, "minimum": 0.08920038515076335, "maximum": 0.13568646747045998, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9761724781292067, "standard_deviation": 0.0026134461633268396, "minimum": 0.9715683559097817, "maximum": 0.9804694485245755, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.695530948141637, "standard_deviation": 0.02388195326152569, "minimum": 1.669963336498953, "maximum": 1.746515482406632, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5925656849831206, "standard_deviation": 0.13291586369042108, "minimum": 0.3726901626470154, "maximum": 0.7389762368871917, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1769517484185988, "standard_deviation": 0.009976517268327904, "minimum": 0.15896899928092692, "maximum": 0.1905404060403513, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9923127822058724, "standard_deviation": 0.0012676353411389758, "minimum": 0.99044690158713, "maximum": 0.9935975515824049, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9849260165144342, "standard_deviation": 0.02832783658319329, "minimum": 0.946506301250987, "maximum": 1.037661440714077, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6788720868042599, "standard_deviation": 0.22807227762368143, "minimum": 0.368681259898955, "maximum": 1.014027305586126, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09767475886547178, "standard_deviation": 0.007488076949628743, "minimum": 0.0883704209165723, "maximum": 0.10684780922969679, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9528077181083916, "standard_deviation": 0.005914780026880087, "minimum": 0.94325574855513, "maximum": 0.9585581114688921, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.513287811849726, "standard_deviation": 0.033565151429079135, "minimum": 2.4800703760643263, "maximum": 2.572241347722956, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.48501318314263464, "standard_deviation": 0.20710756143694706, "minimum": 0.23546787808562097, "maximum": 0.8171643269766387, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2529763757075031, "standard_deviation": 0.015256711879059283, "minimum": 0.23517503678815657, "maximum": 0.2734528288794293, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9804243236206638, "standard_deviation": 0.002562857597919848, "minimum": 0.9774066231633304, "maximum": 0.9849027062654013, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.7095908402806843, "standard_deviation": 0.07133307675230696, "minimum": 1.579614689707704, "maximum": 1.8049948680970045, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5692282700493125, "standard_deviation": 0.17528065154765277, "minimum": 0.30004339606043146, "maximum": 0.8425697574795707, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1552556618629441, "standard_deviation": 0.010095051912309552, "minimum": 0.13637925634113093, "maximum": 0.16579554915704212, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.41350875715345015, "standard_deviation": 0.17260789584811043, "minimum": 0.17153609491115995, "maximum": 0.6247652983444837, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.131892498360841, "standard_deviation": 0.0094552413867145, "minimum": 6.118158720745453, "maximum": 6.144605627121099, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.0572626792715499, "standard_deviation": 0.006076312222751203, "minimum": 0.049345619907640734, "maximum": 0.06493254636297152, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07336640489447029, "standard_deviation": 0.12252961383447283, "minimum": -0.24887628731000416, "maximum": 0.09483590295092688, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9776753396630251, "standard_deviation": 0.003827674786960956, "minimum": 0.9723740620059494, "maximum": 0.9845099635201979, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.6979882145070415, "standard_deviation": 0.028890345600453775, "minimum": 1.660986386439392, "maximum": 1.7405244911093252, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.42807567626771026, "standard_deviation": 0.2169995639785582, "minimum": 0.17547701091528636, "maximum": 0.7852496985839138, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.1546398548970473, "standard_deviation": 0.013507067598927027, "minimum": 0.13066990957523106, "maximum": 0.17365680507288955, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9928240653208227, "standard_deviation": 0.001868503884655837, "minimum": 0.9894452674316899, "maximum": 0.9956270010167084, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.906929923821624, "standard_deviation": 0.03344059049741639, "minimum": 0.8558901464797463, "maximum": 0.9732235256852914, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5615399548964823, "standard_deviation": 0.21905679516497373, "minimum": 0.2322732799133889, "maximum": 0.8497251430754762, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.08321458564859291, "standard_deviation": 0.009764470673290422, "minimum": 0.0702482207290643, "maximum": 0.10105972163414632, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_whisper10_BASIC5000_2372", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 1.3219339847564697, "predicted_mos": 1.3219339847564697, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 96209, "input_sample_rate": 24000, "input_seconds": 4.008708333333334, "input_float32_sha256": "0bf3b60afab2e2b5ec68d25e7dd4407aac6e78f1a1febaf00806cfc9e12b5bf2", "internal_samples": 64140, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 4.818432999774814}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.612717471105641, "全帯域_10ms_rms_envelope_nrmse": 0.14977225721800008, "全帯域_10ms_envelope_correlation": 0.9790030602857798, "全帯域_10ms_modulation_mae_db": 0.6876123528472897, "全帯域_40ms_log_rms_mae_db": 0.8498367628415248, "全帯域_40ms_rms_envelope_nrmse": 0.0794878808697413, "全帯域_40ms_envelope_correlation": 0.9933287185859906, "全帯域_40ms_modulation_mae_db": 0.9413775167204489, "300–1000 Hz_10ms_log_rms_mae_db": 2.8634989946674283, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2480018791232653, "300–1000 Hz_10ms_envelope_correlation": 0.9541723565377803, "300–1000 Hz_10ms_modulation_mae_db": 0.5870735000657165, "300–1000 Hz_40ms_log_rms_mae_db": 2.0800246962995828, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14486910347420037, "300–1000 Hz_40ms_envelope_correlation": 0.9825884274200781, "300–1000 Hz_40ms_modulation_mae_db": 0.7860363622719652, "1000–3000 Hz_10ms_log_rms_mae_db": 2.162535152137071, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19430604985393024, "1000–3000 Hz_10ms_envelope_correlation": 0.9713990069955619, "1000–3000 Hz_10ms_modulation_mae_db": 0.8410263947620912, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3134873118956794, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10382352082666675, "1000–3000 Hz_40ms_envelope_correlation": 0.9909754717522452, "1000–3000 Hz_40ms_modulation_mae_db": 1.4403370828047644, "3000–6000 Hz_10ms_log_rms_mae_db": 2.0834581716504887, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1893795860342306, "3000–6000 Hz_10ms_envelope_correlation": 0.9726719137416369, "3000–6000 Hz_10ms_modulation_mae_db": 0.7690014988819932, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2307584787545498, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09591559713593845, "3000–6000 Hz_40ms_envelope_correlation": 0.9923979927009948, "3000–6000 Hz_40ms_modulation_mae_db": 1.004112548119268, "mr_stft_db": 6.344595784033693, "band_mae_db": 0.4188265848546479, "rms_gain_error_db": -0.06041661635419279, "output_peak": 0.06470490846690563}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5783985580452002, "全帯域_10ms_rms_envelope_nrmse": 0.14205467909492292, "全帯域_10ms_envelope_correlation": 0.9811310002051233, "全帯域_10ms_modulation_mae_db": 0.6068502458223463, "全帯域_40ms_log_rms_mae_db": 0.8854700725727007, "全帯域_40ms_rms_envelope_nrmse": 0.07765405828805869, "全帯域_40ms_envelope_correlation": 0.9937488669987318, "全帯域_40ms_modulation_mae_db": 0.9097813555660025, "300–1000 Hz_10ms_log_rms_mae_db": 2.7679944855170144, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2648121073623154, "300–1000 Hz_10ms_envelope_correlation": 0.9471797174539355, "300–1000 Hz_10ms_modulation_mae_db": 0.42074162418742245, "300–1000 Hz_40ms_log_rms_mae_db": 1.8094029819075335, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.12660881088464251, "300–1000 Hz_40ms_envelope_correlation": 0.9867348013919511, "300–1000 Hz_40ms_modulation_mae_db": 0.6613593116518924, "1000–3000 Hz_10ms_log_rms_mae_db": 2.144038076424203, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17902976178545507, "1000–3000 Hz_10ms_envelope_correlation": 0.9758031263309817, "1000–3000 Hz_10ms_modulation_mae_db": 0.8606948720267619, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3391594476605946, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09830684171796904, "1000–3000 Hz_40ms_envelope_correlation": 0.9924737288672004, "1000–3000 Hz_40ms_modulation_mae_db": 1.1917097713943425, "3000–6000 Hz_10ms_log_rms_mae_db": 2.077054136591718, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1917241060069746, "3000–6000 Hz_10ms_envelope_correlation": 0.9748230229531111, "3000–6000 Hz_10ms_modulation_mae_db": 0.21922194278023302, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2741823200352134, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10867101888101277, "3000–6000 Hz_40ms_envelope_correlation": 0.9925303840857297, "3000–6000 Hz_40ms_modulation_mae_db": 0.4486547603322702, "mr_stft_db": 6.347066874124472, "band_mae_db": 0.31077517922752707, "rms_gain_error_db": -0.12154196983124053, "output_peak": 0.05222931113872703}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.649454818483599, "全帯域_10ms_rms_envelope_nrmse": 0.1397353680841088, "全帯域_10ms_envelope_correlation": 0.9819807078517864, "全帯域_10ms_modulation_mae_db": 0.21669044472967083, "全帯域_40ms_log_rms_mae_db": 0.8831183251876763, "全帯域_40ms_rms_envelope_nrmse": 0.0748606472358321, "全帯域_40ms_envelope_correlation": 0.9941732066937996, "全帯域_40ms_modulation_mae_db": 0.29132863246643487, "300–1000 Hz_10ms_log_rms_mae_db": 2.939600147416968, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2670110031788004, "300–1000 Hz_10ms_envelope_correlation": 0.9497816951170657, "300–1000 Hz_10ms_modulation_mae_db": 0.632633991941309, "300–1000 Hz_40ms_log_rms_mae_db": 2.0679301483310173, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15884761308220424, "300–1000 Hz_40ms_envelope_correlation": 0.9813384150959313, "300–1000 Hz_40ms_modulation_mae_db": 0.618108781163636, "1000–3000 Hz_10ms_log_rms_mae_db": 2.1515587982589364, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1791427343257732, "1000–3000 Hz_10ms_envelope_correlation": 0.9759251338530648, "1000–3000 Hz_10ms_modulation_mae_db": 0.3315207568927936, "1000–3000 Hz_40ms_log_rms_mae_db": 1.306178730868227, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09329276964172263, "1000–3000 Hz_40ms_envelope_correlation": 0.992836776927432, "1000–3000 Hz_40ms_modulation_mae_db": 0.6079964601450007, "3000–6000 Hz_10ms_log_rms_mae_db": 2.048902497369574, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17471361007359723, "3000–6000 Hz_10ms_envelope_correlation": 0.9773639561655655, "3000–6000 Hz_10ms_modulation_mae_db": 0.5693728966649095, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2077251713254284, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09362071979543005, "3000–6000 Hz_40ms_envelope_correlation": 0.9932145849965385, "3000–6000 Hz_40ms_modulation_mae_db": 0.8515768148040045, "mr_stft_db": 6.358130394035023, "band_mae_db": 0.24397964024185478, "rms_gain_error_db": 0.056260336046200725, "output_peak": 0.05524243184647828}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.672782227378226, "全帯域_10ms_rms_envelope_nrmse": 0.15152496694585194, "全帯域_10ms_envelope_correlation": 0.9785234055308776, "全帯域_10ms_modulation_mae_db": 0.4902599536771077, "全帯域_40ms_log_rms_mae_db": 0.8431989647488253, "全帯域_40ms_rms_envelope_nrmse": 0.07024311050512604, "全帯域_40ms_envelope_correlation": 0.994793313325551, "全帯域_40ms_modulation_mae_db": 0.7329686833292212, "300–1000 Hz_10ms_log_rms_mae_db": 2.90777886675216, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26307610745332716, "300–1000 Hz_10ms_envelope_correlation": 0.9479435969204734, "300–1000 Hz_10ms_modulation_mae_db": 0.6067003609833375, "300–1000 Hz_40ms_log_rms_mae_db": 1.9872639378924404, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15699061664744088, "300–1000 Hz_40ms_envelope_correlation": 0.9792833147937623, "300–1000 Hz_40ms_modulation_mae_db": 0.9540708362983613, "1000–3000 Hz_10ms_log_rms_mae_db": 2.13626736716132, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19453377755492351, "1000–3000 Hz_10ms_envelope_correlation": 0.9712739964743073, "1000–3000 Hz_10ms_modulation_mae_db": 0.48566148937238224, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2559058736382898, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09760288421901904, "1000–3000 Hz_40ms_envelope_correlation": 0.9920664898993913, "1000–3000 Hz_40ms_modulation_mae_db": 0.9151409830996292, "3000–6000 Hz_10ms_log_rms_mae_db": 2.0764532638278355, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.215638940034285, "3000–6000 Hz_10ms_envelope_correlation": 0.9648184512475326, "3000–6000 Hz_10ms_modulation_mae_db": 0.45021577314093336, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2338618131057604, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10479278328131043, "3000–6000 Hz_40ms_envelope_correlation": 0.9910928389694951, "3000–6000 Hz_40ms_modulation_mae_db": 0.5753643335811544, "mr_stft_db": 6.343796241051291, "band_mae_db": 0.4079036848389136, "rms_gain_error_db": -0.054970330274189044, "output_peak": 0.05672034945511235}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6470077136309813, "全帯域_10ms_rms_envelope_nrmse": 0.14721124430497154, "全帯域_10ms_envelope_correlation": 0.9797447640088677, "全帯域_10ms_modulation_mae_db": 0.29072042832136097, "全帯域_40ms_log_rms_mae_db": 0.8740918221450719, "全帯域_40ms_rms_envelope_nrmse": 0.07942839368499277, "全帯域_40ms_envelope_correlation": 0.993539814998788, "全帯域_40ms_modulation_mae_db": 0.6382920035916956, "300–1000 Hz_10ms_log_rms_mae_db": 2.760036567116493, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24915166201736536, "300–1000 Hz_10ms_envelope_correlation": 0.9535404155694942, "300–1000 Hz_10ms_modulation_mae_db": 0.4970035227068617, "300–1000 Hz_40ms_log_rms_mae_db": 1.94031550393046, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15705039903842571, "300–1000 Hz_40ms_envelope_correlation": 0.9795590944670534, "300–1000 Hz_40ms_modulation_mae_db": 0.5987920563476378, "1000–3000 Hz_10ms_log_rms_mae_db": 2.1259447561548557, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1993516777872452, "1000–3000 Hz_10ms_envelope_correlation": 0.9698542896904657, "1000–3000 Hz_10ms_modulation_mae_db": 0.3299921209026828, "1000–3000 Hz_40ms_log_rms_mae_db": 1.292610177883141, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1135838501702576, "1000–3000 Hz_40ms_envelope_correlation": 0.9899122770095791, "1000–3000 Hz_40ms_modulation_mae_db": 0.8390817658568824, "3000–6000 Hz_10ms_log_rms_mae_db": 2.0597853812280835, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18484049086659485, "3000–6000 Hz_10ms_envelope_correlation": 0.974856848318342, "3000–6000 Hz_10ms_modulation_mae_db": 0.2406303896122776, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1807448838757313, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08094414811147553, "3000–6000 Hz_40ms_envelope_correlation": 0.9952482648358599, "3000–6000 Hz_40ms_modulation_mae_db": 0.37879405486451034, "mr_stft_db": 6.344964775986825, "band_mae_db": 0.36258398657584356, "rms_gain_error_db": -0.14435187393751056, "output_peak": 0.05005636091917014}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7442071106443573, "全帯域_10ms_rms_envelope_nrmse": 0.1475967221514494, "全帯域_10ms_envelope_correlation": 0.9796370084089051, "全帯域_10ms_modulation_mae_db": 0.6196881971378257, "全帯域_40ms_log_rms_mae_db": 0.8850707307112811, "全帯域_40ms_rms_envelope_nrmse": 0.08036590624386743, "全帯域_40ms_envelope_correlation": 0.9931634148741095, "全帯域_40ms_modulation_mae_db": 0.7906332215007895, "300–1000 Hz_10ms_log_rms_mae_db": 2.984493726420051, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3156324582694748, "300–1000 Hz_10ms_envelope_correlation": 0.9367425598825798, "300–1000 Hz_10ms_modulation_mae_db": 0.6210184711472718, "300–1000 Hz_40ms_log_rms_mae_db": 2.088845871000923, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20614388900230815, "300–1000 Hz_40ms_envelope_correlation": 0.9735262528027063, "300–1000 Hz_40ms_modulation_mae_db": 0.5813165557629261, "1000–3000 Hz_10ms_log_rms_mae_db": 2.198612384595921, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18165904075476813, "1000–3000 Hz_10ms_envelope_correlation": 0.975066859178461, "1000–3000 Hz_10ms_modulation_mae_db": 0.8623423535344674, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3323398748740916, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10419197301142841, "1000–3000 Hz_40ms_envelope_correlation": 0.9914379069170931, "1000–3000 Hz_40ms_modulation_mae_db": 0.9833782317919901, "3000–6000 Hz_10ms_log_rms_mae_db": 2.06204483284087, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18008921132131056, "3000–6000 Hz_10ms_envelope_correlation": 0.9746963741568686, "3000–6000 Hz_10ms_modulation_mae_db": 0.793496122106737, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2469606094823251, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0922565594168197, "3000–6000 Hz_40ms_envelope_correlation": 0.9928864857951712, "3000–6000 Hz_40ms_modulation_mae_db": 0.9742225183936911, "mr_stft_db": 6.335379283142668, "band_mae_db": 0.3998703222792539, "rms_gain_error_db": -0.0391950887927585, "output_peak": 0.05606710091839454}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7115561493487654, "全帯域_10ms_rms_envelope_nrmse": 0.14613251591599064, "全帯域_10ms_envelope_correlation": 0.980157832098151, "全帯域_10ms_modulation_mae_db": 0.13368080292845005, "全帯域_40ms_log_rms_mae_db": 0.9347965684287514, "全帯域_40ms_rms_envelope_nrmse": 0.0772244785768136, "全帯域_40ms_envelope_correlation": 0.9937171071044271, "全帯域_40ms_modulation_mae_db": 0.31147229886601424, "300–1000 Hz_10ms_log_rms_mae_db": 2.959842951300372, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27470683057646855, "300–1000 Hz_10ms_envelope_correlation": 0.9464390504921364, "300–1000 Hz_10ms_modulation_mae_db": 0.18541747738141756, "300–1000 Hz_40ms_log_rms_mae_db": 2.1038908863359413, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16369368826125444, "300–1000 Hz_40ms_envelope_correlation": 0.9797084145798192, "300–1000 Hz_40ms_modulation_mae_db": 0.22891561591921858, "1000–3000 Hz_10ms_log_rms_mae_db": 2.1717080400383195, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17668891160762704, "1000–3000 Hz_10ms_envelope_correlation": 0.9763250503060761, "1000–3000 Hz_10ms_modulation_mae_db": 0.28000536655374386, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3342509255734138, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09598259620666444, "1000–3000 Hz_40ms_envelope_correlation": 0.992320238928369, "1000–3000 Hz_40ms_modulation_mae_db": 0.5755193159233346, "3000–6000 Hz_10ms_log_rms_mae_db": 2.1043254270035368, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.20455555489901026, "3000–6000 Hz_10ms_envelope_correlation": 0.9685159856467054, "3000–6000 Hz_10ms_modulation_mae_db": 0.573556626196915, "3000–6000 Hz_40ms_log_rms_mae_db": 1.270888296740147, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11802852935301145, "3000–6000 Hz_40ms_envelope_correlation": 0.9887064280084904, "3000–6000 Hz_40ms_modulation_mae_db": 0.7850580677619697, "mr_stft_db": 6.349080938749521, "band_mae_db": 0.4405632579706898, "rms_gain_error_db": 0.017914527090586812, "output_peak": 0.05819748095803289}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7030699027225964, "全帯域_10ms_rms_envelope_nrmse": 0.14563935789161464, "全帯域_10ms_envelope_correlation": 0.9802973784206264, "全帯域_10ms_modulation_mae_db": 0.3817671210379396, "全帯域_40ms_log_rms_mae_db": 0.9237726262397091, "全帯域_40ms_rms_envelope_nrmse": 0.07325327937934895, "全帯域_40ms_envelope_correlation": 0.9943648023891003, "全帯域_40ms_modulation_mae_db": 0.8411954718594576, "300–1000 Hz_10ms_log_rms_mae_db": 2.7412242567509564, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24912196621317603, "300–1000 Hz_10ms_envelope_correlation": 0.9586520927154375, "300–1000 Hz_10ms_modulation_mae_db": 0.23034585921825879, "300–1000 Hz_40ms_log_rms_mae_db": 1.8350594347180738, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15841721618051363, "300–1000 Hz_40ms_envelope_correlation": 0.9831442786608229, "300–1000 Hz_40ms_modulation_mae_db": 0.4122077616796342, "1000–3000 Hz_10ms_log_rms_mae_db": 2.2043474681575095, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20051295009821293, "1000–3000 Hz_10ms_envelope_correlation": 0.9695166652647852, "1000–3000 Hz_10ms_modulation_mae_db": 0.6633695608021651, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3036987605169392, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10211402241321395, "1000–3000 Hz_40ms_envelope_correlation": 0.9914826515430405, "1000–3000 Hz_40ms_modulation_mae_db": 1.3589969266533233, "3000–6000 Hz_10ms_log_rms_mae_db": 2.109441089863522, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18844657261894376, "3000–6000 Hz_10ms_envelope_correlation": 0.9728292326896971, "3000–6000 Hz_10ms_modulation_mae_db": 0.6893139293809982, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2602718663019972, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09245845842146659, "3000–6000 Hz_40ms_envelope_correlation": 0.9928828712860328, "3000–6000 Hz_40ms_modulation_mae_db": 0.9217926970712279, "mr_stft_db": 6.344579099006882, "band_mae_db": 0.2862530440716785, "rms_gain_error_db": 0.018858463973961945, "output_peak": 0.05804699741285826}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 96209, "output_samples": 96209, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.730267328025829, "spectral_convergence": 0.6051325809530465, "spectral_convergence_status": "ok", "amplitude_floor": 1.776300245720871e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.2525725764271245, "spectral_convergence": 0.6118097592634314, "spectral_convergence_status": "ok", "amplitude_floor": 1.1913344769267054e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.050947447648125, "spectral_convergence": 0.6168112914820304, "spectral_convergence_status": "ok", "amplitude_floor": 5.645485889979311e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0529488065388325e-06, "output_power": 9.893789309559197e-07, "delta_db": -0.2704459894712801, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.178233710401702e-07, "output_power": 8.088992717537396e-07, "delta_db": 1.1703011164396062, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.652745613182611e-06, "output_power": 5.2471187278950495e-06, "delta_db": -0.3233855042743245, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.2826510059132755e-05, "output_power": 1.1685034071935114e-05, "delta_db": -0.40478523011074413, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2385922939210616e-05, "output_power": 1.3060821298572136e-05, "delta_db": 0.23042113712822349, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.5916906482380547e-06, "output_power": 1.7027249375987447e-06, "delta_db": 0.292858319764318, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.299457135974266e-06, "output_power": 2.4298764840061957e-06, "delta_db": 0.2395887967940388, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.4188265848546479, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.06041661635419279, "pitch": null, "output_rms_dbfs": -44.446170806701765, "output_peak": 0.06470490846690563, "reference_rms_dbfs": -44.38575419034756, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.344595784033693}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 96209, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.089458070502993e-05, "log_rms_mae_db": 1.612717471105641, "rms_envelope_nrmse": 0.14977225721800008, "envelope_correlation": 0.9790030602857798, "rms_gain_error_db": -0.060414183817909625, "reference_mean_power": 3.6506204511776254e-05, "output_mean_power": 3.6001886967988575e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 2.0041859534078988e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.999428757782778e-06, "output_power": 7.3022694265002824e-06, "reference_active": true, "delta_db": -0.39601122211326567}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3205374160249087e-06, "output_power": 3.2711309681410903e-06, "reference_active": true, "delta_db": -0.06510445690438775}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.233369046941817e-06, "output_power": 8.529447631044175e-07, "reference_active": true, "delta_db": -1.6017213795242156}], "active_band_count": 3, "active_band_mae_db": 0.6876123528472897}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.7773650083170072e-05, "log_rms_mae_db": 0.8498367628415248, "rms_envelope_nrmse": 0.0794878808697413, "envelope_correlation": 0.9933287185859906, "rms_gain_error_db": -0.06043725331012752, "reference_mean_power": 3.678163866257165e-05, "output_mean_power": 3.6273323431751016e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.6475917872957343e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.744366291346524e-06, "output_power": 6.1401330492482e-06, "reference_active": true, "delta_db": -0.4076336722180153}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5635835823033082e-06, "output_power": 1.5211823335812517e-06, "reference_active": true, "delta_db": -0.11939828630919304}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.396664522501232e-08, "output_power": 5.536861535164947e-08, "reference_active": true, "delta_db": -2.2971005916341385}], "active_band_count": 3, "active_band_mae_db": 0.9413775167204489}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1737971097625835e-05, "log_rms_mae_db": 2.8634989946674283, "rms_envelope_nrmse": 0.2480018791232653, "envelope_correlation": 0.9541723565377803, "rms_gain_error_db": 0.13999781399507386, "reference_mean_power": 3.7178438627460445e-06, "output_mean_power": 3.8396437214202894e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.0069118410394303e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5873171334916186e-06, "output_power": 1.6258370131280014e-06, "reference_active": true, "delta_db": 0.10413302247739786}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.351037742291938e-07, "output_power": 6.044023931969682e-07, "reference_active": true, "delta_db": -0.2151851832059271}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7445146919256035e-07, "output_power": 1.9691342700404492e-07, "reference_active": true, "delta_db": -1.4419022945138242}], "active_band_count": 3, "active_band_mae_db": 0.5870735000657165}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 7.730313378567735e-06, "log_rms_mae_db": 2.0800246962995828, "rms_envelope_nrmse": 0.14486910347420037, "envelope_correlation": 0.9825884274200781, "rms_gain_error_db": 0.1399878350965819, "reference_mean_power": 3.745927267695172e-06, "output_mean_power": 3.868638274513253e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.5331447910659217e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5569974188207908e-06, "output_power": 1.5817089978355027e-06, "reference_active": true, "delta_db": 0.06838692594030789}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5335281635338005e-07, "output_power": 3.1262493459660745e-07, "reference_active": true, "delta_db": -0.5318494327206925}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.1249603669561348e-08, "output_power": 1.417632175017908e-08, "reference_active": true, "delta_db": -1.7578727281548954}], "active_band_count": 3, "active_band_mae_db": 0.7860363622719652}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.066376004316646e-05, "log_rms_mae_db": 2.162535152137071, "rms_envelope_nrmse": 0.19430604985393024, "envelope_correlation": 0.9713990069955619, "rms_gain_error_db": -0.0286501709511833, "reference_mean_power": 1.9040046826256083e-05, "output_mean_power": 1.8914854071016352e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 1.3406247189798443e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.3392457188005514e-06, "output_power": 5.7702060607055376e-06, "reference_active": true, "delta_db": -0.40846263423635476}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.391738535251293e-06, "output_power": 2.13689819391957e-06, "reference_active": true, "delta_db": -0.4892986885416257}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.54995852980617e-07, "output_power": 5.19293372587257e-07, "reference_active": true, "delta_db": -1.625317861508293}], "active_band_count": 3, "active_band_mae_db": 0.8410263947620912}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.6710315888953048e-05, "log_rms_mae_db": 1.3134873118956794, "rms_envelope_nrmse": 0.10382352082666675, "envelope_correlation": 0.9909754717522452, "rms_gain_error_db": -0.028650614199898623, "reference_mean_power": 1.9183917331823965e-05, "output_mean_power": 1.9057776649334112e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.1409929070898633e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.5949700460751985e-06, "output_power": 5.141861760400096e-06, "reference_active": true, "delta_db": -0.3667736937580329}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1687645280234336e-06, "output_power": 1.022786835915711e-06, "reference_active": true, "delta_db": -0.5794189262563773}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.657756100862398e-08, "output_power": 3.5206241776374423e-08, "reference_active": true, "delta_db": -3.374818628399883}], "active_band_count": 3, "active_band_mae_db": 1.4403370828047644}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1530093504582296e-05, "log_rms_mae_db": 2.0834581716504887, "rms_envelope_nrmse": 0.1893795860342306, "envelope_correlation": 0.9726719137416369, "rms_gain_error_db": 0.11730302879793161, "reference_mean_power": 5.108146850353514e-06, "output_mean_power": 5.247998193391666e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.254259363144466e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7396247028720546e-06, "output_power": 1.7310265584465276e-06, "reference_active": true, "delta_db": -0.021518349363362527}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.118165550857846e-07, "output_power": 4.5732744720154634e-07, "reference_active": true, "delta_db": -0.4888706234922211}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4689547511366827e-07, "output_power": 9.712854116743444e-08, "reference_active": true, "delta_db": -1.796615523790396}], "active_band_count": 3, "active_band_mae_db": 0.7690014988819932}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 9.091353933231884e-06, "log_rms_mae_db": 1.2307584787545498, "rms_envelope_nrmse": 0.09591559713593845, "envelope_correlation": 0.9923979927009948, "rms_gain_error_db": 0.11730202609544652, "reference_mean_power": 5.146742550240226e-06, "output_mean_power": 5.2876493493001785e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.7984368001248054e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6090100968943592e-06, "output_power": 1.5779310842804046e-06, "reference_active": true, "delta_db": -0.08470737809710042}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.367924284305246e-07, "output_power": 2.1434931977493123e-07, "reference_active": true, "delta_db": -0.4324570182489593}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2506680970493352e-08, "output_power": 7.040844403346689e-09, "reference_active": true, "delta_db": -2.495173248011745}], "active_band_count": 3, "active_band_mae_db": 1.004112548119268}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5890553025662634, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "bc764c76c003f052cc3a16da262d9b786edc20ba523ca237d8cdea4458df3dc4", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9731455160117131, "standard_deviation": 0.0029067353658608183, "minimum": 0.9695166652647852, "maximum": 0.9763250503060761, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 2.161876505366017, "standard_deviation": 0.028339733794578062, "minimum": 2.1259447561548557, "maximum": 2.2043474681575095, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.581826614355886, "standard_deviation": 0.2554289933767342, "minimum": 0.28000536655374386, "maximum": 0.8623423535344674, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1881531129709919, "standard_deviation": 0.009962560540109838, "minimum": 0.17668891160762704, "maximum": 0.20051295009821293, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9916881927305439, "standard_deviation": 0.0009445816785774619, "minimum": 0.9899122770095791, "maximum": 0.992836776927432, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.309703887863797, "standard_deviation": 0.027338614267320486, "minimum": 1.2559058736382898, "maximum": 1.3391594476605946, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.9890200672086584, "standard_deviation": 0.3219996329446077, "minimum": 0.5755193159233346, "maximum": 1.4403370828047644, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10111230727586773, "standard_deviation": 0.006336105462208887, "minimum": 0.09329276964172263, "maximum": 0.1135838501702576, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9725719731149324, "standard_deviation": 0.004042777823689156, "minimum": 0.9648184512475326, "maximum": 0.9773639561655655, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 2.0776831000469533, "standard_deviation": 0.021202593768660773, "minimum": 2.048902497369574, "maximum": 2.109441089863522, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5381011473456246, "standard_deviation": 0.22088734103920646, "minimum": 0.21922194278023302, "maximum": 0.793496122106737, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.19117350898186836, "standard_deviation": 0.013215202356211568, "minimum": 0.17471361007359723, "maximum": 0.215638940034285, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.992369981334789, "standard_deviation": 0.001874906987889858, "minimum": 0.9887064280084904, "maximum": 0.9952482648358599, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.2381741799526442, "standard_deviation": 0.03214068179030216, "minimum": 1.1807448838757313, "maximum": 1.2741823200352134, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.742446974366012, "standard_deviation": 0.24335529893684243, "minimum": 0.37879405486451034, "maximum": 1.004112548119268, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09833597679955813, "standard_deviation": 0.01157813333267105, "minimum": 0.08094414811147553, "maximum": 0.11802852935301145, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9493064355861128, "standard_deviation": 0.006564232968154974, "minimum": 0.9367425598825798, "maximum": 0.9586520927154375, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.8655587494926804, "standard_deviation": 0.09740690178615485, "minimum": 2.7412242567509564, "maximum": 2.984493726420051, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4726168509539494, "standard_deviation": 0.1785543938739195, "minimum": 0.18541747738141756, "maximum": 0.632633991941309, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2664392517742741, "standard_deviation": 0.022172362178233682, "minimum": 0.2480018791232653, "maximum": 0.3156324582694748, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9807353749015156, "standard_deviation": 0.0038193417496302858, "minimum": 0.9735262528027063, "maximum": 0.9867348013919511, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.9890916825519964, "standard_deviation": 0.11711440727624738, "minimum": 1.8094029819075335, "maximum": 2.1038908863359413, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6051009101369089, "standard_deviation": 0.21947355815699654, "minimum": 0.22891561591921858, "maximum": 0.9540708362983613, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15907766707137372, "standard_deviation": 0.022365795043240138, "minimum": 0.12660881088464251, "maximum": 0.20614388900230815, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.35884446250755114, "standard_deviation": 0.07086589594735393, "minimum": 0.24397964024185478, "maximum": 0.4405632579706898, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.3459491737662965, "standard_deviation": 0.006329915909053202, "minimum": 6.335379283142668, "maximum": 6.358130394035023, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.056408117639459895, "standard_deviation": 0.004376957973539562, "minimum": 0.05005636091917014, "maximum": 0.06470490846690563, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.04093031900989274, "standard_deviation": 0.0699566630235154, "minimum": -0.14435187393751056, "maximum": 0.056260336046200725, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9800593946012646, "standard_deviation": 0.0011121803894994762, "minimum": 0.9785234055308776, "maximum": 0.9819807078517864, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.6648992439199208, "standard_deviation": 0.05444484545218696, "minimum": 1.5783985580452002, "maximum": 1.7442071106443573, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4284086933127489, "standard_deviation": 0.20433305882603636, "minimum": 0.13368080292845005, "maximum": 0.6876123528472897, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.14620838895086374, "standard_deviation": 0.0038430494646086335, "minimum": 0.1397353680841088, "maximum": 0.15152496694585194, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9938536556213122, "standard_deviation": 0.000551161601485802, "minimum": 0.9931634148741095, "maximum": 0.994793313325551, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8849194841094425, "standard_deviation": 0.031824289288750966, "minimum": 0.8431989647488253, "maximum": 0.9347965684287514, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6821311479875081, "standard_deviation": 0.2537513884403718, "minimum": 0.29132863246643487, "maximum": 0.9413775167204489, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0765647193479726, "standard_deviation": 0.003518293055404189, "minimum": 0.07024311050512604, "maximum": 0.08036590624386743, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_whisper10_BASIC5000_2372", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 0.7902069091796875, "predicted_mos": 0.7902069091796875, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 96209, "input_sample_rate": 24000, "input_seconds": 4.008708333333334, "input_float32_sha256": "79d2f9a48dc48b53faa028b91eb2ed32af9f911b578affe0d3d697b582ddf70e", "internal_samples": 64140, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.1604321002960205}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.649309816988148, "全帯域_10ms_rms_envelope_nrmse": 0.15203767062521117, "全帯域_10ms_envelope_correlation": 0.9792802022351341, "全帯域_10ms_modulation_mae_db": 0.4750659137113907, "全帯域_40ms_log_rms_mae_db": 0.8969711583286323, "全帯域_40ms_rms_envelope_nrmse": 0.09104944238896037, "全帯域_40ms_envelope_correlation": 0.9918158122022688, "全帯域_40ms_modulation_mae_db": 0.5623994676943366, "300–1000 Hz_10ms_log_rms_mae_db": 2.646800633401588, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27950609569335955, "300–1000 Hz_10ms_envelope_correlation": 0.9511171507117036, "300–1000 Hz_10ms_modulation_mae_db": 0.5050269142103673, "300–1000 Hz_40ms_log_rms_mae_db": 1.9505441253455784, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19480769257993932, "300–1000 Hz_40ms_envelope_correlation": 0.9764288846454968, "300–1000 Hz_40ms_modulation_mae_db": 0.59729680419172, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7611303878981783, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18483581378751565, "1000–3000 Hz_10ms_envelope_correlation": 0.9746762096746464, "1000–3000 Hz_10ms_modulation_mae_db": 0.3233979988167635, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1219171310081333, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11144086255967328, "1000–3000 Hz_40ms_envelope_correlation": 0.989912128531667, "1000–3000 Hz_40ms_modulation_mae_db": 0.7331706709582297, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5931894163672748, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16991413245500483, "3000–6000 Hz_10ms_envelope_correlation": 0.9778159760644666, "3000–6000 Hz_10ms_modulation_mae_db": 0.14110349495977342, "3000–6000 Hz_40ms_log_rms_mae_db": 0.941771576927908, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08390620295905532, "3000–6000 Hz_40ms_envelope_correlation": 0.9940873859682412, "3000–6000 Hz_40ms_modulation_mae_db": 0.39363177771488833, "mr_stft_db": 6.084829209575304, "band_mae_db": 0.4202298655223064, "rms_gain_error_db": 0.17193725142944033, "output_peak": 0.05995261285626614}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7604989067194488, "全帯域_10ms_rms_envelope_nrmse": 0.15428869821632654, "全帯域_10ms_envelope_correlation": 0.977703889820596, "全帯域_10ms_modulation_mae_db": 0.7479849833996987, "全帯域_40ms_log_rms_mae_db": 0.8746819320614101, "全帯域_40ms_rms_envelope_nrmse": 0.07011523877525001, "全帯域_40ms_envelope_correlation": 0.9948279868145853, "全帯域_40ms_modulation_mae_db": 0.8364817333798439, "300–1000 Hz_10ms_log_rms_mae_db": 2.625566775058336, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26403981235230606, "300–1000 Hz_10ms_envelope_correlation": 0.9475802395172485, "300–1000 Hz_10ms_modulation_mae_db": 0.5604532795176781, "300–1000 Hz_40ms_log_rms_mae_db": 1.9790241084413442, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1558576203829465, "300–1000 Hz_40ms_envelope_correlation": 0.9796699195502068, "300–1000 Hz_40ms_modulation_mae_db": 0.7822897717909537, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8127359846119162, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18654246528610263, "1000–3000 Hz_10ms_envelope_correlation": 0.9736959422408481, "1000–3000 Hz_10ms_modulation_mae_db": 0.45733348869222606, "1000–3000 Hz_40ms_log_rms_mae_db": 1.149740233854086, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08764332399984695, "1000–3000 Hz_40ms_envelope_correlation": 0.9936126211483088, "1000–3000 Hz_40ms_modulation_mae_db": 0.6568427512541616, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5680186713526718, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16938494891291664, "3000–6000 Hz_10ms_envelope_correlation": 0.9777192111316944, "3000–6000 Hz_10ms_modulation_mae_db": 0.6231193771417055, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9609107819323729, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08977117780531563, "3000–6000 Hz_40ms_envelope_correlation": 0.9931100370723458, "3000–6000 Hz_40ms_modulation_mae_db": 0.7279982260999498, "mr_stft_db": 6.090537464028213, "band_mae_db": 0.38187903641791354, "rms_gain_error_db": -0.06477973086211887, "output_peak": 0.04878855547534863}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7924524002969764, "全帯域_10ms_rms_envelope_nrmse": 0.1575700723860847, "全帯域_10ms_envelope_correlation": 0.9767752410161874, "全帯域_10ms_modulation_mae_db": 0.5614299010345178, "全帯域_40ms_log_rms_mae_db": 0.9605743528814277, "全帯域_40ms_rms_envelope_nrmse": 0.07939514351664687, "全帯域_40ms_envelope_correlation": 0.9934396883424014, "全帯域_40ms_modulation_mae_db": 0.7258916101045597, "300–1000 Hz_10ms_log_rms_mae_db": 2.7055931837516862, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2740182378692321, "300–1000 Hz_10ms_envelope_correlation": 0.943551167777783, "300–1000 Hz_10ms_modulation_mae_db": 0.5054572500408566, "300–1000 Hz_40ms_log_rms_mae_db": 1.972796260301952, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16134063943594476, "300–1000 Hz_40ms_envelope_correlation": 0.9780482731532428, "300–1000 Hz_40ms_modulation_mae_db": 0.49571257403463004, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7842131494183573, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20603486377325805, "1000–3000 Hz_10ms_envelope_correlation": 0.9682049027007682, "1000–3000 Hz_10ms_modulation_mae_db": 0.38620614480299037, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1053126618655509, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10238049995354656, "1000–3000 Hz_40ms_envelope_correlation": 0.9913298143919341, "1000–3000 Hz_40ms_modulation_mae_db": 0.6887110049492992, "3000–6000 Hz_10ms_log_rms_mae_db": 1.55292473139469, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1691722059094264, "3000–6000 Hz_10ms_envelope_correlation": 0.9777114286410831, "3000–6000 Hz_10ms_modulation_mae_db": 0.4688168765942355, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9548893871632185, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0905339217742561, "3000–6000 Hz_40ms_envelope_correlation": 0.9929831925187435, "3000–6000 Hz_40ms_modulation_mae_db": 0.9462810282750906, "mr_stft_db": 6.089416610151211, "band_mae_db": 0.5408628583709881, "rms_gain_error_db": -0.11089156123982673, "output_peak": 0.0625018837856814}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.674074480119163, "全帯域_10ms_rms_envelope_nrmse": 0.14299210585673802, "全帯域_10ms_envelope_correlation": 0.9808846192331441, "全帯域_10ms_modulation_mae_db": 0.500097367761617, "全帯域_40ms_log_rms_mae_db": 0.8436757857741869, "全帯域_40ms_rms_envelope_nrmse": 0.06614916340767464, "全帯域_40ms_envelope_correlation": 0.9953937107386177, "全帯域_40ms_modulation_mae_db": 0.7438173186271474, "300–1000 Hz_10ms_log_rms_mae_db": 2.585785819422487, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2535952735220076, "300–1000 Hz_10ms_envelope_correlation": 0.9555589615396552, "300–1000 Hz_10ms_modulation_mae_db": 0.3640112974228867, "300–1000 Hz_40ms_log_rms_mae_db": 1.8077400520438607, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1395248874833203, "300–1000 Hz_40ms_envelope_correlation": 0.9864273615306383, "300–1000 Hz_40ms_modulation_mae_db": 0.48770340636468085, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7676891584611238, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1738896677958118, "1000–3000 Hz_10ms_envelope_correlation": 0.9770412191534377, "1000–3000 Hz_10ms_modulation_mae_db": 0.9579476494175729, "1000–3000 Hz_40ms_log_rms_mae_db": 1.093611569791948, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0904227281956701, "1000–3000 Hz_40ms_envelope_correlation": 0.993211022190582, "1000–3000 Hz_40ms_modulation_mae_db": 1.0619883838542987, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6490068032731307, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1794492612014119, "3000–6000 Hz_10ms_envelope_correlation": 0.9748725331594433, "3000–6000 Hz_10ms_modulation_mae_db": 0.9244819878074058, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9585409479962254, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08483955975304998, "3000–6000 Hz_40ms_envelope_correlation": 0.993886319271404, "3000–6000 Hz_40ms_modulation_mae_db": 1.1909695855030225, "mr_stft_db": 6.091276549880621, "band_mae_db": 0.33738142001498994, "rms_gain_error_db": -0.04934936649844825, "output_peak": 0.05215040010422301}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8081483316016076, "全帯域_10ms_rms_envelope_nrmse": 0.17413412116760765, "全帯域_10ms_envelope_correlation": 0.9715639690517925, "全帯域_10ms_modulation_mae_db": 0.23284182666674788, "全帯域_40ms_log_rms_mae_db": 0.9825848971516081, "全帯域_40ms_rms_envelope_nrmse": 0.09652847701848763, "全帯域_40ms_envelope_correlation": 0.9903318637590766, "全帯域_40ms_modulation_mae_db": 0.49430056810265155, "300–1000 Hz_10ms_log_rms_mae_db": 2.534217174224318, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.243578644650518, "300–1000 Hz_10ms_envelope_correlation": 0.9570652576687971, "300–1000 Hz_10ms_modulation_mae_db": 0.25779994370641285, "300–1000 Hz_40ms_log_rms_mae_db": 1.7431200081695786, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1492805662941318, "300–1000 Hz_40ms_envelope_correlation": 0.9823785365006464, "300–1000 Hz_40ms_modulation_mae_db": 0.3654076008313541, "1000–3000 Hz_10ms_log_rms_mae_db": 1.752161621522185, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21384361336398766, "1000–3000 Hz_10ms_envelope_correlation": 0.9650338316774548, "1000–3000 Hz_10ms_modulation_mae_db": 0.15328952347807578, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1325821657346342, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.13357340164554088, "1000–3000 Hz_40ms_envelope_correlation": 0.9851497117186199, "1000–3000 Hz_40ms_modulation_mae_db": 0.18541891429265667, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6068865306644562, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1909992102147583, "3000–6000 Hz_10ms_envelope_correlation": 0.9718728901260796, "3000–6000 Hz_10ms_modulation_mae_db": 0.4096637545600834, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9547361385849658, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10264476911038918, "3000–6000 Hz_40ms_envelope_correlation": 0.9910916488015581, "3000–6000 Hz_40ms_modulation_mae_db": 0.6928364877718844, "mr_stft_db": 6.096078608672126, "band_mae_db": 0.2746354447046907, "rms_gain_error_db": -0.15906520398233256, "output_peak": 0.06435840772739679}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5885444186170514, "全帯域_10ms_rms_envelope_nrmse": 0.14635248323107564, "全帯域_10ms_envelope_correlation": 0.9800223043209854, "全帯域_10ms_modulation_mae_db": 0.6025951322287991, "全帯域_40ms_log_rms_mae_db": 0.8289159746191154, "全帯域_40ms_rms_envelope_nrmse": 0.07671978112228162, "全帯域_40ms_envelope_correlation": 0.9937728883031766, "全帯域_40ms_modulation_mae_db": 0.677060958533835, "300–1000 Hz_10ms_log_rms_mae_db": 2.4862942761995503, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2411189235476178, "300–1000 Hz_10ms_envelope_correlation": 0.9601315958758524, "300–1000 Hz_10ms_modulation_mae_db": 0.33070622884647144, "300–1000 Hz_40ms_log_rms_mae_db": 1.7739381812392179, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15288359336138987, "300–1000 Hz_40ms_envelope_correlation": 0.9833251335447827, "300–1000 Hz_40ms_modulation_mae_db": 0.36555042214608185, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7371367496751702, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19291926920340155, "1000–3000 Hz_10ms_envelope_correlation": 0.9717618157331477, "1000–3000 Hz_10ms_modulation_mae_db": 0.5244008193524763, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1554440701642723, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11082345777832042, "1000–3000 Hz_40ms_envelope_correlation": 0.9898092532278165, "1000–3000 Hz_40ms_modulation_mae_db": 0.8854284365909466, "3000–6000 Hz_10ms_log_rms_mae_db": 1.614200504406113, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17724474027060286, "3000–6000 Hz_10ms_envelope_correlation": 0.9759091760083122, "3000–6000 Hz_10ms_modulation_mae_db": 0.9907328115508164, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9948954538046846, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09450457000197202, "3000–6000 Hz_40ms_envelope_correlation": 0.992494160387713, "3000–6000 Hz_40ms_modulation_mae_db": 1.104313045008772, "mr_stft_db": 6.0781532421351905, "band_mae_db": 0.24772112003007327, "rms_gain_error_db": -0.014146159694603847, "output_peak": 0.053512655731769235}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7055575852655454, "全帯域_10ms_rms_envelope_nrmse": 0.15261684983849363, "全帯域_10ms_envelope_correlation": 0.9782055839113138, "全帯域_10ms_modulation_mae_db": 0.43429326866196183, "全帯域_40ms_log_rms_mae_db": 0.8313717581863245, "全帯域_40ms_rms_envelope_nrmse": 0.0705829664922991, "全帯域_40ms_envelope_correlation": 0.9947956788174511, "全帯域_40ms_modulation_mae_db": 0.6319305657985481, "300–1000 Hz_10ms_log_rms_mae_db": 2.5435239476763667, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.23474501834776718, "300–1000 Hz_10ms_envelope_correlation": 0.957848066978791, "300–1000 Hz_10ms_modulation_mae_db": 0.48583806265140855, "300–1000 Hz_40ms_log_rms_mae_db": 1.8478153347791435, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14777395326558834, "300–1000 Hz_40ms_envelope_correlation": 0.9811142418546546, "300–1000 Hz_40ms_modulation_mae_db": 0.5308938301153392, "1000–3000 Hz_10ms_log_rms_mae_db": 1.801600276223152, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18748838005296545, "1000–3000 Hz_10ms_envelope_correlation": 0.9736100127978652, "1000–3000 Hz_10ms_modulation_mae_db": 0.599703600225229, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0749707902428556, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0895773233771989, "1000–3000 Hz_40ms_envelope_correlation": 0.9933476594114053, "1000–3000 Hz_40ms_modulation_mae_db": 1.0434602353108875, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5528530187827827, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17354393645900174, "3000–6000 Hz_10ms_envelope_correlation": 0.9766376071551456, "3000–6000 Hz_10ms_modulation_mae_db": 0.3441438876070854, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9008526543942016, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08994161313637035, "3000–6000 Hz_40ms_envelope_correlation": 0.9930920418292932, "3000–6000 Hz_40ms_modulation_mae_db": 0.4382486805320345, "mr_stft_db": 6.086727663080182, "band_mae_db": 0.32372379173091437, "rms_gain_error_db": -0.0887988604827633, "output_peak": 0.05110724300755769}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7171525083702717, "全帯域_10ms_rms_envelope_nrmse": 0.1519811959483415, "全帯域_10ms_envelope_correlation": 0.9784034511409965, "全帯域_10ms_modulation_mae_db": 0.21737988295324293, "全帯域_40ms_log_rms_mae_db": 0.895788546995428, "全帯域_40ms_rms_envelope_nrmse": 0.08173219497496, "全帯域_40ms_envelope_correlation": 0.9929263164405351, "全帯域_40ms_modulation_mae_db": 0.4939420400530252, "300–1000 Hz_10ms_log_rms_mae_db": 2.5796885390593713, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2310294387778157, "300–1000 Hz_10ms_envelope_correlation": 0.9602509510497584, "300–1000 Hz_10ms_modulation_mae_db": 0.5956595049787535, "300–1000 Hz_40ms_log_rms_mae_db": 1.8967317523264058, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13405303185513773, "300–1000 Hz_40ms_envelope_correlation": 0.9856712667873225, "300–1000 Hz_40ms_modulation_mae_db": 0.7937707664671834, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7492834292849715, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19438352664803643, "1000–3000 Hz_10ms_envelope_correlation": 0.9714847679852143, "1000–3000 Hz_10ms_modulation_mae_db": 0.2651993740811524, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0992734782963502, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10693778116041686, "1000–3000 Hz_40ms_envelope_correlation": 0.9904424929538921, "1000–3000 Hz_40ms_modulation_mae_db": 0.5597309105605445, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6062462858980318, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17555595413670566, "3000–6000 Hz_10ms_envelope_correlation": 0.9763471147207229, "3000–6000 Hz_10ms_modulation_mae_db": 0.509726428781608, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9927473920084379, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10396212352497737, "3000–6000 Hz_40ms_envelope_correlation": 0.9909445490100436, "3000–6000 Hz_40ms_modulation_mae_db": 0.6595751582212822, "mr_stft_db": 6.081024998454784, "band_mae_db": 0.4477464747474862, "rms_gain_error_db": -0.04484421497364236, "output_peak": 0.062438901408388134}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 96209, "output_samples": 96209, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.304285795107957, "spectral_convergence": 0.5949283307323489, "spectral_convergence_status": "ok", "amplitude_floor": 1.776300245720871e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.950815960220316, "spectral_convergence": 0.6129235955524514, "spectral_convergence_status": "ok", "amplitude_floor": 1.1913344769267054e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.99938587339764, "spectral_convergence": 0.6436098621356117, "spectral_convergence_status": "ok", "amplitude_floor": 5.645485889979311e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0529488065388325e-06, "output_power": 1.133229129371988e-06, "delta_db": 0.3191047274685198, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.178233710401702e-07, "output_power": 9.370745668228625e-07, "delta_db": 1.8090981805543866, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.652745613182611e-06, "output_power": 5.825884536904618e-06, "delta_db": 0.13102431473754603, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.2826510059132755e-05, "output_power": 1.3711393589969869e-05, "delta_db": 0.2897309149783516, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2385922939210616e-05, "output_power": 1.2249043125897065e-05, "delta_db": -0.04826209966351736, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.5916906482380547e-06, "output_power": 1.6722689634963099e-06, "delta_db": 0.2144746489666778, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.299457135974266e-06, "output_power": 2.3692818939171666e-06, "delta_db": 0.12991417228714558, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.4202298655223064, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.17193725142944033, "pitch": null, "output_rms_dbfs": -44.21381693891813, "output_peak": 0.05995261285626614, "reference_rms_dbfs": -44.38575419034756, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.084829209575304}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 96209, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.089458070502993e-05, "log_rms_mae_db": 1.649309816988148, "rms_envelope_nrmse": 0.15203767062521117, "envelope_correlation": 0.9792802022351341, "rms_gain_error_db": 0.17193255324150292, "reference_mean_power": 3.6506204511776254e-05, "output_mean_power": 3.7980435283361315e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 2.0041859534078988e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.999428757782778e-06, "output_power": 7.629406919267766e-06, "reference_active": true, "delta_db": -0.20568196081506207}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3205374160249087e-06, "output_power": 3.8088320060107867e-06, "reference_active": true, "delta_db": 0.5958343964337696}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.233369046941817e-06, "output_power": 1.0683779266115544e-06, "reference_active": true, "delta_db": -0.6236813838853404}], "active_band_count": 3, "active_band_mae_db": 0.4750659137113907}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.7773650083170072e-05, "log_rms_mae_db": 0.8969711583286323, "rms_envelope_nrmse": 0.09104944238896037, "envelope_correlation": 0.9918158122022688, "rms_gain_error_db": 0.17191645148535806, "reference_mean_power": 3.678163866257165e-05, "output_mean_power": 3.826685041971065e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.6475917872957343e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.744366291346524e-06, "output_power": 6.555361608939689e-06, "reference_active": true, "delta_db": -0.12344495723407337}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5635835823033082e-06, "output_power": 1.7729821147192459e-06, "reference_active": true, "delta_db": 0.545832529252414}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.396664522501232e-08, "output_power": 7.433299479305445e-08, "reference_active": true, "delta_db": -1.0179209165965224}], "active_band_count": 3, "active_band_mae_db": 0.5623994676943366}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1737971097625835e-05, "log_rms_mae_db": 2.646800633401588, "rms_envelope_nrmse": 0.27950609569335955, "envelope_correlation": 0.9511171507117036, "rms_gain_error_db": 0.7509474923569192, "reference_mean_power": 3.7178438627460445e-06, "output_mean_power": 4.419629829548947e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.0069118410394303e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5873171334916186e-06, "output_power": 1.6383402976045168e-06, "reference_active": true, "delta_db": 0.13740409506123674}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.351037742291938e-07, "output_power": 7.757268743865805e-07, "reference_active": true, "delta_db": 0.868641438342981}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7445146919256035e-07, "output_power": 3.0858092810173454e-07, "reference_active": true, "delta_db": 0.509035209226884}], "active_band_count": 3, "active_band_mae_db": 0.5050269142103673}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 7.730313378567735e-06, "log_rms_mae_db": 1.9505441253455784, "rms_envelope_nrmse": 0.19480769257993932, "envelope_correlation": 0.9764288846454968, "rms_gain_error_db": 0.7509462302609666, "reference_mean_power": 3.745927267695172e-06, "output_mean_power": 4.4530130074370925e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.5331447910659217e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5569974188207908e-06, "output_power": 1.6546460584081953e-06, "reference_active": true, "delta_db": 0.2641721649853028}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5335281635338005e-07, "output_power": 4.203601289232983e-07, "reference_active": true, "delta_db": 0.7541295940916602}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.1249603669561348e-08, "output_power": 2.5392747824042038e-08, "reference_active": true, "delta_db": 0.773588653498197}], "active_band_count": 3, "active_band_mae_db": 0.59729680419172}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.066376004316646e-05, "log_rms_mae_db": 1.7611303878981783, "rms_envelope_nrmse": 0.18483581378751565, "envelope_correlation": 0.9746762096746464, "rms_gain_error_db": 0.11382157243446074, "reference_mean_power": 1.9040046826256083e-05, "output_mean_power": 1.9545652326674533e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 1.3406247189798443e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.3392457188005514e-06, "output_power": 6.391892589614295e-06, "reference_active": true, "delta_db": 0.03591882400754463}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.391738535251293e-06, "output_power": 2.434810022469395e-06, "reference_active": true, "delta_db": 0.07751379923766744}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.54995852980617e-07, "output_power": 6.198240577063095e-07, "reference_active": true, "delta_db": -0.8567613732050784}], "active_band_count": 3, "active_band_mae_db": 0.3233979988167635}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.6710315888953048e-05, "log_rms_mae_db": 1.1219171310081333, "rms_envelope_nrmse": 0.11144086255967328, "envelope_correlation": 0.989912128531667, "rms_gain_error_db": 0.1138216900512384, "reference_mean_power": 1.9183917331823965e-05, "output_mean_power": 1.969334382461979e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.1409929070898633e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.5949700460751985e-06, "output_power": 5.762746262515166e-06, "reference_active": true, "delta_db": 0.12831731954556644}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1687645280234336e-06, "output_power": 1.1928264881148987e-06, "reference_active": true, "delta_db": 0.08850252272996881}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.657756100862398e-08, "output_power": 4.851011597536966e-08, "reference_active": true, "delta_db": -1.9826921705991538}], "active_band_count": 3, "active_band_mae_db": 0.7331706709582297}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1530093504582296e-05, "log_rms_mae_db": 1.5931894163672748, "rms_envelope_nrmse": 0.16991413245500483, "envelope_correlation": 0.9778159760644666, "rms_gain_error_db": 0.04216249368045127, "reference_mean_power": 5.108146850353514e-06, "output_mean_power": 5.157979637965811e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.254259363144466e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7396247028720546e-06, "output_power": 1.7600209122449197e-06, "reference_active": true, "delta_db": 0.05062261983024606}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.118165550857846e-07, "output_power": 5.155770775489524e-07, "reference_active": true, "delta_db": 0.031792711118170634}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4689547511366827e-07, "output_power": 1.3580598281647883e-07, "reference_active": true, "delta_db": -0.3408951539309036}], "active_band_count": 3, "active_band_mae_db": 0.14110349495977342}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 9.091353933231884e-06, "log_rms_mae_db": 0.941771576927908, "rms_envelope_nrmse": 0.08390620295905532, "envelope_correlation": 0.9940873859682412, "rms_gain_error_db": 0.04216238724216116, "reference_mean_power": 5.146742550240226e-06, "output_mean_power": 5.196951732806344e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.7984368001248054e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6090100968943592e-06, "output_power": 1.6556957102420377e-06, "reference_active": true, "delta_db": 0.12421754167083478}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.367924284305246e-07, "output_power": 2.2356579006137943e-07, "reference_active": true, "delta_db": -0.24962462717282413}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2506680970493352e-08, "output_power": 1.0385723478570482e-08, "reference_active": true, "delta_db": -0.8070531643010062}], "active_band_count": 3, "active_band_mae_db": 0.39363177771488833}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.6218763715754786, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "7d567923b392acb47f5e4944402f720e717138a9abf864d08f5481af0d10fb75", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9719385877454227, "standard_deviation": 0.0038035066288857862, "minimum": 0.9650338316774548, "maximum": 0.9770412191534377, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.7707438446368817, "standard_deviation": 0.02654892059695247, "minimum": 1.7371367496751702, "maximum": 1.8127359846119162, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4584348248583108, "standard_deviation": 0.24719228350334624, "minimum": 0.15328952347807578, "maximum": 0.9579476494175729, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.19249219998888492, "standard_deviation": 0.01258206269019585, "minimum": 0.1738896677958118, "maximum": 0.21384361336398766, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9908518379467782, "standard_deviation": 0.0027850905082394007, "minimum": 0.9851497117186199, "maximum": 0.9936126211483088, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.1166065126197289, "standard_deviation": 0.028233489324829702, "minimum": 1.0749707902428556, "maximum": 1.1554440701642723, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.726843913471378, "standard_deviation": 0.28414756151852194, "minimum": 0.18541891429265667, "maximum": 1.0619883838542987, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10409992233377674, "standard_deviation": 0.01534173728161254, "minimum": 0.08764332399984695, "maximum": 0.13357340164554088, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9761107421258686, "standard_deviation": 0.0019972778377120325, "minimum": 0.9718728901260796, "maximum": 0.9778159760644666, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5929157452673937, "standard_deviation": 0.03337316361399569, "minimum": 1.5528530187827827, "maximum": 1.6490068032731307, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5514735773753392, "standard_deviation": 0.28717621641807883, "minimum": 0.14110349495977342, "maximum": 0.9907328115508164, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17565804869497856, "standard_deviation": 0.007281410031547447, "minimum": 0.1691722059094264, "maximum": 0.1909992102147583, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9927111668574178, "standard_deviation": 0.0011615256315898343, "minimum": 0.9909445490100436, "maximum": 0.9940873859682412, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9574180416015018, "standard_deviation": 0.029578518177811135, "minimum": 0.9008526543942016, "maximum": 0.9948954538046846, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7692317486408655, "standard_deviation": 0.290731801360664, "minimum": 0.39363177771488833, "maximum": 1.1909695855030225, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09251299225817325, "standard_deviation": 0.007451812208828833, "minimum": 0.08390620295905532, "maximum": 0.10396212352497737, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9541379238899487, "standard_deviation": 0.006116192765699596, "minimum": 0.943551167777783, "maximum": 0.9602509510497584, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.5884337935992128, "standard_deviation": 0.06967698670862603, "minimum": 2.4862942761995503, "maximum": 2.7055931837516862, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4506190601718544, "standard_deviation": 0.11914415609030342, "minimum": 0.25779994370641285, "maximum": 0.5956595049787535, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.252703930595078, "standard_deviation": 0.018172749664038618, "minimum": 0.2310294387778157, "maximum": 0.27950609569335955, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.981632952195874, "standard_deviation": 0.0035207247584940174, "minimum": 0.9764288846454968, "maximum": 0.9864273615306383, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.8714637278308852, "standard_deviation": 0.09206596696414228, "minimum": 1.7431200081695786, "maximum": 1.9790241084413442, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5523281469927429, "standard_deviation": 0.16512566068974743, "minimum": 0.3654076008313541, "maximum": 0.7937707664671834, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15444024808229984, "standard_deviation": 0.01848067123197854, "minimum": 0.13405303185513773, "maximum": 0.19480769257993932, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.37177250144242036, "standard_deviation": 0.09645845117194984, "minimum": 0.24772112003007327, "maximum": 0.5408628583709881, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.087255543247204, "standard_deviation": 0.0058222911361311665, "minimum": 6.0781532421351905, "maximum": 6.096078608672126, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.05685133251207888, "standard_deviation": 0.006098855160190544, "minimum": 0.04878855547534863, "maximum": 0.06435840772739679, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.04499223078803695, "standard_deviation": 0.09833965762244469, "minimum": -0.15906520398233256, "maximum": 0.17193725142944033, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9778549075912687, "standard_deviation": 0.00285598354171915, "minimum": 0.9715639690517925, "maximum": 0.9808846192331441, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.7119673059972764, "standard_deviation": 0.07439946573745046, "minimum": 1.5885444186170514, "maximum": 1.8081483316016076, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.47146103455224697, "standard_deviation": 0.1794702037825382, "minimum": 0.21737988295324293, "maximum": 0.7479849833996987, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.15399664965873486, "standard_deviation": 0.009317488670231727, "minimum": 0.14299210585673802, "maximum": 0.17413412116760765, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9934129931772641, "standard_deviation": 0.0017007857666876717, "minimum": 0.9903318637590766, "maximum": 0.9953937107386177, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8893205507497666, "standard_deviation": 0.05754528465677367, "minimum": 0.8289159746191154, "maximum": 0.9825848971516081, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6457280327867434, "standard_deviation": 0.12335762073706502, "minimum": 0.4939420400530252, "maximum": 0.8364817333798439, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.07903405096207003, "standard_deviation": 0.010557171934971559, "minimum": 0.06614916340767464, "maximum": 0.09652847701848763, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_whisper10_BASIC5000_2372", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 1.1190028190612793, "predicted_mos": 1.1190028190612793, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 96209, "input_sample_rate": 24000, "input_seconds": 4.008708333333334, "input_float32_sha256": "1095a6f02e8b2093462597d824ac5ee524ecaa2b4dce0da7b6e1aa516396c379", "internal_samples": 64140, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 4.5833302000537515}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6888335017994331, "全帯域_10ms_rms_envelope_nrmse": 0.16280275480096043, "全帯域_10ms_envelope_correlation": 0.9753622857512744, "全帯域_10ms_modulation_mae_db": 0.16984657348910237, "全帯域_40ms_log_rms_mae_db": 0.949299135994107, "全帯域_40ms_rms_envelope_nrmse": 0.08974748927562116, "全帯域_40ms_envelope_correlation": 0.9914966844570454, "全帯域_40ms_modulation_mae_db": 0.24479412654875543, "300–1000 Hz_10ms_log_rms_mae_db": 2.734447200815355, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26107715771485873, "300–1000 Hz_10ms_envelope_correlation": 0.9515429795034229, "300–1000 Hz_10ms_modulation_mae_db": 0.43927538151952517, "300–1000 Hz_40ms_log_rms_mae_db": 2.0349876643493636, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16446891371579533, "300–1000 Hz_40ms_envelope_correlation": 0.979182034670957, "300–1000 Hz_40ms_modulation_mae_db": 0.6018249449030462, "1000–3000 Hz_10ms_log_rms_mae_db": 1.9423392629356937, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21109618545198436, "1000–3000 Hz_10ms_envelope_correlation": 0.9661475013060147, "1000–3000 Hz_10ms_modulation_mae_db": 0.2047490358475974, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2573716176455754, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1265365707012214, "1000–3000 Hz_40ms_envelope_correlation": 0.9865983032417767, "1000–3000 Hz_40ms_modulation_mae_db": 0.43115494914936275, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7931218885485152, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17639077110242013, "3000–6000 Hz_10ms_envelope_correlation": 0.9776705249436504, "3000–6000 Hz_10ms_modulation_mae_db": 0.596516318505848, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1276826764106296, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0950502150241374, "3000–6000 Hz_40ms_envelope_correlation": 0.993602328161592, "3000–6000 Hz_40ms_modulation_mae_db": 0.6817453497933638, "mr_stft_db": 6.162485468878066, "band_mae_db": 0.23831787519569753, "rms_gain_error_db": 0.014801997876692561, "output_peak": 0.05186498485113748}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6219261727834364, "全帯域_10ms_rms_envelope_nrmse": 0.1536232906657922, "全帯域_10ms_envelope_correlation": 0.9780546042376184, "全帯域_10ms_modulation_mae_db": 0.3584597648121301, "全帯域_40ms_log_rms_mae_db": 0.8797491771207595, "全帯域_40ms_rms_envelope_nrmse": 0.0808348289062986, "全帯域_40ms_envelope_correlation": 0.9930968989556364, "全帯域_40ms_modulation_mae_db": 0.28725949739004303, "300–1000 Hz_10ms_log_rms_mae_db": 2.6836872763409536, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24352785614227915, "300–1000 Hz_10ms_envelope_correlation": 0.9580712967038113, "300–1000 Hz_10ms_modulation_mae_db": 0.27394556326836167, "300–1000 Hz_40ms_log_rms_mae_db": 1.933445512411846, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1518431685901374, "300–1000 Hz_40ms_envelope_correlation": 0.9825459647839568, "300–1000 Hz_40ms_modulation_mae_db": 0.4246557027459454, "1000–3000 Hz_10ms_log_rms_mae_db": 1.9150514804153165, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2028338042306465, "1000–3000 Hz_10ms_envelope_correlation": 0.9688747969136082, "1000–3000 Hz_10ms_modulation_mae_db": 0.45722964619172135, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2410002087503107, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11290710808337077, "1000–3000 Hz_40ms_envelope_correlation": 0.989339597112143, "1000–3000 Hz_40ms_modulation_mae_db": 0.7757005219481033, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7582135523739266, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17987706720117863, "3000–6000 Hz_10ms_envelope_correlation": 0.9752880806968811, "3000–6000 Hz_10ms_modulation_mae_db": 0.5600121049014352, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1203190304988686, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08971520221930152, "3000–6000 Hz_40ms_envelope_correlation": 0.9933047580742085, "3000–6000 Hz_40ms_modulation_mae_db": 0.5762840321099302, "mr_stft_db": 6.162900449973925, "band_mae_db": 0.22890016175772399, "rms_gain_error_db": -0.001056118161414336, "output_peak": 0.06024431994759868}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6634429515179687, "全帯域_10ms_rms_envelope_nrmse": 0.16603831806740488, "全帯域_10ms_envelope_correlation": 0.9741811122538302, "全帯域_10ms_modulation_mae_db": 0.3767247822309893, "全帯域_40ms_log_rms_mae_db": 0.8372493893484173, "全帯域_40ms_rms_envelope_nrmse": 0.08429361167566725, "全帯域_40ms_envelope_correlation": 0.9924955296431623, "全帯域_40ms_modulation_mae_db": 0.5437500556492992, "300–1000 Hz_10ms_log_rms_mae_db": 2.6523188732347136, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2741203427133715, "300–1000 Hz_10ms_envelope_correlation": 0.9429329021313008, "300–1000 Hz_10ms_modulation_mae_db": 0.8524378803551683, "300–1000 Hz_40ms_log_rms_mae_db": 1.7966120761730913, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.158240889354241, "300–1000 Hz_40ms_envelope_correlation": 0.978698071590843, "300–1000 Hz_40ms_modulation_mae_db": 0.7328102824029598, "1000–3000 Hz_10ms_log_rms_mae_db": 1.9667192780947544, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.215180699104801, "1000–3000 Hz_10ms_envelope_correlation": 0.9648377062147213, "1000–3000 Hz_10ms_modulation_mae_db": 0.2641142040566296, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2114982443442783, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11604822320119344, "1000–3000 Hz_40ms_envelope_correlation": 0.9887468723534113, "1000–3000 Hz_40ms_modulation_mae_db": 0.6206983592271939, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7512948446138825, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18207077782670297, "3000–6000 Hz_10ms_envelope_correlation": 0.9741233514781517, "3000–6000 Hz_10ms_modulation_mae_db": 0.6360709432315246, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1347996055515068, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10044719779699823, "3000–6000 Hz_40ms_envelope_correlation": 0.9914267177973619, "3000–6000 Hz_40ms_modulation_mae_db": 0.7227906248421911, "mr_stft_db": 6.138028211776509, "band_mae_db": 0.5406574713174653, "rms_gain_error_db": -0.07180207751597338, "output_peak": 0.05181606639353189}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5988955697635723, "全帯域_10ms_rms_envelope_nrmse": 0.13056039956461432, "全帯域_10ms_envelope_correlation": 0.9844434459892872, "全帯域_10ms_modulation_mae_db": 0.778093078927594, "全帯域_40ms_log_rms_mae_db": 0.8470608806704296, "全帯域_40ms_rms_envelope_nrmse": 0.07023317011558286, "全帯域_40ms_envelope_correlation": 0.9954874285359921, "全帯域_40ms_modulation_mae_db": 0.7488067753429272, "300–1000 Hz_10ms_log_rms_mae_db": 2.6933898720508136, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24039445137451262, "300–1000 Hz_10ms_envelope_correlation": 0.956830835220234, "300–1000 Hz_10ms_modulation_mae_db": 0.4869089863767551, "300–1000 Hz_40ms_log_rms_mae_db": 1.969998279898304, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1492964023981034, "300–1000 Hz_40ms_envelope_correlation": 0.981432638710268, "300–1000 Hz_40ms_modulation_mae_db": 0.5928771049057487, "1000–3000 Hz_10ms_log_rms_mae_db": 1.851148868068426, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.175220032024554, "1000–3000 Hz_10ms_envelope_correlation": 0.9770030051223219, "1000–3000 Hz_10ms_modulation_mae_db": 0.6325338326536288, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1687100663703356, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10086688457740693, "1000–3000 Hz_40ms_envelope_correlation": 0.9923602902863389, "1000–3000 Hz_40ms_modulation_mae_db": 0.8086446748777901, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7811061655629543, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1720644124061469, "3000–6000 Hz_10ms_envelope_correlation": 0.9769647624862319, "3000–6000 Hz_10ms_modulation_mae_db": 0.7367912856313863, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1442900694383764, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10907325359736846, "3000–6000 Hz_40ms_envelope_correlation": 0.9900144297793921, "3000–6000 Hz_40ms_modulation_mae_db": 1.0454377596555733, "mr_stft_db": 6.128493408743303, "band_mae_db": 0.4585836976902194, "rms_gain_error_db": -0.2290989862944666, "output_peak": 0.051923991264538505}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6888759995467035, "全帯域_10ms_rms_envelope_nrmse": 0.14969072331648156, "全帯域_10ms_envelope_correlation": 0.9791002230504319, "全帯域_10ms_modulation_mae_db": 0.31894721122053954, "全帯域_40ms_log_rms_mae_db": 0.8297514397967629, "全帯域_40ms_rms_envelope_nrmse": 0.08235899195013618, "全帯域_40ms_envelope_correlation": 0.9928203499908732, "全帯域_40ms_modulation_mae_db": 0.5105467648269297, "300–1000 Hz_10ms_log_rms_mae_db": 2.721956987390986, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25602793013278313, "300–1000 Hz_10ms_envelope_correlation": 0.9527864481726329, "300–1000 Hz_10ms_modulation_mae_db": 0.7826260431931068, "300–1000 Hz_40ms_log_rms_mae_db": 1.9751463970816965, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15581109399688464, "300–1000 Hz_40ms_envelope_correlation": 0.981036845981783, "300–1000 Hz_40ms_modulation_mae_db": 0.7991378089903245, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8719630918680832, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19147019945466534, "1000–3000 Hz_10ms_envelope_correlation": 0.9721929959832492, "1000–3000 Hz_10ms_modulation_mae_db": 0.5375391003272489, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1902625327178442, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11026325939779397, "1000–3000 Hz_40ms_envelope_correlation": 0.9898414179600037, "1000–3000 Hz_40ms_modulation_mae_db": 0.4113322825850066, "3000–6000 Hz_10ms_log_rms_mae_db": 1.761065510575027, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18953934484275575, "3000–6000 Hz_10ms_envelope_correlation": 0.9744690271076923, "3000–6000 Hz_10ms_modulation_mae_db": 0.7563731958107386, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1392525637990423, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1059027617401557, "3000–6000 Hz_40ms_envelope_correlation": 0.992094753274128, "3000–6000 Hz_40ms_modulation_mae_db": 0.5106542865598656, "mr_stft_db": 6.1422748775443345, "band_mae_db": 0.7015807704646672, "rms_gain_error_db": -0.026781626059252342, "output_peak": 0.06525470499441173}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6115092871805539, "全帯域_10ms_rms_envelope_nrmse": 0.15667320669689885, "全帯域_10ms_envelope_correlation": 0.9771876116156792, "全帯域_10ms_modulation_mae_db": 0.7313536108122723, "全帯域_40ms_log_rms_mae_db": 0.8918937978138137, "全帯域_40ms_rms_envelope_nrmse": 0.0835891158968892, "全帯域_40ms_envelope_correlation": 0.9932330647783594, "全帯域_40ms_modulation_mae_db": 0.902645094934383, "300–1000 Hz_10ms_log_rms_mae_db": 2.7672567796299625, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26559226799062213, "300–1000 Hz_10ms_envelope_correlation": 0.9481511474311506, "300–1000 Hz_10ms_modulation_mae_db": 0.3357092072814763, "300–1000 Hz_40ms_log_rms_mae_db": 2.089634639779488, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1623660885132589, "300–1000 Hz_40ms_envelope_correlation": 0.9785724763209264, "300–1000 Hz_40ms_modulation_mae_db": 0.5611458387811706, "1000–3000 Hz_10ms_log_rms_mae_db": 1.993137489446854, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18774070009240137, "1000–3000 Hz_10ms_envelope_correlation": 0.9733444236028321, "1000–3000 Hz_10ms_modulation_mae_db": 0.7130110823709231, "1000–3000 Hz_40ms_log_rms_mae_db": 1.300412381909478, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10964283355808263, "1000–3000 Hz_40ms_envelope_correlation": 0.9906084955047149, "1000–3000 Hz_40ms_modulation_mae_db": 1.0295138300781896, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7363514738811594, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19120581340880996, "3000–6000 Hz_10ms_envelope_correlation": 0.9714382142922716, "3000–6000 Hz_10ms_modulation_mae_db": 0.36992456795130546, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0893798498970038, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10604785331020639, "3000–6000 Hz_40ms_envelope_correlation": 0.9904815442972906, "3000–6000 Hz_40ms_modulation_mae_db": 0.528838845884921, "mr_stft_db": 6.1361694674208564, "band_mae_db": 0.4451088584543471, "rms_gain_error_db": -0.23323499399001135, "output_peak": 0.058701937988351084}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6446900561542979, "全帯域_10ms_rms_envelope_nrmse": 0.13906565549484895, "全帯域_10ms_envelope_correlation": 0.9819274006657202, "全帯域_10ms_modulation_mae_db": 0.2638245624791777, "全帯域_40ms_log_rms_mae_db": 0.8518692416727488, "全帯域_40ms_rms_envelope_nrmse": 0.07240708499526749, "全帯域_40ms_envelope_correlation": 0.994572157052802, "全帯域_40ms_modulation_mae_db": 0.6093663133083346, "300–1000 Hz_10ms_log_rms_mae_db": 2.67732151351629, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.23331143695274034, "300–1000 Hz_10ms_envelope_correlation": 0.9596551895995526, "300–1000 Hz_10ms_modulation_mae_db": 0.3758901225785983, "300–1000 Hz_40ms_log_rms_mae_db": 1.8657268167971877, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15934325362875024, "300–1000 Hz_40ms_envelope_correlation": 0.9790078349238609, "300–1000 Hz_40ms_modulation_mae_db": 0.5646408589641938, "1000–3000 Hz_10ms_log_rms_mae_db": 1.909300422434102, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17505887853623817, "1000–3000 Hz_10ms_envelope_correlation": 0.9767965002406235, "1000–3000 Hz_10ms_modulation_mae_db": 0.4421023396641575, "1000–3000 Hz_40ms_log_rms_mae_db": 1.227800663305305, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08704745987140203, "1000–3000 Hz_40ms_envelope_correlation": 0.9936749612027382, "1000–3000 Hz_40ms_modulation_mae_db": 0.8099931507417715, "3000–6000 Hz_10ms_log_rms_mae_db": 1.708182203568295, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15534941713176104, "3000–6000 Hz_10ms_envelope_correlation": 0.9812873296414061, "3000–6000 Hz_10ms_modulation_mae_db": 0.5560180041394283, "3000–6000 Hz_40ms_log_rms_mae_db": 1.098004442921894, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08383236836444549, "3000–6000 Hz_40ms_envelope_correlation": 0.9943119011742393, "3000–6000 Hz_40ms_modulation_mae_db": 0.8877704607662475, "mr_stft_db": 6.153716388250793, "band_mae_db": 0.40097400358148044, "rms_gain_error_db": -0.11595389079383847, "output_peak": 0.057304618405541304}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.685642849042925, "全帯域_10ms_rms_envelope_nrmse": 0.17232479877580187, "全帯域_10ms_envelope_correlation": 0.9728138635196623, "全帯域_10ms_modulation_mae_db": 0.4291295470174081, "全帯域_40ms_log_rms_mae_db": 0.9083234798146028, "全帯域_40ms_rms_envelope_nrmse": 0.09944044853467245, "全帯域_40ms_envelope_correlation": 0.9897997192110836, "全帯域_40ms_modulation_mae_db": 0.5751444155982549, "300–1000 Hz_10ms_log_rms_mae_db": 2.8095792699198863, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24030795474183578, "300–1000 Hz_10ms_envelope_correlation": 0.9571982200169463, "300–1000 Hz_10ms_modulation_mae_db": 0.5343237554279038, "300–1000 Hz_40ms_log_rms_mae_db": 2.0094356953553056, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1439713691239974, "300–1000 Hz_40ms_envelope_correlation": 0.9834213827776696, "300–1000 Hz_40ms_modulation_mae_db": 0.29201200693235335, "1000–3000 Hz_10ms_log_rms_mae_db": 1.930573739074788, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2211668026397422, "1000–3000 Hz_10ms_envelope_correlation": 0.9643191748505922, "1000–3000 Hz_10ms_modulation_mae_db": 0.6875955581970222, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2340622371694916, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.13326403738431386, "1000–3000 Hz_40ms_envelope_correlation": 0.9859333049793163, "1000–3000 Hz_40ms_modulation_mae_db": 0.796650531646144, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7389566307514317, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1724085777304167, "3000–6000 Hz_10ms_envelope_correlation": 0.9780862376945735, "3000–6000 Hz_10ms_modulation_mae_db": 0.31121551133707026, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1011595360910862, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09400745186828088, "3000–6000 Hz_40ms_envelope_correlation": 0.9932387657830472, "3000–6000 Hz_40ms_modulation_mae_db": 0.4577783787879242, "mr_stft_db": 6.140200713021521, "band_mae_db": 0.6434218956513679, "rms_gain_error_db": 0.10057133733610224, "output_peak": 0.06415170917986936}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 96209, "output_samples": 96209, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.457219323082445, "spectral_convergence": 0.5938567749167448, "spectral_convergence_status": "ok", "amplitude_floor": 1.776300245720871e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.028735784504337, "spectral_convergence": 0.6066900557114427, "spectral_convergence_status": "ok", "amplitude_floor": 1.1913344769267054e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.001501299047415, "spectral_convergence": 0.623242068773733, "spectral_convergence_status": "ok", "amplitude_floor": 5.645485889979311e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0529488065388325e-06, "output_power": 9.54873621201122e-07, "delta_db": -0.42461360743784293, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.178233710401702e-07, "output_power": 6.931724643962484e-07, "delta_db": 0.4997696967724699, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.652745613182611e-06, "output_power": 5.6337266136360496e-06, "delta_db": -0.014636733616426138, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.2826510059132755e-05, "output_power": 1.2507279459292923e-05, "delta_db": -0.10945652369880342, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2385922939210616e-05, "output_power": 1.2949562939948404e-05, "delta_db": 0.19326737156486967, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.5916906482380547e-06, "output_power": 1.650913353333814e-06, "delta_db": 0.15865615668610403, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.299457135974266e-06, "output_power": 2.161935907039201e-06, "delta_db": -0.26782503659336665, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.23831787519569753, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.014801997876692561, "pitch": null, "output_rms_dbfs": -44.370952192470874, "output_peak": 0.05186498485113748, "reference_rms_dbfs": -44.38575419034756, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.162485468878066}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 96209, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.089458070502993e-05, "log_rms_mae_db": 1.6888335017994331, "rms_envelope_nrmse": 0.16280275480096043, "envelope_correlation": 0.9753622857512744, "rms_gain_error_db": 0.014791888846546641, "reference_mean_power": 3.6506204511776254e-05, "output_mean_power": 3.6630755107803284e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 2.0041859534078988e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.999428757782778e-06, "output_power": 7.930720815420127e-06, "reference_active": true, "delta_db": -0.037463132567380715}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3205374160249087e-06, "output_power": 3.1508689875654064e-06, "reference_active": true, "delta_db": -0.2277803257898339}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.233369046941817e-06, "output_power": 1.1659056819629982e-06, "reference_active": true, "delta_db": -0.24429626211009242}], "active_band_count": 3, "active_band_mae_db": 0.16984657348910237}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.7773650083170072e-05, "log_rms_mae_db": 0.949299135994107, "rms_envelope_nrmse": 0.08974748927562116, "envelope_correlation": 0.9914966844570454, "rms_gain_error_db": 0.014762286146794026, "reference_mean_power": 3.678163866257165e-05, "output_mean_power": 3.690687740700492e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.6475917872957343e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.744366291346524e-06, "output_power": 6.860455245733835e-06, "reference_active": true, "delta_db": 0.07411786453236893}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5635835823033082e-06, "output_power": 1.5130576599947955e-06, "reference_active": true, "delta_db": -0.14265623127299076}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.396664522501232e-08, "output_power": 8.340899601459916e-08, "reference_active": true, "delta_db": -0.5176082838409066}], "active_band_count": 3, "active_band_mae_db": 0.24479412654875543}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1737971097625835e-05, "log_rms_mae_db": 2.734447200815355, "rms_envelope_nrmse": 0.26107715771485873, "envelope_correlation": 0.9515429795034229, "rms_gain_error_db": 0.36827894980501646, "reference_mean_power": 3.7178438627460445e-06, "output_mean_power": 4.046868027677431e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.0069118410394303e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5873171334916186e-06, "output_power": 1.6721710812752373e-06, "reference_active": true, "delta_db": 0.22617004372624688}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.351037742291938e-07, "output_power": 5.718391066031418e-07, "reference_active": true, "delta_db": -0.4557084130896427}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7445146919256035e-07, "output_power": 2.3706682931882662e-07, "reference_active": true, "delta_db": -0.635947687742686}], "active_band_count": 3, "active_band_mae_db": 0.43927538151952517}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 7.730313378567735e-06, "log_rms_mae_db": 2.0349876643493636, "rms_envelope_nrmse": 0.16446891371579533, "envelope_correlation": 0.979182034670957, "rms_gain_error_db": 0.3682629891786721, "reference_mean_power": 3.745927267695172e-06, "output_mean_power": 4.0774217912301745e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.5331447910659217e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5569974188207908e-06, "output_power": 1.6314560280293735e-06, "reference_active": true, "delta_db": 0.2028748032071723}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5335281635338005e-07, "output_power": 3.066444411071276e-07, "reference_active": true, "delta_db": -0.6157346100870641}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.1249603669561348e-08, "output_power": 1.693028590598024e-08, "reference_active": true, "delta_db": -0.9868654214149021}], "active_band_count": 3, "active_band_mae_db": 0.6018249449030462}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.066376004316646e-05, "log_rms_mae_db": 1.9423392629356937, "rms_envelope_nrmse": 0.21109618545198436, "envelope_correlation": 0.9661475013060147, "rms_gain_error_db": -0.048265738256518816, "reference_mean_power": 1.9040046826256083e-05, "output_mean_power": 1.8829614913719324e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 1.3406247189798443e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.3392457188005514e-06, "output_power": 6.047160342321745e-06, "reference_active": true, "delta_db": -0.20486101801782153}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.391738535251293e-06, "output_power": 2.206430602641089e-06, "reference_active": true, "delta_db": -0.35023428428637016}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.54995852980617e-07, "output_power": 7.447823663489497e-07, "reference_active": true, "delta_db": -0.05915180523860053}], "active_band_count": 3, "active_band_mae_db": 0.2047490358475974}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.6710315888953048e-05, "log_rms_mae_db": 1.2573716176455754, "rms_envelope_nrmse": 0.1265365707012214, "envelope_correlation": 0.9865983032417767, "rms_gain_error_db": -0.04826611089855445, "reference_mean_power": 1.9183917331823965e-05, "output_mean_power": 1.897189372465873e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.1409929070898633e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.5949700460751985e-06, "output_power": 5.427950507265238e-06, "reference_active": true, "delta_db": -0.1316188672375283}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1687645280234336e-06, "output_power": 1.0766384389902417e-06, "reference_active": true, "delta_db": -0.35657141019913874}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.657756100862398e-08, "output_power": 6.361713005324522e-08, "reference_active": true, "delta_db": -0.8052745700114212}], "active_band_count": 3, "active_band_mae_db": 0.43115494914936275}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1530093504582296e-05, "log_rms_mae_db": 1.7931218885485152, "rms_envelope_nrmse": 0.17639077110242013, "envelope_correlation": 0.9776705249436504, "rms_gain_error_db": 0.3052553734761097, "reference_mean_power": 5.108146850353514e-06, "output_mean_power": 5.480105398619207e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.254259363144466e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7396247028720546e-06, "output_power": 1.8488207940782117e-06, "reference_active": true, "delta_db": 0.26439251031370775}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.118165550857846e-07, "output_power": 5.603249058248568e-07, "reference_active": true, "delta_db": 0.39325597452701344}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4689547511366827e-07, "output_power": 1.1319268744706378e-07, "reference_active": true, "delta_db": -1.1319004706768228}], "active_band_count": 3, "active_band_mae_db": 0.596516318505848}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 9.091353933231884e-06, "log_rms_mae_db": 1.1276826764106296, "rms_envelope_nrmse": 0.0950502150241374, "envelope_correlation": 0.993602328161592, "rms_gain_error_db": 0.30525444944330116, "reference_mean_power": 5.146742550240226e-06, "output_mean_power": 5.5215103363585116e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.7984368001248054e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6090100968943592e-06, "output_power": 1.6976257338645163e-06, "reference_active": true, "delta_db": 0.2328318056208878}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.367924284305246e-07, "output_power": 2.567166700879105e-07, "reference_active": true, "delta_db": 0.35086259356797794}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2506680970493352e-08, "output_power": 8.93280609163072e-09, "reference_active": true, "delta_db": -1.4615416501912257}], "active_band_count": 3, "active_band_mae_db": 0.6817453497933638}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.5995084299122154, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "7492869b6f7f4f6f6fe90b16aea5339423768cc05b8386753a7aa6ccb28d6263", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9704395130292454, "standard_deviation": 0.005136875133152908, "minimum": 0.9643191748505922, "maximum": 0.9770030051223219, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.9225292040422524, "standard_deviation": 0.04671868189710251, "minimum": 1.851148868068426, "maximum": 1.993137489446854, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4923593499136162, "standard_deviation": 0.18787148420715466, "minimum": 0.2047490358475974, "maximum": 0.7130110823709231, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1974709126918791, "standard_deviation": 0.01779898456456703, "minimum": 0.17505887853623817, "maximum": 0.2211668026397422, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9896379053300554, "standard_deviation": 0.002633271588704859, "minimum": 0.9859333049793163, "maximum": 0.9936749612027382, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.2288897440265774, "standard_deviation": 0.040562875901900615, "minimum": 1.1687100663703356, "maximum": 1.300412381909478, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7104610375316952, "standard_deviation": 0.20995693889009906, "minimum": 0.4113322825850066, "maximum": 1.0295138300781896, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.11207204709684812, "standard_deviation": 0.014321754795503605, "minimum": 0.08704745987140203, "maximum": 0.13326403738431386, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9761659410426073, "standard_deviation": 0.0029998042047845353, "minimum": 0.9714382142922716, "maximum": 0.9812873296414061, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.7535365337343989, "standard_deviation": 0.026660793039924868, "minimum": 1.708182203568295, "maximum": 1.7931218885485152, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5653652414385921, "standard_deviation": 0.15799899737894177, "minimum": 0.31121551133707026, "maximum": 0.7563731958107386, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.177363272706274, "standard_deviation": 0.011380026063268624, "minimum": 0.15534941713176104, "maximum": 0.19120581340880996, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9923093997926575, "standard_deviation": 0.0015569786910021594, "minimum": 0.9900144297793921, "maximum": 0.9943119011742393, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.119360971826051, "standard_deviation": 0.020743042398699455, "minimum": 1.0893798498970038, "maximum": 1.1442900694383764, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.676412467300002, "standard_deviation": 0.20357924302900873, "minimum": 0.4577783787879242, "maximum": 1.0454377596555733, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09800953799011175, "standard_deviation": 0.008862665778769808, "minimum": 0.08383236836444549, "maximum": 0.10907325359736846, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9533961273473814, "standard_deviation": 0.00570815153342045, "minimum": 0.9429329021313008, "maximum": 0.9596551895995526, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.71749472161237, "standard_deviation": 0.05189121837458967, "minimum": 2.6523188732347136, "maximum": 2.8095792699198863, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5101396175001119, "standard_deviation": 0.20763971330218653, "minimum": 0.27394556326836167, "maximum": 0.8524378803551683, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2517949247203754, "standard_deviation": 0.014465595483240442, "minimum": 0.23331143695274034, "maximum": 0.2741203427133715, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.980487156220033, "standard_deviation": 0.001882362909049508, "minimum": 0.9785724763209264, "maximum": 0.9834213827776696, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.9593733852307853, "standard_deviation": 0.09372193135795029, "minimum": 1.7966120761730913, "maximum": 2.089634639779488, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5711380685782177, "standard_deviation": 0.15993148381587943, "minimum": 0.29201200693235335, "maximum": 0.7991378089903245, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15566764741514605, "standard_deviation": 0.006912782785642969, "minimum": 0.1439713691239974, "maximum": 0.16446891371579533, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.45719309176412115, "standard_deviation": 0.17100767661404434, "minimum": 0.22890016175772399, "maximum": 0.7015807704646672, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.145533623201164, "standard_deviation": 0.0127019473479305, "minimum": 6.128493408743303, "maximum": 6.162900449973925, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.057657791628122505, "standard_deviation": 0.005455639156471053, "minimum": 0.05181606639353189, "maximum": 0.06525470499441173, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07031929470027021, "standard_deviation": 0.1177038592194269, "minimum": -0.23323499399001135, "maximum": 0.10057133733610224, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9778838183854379, "standard_deviation": 0.003912350148739168, "minimum": 0.9728138635196623, "maximum": 0.9844434459892872, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.6504770484736113, "standard_deviation": 0.03660254143317807, "minimum": 1.5988955697635723, "maximum": 1.6888759995467035, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.42829739137365164, "standard_deviation": 0.21631439234911565, "minimum": 0.16984657348910237, "maximum": 0.778093078927594, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.15384739342285036, "standard_deviation": 0.013919815566734668, "minimum": 0.13056039956461432, "maximum": 0.17232479877580187, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9928752290781193, "standard_deviation": 0.0017479238325831903, "minimum": 0.9897997192110836, "maximum": 0.9954874285359921, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8743995677789551, "standard_deviation": 0.04092511284258095, "minimum": 0.8297514397967629, "maximum": 0.949299135994107, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5527891304498659, "standard_deviation": 0.2177009351566901, "minimum": 0.24479412654875543, "maximum": 0.902645094934383, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0828630926687669, "standard_deviation": 0.009242666205426929, "minimum": 0.07023317011558286, "maximum": 0.09944044853467245, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs066_whisper10_BASIC5000_2372", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 1.1722850799560547, "predicted_mos": 1.1722850799560547, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 96209, "input_sample_rate": 24000, "input_seconds": 4.008708333333334, "input_float32_sha256": "5a859ec9bb5db4baf135f26dd51881b987f153baca225bd3f4a66b74b076dbad", "internal_samples": 64140, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 10.014877799898386}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6718943262290775, "全帯域_10ms_rms_envelope_nrmse": 0.13648080615833857, "全帯域_10ms_envelope_correlation": 0.9828137992484979, "全帯域_10ms_modulation_mae_db": 0.05543058780266131, "全帯域_40ms_log_rms_mae_db": 0.8847312399898293, "全帯域_40ms_rms_envelope_nrmse": 0.07090219107655071, "全帯域_40ms_envelope_correlation": 0.9947644212136186, "全帯域_40ms_modulation_mae_db": 0.15797244369625185, "300–1000 Hz_10ms_log_rms_mae_db": 2.5699658201507223, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24335499258718907, "300–1000 Hz_10ms_envelope_correlation": 0.9567007432193744, "300–1000 Hz_10ms_modulation_mae_db": 0.15739430111383015, "300–1000 Hz_40ms_log_rms_mae_db": 1.8030128611593204, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1403486349754009, "300–1000 Hz_40ms_envelope_correlation": 0.9842787249190663, "300–1000 Hz_40ms_modulation_mae_db": 0.2886306337070808, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8488627141211091, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.166607712896282, "1000–3000 Hz_10ms_envelope_correlation": 0.9793697192543018, "1000–3000 Hz_10ms_modulation_mae_db": 0.07561675154576329, "1000–3000 Hz_40ms_log_rms_mae_db": 1.121604431934255, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08623024471406512, "1000–3000 Hz_40ms_envelope_correlation": 0.993958223935697, "1000–3000 Hz_40ms_modulation_mae_db": 0.3861700458711519, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6472665468095051, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.164827857215106, "3000–6000 Hz_10ms_envelope_correlation": 0.9789092022007232, "3000–6000 Hz_10ms_modulation_mae_db": 0.7291625615783914, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9659075389143381, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08836303217198706, "3000–6000 Hz_40ms_envelope_correlation": 0.9933450755284406, "3000–6000 Hz_40ms_modulation_mae_db": 0.9903608829457676, "mr_stft_db": 6.07339756075855, "band_mae_db": 0.38240632429315197, "rms_gain_error_db": 0.03885873367708707, "output_peak": 0.055297376389687986}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.600034799663463, "全帯域_10ms_rms_envelope_nrmse": 0.13191421243402376, "全帯域_10ms_envelope_correlation": 0.9839269941014649, "全帯域_10ms_modulation_mae_db": 0.3859469687233019, "全帯域_40ms_log_rms_mae_db": 0.8993707310424461, "全帯域_40ms_rms_envelope_nrmse": 0.06995160615120234, "全帯域_40ms_envelope_correlation": 0.9948918740043028, "全帯域_40ms_modulation_mae_db": 0.7532141444332948, "300–1000 Hz_10ms_log_rms_mae_db": 2.5635338459956913, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24438894544486273, "300–1000 Hz_10ms_envelope_correlation": 0.9582103830359762, "300–1000 Hz_10ms_modulation_mae_db": 0.27008278509213857, "300–1000 Hz_40ms_log_rms_mae_db": 1.8279482672531426, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14544640426042824, "300–1000 Hz_40ms_envelope_correlation": 0.9845888809093403, "300–1000 Hz_40ms_modulation_mae_db": 0.5662865661371569, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7986690398145888, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16151258940580346, "1000–3000 Hz_10ms_envelope_correlation": 0.9807103311973603, "1000–3000 Hz_10ms_modulation_mae_db": 0.31713151272760404, "1000–3000 Hz_40ms_log_rms_mae_db": 1.131748757597023, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0973027526807565, "1000–3000 Hz_40ms_envelope_correlation": 0.9923379102926272, "1000–3000 Hz_40ms_modulation_mae_db": 0.6685266957375715, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6424309498640852, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16351388319725638, "3000–6000 Hz_10ms_envelope_correlation": 0.979563028250803, "3000–6000 Hz_10ms_modulation_mae_db": 0.3868305476402711, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9306595453662304, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07685428321494286, "3000–6000 Hz_40ms_envelope_correlation": 0.9951094729208608, "3000–6000 Hz_40ms_modulation_mae_db": 0.5422323297829614, "mr_stft_db": 6.092388286934153, "band_mae_db": 0.3028039217614733, "rms_gain_error_db": 0.04814235153833196, "output_peak": 0.055907704004699285}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.653381619162078, "全帯域_10ms_rms_envelope_nrmse": 0.14447242410514358, "全帯域_10ms_envelope_correlation": 0.9804893080895714, "全帯域_10ms_modulation_mae_db": 0.35127292688327616, "全帯域_40ms_log_rms_mae_db": 0.8133981886213698, "全帯域_40ms_rms_envelope_nrmse": 0.07805910782339953, "全帯域_40ms_envelope_correlation": 0.9935858816275916, "全帯域_40ms_modulation_mae_db": 0.592342868036576, "300–1000 Hz_10ms_log_rms_mae_db": 2.52453502207599, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2483586336317149, "300–1000 Hz_10ms_envelope_correlation": 0.9561715891315193, "300–1000 Hz_10ms_modulation_mae_db": 0.35050244122453544, "300–1000 Hz_40ms_log_rms_mae_db": 1.7824078543992699, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15371364739486212, "300–1000 Hz_40ms_envelope_correlation": 0.9820275584606227, "300–1000 Hz_40ms_modulation_mae_db": 0.6950631188947279, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8121004157921106, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17148962752873795, "1000–3000 Hz_10ms_envelope_correlation": 0.977668707799078, "1000–3000 Hz_10ms_modulation_mae_db": 0.24766252956680956, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0398247484701304, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09574416298835582, "1000–3000 Hz_40ms_envelope_correlation": 0.9923617179623277, "1000–3000 Hz_40ms_modulation_mae_db": 0.6561153117936899, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6651579076554612, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15674518734391274, "3000–6000 Hz_10ms_envelope_correlation": 0.9813118455790559, "3000–6000 Hz_10ms_modulation_mae_db": 0.18788107441059543, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9974049995973385, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07639151574521574, "3000–6000 Hz_40ms_envelope_correlation": 0.9952035525903618, "3000–6000 Hz_40ms_modulation_mae_db": 0.28521449064572685, "mr_stft_db": 6.103835068836374, "band_mae_db": 0.29337078431279107, "rms_gain_error_db": -0.07305467752072524, "output_peak": 0.0608022437308622}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6126829071722677, "全帯域_10ms_rms_envelope_nrmse": 0.13717522380922392, "全帯域_10ms_envelope_correlation": 0.983268075914735, "全帯域_10ms_modulation_mae_db": 0.5070958101365447, "全帯域_40ms_log_rms_mae_db": 0.826558425698094, "全帯域_40ms_rms_envelope_nrmse": 0.07555155755810639, "全帯域_40ms_envelope_correlation": 0.9945607533550854, "全帯域_40ms_modulation_mae_db": 0.6729962102192498, "300–1000 Hz_10ms_log_rms_mae_db": 2.4398107796503616, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.21524674145722192, "300–1000 Hz_10ms_envelope_correlation": 0.9646169322414948, "300–1000 Hz_10ms_modulation_mae_db": 0.7349291690548725, "300–1000 Hz_40ms_log_rms_mae_db": 1.7072238281476175, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.12438517879675787, "300–1000 Hz_40ms_envelope_correlation": 0.9871337839584375, "300–1000 Hz_40ms_modulation_mae_db": 0.8308491759333666, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8577143571924017, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17736323037025287, "1000–3000 Hz_10ms_envelope_correlation": 0.9793667119484768, "1000–3000 Hz_10ms_modulation_mae_db": 0.8306357444715277, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0957878044765896, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10194422766905228, "1000–3000 Hz_40ms_envelope_correlation": 0.9938775206811719, "1000–3000 Hz_40ms_modulation_mae_db": 1.1329236295393046, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6999948050887752, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1729753352694187, "3000–6000 Hz_10ms_envelope_correlation": 0.976818768076831, "3000–6000 Hz_10ms_modulation_mae_db": 0.2935499159562039, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9930097745612428, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08658178169410757, "3000–6000 Hz_40ms_envelope_correlation": 0.9936192513690802, "3000–6000 Hz_40ms_modulation_mae_db": 0.7914446339280188, "mr_stft_db": 6.085105634877679, "band_mae_db": 0.48519267683074957, "rms_gain_error_db": 0.17427832002027643, "output_peak": 0.05753276798142286}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5920187106828347, "全帯域_10ms_rms_envelope_nrmse": 0.14418840881396816, "全帯域_10ms_envelope_correlation": 0.9805863818357136, "全帯域_10ms_modulation_mae_db": 0.29847546518310236, "全帯域_40ms_log_rms_mae_db": 0.788884442411282, "全帯域_40ms_rms_envelope_nrmse": 0.05930156594308592, "全帯域_40ms_envelope_correlation": 0.996288982027008, "全帯域_40ms_modulation_mae_db": 0.609778792952243, "300–1000 Hz_10ms_log_rms_mae_db": 2.407766423112253, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.22740003822160576, "300–1000 Hz_10ms_envelope_correlation": 0.9615678531126673, "300–1000 Hz_10ms_modulation_mae_db": 0.7823124045960848, "300–1000 Hz_40ms_log_rms_mae_db": 1.6445649013699244, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14280921615827954, "300–1000 Hz_40ms_envelope_correlation": 0.9830175081241465, "300–1000 Hz_40ms_modulation_mae_db": 0.8916152415311055, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7437916991136677, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18445226044747748, "1000–3000 Hz_10ms_envelope_correlation": 0.9741293814440036, "1000–3000 Hz_10ms_modulation_mae_db": 0.34000225343025975, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0439537713280527, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08429213543782457, "1000–3000 Hz_40ms_envelope_correlation": 0.9941681369165182, "1000–3000 Hz_40ms_modulation_mae_db": 0.3268895526505864, "3000–6000 Hz_10ms_log_rms_mae_db": 1.641035447913003, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16702644551846801, "3000–6000 Hz_10ms_envelope_correlation": 0.9797816350822085, "3000–6000 Hz_10ms_modulation_mae_db": 0.44998451807594186, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9233217896501936, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08964081049600849, "3000–6000 Hz_40ms_envelope_correlation": 0.994156229805078, "3000–6000 Hz_40ms_modulation_mae_db": 0.6807157857671093, "mr_stft_db": 6.079957964938392, "band_mae_db": 0.43902522243218767, "rms_gain_error_db": -0.029150848214725442, "output_peak": 0.05142653918257302}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6539412664276463, "全帯域_10ms_rms_envelope_nrmse": 0.14229176981272784, "全帯域_10ms_envelope_correlation": 0.9810596911149254, "全帯域_10ms_modulation_mae_db": 0.3064031597452778, "全帯域_40ms_log_rms_mae_db": 0.8374698958458664, "全帯域_40ms_rms_envelope_nrmse": 0.07152271558164773, "全帯域_40ms_envelope_correlation": 0.9946268636319281, "全帯域_40ms_modulation_mae_db": 0.6997013326203637, "300–1000 Hz_10ms_log_rms_mae_db": 2.5299421854731183, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2513026249131755, "300–1000 Hz_10ms_envelope_correlation": 0.9538008485948256, "300–1000 Hz_10ms_modulation_mae_db": 0.3472571875116402, "300–1000 Hz_40ms_log_rms_mae_db": 1.781688447614972, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16064522563485367, "300–1000 Hz_40ms_envelope_correlation": 0.9791518039090304, "300–1000 Hz_40ms_modulation_mae_db": 0.3026819474890767, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7963934099473837, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17364686190683648, "1000–3000 Hz_10ms_envelope_correlation": 0.9772751286225031, "1000–3000 Hz_10ms_modulation_mae_db": 0.26526245839067536, "1000–3000 Hz_40ms_log_rms_mae_db": 1.071371487079787, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08947524786472331, "1000–3000 Hz_40ms_envelope_correlation": 0.9933300621286686, "1000–3000 Hz_40ms_modulation_mae_db": 0.8234899340738991, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6794486084056992, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1699549398174797, "3000–6000 Hz_10ms_envelope_correlation": 0.9775099600213334, "3000–6000 Hz_10ms_modulation_mae_db": 0.8194450531162971, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9946353760784714, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09200905212260084, "3000–6000 Hz_40ms_envelope_correlation": 0.9930211661347678, "3000–6000 Hz_40ms_modulation_mae_db": 1.0456227881226636, "mr_stft_db": 6.0834246253268836, "band_mae_db": 0.2652489269150608, "rms_gain_error_db": -0.07596011847678454, "output_peak": 0.06131893788843347}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6368759080433304, "全帯域_10ms_rms_envelope_nrmse": 0.13448559040566554, "全帯域_10ms_envelope_correlation": 0.983227074219327, "全帯域_10ms_modulation_mae_db": 0.5594384091000654, "全帯域_40ms_log_rms_mae_db": 0.860120609834983, "全帯域_40ms_rms_envelope_nrmse": 0.062028933344513634, "全帯域_40ms_envelope_correlation": 0.9959603037838272, "全帯域_40ms_modulation_mae_db": 0.6914984381317498, "300–1000 Hz_10ms_log_rms_mae_db": 2.450415839181633, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.23098094943787187, "300–1000 Hz_10ms_envelope_correlation": 0.9612036246956549, "300–1000 Hz_10ms_modulation_mae_db": 0.5674582729308218, "300–1000 Hz_40ms_log_rms_mae_db": 1.723683860054791, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1441017259669714, "300–1000 Hz_40ms_envelope_correlation": 0.9834487075029619, "300–1000 Hz_40ms_modulation_mae_db": 0.7044983044888645, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7285106027701738, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15844932297038428, "1000–3000 Hz_10ms_envelope_correlation": 0.9815739024547292, "1000–3000 Hz_10ms_modulation_mae_db": 0.43206005615298365, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0360416220150577, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07430196251494947, "1000–3000 Hz_40ms_envelope_correlation": 0.9957053675421186, "1000–3000 Hz_40ms_modulation_mae_db": 0.5830634349151556, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6606633087745843, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1705433863508402, "3000–6000 Hz_10ms_envelope_correlation": 0.9774146301121927, "3000–6000 Hz_10ms_modulation_mae_db": 0.47604354246859065, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9563605039517241, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08869973431479096, "3000–6000 Hz_40ms_envelope_correlation": 0.993283341308765, "3000–6000 Hz_40ms_modulation_mae_db": 0.6720724842079037, "mr_stft_db": 6.084890019599439, "band_mae_db": 0.3772180030001843, "rms_gain_error_db": 0.02587814862145532, "output_peak": 0.05288914366168825}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6415973351767084, "全帯域_10ms_rms_envelope_nrmse": 0.13505334251900614, "全帯域_10ms_envelope_correlation": 0.9829747716084396, "全帯域_10ms_modulation_mae_db": 0.06320804313228262, "全帯域_40ms_log_rms_mae_db": 0.8609454653044293, "全帯域_40ms_rms_envelope_nrmse": 0.06978295176697688, "全帯域_40ms_envelope_correlation": 0.9948708821983142, "全帯域_40ms_modulation_mae_db": 0.36636269838941976, "300–1000 Hz_10ms_log_rms_mae_db": 2.4951872126631125, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24533218054589306, "300–1000 Hz_10ms_envelope_correlation": 0.9590155491077932, "300–1000 Hz_10ms_modulation_mae_db": 0.1537051499034423, "300–1000 Hz_40ms_log_rms_mae_db": 1.750971802676805, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15644401246339307, "300–1000 Hz_40ms_envelope_correlation": 0.9827477736877394, "300–1000 Hz_40ms_modulation_mae_db": 0.20322208332307046, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7879145756850487, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16786375019162342, "1000–3000 Hz_10ms_envelope_correlation": 0.9785921090199717, "1000–3000 Hz_10ms_modulation_mae_db": 0.07557866924092499, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0513230154063504, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08975517850343097, "1000–3000 Hz_40ms_envelope_correlation": 0.9933677706921054, "1000–3000 Hz_40ms_modulation_mae_db": 0.5143949877651928, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6023549603664993, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16332271861801975, "3000–6000 Hz_10ms_envelope_correlation": 0.9800853223970784, "3000–6000 Hz_10ms_modulation_mae_db": 0.30191792380199717, "3000–6000 Hz_40ms_log_rms_mae_db": 0.954262080751708, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08335637462747925, "3000–6000 Hz_40ms_envelope_correlation": 0.9945527274359188, "3000–6000 Hz_40ms_modulation_mae_db": 0.2628006281798858, "mr_stft_db": 6.070524773768546, "band_mae_db": 0.4660215555866068, "rms_gain_error_db": -0.05628383885711591, "output_peak": 0.060927617060682136}, "full_scale": {"sample_count": 96209, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 96209, "output_samples": 96209, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.389689940964655, "spectral_convergence": 0.5811912665790511, "spectral_convergence_status": "ok", "amplitude_floor": 1.776300245720871e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.908456901034775, "spectral_convergence": 0.5896988044646465, "spectral_convergence_status": "ok", "amplitude_floor": 1.1913344769267054e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.92204584027622, "spectral_convergence": 0.6198634834287217, "spectral_convergence_status": "ok", "amplitude_floor": 5.645485889979311e-08}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0529488065388325e-06, "output_power": 9.74646552787842e-07, "delta_db": -0.3356010559652461, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.178233710401702e-07, "output_power": 8.266555791411974e-07, "delta_db": 1.2646026838666566, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.652745613182611e-06, "output_power": 5.196803723824325e-06, "delta_db": -0.36523127205619393, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.2826510059132755e-05, "output_power": 1.3177191074810548e-05, "delta_db": 0.11714337351940178, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2385922939210616e-05, "output_power": 1.2737154795912633e-05, "delta_db": 0.12144053209567857, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.5916906482380547e-06, "output_power": 1.6736264994652973e-06, "delta_db": 0.217998790226882, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.299457135974266e-06, "output_power": 2.168416294426416e-06, "delta_db": -0.25482656232200523, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.38240632429315197, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.03885873367708707, "pitch": null, "output_rms_dbfs": -44.34689545667048, "output_peak": 0.055297376389687986, "reference_rms_dbfs": -44.38575419034756, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.07339756075855}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 96209, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.089458070502993e-05, "log_rms_mae_db": 1.6718943262290775, "rms_envelope_nrmse": 0.13648080615833857, "envelope_correlation": 0.9828137992484979, "rms_gain_error_db": 0.038864131559141556, "reference_mean_power": 3.6506204511776254e-05, "output_mean_power": 3.6834357221215085e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 2.0041859534078988e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.999428757782778e-06, "output_power": 7.983076687507994e-06, "reference_active": true, "delta_db": -0.00888673730196833}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3205374160249087e-06, "output_power": 3.267087115834288e-06, "reference_active": true, "delta_db": -0.0704766330657171}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.233369046941817e-06, "output_power": 1.2089273578611566e-06, "reference_active": true, "delta_db": -0.08692839304029851}], "active_band_count": 3, "active_band_mae_db": 0.05543058780266131}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.7773650083170072e-05, "log_rms_mae_db": 0.8847312399898293, "rms_envelope_nrmse": 0.07090219107655071, "envelope_correlation": 0.9947644212136186, "rms_gain_error_db": 0.03887634725188609, "reference_mean_power": 3.678163866257165e-05, "output_mean_power": 3.7112371626114864e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.6475917872957343e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.744366291346524e-06, "output_power": 6.830737758646488e-06, "reference_active": true, "delta_db": 0.05526463395959737}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5635835823033082e-06, "output_power": 1.5623019941833355e-06, "reference_active": true, "delta_db": -0.0035611455771112945}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.396664522501232e-08, "output_power": 8.540131675779138e-08, "reference_active": true, "delta_db": -0.4150915515520469}], "active_band_count": 3, "active_band_mae_db": 0.15797244369625185}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1737971097625835e-05, "log_rms_mae_db": 2.5699658201507223, "rms_envelope_nrmse": 0.24335499258718907, "envelope_correlation": 0.9567007432193744, "rms_gain_error_db": 0.2370900157328964, "reference_mean_power": 3.7178438627460445e-06, "output_mean_power": 3.926450696109135e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.0069118410394303e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5873171334916186e-06, "output_power": 1.5977867552019048e-06, "reference_active": true, "delta_db": 0.028551127193533872}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.351037742291938e-07, "output_power": 6.298735048340494e-07, "reference_active": true, "delta_db": -0.03591353171231087}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7445146919256035e-07, "output_power": 2.498582739792821e-07, "reference_active": true, "delta_db": -0.40771824443564575}], "active_band_count": 3, "active_band_mae_db": 0.15739430111383015}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 7.730313378567735e-06, "log_rms_mae_db": 1.8030128611593204, "rms_envelope_nrmse": 0.1403486349754009, "envelope_correlation": 0.9842787249190663, "rms_gain_error_db": 0.23707729000495498, "reference_mean_power": 3.745927267695172e-06, "output_mean_power": 3.956098258237883e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.5331447910659217e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.5569974188207908e-06, "output_power": 1.5470553961000185e-06, "reference_active": true, "delta_db": -0.027820276451330228}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5335281635338005e-07, "output_power": 3.49302804305478e-07, "reference_active": true, "delta_db": -0.05006484857833422}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.1249603669561348e-08, "output_power": 1.7723527226304944e-08, "reference_active": true, "delta_db": -0.7880067760915779}], "active_band_count": 3, "active_band_mae_db": 0.2886306337070808}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 2.066376004316646e-05, "log_rms_mae_db": 1.8488627141211091, "rms_envelope_nrmse": 0.166607712896282, "envelope_correlation": 0.9793697192543018, "rms_gain_error_db": 0.09220715402913365, "reference_mean_power": 1.9040046826256083e-05, "output_mean_power": 1.944861716371815e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 1.3406247189798443e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.3392457188005514e-06, "output_power": 6.261576346855369e-06, "reference_active": true, "delta_db": -0.053539057477948265}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.391738535251293e-06, "output_power": 2.4235430272765635e-06, "reference_active": true, "delta_db": 0.05737033678437463}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.54995852980617e-07, "output_power": 7.351068676569035e-07, "reference_active": true, "delta_db": -0.11594086037496695}], "active_band_count": 3, "active_band_mae_db": 0.07561675154576329}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 1.6710315888953048e-05, "log_rms_mae_db": 1.121604431934255, "rms_envelope_nrmse": 0.08623024471406512, "envelope_correlation": 0.993958223935697, "rms_gain_error_db": 0.09220608757978582, "reference_mean_power": 1.9183917331823965e-05, "output_mean_power": 1.9595570098826136e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.1409929070898633e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.5949700460751985e-06, "output_power": 5.497077733025259e-06, "reference_active": true, "delta_db": -0.07665887501360215}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1687645280234336e-06, "output_power": 1.2485876576903624e-06, "reference_active": true, "delta_db": 0.2869201530964551}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.657756100862398e-08, "output_power": 6.37688256231742e-08, "reference_active": true, "delta_db": -0.7949311095033985}], "active_band_count": 3, "active_band_mae_db": 0.3861700458711519}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 800, "rms_floor": 1.1530093504582296e-05, "log_rms_mae_db": 1.6472665468095051, "rms_envelope_nrmse": 0.164827857215106, "envelope_correlation": 0.9789092022007232, "rms_gain_error_db": -0.011060062631312395, "reference_mean_power": 5.108146850353514e-06, "output_mean_power": 5.095154618469041e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.254259363144466e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7396247028720546e-06, "output_power": 1.644991575145284e-06, "reference_active": true, "delta_db": -0.24291888024492378}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.118165550857846e-07, "output_power": 5.085871274849833e-07, "reference_active": true, "delta_db": -0.027489655190613145}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4689547511366827e-07, "output_power": 9.447143305501128e-08, "reference_active": true, "delta_db": -1.9170791492996373}], "active_band_count": 3, "active_band_mae_db": 0.7291625615783914}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 96120, "uncovered_tail_samples": 89, "metrics": {"frame_count": 794, "rms_floor": 9.091353933231884e-06, "log_rms_mae_db": 0.9659075389143381, "rms_envelope_nrmse": 0.08836303217198706, "envelope_correlation": 0.9933450755284406, "rms_gain_error_db": -0.01106106119660097, "reference_mean_power": 5.146742550240226e-06, "output_mean_power": 5.133650972388203e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.7984368001248054e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6090100968943592e-06, "output_power": 1.5183920975486092e-06, "reference_active": true, "delta_db": -0.2517483459227522}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.367924284305246e-07, "output_power": 2.302160127815139e-07, "reference_active": true, "delta_db": -0.12232283567086008}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2506680970493352e-08, "output_power": 6.877663523226045e-09, "reference_active": true, "delta_db": -2.5970114672436906}], "active_band_count": 3, "active_band_mae_db": 0.9903608829457676}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.6143036841712004, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "8b01dd68fdfb2b0c5f47611011ff9a6fe116d016ddf03aaa5363dd0d4dc51c22", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9785857489675531, "standard_deviation": 0.002301718787929814, "minimum": 0.9741293814440036, "maximum": 0.9815739024547292, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.7967446018045605, "standard_deviation": 0.04505725629364092, "minimum": 1.7285106027701738, "maximum": 1.8577143571924017, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.3229937469408185, "standard_deviation": 0.23944483559676824, "minimum": 0.07557866924092499, "maximum": 0.8306357444715277, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17017316946467473, "standard_deviation": 0.008450605537355563, "minimum": 0.15844932297038428, "maximum": 0.18445226044747748, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9936383387689043, "standard_deviation": 0.0010824538928085735, "minimum": 0.9923379102926272, "maximum": 0.9957053675421186, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.0739569547884056, "standard_deviation": 0.038000961244962383, "minimum": 1.0360416220150577, "maximum": 1.131748757597023, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.636446699043319, "standard_deviation": 0.2560973358263882, "minimum": 0.3268895526505864, "maximum": 1.1329236295393046, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08988073904664476, "standard_deviation": 0.008639038061447491, "minimum": 0.07430196251494947, "maximum": 0.10194422766905228, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9789242989650283, "standard_deviation": 0.001553994736549807, "minimum": 0.976818768076831, "maximum": 0.9813118455790559, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.6547940668597017, "standard_deviation": 0.029133878308523778, "minimum": 1.6023549603664993, "maximum": 1.6999948050887752, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.4556018921310361, "standard_deviation": 0.21841972725908376, "minimum": 0.18788107441059543, "maximum": 0.8194450531162971, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16611371916631268, "standard_deviation": 0.005158397217691422, "minimum": 0.15674518734391274, "maximum": 0.1729753352694187, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9940363521366591, "standard_deviation": 0.0008489004271431869, "minimum": 0.9930211661347678, "maximum": 0.9952035525903618, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9644452011089059, "standard_deviation": 0.02882838888952511, "minimum": 0.9233217896501936, "maximum": 0.9974049995973385, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6588080029475046, "standard_deviation": 0.2897745932943577, "minimum": 0.2628006281798858, "maximum": 1.0456227881226636, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08523707304839159, "standard_deviation": 0.0058660593351573635, "minimum": 0.07639151574521574, "maximum": 0.09200905212260084, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9589109403924132, "standard_deviation": 0.003461579081166735, "minimum": 0.9538008485948256, "maximum": 0.9646169322414948, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.4976446410378603, "standard_deviation": 0.05975833774059864, "minimum": 2.407766423112253, "maximum": 2.5699658201507223, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.42045521392842067, "standard_deviation": 0.24630534000052015, "minimum": 0.1537051499034423, "maximum": 0.7823124045960848, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.23829563827994188, "standard_deviation": 0.012456520840975996, "minimum": 0.21524674145722192, "maximum": 0.2513026249131755, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.983299342683918, "standard_deviation": 0.00228506080602752, "minimum": 0.9791518039090304, "maximum": 0.9871337839584375, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.7526877278344803, "standard_deviation": 0.0591882903855082, "minimum": 1.6445649013699244, "maximum": 1.8279482672531426, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5603558839380562, "standard_deviation": 0.2644759382062648, "minimum": 0.20322208332307046, "maximum": 0.8916152415311055, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.14598675570636835, "standard_deviation": 0.01131552927513053, "minimum": 0.12438517879675787, "maximum": 0.16064522563485367, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.37641092689152567, "standard_deviation": 0.08323059772647935, "minimum": 0.2652489269150608, "maximum": 0.48519267683074957, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.084190491880002, "standard_deviation": 0.010530093764770236, "minimum": 6.070524773768546, "maximum": 6.103835068836374, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.05701279123750615, "standard_deviation": 0.0037961189478152918, "minimum": 0.05142653918257302, "maximum": 0.06131893788843347, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": 0.006588508848474957, "standard_deviation": 0.08421706561347946, "minimum": -0.07596011847678454, "maximum": 0.17427832002027643, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9822932620165843, "standard_deviation": 0.0013583681973414398, "minimum": 0.9804893080895714, "maximum": 0.9839269941014649, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.6328033590696758, "standard_deviation": 0.028370754344240443, "minimum": 1.5920187106828347, "maximum": 1.6718943262290775, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.31590892133831405, "standard_deviation": 0.18288011678697508, "minimum": 0.05543058780266131, "maximum": 0.5594384091000654, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.13825772225726218, "standard_deviation": 0.004767980713267396, "minimum": 0.13191421243402376, "maximum": 0.14447242410514358, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9949437452302095, "standard_deviation": 0.0008429624943248825, "minimum": 0.9935858816275916, "maximum": 0.996288982027008, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8464348748435375, "standard_deviation": 0.03692771321195564, "minimum": 0.788884442411282, "maximum": 0.8993707310424461, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5679833660598936, "standard_deviation": 0.20320427005286784, "minimum": 0.15797244369625185, "maximum": 0.7532141444332948, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.06963757865568539, "standard_deviation": 0.006278019190127172, "minimum": 0.05930156594308592, "maximum": 0.07805910782339953, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs082_falset10_BASIC5000_1728", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs082", "source_utterance_id": "BASIC5000_1728", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 130065, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs082_falset10_BASIC5000_1728.wav", "source_file_sha256": "814e0d7ce300263f87677845a8de36c26e893df7df52f89458bca20434e530df", "decoded_pcm_sha256": "c7de35fa3bfe83887f9c61f8f38a56132da6836a3a6eae0bee50f16a0465b83f", "original_source_sha256": "814e0d7ce300263f87677845a8de36c26e893df7df52f89458bca20434e530df", "corpus_entry_id": "jvs_jvs082_falset10_BASIC5000_1728"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 2.992427349090576, "predicted_mos": 2.992427349090576, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 130065, "input_sample_rate": 24000, "input_seconds": 5.419375, "input_float32_sha256": "7683aee146ce216500350a2de9153eec42bbd55cfb2a83d978427b5b9ffa159d", "internal_samples": 86710, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.002360299695283}, "waveform_sha256": "9ba71ebe6783d43b71fdc62f44aa7451baff304a8860a3d16ae3f6f775573b00"}, "rows": [{"case": "jvs_jvs082_falset10_BASIC5000_1728", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 1.6691105365753174, "predicted_mos": 1.6691105365753174, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 130065, "input_sample_rate": 24000, "input_seconds": 5.419375, "input_float32_sha256": "bdca9b8087f0339f158ed611d112655c4fe106ac33cf84da3ce7825c826c54eb", "internal_samples": 86710, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 10.219379500020295}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.274883390161224, "全帯域_10ms_rms_envelope_nrmse": 0.05300869794327412, "全帯域_10ms_envelope_correlation": 0.9977129803276676, "全帯域_10ms_modulation_mae_db": 0.22669309080402977, "全帯域_40ms_log_rms_mae_db": 0.7023181666967478, "全帯域_40ms_rms_envelope_nrmse": 0.02839643519358763, "全帯域_40ms_envelope_correlation": 0.9994020226936221, "全帯域_40ms_modulation_mae_db": 0.488362440284523, "300–1000 Hz_10ms_log_rms_mae_db": 0.7627626877913232, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07143809238849926, "300–1000 Hz_10ms_envelope_correlation": 0.9960090240838531, "300–1000 Hz_10ms_modulation_mae_db": 0.3788856112581754, "300–1000 Hz_40ms_log_rms_mae_db": 0.5374293616790238, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04199188707797807, "300–1000 Hz_40ms_envelope_correlation": 0.9986240656182777, "300–1000 Hz_40ms_modulation_mae_db": 0.9421943369232654, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8019837953155559, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05924398720634113, "1000–3000 Hz_10ms_envelope_correlation": 0.9978488286082511, "1000–3000 Hz_10ms_modulation_mae_db": 0.6652936809875378, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5234844173311508, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03312000903594593, "1000–3000 Hz_40ms_envelope_correlation": 0.9993872579002265, "1000–3000 Hz_40ms_modulation_mae_db": 0.5784975033608233, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1079161343381863, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12871521232890742, "3000–6000 Hz_10ms_envelope_correlation": 0.9893595608915976, "3000–6000 Hz_10ms_modulation_mae_db": 0.5024341406974855, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7679531589521251, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06109325924214959, "3000–6000 Hz_40ms_envelope_correlation": 0.9976782961895735, "3000–6000 Hz_40ms_modulation_mae_db": 0.5879702119559104, "mr_stft_db": 5.410515843269717, "band_mae_db": 1.0009494041817866, "rms_gain_error_db": -0.10335498557354507, "output_peak": 0.21619555418188258}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2637285384295904, "全帯域_10ms_rms_envelope_nrmse": 0.06141800287538498, "全帯域_10ms_envelope_correlation": 0.996870719304692, "全帯域_10ms_modulation_mae_db": 0.6544525026957239, "全帯域_40ms_log_rms_mae_db": 0.7519415650540441, "全帯域_40ms_rms_envelope_nrmse": 0.03333369715538535, "全帯域_40ms_envelope_correlation": 0.9991038603675173, "全帯域_40ms_modulation_mae_db": 0.7954699991450389, "300–1000 Hz_10ms_log_rms_mae_db": 0.8015208616461227, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08061206579381781, "300–1000 Hz_10ms_envelope_correlation": 0.9948494041467084, "300–1000 Hz_10ms_modulation_mae_db": 0.5182386894194558, "300–1000 Hz_40ms_log_rms_mae_db": 0.5478114666996449, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04874236812526565, "300–1000 Hz_40ms_envelope_correlation": 0.9980415738828234, "300–1000 Hz_40ms_modulation_mae_db": 1.0407026814232696, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7974341123499596, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0618956082358186, "1000–3000 Hz_10ms_envelope_correlation": 0.997691643210373, "1000–3000 Hz_10ms_modulation_mae_db": 0.6891046277671812, "1000–3000 Hz_40ms_log_rms_mae_db": 0.48878768525273014, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.037439799768653144, "1000–3000 Hz_40ms_envelope_correlation": 0.9992360609260352, "1000–3000 Hz_40ms_modulation_mae_db": 0.7781169458423881, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1170490372772783, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11447606513567815, "3000–6000 Hz_10ms_envelope_correlation": 0.9917711778091314, "3000–6000 Hz_10ms_modulation_mae_db": 0.36627678433346217, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7773494322053423, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06639098541264132, "3000–6000 Hz_40ms_envelope_correlation": 0.9974140020284659, "3000–6000 Hz_40ms_modulation_mae_db": 0.6446503072263233, "mr_stft_db": 5.398753750158218, "band_mae_db": 1.2306233953748233, "rms_gain_error_db": -0.0939483030791685, "output_peak": 0.21119314319962076}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2571003818285549, "全帯域_10ms_rms_envelope_nrmse": 0.065214113022703, "全帯域_10ms_envelope_correlation": 0.996483241568699, "全帯域_10ms_modulation_mae_db": 0.4404959989110326, "全帯域_40ms_log_rms_mae_db": 0.7434569816872768, "全帯域_40ms_rms_envelope_nrmse": 0.03569806611179254, "全帯域_40ms_envelope_correlation": 0.9989863649671812, "全帯域_40ms_modulation_mae_db": 0.6013855918919214, "300–1000 Hz_10ms_log_rms_mae_db": 0.7819029717164909, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07211255087783255, "300–1000 Hz_10ms_envelope_correlation": 0.9959231057368239, "300–1000 Hz_10ms_modulation_mae_db": 0.45818704023138584, "300–1000 Hz_40ms_log_rms_mae_db": 0.5310248642568816, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.040609405931012366, "300–1000 Hz_40ms_envelope_correlation": 0.9986630067887227, "300–1000 Hz_40ms_modulation_mae_db": 0.8833986280993537, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8073615160740545, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06585138466354652, "1000–3000 Hz_10ms_envelope_correlation": 0.9973261893921669, "1000–3000 Hz_10ms_modulation_mae_db": 0.43028314685229746, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4793152385189842, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03900888557024124, "1000–3000 Hz_40ms_envelope_correlation": 0.9991164612063762, "1000–3000 Hz_40ms_modulation_mae_db": 0.7256262722026773, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1535612507017623, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13635140318163547, "3000–6000 Hz_10ms_envelope_correlation": 0.9902636893802476, "3000–6000 Hz_10ms_modulation_mae_db": 0.827149223815487, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7944964691474652, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10174725728575056, "3000–6000 Hz_40ms_envelope_correlation": 0.9957815132631004, "3000–6000 Hz_40ms_modulation_mae_db": 1.361508342800693, "mr_stft_db": 5.4012258164390765, "band_mae_db": 1.2224656316549738, "rms_gain_error_db": -0.10612896735519076, "output_peak": 0.2268518028268996}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.22918985942171, "全帯域_10ms_rms_envelope_nrmse": 0.07274402694343657, "全帯域_10ms_envelope_correlation": 0.995609564776062, "全帯域_10ms_modulation_mae_db": 0.4066871181811063, "全帯域_40ms_log_rms_mae_db": 0.7079195216888374, "全帯域_40ms_rms_envelope_nrmse": 0.03833727970899077, "全帯域_40ms_envelope_correlation": 0.9988366867855002, "全帯域_40ms_modulation_mae_db": 0.6907489970747772, "300–1000 Hz_10ms_log_rms_mae_db": 0.7943567850581916, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0775866077980884, "300–1000 Hz_10ms_envelope_correlation": 0.9952814292151776, "300–1000 Hz_10ms_modulation_mae_db": 0.24384857008122737, "300–1000 Hz_40ms_log_rms_mae_db": 0.5489628496890561, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043715162684594154, "300–1000 Hz_40ms_envelope_correlation": 0.9984544430945027, "300–1000 Hz_40ms_modulation_mae_db": 0.5789582979017485, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7718310826831132, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06474384053186402, "1000–3000 Hz_10ms_envelope_correlation": 0.9975324648929805, "1000–3000 Hz_10ms_modulation_mae_db": 0.5455736923792344, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5035599363913452, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03909571662708339, "1000–3000 Hz_40ms_envelope_correlation": 0.9992420418867914, "1000–3000 Hz_40ms_modulation_mae_db": 0.7775857397652004, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1148425274181186, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11759258793524388, "3000–6000 Hz_10ms_envelope_correlation": 0.9913575611104051, "3000–6000 Hz_10ms_modulation_mae_db": 0.9303582096731509, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7834766982139182, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.059234981764093524, "3000–6000 Hz_40ms_envelope_correlation": 0.9981092254516334, "3000–6000 Hz_40ms_modulation_mae_db": 0.4299559102228186, "mr_stft_db": 5.4041719628193645, "band_mae_db": 1.2601105725859774, "rms_gain_error_db": -0.11515782853337327, "output_peak": 0.21098262277196497}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2095175428119416, "全帯域_10ms_rms_envelope_nrmse": 0.05753113248445902, "全帯域_10ms_envelope_correlation": 0.9973043801837019, "全帯域_10ms_modulation_mae_db": 0.22066836264927306, "全帯域_40ms_log_rms_mae_db": 0.6663819794241138, "全帯域_40ms_rms_envelope_nrmse": 0.032800763173035236, "全帯域_40ms_envelope_correlation": 0.9991799551504459, "全帯域_40ms_modulation_mae_db": 0.15712505151200318, "300–1000 Hz_10ms_log_rms_mae_db": 0.8653320919826375, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06928700697924621, "300–1000 Hz_10ms_envelope_correlation": 0.9962209727552481, "300–1000 Hz_10ms_modulation_mae_db": 0.615963884821855, "300–1000 Hz_40ms_log_rms_mae_db": 0.6452887012071991, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0423265986535857, "300–1000 Hz_40ms_envelope_correlation": 0.9985330824353372, "300–1000 Hz_40ms_modulation_mae_db": 0.7208750332144427, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8022597635371254, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06596958756731797, "1000–3000 Hz_10ms_envelope_correlation": 0.9973122514868753, "1000–3000 Hz_10ms_modulation_mae_db": 0.7288760236889941, "1000–3000 Hz_40ms_log_rms_mae_db": 0.49509463049818914, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.037073090941206886, "1000–3000 Hz_40ms_envelope_correlation": 0.9992022417828419, "1000–3000 Hz_40ms_modulation_mae_db": 0.5269520498861858, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0997759477753786, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13607426975038434, "3000–6000 Hz_10ms_envelope_correlation": 0.9881830687467458, "3000–6000 Hz_10ms_modulation_mae_db": 1.4652544616121699, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7543580858948562, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06325147408744979, "3000–6000 Hz_40ms_envelope_correlation": 0.9976702609481044, "3000–6000 Hz_40ms_modulation_mae_db": 0.8958022229098569, "mr_stft_db": 5.403385851659529, "band_mae_db": 1.229066268151215, "rms_gain_error_db": -0.10869018309368589, "output_peak": 0.2303543124743544}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.207597105664091, "全帯域_10ms_rms_envelope_nrmse": 0.05732972238840409, "全帯域_10ms_envelope_correlation": 0.9972239958751159, "全帯域_10ms_modulation_mae_db": 0.5853370008977932, "全帯域_40ms_log_rms_mae_db": 0.624175896918615, "全帯域_40ms_rms_envelope_nrmse": 0.028601270652279298, "全帯域_40ms_envelope_correlation": 0.9992851890394239, "全帯域_40ms_modulation_mae_db": 0.7529555558266551, "300–1000 Hz_10ms_log_rms_mae_db": 0.753776781738257, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07755654675556584, "300–1000 Hz_10ms_envelope_correlation": 0.9952825910413013, "300–1000 Hz_10ms_modulation_mae_db": 0.7096924135325459, "300–1000 Hz_40ms_log_rms_mae_db": 0.49642330450320765, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04291387370188785, "300–1000 Hz_40ms_envelope_correlation": 0.9985053031872434, "300–1000 Hz_40ms_modulation_mae_db": 1.196141687382646, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7954396691805776, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06220107831945544, "1000–3000 Hz_10ms_envelope_correlation": 0.9975832217265527, "1000–3000 Hz_10ms_modulation_mae_db": 0.6312916741784421, "1000–3000 Hz_40ms_log_rms_mae_db": 0.49576752691496273, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03518519014931901, "1000–3000 Hz_40ms_envelope_correlation": 0.9992525979847426, "1000–3000 Hz_40ms_modulation_mae_db": 1.101346233150639, "3000–6000 Hz_10ms_log_rms_mae_db": 1.115005489307434, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13966112951657075, "3000–6000 Hz_10ms_envelope_correlation": 0.9874545931715759, "3000–6000 Hz_10ms_modulation_mae_db": 0.6897489085770387, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7652846868854182, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08946885252425296, "3000–6000 Hz_40ms_envelope_correlation": 0.9946979872791093, "3000–6000 Hz_40ms_modulation_mae_db": 0.45646225991646205, "mr_stft_db": 5.397882024585127, "band_mae_db": 1.0945818257427922, "rms_gain_error_db": -0.03391296496903806, "output_peak": 0.22605474662626543}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.265678613973446, "全帯域_10ms_rms_envelope_nrmse": 0.0742259678424729, "全帯域_10ms_envelope_correlation": 0.9954985677701392, "全帯域_10ms_modulation_mae_db": 0.06743252628580232, "全帯域_40ms_log_rms_mae_db": 0.6980033318902894, "全帯域_40ms_rms_envelope_nrmse": 0.05229140778914257, "全帯域_40ms_envelope_correlation": 0.9977801057986692, "全帯域_40ms_modulation_mae_db": 0.2628780000375764, "300–1000 Hz_10ms_log_rms_mae_db": 0.781556023306523, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0703511259391723, "300–1000 Hz_10ms_envelope_correlation": 0.9961237266111634, "300–1000 Hz_10ms_modulation_mae_db": 0.5236337660356846, "300–1000 Hz_40ms_log_rms_mae_db": 0.5459287561154839, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03872131248604702, "300–1000 Hz_40ms_envelope_correlation": 0.9987973724759514, "300–1000 Hz_40ms_modulation_mae_db": 0.4778507608120816, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7902761190387051, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.056172069087167875, "1000–3000 Hz_10ms_envelope_correlation": 0.9980910424060796, "1000–3000 Hz_10ms_modulation_mae_db": 0.3438613232526016, "1000–3000 Hz_40ms_log_rms_mae_db": 0.49234756794250123, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.033698695192179044, "1000–3000 Hz_40ms_envelope_correlation": 0.999377359826891, "1000–3000 Hz_40ms_modulation_mae_db": 0.6865145240812219, "3000–6000 Hz_10ms_log_rms_mae_db": 1.087756676545471, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12289080499184586, "3000–6000 Hz_10ms_envelope_correlation": 0.9908752307454067, "3000–6000 Hz_10ms_modulation_mae_db": 0.6585029869589136, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7257623589055426, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07532260681233387, "3000–6000 Hz_40ms_envelope_correlation": 0.9970680815035974, "3000–6000 Hz_40ms_modulation_mae_db": 0.33560398484632853, "mr_stft_db": 5.405067055448794, "band_mae_db": 1.260468097490215, "rms_gain_error_db": -0.1468121930113637, "output_peak": 0.2387609470572053}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2156728826448562, "全帯域_10ms_rms_envelope_nrmse": 0.06556812378813312, "全帯域_10ms_envelope_correlation": 0.9964540627446977, "全帯域_10ms_modulation_mae_db": 0.5673923295974697, "全帯域_40ms_log_rms_mae_db": 0.6597721356111336, "全帯域_40ms_rms_envelope_nrmse": 0.033201449445886405, "全帯域_40ms_envelope_correlation": 0.9991542814224896, "全帯域_40ms_modulation_mae_db": 0.7449175754969238, "300–1000 Hz_10ms_log_rms_mae_db": 0.8182501160236652, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06738259473991773, "300–1000 Hz_10ms_envelope_correlation": 0.9964000569898945, "300–1000 Hz_10ms_modulation_mae_db": 0.2204932880622731, "300–1000 Hz_40ms_log_rms_mae_db": 0.5388503277607443, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03691238994374765, "300–1000 Hz_40ms_envelope_correlation": 0.9988726819157779, "300–1000 Hz_40ms_modulation_mae_db": 0.7703913293630702, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7758516440916006, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.058176793210611824, "1000–3000 Hz_10ms_envelope_correlation": 0.998083704222405, "1000–3000 Hz_10ms_modulation_mae_db": 0.5848164561904351, "1000–3000 Hz_40ms_log_rms_mae_db": 0.48874539461828853, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.036615880422405815, "1000–3000 Hz_40ms_envelope_correlation": 0.9993909949197495, "1000–3000 Hz_40ms_modulation_mae_db": 0.7141929748933302, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1095802437859954, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12291248952163387, "3000–6000 Hz_10ms_envelope_correlation": 0.9910397181553693, "3000–6000 Hz_10ms_modulation_mae_db": 0.46152942622592524, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7594523014497865, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07277785378281748, "3000–6000 Hz_40ms_envelope_correlation": 0.9975332608256496, "3000–6000 Hz_40ms_modulation_mae_db": 0.7780755542600044, "mr_stft_db": 5.403647866419607, "band_mae_db": 1.3054892273066092, "rms_gain_error_db": -0.1100365521093635, "output_peak": 0.2260540723727542}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 130065, "output_samples": 130065, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.547973902984725, "spectral_convergence": 0.16244842982069893, "spectral_convergence_status": "ok", "amplitude_floor": 8.628776010687778e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.470656842709375, "spectral_convergence": 0.1774542990637728, "spectral_convergence_status": "ok", "amplitude_floor": 8.696913128358987e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.212916784115051, "spectral_convergence": 0.1737463211319541, "spectral_convergence_status": "ok", "amplitude_floor": 6.997748100750841e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.5012142154628568e-06, "output_power": 6.263820716588639e-06, "delta_db": 6.2039665059828275, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008569985031977355, "output_power": 0.000827127512985219, "delta_db": -0.1540759627047445, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0002039561579698118, "output_power": 0.000207074894468186, "delta_db": 0.06590626363750493, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00031755380447674584, "output_power": 0.00030961691393990094, "delta_db": -0.10992642642948523, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 8.391217397004902e-05, "output_power": 7.973124152188622e-05, "delta_db": -0.2219644610999278, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2641952404694477e-05, "output_power": 1.1964817179188716e-05, "delta_db": -0.23908083894245427, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.274471551779886e-06, "output_power": 2.280620618026805e-06, "delta_db": 0.011725370475561759, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.0009494041817866, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.10335498557354507, "pitch": null, "output_rms_dbfs": -28.40414815368609, "output_peak": 0.21619555418188258, "reference_rms_dbfs": -28.300793168112545, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.410515843269717}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 130065, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 0.0001318526099400404, "log_rms_mae_db": 1.274883390161224, "rms_envelope_nrmse": 0.05300869794327412, "envelope_correlation": 0.9977129803276676, "rms_gain_error_db": -0.1033550975947349, "reference_mean_power": 0.0014814008893508253, "output_mean_power": 0.0014465621296765566}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 7.673423983742615e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002922132888675935, "output_power": 0.0002838632089367211, "reference_active": true, "delta_db": -0.12590854335220436}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.0438146457063534e-05, "output_power": 3.0021597235435395e-05, "reference_active": true, "delta_db": -0.05984408130804261}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.705913608511969e-06, "output_power": 5.092048448060104e-06, "reference_active": true, "delta_db": -0.4943266477518424}], "active_band_count": 3, "active_band_mae_db": 0.22669309080402977}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 0.00011771272815729935, "log_rms_mae_db": 0.7023181666967478, "rms_envelope_nrmse": 0.02839643519358763, "envelope_correlation": 0.9994020226936221, "rms_gain_error_db": -0.10335526700760307, "reference_mean_power": 0.001489661173505724, "output_mean_power": 0.0014546280963337029}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 7.348414354743223e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000259482167884596, "output_power": 0.0002528305083123487, "reference_active": true, "delta_db": -0.11278039847271301}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3907004138768798e-05, "output_power": 1.3500096171287257e-05, "reference_active": true, "delta_db": -0.12896721590006133}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.4011744172060643e-07, "output_power": 3.3207379792359805e-07, "reference_active": true, "delta_db": -1.2233397064807947}], "active_band_count": 3, "active_band_mae_db": 0.488362440284523}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 8.480086855572389e-05, "log_rms_mae_db": 0.7627626877913232, "rms_envelope_nrmse": 0.07143809238849926, "envelope_correlation": 0.9960090240838531, "rms_gain_error_db": -0.07531659055903686, "reference_mean_power": 0.0005471873658289661, "output_mean_power": 0.0005377796971299042}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 3.0613556922446793e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0001155073862142863, "output_power": 0.00011135645973591082, "reference_active": true, "delta_db": -0.1589434111233069}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3854221447460866e-05, "output_power": 1.1829726650346905e-05, "reference_active": true, "delta_db": -0.6860741567356604}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9357817767829245e-06, "output_power": 1.8100579136804908e-06, "reference_active": true, "delta_db": -0.29163926591555894}], "active_band_count": 3, "active_band_mae_db": 0.3788856112581754}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.44475219971024e-05, "log_rms_mae_db": 0.5374293616790238, "rms_envelope_nrmse": 0.04199188707797807, "envelope_correlation": 0.9986240656182777, "rms_gain_error_db": -0.075316682362581, "reference_mean_power": 0.0005502385876291546, "output_mean_power": 0.0005407784485320838}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.936750998626233e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.910211940271478e-05, "output_power": 9.587066926989989e-05, "reference_active": true, "delta_db": -0.1439718325041119}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.231208448817648e-06, "output_power": 5.38784859939785e-06, "reference_active": true, "delta_db": -0.6315689630462011}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.518968227553501e-07, "output_power": 1.570791230976499e-07, "reference_active": true, "delta_db": -2.051042215219483}], "active_band_count": 3, "active_band_mae_db": 0.9421943369232654}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 7.92844222433349e-05, "log_rms_mae_db": 0.8019837953155559, "rms_envelope_nrmse": 0.05924398720634113, "envelope_correlation": 0.9978488286082511, "rms_gain_error_db": -0.11619595643298562, "reference_mean_power": 0.0003517587960046477, "output_mean_power": 0.00034247223693631017}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 1.184446345593241e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.4086641780542994e-05, "output_power": 3.20904621180351e-05, "reference_active": true, "delta_db": -0.26208245410140324}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.908924984845658e-06, "output_power": 7.685636039781084e-06, "reference_active": true, "delta_db": -0.6414548788456058}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.00669572393549e-07, "output_power": 4.6709074458589844e-07, "reference_active": true, "delta_db": -1.0923437100156044}], "active_band_count": 3, "active_band_mae_db": 0.6652936809875378}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.287723098191666e-05, "log_rms_mae_db": 0.5234844173311508, "rms_envelope_nrmse": 0.03312000903594593, "envelope_correlation": 0.9993872579002265, "rms_gain_error_db": -0.1161959721232278, "reference_mean_power": 0.0003537202709185465, "output_mean_power": 0.0003443819269609336}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 1.1592322619199725e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.0388893978542697e-05, "output_power": 2.8653104646306325e-05, "reference_active": true, "delta_db": -0.25543208058214795}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.277692934034562e-06, "output_power": 3.6468715152653596e-06, "reference_active": true, "delta_db": -0.6928914362016342}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.6389202390485585e-08, "output_power": 4.704127153870035e-08, "reference_active": true, "delta_db": -0.7871689932986876}], "active_band_count": 3, "active_band_mae_db": 0.5784975033608233}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 3.178621250284737e-05, "log_rms_mae_db": 1.1079161343381863, "rms_envelope_nrmse": 0.12871521232890742, "envelope_correlation": 0.9893595608915976, "rms_gain_error_db": -0.15356994191196888, "reference_mean_power": 4.4150646761510114e-05, "output_mean_power": 4.2616725356699855e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 2.2237128168975068e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.193805277966022e-06, "output_power": 8.357589118349174e-06, "reference_active": true, "delta_db": -0.4141428504215138}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0890347422283183e-06, "output_power": 1.0777195553638809e-06, "reference_active": true, "delta_db": -0.04535971516894571}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8576888047519497e-07, "output_power": 2.3645742154778738e-07, "reference_active": true, "delta_db": 1.047799856501997}], "active_band_count": 3, "active_band_mae_db": 0.5024341406974855}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 2.883918900864625e-05, "log_rms_mae_db": 0.7679531589521251, "rms_envelope_nrmse": 0.06109325924214959, "envelope_correlation": 0.9976782961895735, "rms_gain_error_db": -0.15356995601580395, "reference_mean_power": 4.439683700027618e-05, "output_mean_power": 4.2854362094009494e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.1738925168287815e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.247468496821311e-06, "output_power": 7.55623735622666e-06, "reference_active": true, "delta_db": -0.38015073823876727}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.957219370502507e-07, "output_power": 4.4011575527376847e-07, "reference_active": true, "delta_db": -0.5167122232299856}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6536836687109635e-08, "output_power": 1.3544022607449714e-08, "reference_active": true, "delta_db": -0.8670476743989783}], "active_band_count": 3, "active_band_mae_db": 0.5879702119559104}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.875316026690208, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "69850c55e63a6ffa5e4dd97ec6d3c4ed216aec7259b5445204fc5f47ef9ba426", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9976836682432105, "standard_deviation": 0.00030519725030695046, "minimum": 0.9973122514868753, "maximum": 0.9980910424060796, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.7928047127838365, "standard_deviation": 0.012804139299854717, "minimum": 0.7718310826831132, "maximum": 0.8073615160740545, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5773875781620905, "standard_deviation": 0.13272103923122572, "minimum": 0.3438613232526016, "maximum": 0.7288760236889941, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06178179360276542, "standard_deviation": 0.003663861417765167, "minimum": 0.056172069087167875, "maximum": 0.06596958756731797, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9992756270542068, "standard_deviation": 0.00010004548422671017, "minimum": 0.9991164612063762, "maximum": 0.9993909949197495, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.49588779968351904, "standard_deviation": 0.013145815029490526, "minimum": 0.4793152385189842, "maximum": 0.5234844173311508, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7361040303978083, "standard_deviation": 0.17259409407681148, "minimum": 0.5269520498861858, "maximum": 1.101346233150639, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.036404658463379314, "standard_deviation": 0.002241969451016765, "minimum": 0.03312000903594593, "maximum": 0.03909571662708339, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9900380750013099, "standard_deviation": 0.001561844948250167, "minimum": 0.9874545931715759, "maximum": 0.9917711778091314, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.113185913393703, "standard_deviation": 0.018967609626462732, "minimum": 1.087756676545471, "maximum": 1.1535612507017623, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7376567677367041, "standard_deviation": 0.348998714407499, "minimum": 0.36627678433346217, "maximum": 1.4652544616121699, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12733424529523746, "standard_deviation": 0.009343332835812752, "minimum": 0.11447606513567815, "maximum": 0.13966112951657075, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9969940784361542, "standard_deviation": 0.0011578186643468422, "minimum": 0.9946979872791093, "maximum": 0.9981092254516334, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7660166489568068, "standard_deviation": 0.020867239916539382, "minimum": 0.7257623589055426, "maximum": 0.7944964691474652, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6862535992672996, "standard_deviation": 0.32975078057469354, "minimum": 0.33560398484632853, "maximum": 1.361508342800693, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07366090886393614, "standard_deviation": 0.014973960187352298, "minimum": 0.059234981764093524, "maximum": 0.10174725728575056, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9957612888225214, "standard_deviation": 0.0005515177997698986, "minimum": 0.9948494041467084, "maximum": 0.9964000569898945, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.7949322899079014, "standard_deviation": 0.03509363072873467, "minimum": 0.753776781738257, "maximum": 0.8653320919826375, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.45861790793032536, "standard_deviation": 0.171032365794537, "minimum": 0.2204932880622731, "maximum": 0.7096924135325459, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.0732908239090175, "standard_deviation": 0.004700322494402397, "minimum": 0.06738259473991773, "maximum": 0.08061206579381781, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9985614411748295, "standard_deviation": 0.0002542321927364286, "minimum": 0.9980415738828234, "maximum": 0.9988726819157779, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5489649539889051, "standard_deviation": 0.0424376191216524, "minimum": 0.49642330450320765, "maximum": 0.6452887012071991, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8263140943899847, "standard_deviation": 0.23793100007044415, "minimum": 0.4778507608120816, "maximum": 1.196141687382646, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04199162482551481, "standard_deviation": 0.0035438068157039003, "minimum": 0.03691238994374765, "maximum": 0.04874236812526565, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.2004693028110491, "standard_deviation": 0.10100732853249866, "minimum": 1.0009494041817866, "maximum": 1.3054892273066092, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.403081271349929, "standard_deviation": 0.003964519870939243, "minimum": 5.397882024585127, "maximum": 5.410515843269717, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.2233059001888684, "standard_deviation": 0.009749429950876538, "minimum": 0.21098262277196497, "maximum": 0.2387609470572053, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.1022552472155911, "standard_deviation": 0.031644550703632764, "minimum": -0.1468121930113637, "maximum": -0.03391296496903806, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.996644689068847, "standard_deviation": 0.0007937798046260023, "minimum": 0.9954985677701392, "maximum": 0.9977129803276676, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.2404210393669266, "standard_deviation": 0.027821076445066296, "minimum": 1.207597105664091, "maximum": 1.274883390161224, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.39614486625277884, "standard_deviation": 0.2075290219181986, "minimum": 0.06743252628580232, "maximum": 0.6544525026957239, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.06337997341103348, "standard_deviation": 0.0075185515776883755, "minimum": 0.05300869794327412, "maximum": 0.0742259678424729, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9989660582781061, "standard_deviation": 0.0005093008208098113, "minimum": 0.9977801057986692, "maximum": 0.9994020226936221, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6942461973713823, "standard_deviation": 0.04291421987623274, "minimum": 0.624175896918615, "maximum": 0.7519415650540441, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5617304014086775, "standard_deviation": 0.23945719475283714, "minimum": 0.15712505151200318, "maximum": 0.7954699991450389, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.035332546153762474, "standard_deviation": 0.007607624157312365, "minimum": 0.02839643519358763, "maximum": 0.05229140778914257, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_falset10_BASIC5000_1728", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 1.6658000946044922, "predicted_mos": 1.6658000946044922, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 130065, "input_sample_rate": 24000, "input_seconds": 5.419375, "input_float32_sha256": "bdd4b992dba01bc520cb2727dc388a1607c415246baf6a482ca5a11f37022d90", "internal_samples": 86710, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.948229799978435}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.277795578402249, "全帯域_10ms_rms_envelope_nrmse": 0.056069841388451454, "全帯域_10ms_envelope_correlation": 0.9974119025575953, "全帯域_10ms_modulation_mae_db": 0.1299970392179207, "全帯域_40ms_log_rms_mae_db": 0.6988364587160848, "全帯域_40ms_rms_envelope_nrmse": 0.029882220248875106, "全帯域_40ms_envelope_correlation": 0.9993066071318064, "全帯域_40ms_modulation_mae_db": 0.42946618726096414, "300–1000 Hz_10ms_log_rms_mae_db": 0.7932646385346134, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0736861514520258, "300–1000 Hz_10ms_envelope_correlation": 0.9957400190562525, "300–1000 Hz_10ms_modulation_mae_db": 0.2918056143871585, "300–1000 Hz_40ms_log_rms_mae_db": 0.550026389124623, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0432415904028723, "300–1000 Hz_40ms_envelope_correlation": 0.9985256142210024, "300–1000 Hz_40ms_modulation_mae_db": 0.892202818378634, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7945539644758771, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0591419630733353, "1000–3000 Hz_10ms_envelope_correlation": 0.9978433938589544, "1000–3000 Hz_10ms_modulation_mae_db": 0.6657771322064397, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5088215943939841, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03251465556066665, "1000–3000 Hz_40ms_envelope_correlation": 0.9993991225401254, "1000–3000 Hz_40ms_modulation_mae_db": 0.5792875165740269, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1244944272571145, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12925311959460584, "3000–6000 Hz_10ms_envelope_correlation": 0.9893062830648655, "3000–6000 Hz_10ms_modulation_mae_db": 0.5349411151517813, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7720254869318891, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06147931567070651, "3000–6000 Hz_40ms_envelope_correlation": 0.9977050770853085, "3000–6000 Hz_40ms_modulation_mae_db": 0.5424768092707056, "mr_stft_db": 5.366189681341438, "band_mae_db": 1.0430344775759424, "rms_gain_error_db": -0.096261379230511, "output_peak": 0.21497888012182256}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.292416286502776, "全帯域_10ms_rms_envelope_nrmse": 0.06165016842321083, "全帯域_10ms_envelope_correlation": 0.9968416528117819, "全帯域_10ms_modulation_mae_db": 0.5448479248328536, "全帯域_40ms_log_rms_mae_db": 0.7956985011777675, "全帯域_40ms_rms_envelope_nrmse": 0.03357058021035576, "全帯域_40ms_envelope_correlation": 0.9990842996624906, "全帯域_40ms_modulation_mae_db": 0.6480835182153482, "300–1000 Hz_10ms_log_rms_mae_db": 0.7874876702158276, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08168166800697539, "300–1000 Hz_10ms_envelope_correlation": 0.99471252391935, "300–1000 Hz_10ms_modulation_mae_db": 0.4363673153217437, "300–1000 Hz_40ms_log_rms_mae_db": 0.5388424255842386, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.049911713592816584, "300–1000 Hz_40ms_envelope_correlation": 0.997946876546508, "300–1000 Hz_40ms_modulation_mae_db": 0.9333961339753906, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7904462824633579, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06144392823193632, "1000–3000 Hz_10ms_envelope_correlation": 0.9976947879283604, "1000–3000 Hz_10ms_modulation_mae_db": 0.7036629364510579, "1000–3000 Hz_40ms_log_rms_mae_db": 0.49757212251939203, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03699390182306878, "1000–3000 Hz_40ms_envelope_correlation": 0.9992221650967087, "1000–3000 Hz_40ms_modulation_mae_db": 0.794660986980661, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1324042473921407, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1151028627634934, "3000–6000 Hz_10ms_envelope_correlation": 0.9917725745745863, "3000–6000 Hz_10ms_modulation_mae_db": 0.32141296297422506, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8010085645647863, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0680432315533063, "3000–6000 Hz_40ms_envelope_correlation": 0.997381827171045, "3000–6000 Hz_40ms_modulation_mae_db": 0.6511348403867028, "mr_stft_db": 5.3678013830192866, "band_mae_db": 1.2498351342172902, "rms_gain_error_db": -0.09153743330449712, "output_peak": 0.2098861870894979}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.25558166365459, "全帯域_10ms_rms_envelope_nrmse": 0.06646559277661718, "全帯域_10ms_envelope_correlation": 0.9963416379407513, "全帯域_10ms_modulation_mae_db": 0.47595418242005394, "全帯域_40ms_log_rms_mae_db": 0.7419922376110291, "全帯域_40ms_rms_envelope_nrmse": 0.036098342713008824, "全帯域_40ms_envelope_correlation": 0.9989603499222067, "全帯域_40ms_modulation_mae_db": 0.6208674832976321, "300–1000 Hz_10ms_log_rms_mae_db": 0.7675899468496233, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07289159899761719, "300–1000 Hz_10ms_envelope_correlation": 0.9958254043371285, "300–1000 Hz_10ms_modulation_mae_db": 0.4681492859883188, "300–1000 Hz_40ms_log_rms_mae_db": 0.5206355918358299, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.041409121831285076, "300–1000 Hz_40ms_envelope_correlation": 0.9986022530833297, "300–1000 Hz_40ms_modulation_mae_db": 0.9072598133595245, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8109694481195674, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06666995095652223, "1000–3000 Hz_10ms_envelope_correlation": 0.997245180253323, "1000–3000 Hz_10ms_modulation_mae_db": 0.4126885525485708, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4823419630864081, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03975343939670977, "1000–3000 Hz_40ms_envelope_correlation": 0.999065890234732, "1000–3000 Hz_40ms_modulation_mae_db": 0.7739372822311686, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1529617396010354, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13397487800908936, "3000–6000 Hz_10ms_envelope_correlation": 0.9907508412073397, "3000–6000 Hz_10ms_modulation_mae_db": 0.8175067819264812, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7951697573686068, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09970855805462804, "3000–6000 Hz_40ms_envelope_correlation": 0.9961264721166037, "3000–6000 Hz_40ms_modulation_mae_db": 1.3747726630899642, "mr_stft_db": 5.362833672120043, "band_mae_db": 1.2552442769321384, "rms_gain_error_db": -0.1062487122128057, "output_peak": 0.22884929416957553}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2241950207452572, "全帯域_10ms_rms_envelope_nrmse": 0.07442868310193854, "全帯域_10ms_envelope_correlation": 0.9953948378022509, "全帯域_10ms_modulation_mae_db": 0.4051039133330654, "全帯域_40ms_log_rms_mae_db": 0.6822011558586095, "全帯域_40ms_rms_envelope_nrmse": 0.03921072065618444, "全帯域_40ms_envelope_correlation": 0.9987740849569364, "全帯域_40ms_modulation_mae_db": 0.6989738844260218, "300–1000 Hz_10ms_log_rms_mae_db": 0.7865815894499767, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07812103474250348, "300–1000 Hz_10ms_envelope_correlation": 0.9952222498625931, "300–1000 Hz_10ms_modulation_mae_db": 0.24987950400635564, "300–1000 Hz_40ms_log_rms_mae_db": 0.5476773723517326, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.044180710176084693, "300–1000 Hz_40ms_envelope_correlation": 0.9984259855798866, "300–1000 Hz_40ms_modulation_mae_db": 0.5974959082586189, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7855749879436076, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06661214948259365, "1000–3000 Hz_10ms_envelope_correlation": 0.9973729109346179, "1000–3000 Hz_10ms_modulation_mae_db": 0.5473510589440046, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5207838537705985, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04005736607886341, "1000–3000 Hz_40ms_envelope_correlation": 0.9991911653039866, "1000–3000 Hz_40ms_modulation_mae_db": 0.8366029251251428, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1500299733494366, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.118290513137801, "3000–6000 Hz_10ms_envelope_correlation": 0.9913036371551661, "3000–6000 Hz_10ms_modulation_mae_db": 0.9627161036293281, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7939943915254234, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.059919783737148846, "3000–6000 Hz_40ms_envelope_correlation": 0.9981218330257855, "3000–6000 Hz_40ms_modulation_mae_db": 0.4311709756857664, "mr_stft_db": 5.374389271364418, "band_mae_db": 1.260172854895467, "rms_gain_error_db": -0.11446592709080149, "output_peak": 0.21170017254612072}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2383553319921266, "全帯域_10ms_rms_envelope_nrmse": 0.05777149991342903, "全帯域_10ms_envelope_correlation": 0.9972895056717986, "全帯域_10ms_modulation_mae_db": 0.24656845328959123, "全帯域_40ms_log_rms_mae_db": 0.6801033094180203, "全帯域_40ms_rms_envelope_nrmse": 0.033004282054768914, "全帯域_40ms_envelope_correlation": 0.9991775157956969, "全帯域_40ms_modulation_mae_db": 0.1809063631598741, "300–1000 Hz_10ms_log_rms_mae_db": 0.8514611196684778, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06768779503981341, "300–1000 Hz_10ms_envelope_correlation": 0.9963986376193313, "300–1000 Hz_10ms_modulation_mae_db": 0.7067142037614801, "300–1000 Hz_40ms_log_rms_mae_db": 0.6412514474487253, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04114211136791189, "300–1000 Hz_40ms_envelope_correlation": 0.9986177228811393, "300–1000 Hz_40ms_modulation_mae_db": 0.8659221021918206, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8121705387508584, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06647337460714424, "1000–3000 Hz_10ms_envelope_correlation": 0.9972686474537324, "1000–3000 Hz_10ms_modulation_mae_db": 0.7697423955015094, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5116501851939507, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0379517524551653, "1000–3000 Hz_40ms_envelope_correlation": 0.9991600799346245, "1000–3000 Hz_40ms_modulation_mae_db": 0.5560486546780575, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1141153620908637, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.136663737722961, "3000–6000 Hz_10ms_envelope_correlation": 0.9881785607216667, "3000–6000 Hz_10ms_modulation_mae_db": 1.4052969388267276, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7630189444572063, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06585941020421518, "3000–6000 Hz_40ms_envelope_correlation": 0.9975872192286638, "3000–6000 Hz_40ms_modulation_mae_db": 0.8349432872445529, "mr_stft_db": 5.366535683262711, "band_mae_db": 1.2571496293815698, "rms_gain_error_db": -0.11198057372106018, "output_peak": 0.22738280499997762}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.225294375424933, "全帯域_10ms_rms_envelope_nrmse": 0.058425755557524356, "全帯域_10ms_envelope_correlation": 0.9971195290795433, "全帯域_10ms_modulation_mae_db": 0.5007262748494233, "全帯域_40ms_log_rms_mae_db": 0.6314646885575976, "全帯域_40ms_rms_envelope_nrmse": 0.028905820264806883, "全帯域_40ms_envelope_correlation": 0.999276213764513, "全帯域_40ms_modulation_mae_db": 0.6619178455272535, "300–1000 Hz_10ms_log_rms_mae_db": 0.7759281753483961, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07854888562839785, "300–1000 Hz_10ms_envelope_correlation": 0.9951604582010103, "300–1000 Hz_10ms_modulation_mae_db": 0.7539804001474693, "300–1000 Hz_40ms_log_rms_mae_db": 0.5210219559344547, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04332617756769396, "300–1000 Hz_40ms_envelope_correlation": 0.998475480937811, "300–1000 Hz_40ms_modulation_mae_db": 1.2021789888648662, "1000–3000 Hz_10ms_log_rms_mae_db": 0.793658048398071, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.062721459156068, "1000–3000 Hz_10ms_envelope_correlation": 0.9975678068362013, "1000–3000 Hz_10ms_modulation_mae_db": 0.6694321301457248, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4933421203061267, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03633937731881418, "1000–3000 Hz_40ms_envelope_correlation": 0.9992287189521695, "1000–3000 Hz_40ms_modulation_mae_db": 1.1534897180393147, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1273554877074967, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13915936569764076, "3000–6000 Hz_10ms_envelope_correlation": 0.9875760931127808, "3000–6000 Hz_10ms_modulation_mae_db": 0.6065575377837623, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7789682376482893, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0902727779746204, "3000–6000 Hz_40ms_envelope_correlation": 0.9946337799737422, "3000–6000 Hz_40ms_modulation_mae_db": 0.4544934020775198, "mr_stft_db": 5.361721526667476, "band_mae_db": 1.1285514175164113, "rms_gain_error_db": -0.042000962737148366, "output_peak": 0.23049202889595552}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.283014488109624, "全帯域_10ms_rms_envelope_nrmse": 0.07538015533101454, "全帯域_10ms_envelope_correlation": 0.9953509250401716, "全帯域_10ms_modulation_mae_db": 0.08517719777001224, "全帯域_40ms_log_rms_mae_db": 0.6974582232185917, "全帯域_40ms_rms_envelope_nrmse": 0.052785560591302544, "全帯域_40ms_envelope_correlation": 0.9977353015192042, "全帯域_40ms_modulation_mae_db": 0.2600675263856309, "300–1000 Hz_10ms_log_rms_mae_db": 0.7574160742415933, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0717287044072837, "300–1000 Hz_10ms_envelope_correlation": 0.9959668657030546, "300–1000 Hz_10ms_modulation_mae_db": 0.5223217051046805, "300–1000 Hz_40ms_log_rms_mae_db": 0.5368928598967962, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03966416111574991, "300–1000 Hz_40ms_envelope_correlation": 0.998735478411391, "300–1000 Hz_40ms_modulation_mae_db": 0.5465881413289124, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7911546246977551, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05581611509553891, "1000–3000 Hz_10ms_envelope_correlation": 0.9981127269710219, "1000–3000 Hz_10ms_modulation_mae_db": 0.3227283885634978, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4814657874943565, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03294454074503807, "1000–3000 Hz_40ms_envelope_correlation": 0.9994068988633735, "1000–3000 Hz_40ms_modulation_mae_db": 0.6057466619817046, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1054074211090885, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12501856362987004, "3000–6000 Hz_10ms_envelope_correlation": 0.9906037452286479, "3000–6000 Hz_10ms_modulation_mae_db": 0.7294802022418277, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7378060968089123, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07806457111981133, "3000–6000 Hz_40ms_envelope_correlation": 0.996875925637757, "3000–6000 Hz_40ms_modulation_mae_db": 0.36792142495184393, "mr_stft_db": 5.36792281649214, "band_mae_db": 1.2817234793889103, "rms_gain_error_db": -0.14794648396875126, "output_peak": 0.24517949904811537}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2283683793723215, "全帯域_10ms_rms_envelope_nrmse": 0.06680148628102692, "全帯域_10ms_envelope_correlation": 0.9963105291962676, "全帯域_10ms_modulation_mae_db": 0.5812633383175011, "全帯域_40ms_log_rms_mae_db": 0.665747219897534, "全帯域_40ms_rms_envelope_nrmse": 0.03374079549446099, "全帯域_40ms_envelope_correlation": 0.9991179708789029, "全帯域_40ms_modulation_mae_db": 0.774272526625572, "300–1000 Hz_10ms_log_rms_mae_db": 0.8155118670180563, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07041188796584928, "300–1000 Hz_10ms_envelope_correlation": 0.9960692064826511, "300–1000 Hz_10ms_modulation_mae_db": 0.244851851844998, "300–1000 Hz_40ms_log_rms_mae_db": 0.5342923373871235, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03896849216707552, "300–1000 Hz_40ms_envelope_correlation": 0.9987423556754091, "300–1000 Hz_40ms_modulation_mae_db": 0.878953130674391, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7844558157887173, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05890444570576274, "1000–3000 Hz_10ms_envelope_correlation": 0.9980223739827654, "1000–3000 Hz_10ms_modulation_mae_db": 0.6130542642286018, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4863766060008777, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03719430007725473, "1000–3000 Hz_40ms_envelope_correlation": 0.9993569594448221, "1000–3000 Hz_40ms_modulation_mae_db": 0.7142455479666777, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1316021936501592, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1253195058614708, "3000–6000 Hz_10ms_envelope_correlation": 0.9908636031663773, "3000–6000 Hz_10ms_modulation_mae_db": 0.44552978343486555, "3000–6000 Hz_40ms_log_rms_mae_db": 0.790406592543466, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07631848171334604, "3000–6000 Hz_40ms_envelope_correlation": 0.9974337328056201, "3000–6000 Hz_40ms_modulation_mae_db": 0.8233863327629708, "mr_stft_db": 5.365535077338123, "band_mae_db": 1.35101923393818, "rms_gain_error_db": -0.10905889789922109, "output_peak": 0.2228245091120334}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 130065, "output_samples": 130065, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.525977879282374, "spectral_convergence": 0.16345603405228595, "spectral_convergence_status": "ok", "amplitude_floor": 8.628776010687778e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.43418199724491, "spectral_convergence": 0.17796471793283247, "spectral_convergence_status": "ok", "amplitude_floor": 8.696913128358987e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.138409167497026, "spectral_convergence": 0.173922300814317, "spectral_convergence_status": "ok", "amplitude_floor": 6.997748100750841e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.5012142154628568e-06, "output_power": 6.36977893916315e-06, "delta_db": 6.276816923368931, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008569985031977355, "output_power": 0.0008289444362970089, "delta_db": -0.1445464240238128, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0002039561579698118, "output_power": 0.0002071897284640813, "delta_db": 0.06831398900283318, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00031755380447674584, "output_power": 0.0003102548099943686, "delta_db": -0.10098796953333199, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 8.391217397004902e-05, "output_power": 7.965269587836493e-05, "delta_db": -0.22624493539071425, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2641952404694477e-05, "output_power": 1.1835986610931458e-05, "delta_db": -0.28609685725019485, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.274471551779886e-06, "output_power": 2.172986782968734e-06, "delta_db": -0.1982342444617793, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.0430344775759424, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.096261379230511, "pitch": null, "output_rms_dbfs": -28.397054547343057, "output_peak": 0.21497888012182256, "reference_rms_dbfs": -28.300793168112545, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.366189681341438}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 130065, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 0.0001318526099400404, "log_rms_mae_db": 1.277795578402249, "rms_envelope_nrmse": 0.056069841388451454, "envelope_correlation": 0.9974119025575953, "rms_gain_error_db": -0.09626153567518488, "reference_mean_power": 0.0014814008893508253, "output_mean_power": 0.001448926806911545}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 7.673423983742615e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002922132888675935, "output_power": 0.0002848205320945103, "reference_active": true, "delta_db": -0.11128668844193225}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.0438146457063534e-05, "output_power": 3.008469996065297e-05, "reference_active": true, "delta_db": -0.05072517806427378}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.705913608511969e-06, "output_power": 5.414112387685884e-06, "reference_active": true, "delta_db": -0.22797925114755607}], "active_band_count": 3, "active_band_mae_db": 0.1299970392179207}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 0.00011771272815729935, "log_rms_mae_db": 0.6988364587160848, "rms_envelope_nrmse": 0.029882220248875106, "envelope_correlation": 0.9993066071318064, "rms_gain_error_db": -0.09626172687844063, "reference_mean_power": 0.001489661173505724, "output_mean_power": 0.0014570059515942825}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 7.348414354743223e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000259482167884596, "output_power": 0.0002536761156901729, "reference_active": true, "delta_db": -0.09827938538283605}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3907004138768798e-05, "output_power": 1.3503045370143163e-05, "reference_active": true, "delta_db": -0.12801857013432125}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.4011744172060643e-07, "output_power": 3.446343162460498e-07, "reference_active": true, "delta_db": -1.062100606265735}], "active_band_count": 3, "active_band_mae_db": 0.42946618726096414}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 8.480086855572389e-05, "log_rms_mae_db": 0.7932646385346134, "rms_envelope_nrmse": 0.0736861514520258, "envelope_correlation": 0.9957400190562525, "rms_gain_error_db": -0.06950654907995882, "reference_mean_power": 0.0005471873658289661, "output_mean_power": 0.0005384996264452623}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 3.0613556922446793e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0001155073862142863, "output_power": 0.00011114741195702341, "reference_active": true, "delta_db": -0.1671040173048799}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3854221447460866e-05, "output_power": 1.1867836035207448e-05, "reference_active": true, "delta_db": -0.6721058765028651}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9357817767829245e-06, "output_power": 1.9197103316256184e-06, "reference_active": true, "delta_db": -0.03620694935373063}], "active_band_count": 3, "active_band_mae_db": 0.2918056143871585}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.44475219971024e-05, "log_rms_mae_db": 0.550026389124623, "rms_envelope_nrmse": 0.0432415904028723, "envelope_correlation": 0.9985256142210024, "rms_gain_error_db": -0.06950662836493822, "reference_mean_power": 0.0005502385876291546, "output_mean_power": 0.0005415023938570963}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.936750998626233e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.910211940271478e-05, "output_power": 9.574214981840045e-05, "reference_active": true, "delta_db": -0.1497976741402739}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.231208448817648e-06, "output_power": 5.413581966709244e-06, "reference_active": true, "delta_db": -0.610875628955023}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.518968227553501e-07, "output_power": 1.6204258938787543e-07, "reference_active": true, "delta_db": -1.9159351520406054}], "active_band_count": 3, "active_band_mae_db": 0.892202818378634}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 7.92844222433349e-05, "log_rms_mae_db": 0.7945539644758771, "rms_envelope_nrmse": 0.0591419630733353, "envelope_correlation": 0.9978433938589544, "rms_gain_error_db": -0.10846587198457464, "reference_mean_power": 0.0003517587960046477, "output_mean_power": 0.0003430823521564451}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 1.184446345593241e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.4086641780542994e-05, "output_power": 3.222649370699455e-05, "reference_active": true, "delta_db": -0.24371160436729974}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.908924984845658e-06, "output_power": 7.664388429495802e-06, "reference_active": true, "delta_db": -0.653477955176891}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.00669572393549e-07, "output_power": 4.66252795928147e-07, "reference_active": true, "delta_db": -1.1001418370751284}], "active_band_count": 3, "active_band_mae_db": 0.6657771322064397}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.287723098191666e-05, "log_rms_mae_db": 0.5088215943939841, "rms_envelope_nrmse": 0.03251465556066665, "envelope_correlation": 0.9993991225401254, "rms_gain_error_db": -0.10846587854269998, "reference_mean_power": 0.0003537202709185465, "output_mean_power": 0.0003449954450244718}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 1.1592322619199725e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.0388893978542697e-05, "output_power": 2.8775864868420917e-05, "reference_active": true, "delta_db": -0.23686508600931433}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.277692934034562e-06, "output_power": 3.643951868380046e-06, "reference_active": true, "delta_db": -0.6963697445694437}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.6389202390485585e-08, "output_power": 4.685254427534651e-08, "reference_active": true, "delta_db": -0.8046277191433225}], "active_band_count": 3, "active_band_mae_db": 0.5792875165740269}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 3.178621250284737e-05, "log_rms_mae_db": 1.1244944272571145, "rms_envelope_nrmse": 0.12925311959460584, "envelope_correlation": 0.9893062830648655, "rms_gain_error_db": -0.1772460316809374, "reference_mean_power": 4.4150646761510114e-05, "output_mean_power": 4.238502725496422e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 2.2237128168975068e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.193805277966022e-06, "output_power": 8.32311449490418e-06, "reference_active": true, "delta_db": -0.432094323443728}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0890347422283183e-06, "output_power": 1.0826198694380873e-06, "reference_active": true, "delta_db": -0.025657412951229114}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8576888047519497e-07, "output_power": 2.419246518647307e-07, "reference_active": true, "delta_db": 1.147071609060387}], "active_band_count": 3, "active_band_mae_db": 0.5349411151517813}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 2.883918900864625e-05, "log_rms_mae_db": 0.7720254869318891, "rms_envelope_nrmse": 0.06147931567070651, "envelope_correlation": 0.9977050770853085, "rms_gain_error_db": -0.17724601581437688, "reference_mean_power": 4.439683700027618e-05, "output_mean_power": 4.2621372305835566e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.1738925168287815e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.247468496821311e-06, "output_power": 7.5324406916796995e-06, "reference_active": true, "delta_db": -0.3938494448268853}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.957219370502507e-07, "output_power": 4.4434756053615536e-07, "reference_active": true, "delta_db": -0.47515337809622693}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6536836687109635e-08, "output_power": 1.3887039697201057e-08, "reference_active": true, "delta_db": -0.7584276048890048}], "active_band_count": 3, "active_band_mae_db": 0.5424768092707056}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8728552695806655, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "cec4cc2955c2179b3c733c3240a2289d398e1f46468fcd7e49e551bbb62a6e38", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9976409785273721, "standard_deviation": 0.00033474458032244157, "minimum": 0.997245180253323, "maximum": 0.9981127269710219, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.7953729638297264, "standard_deviation": 0.010598325793970307, "minimum": 0.7844558157887173, "maximum": 0.8121705387508584, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5880546073236759, "standard_deviation": 0.15234915136732213, "minimum": 0.3227283885634978, "maximum": 0.7697423955015094, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06222292328861267, "standard_deviation": 0.004132015591185335, "minimum": 0.05581611509553891, "maximum": 0.06666995095652223, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9992538750463178, "standard_deviation": 0.0001223847506743973, "minimum": 0.999065890234732, "maximum": 0.9994068988633735, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.4977942790957118, "standard_deviation": 0.014627451680133166, "minimum": 0.4814657874943565, "maximum": 0.5207838537705985, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7517524116970942, "standard_deviation": 0.1933517636653862, "minimum": 0.5560486546780575, "maximum": 1.1534897180393147, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.036718666681947607, "standard_deviation": 0.002783647084658018, "minimum": 0.03251465556066665, "maximum": 0.04005736607886341, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9900444172789288, "standard_deviation": 0.0015200562665736125, "minimum": 0.9875760931127808, "maximum": 0.9917725745745863, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.129796356519667, "standard_deviation": 0.016172633044153617, "minimum": 1.1054074211090885, "maximum": 1.1529617396010354, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7279301782461249, "standard_deviation": 0.34204403543312023, "minimum": 0.32141296297422506, "maximum": 1.4052969388267276, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12784781830211653, "standard_deviation": 0.008563713243137174, "minimum": 0.1151028627634934, "maximum": 0.13915936569764076, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9969832333805657, "standard_deviation": 0.0011218339104586159, "minimum": 0.9946337799737422, "maximum": 0.9981218330257855, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7790497589810724, "standard_deviation": 0.021050065925738454, "minimum": 0.7378060968089123, "maximum": 0.8010085645647863, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6850374669337533, "standard_deviation": 0.328846703095468, "minimum": 0.36792142495184393, "maximum": 1.3747726630899642, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07495826625347282, "standard_deviation": 0.014127255729038064, "minimum": 0.059919783737148846, "maximum": 0.09970855805462804, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9956369206476714, "standard_deviation": 0.0005574919019349268, "minimum": 0.99471252391935, "maximum": 0.9963986376193313, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.7919051351658206, "standard_deviation": 0.0297366594701407, "minimum": 0.7574160742415933, "maximum": 0.8514611196684778, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.45925873507027554, "standard_deviation": 0.19658716265171322, "minimum": 0.244851851844998, "maximum": 0.7539804001474693, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07434471578005827, "standard_deviation": 0.004704663282592948, "minimum": 0.06768779503981341, "maximum": 0.08168166800697539, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9985089709170596, "standard_deviation": 0.0002536977584565253, "minimum": 0.997946876546508, "maximum": 0.9987423556754091, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5488300474454404, "standard_deviation": 0.038851891667884816, "minimum": 0.5206355918358299, "maximum": 0.6412514474487253, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8529996296290198, "standard_deviation": 0.20454884386450412, "minimum": 0.5465881413289124, "maximum": 1.2021789888648662, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04273050977768624, "standard_deviation": 0.0034249742268816054, "minimum": 0.03896849216707552, "maximum": 0.049911713592816584, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.2283413129807386, "standard_deviation": 0.0965291180648396, "minimum": 1.0430344775759424, "maximum": 1.35101923393818, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.366616138950704, "standard_deviation": 0.0038388077644932257, "minimum": 5.361721526667476, "maximum": 5.374389271364418, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.22391167199788733, "standard_deviation": 0.01170385822215621, "minimum": 0.2098861870894979, "maximum": 0.24517949904811537, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.10243754627059953, "standard_deviation": 0.02970021679309014, "minimum": -0.14794648396875126, "maximum": -0.042000962737148366, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9965075650125201, "standard_deviation": 0.0008069081239210436, "minimum": 0.9953509250401716, "maximum": 0.9974119025575953, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.2531276405254848, "standard_deviation": 0.028016270771557637, "minimum": 1.2241950207452572, "maximum": 1.292416286502776, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3712047905038027, "standard_deviation": 0.19224281959148176, "minimum": 0.08517719777001224, "maximum": 0.5812633383175011, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.0646241478466516, "standard_deviation": 0.007438816091692907, "minimum": 0.056069841388451454, "maximum": 0.07538015533101454, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9989290429539697, "standard_deviation": 0.0005119472851902773, "minimum": 0.9977353015192042, "maximum": 0.9993066071318064, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6991877243069042, "standard_deviation": 0.05001015079604904, "minimum": 0.6314646885575976, "maximum": 0.7956985011777675, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5343194168622871, "standard_deviation": 0.2179488379830116, "minimum": 0.1809063631598741, "maximum": 0.774272526625572, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03589979027922044, "standard_deviation": 0.007556720127508755, "minimum": 0.028905820264806883, "maximum": 0.052785560591302544, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_falset10_BASIC5000_1728", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 1.8943874835968018, "predicted_mos": 1.8943874835968018, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 130065, "input_sample_rate": 24000, "input_seconds": 5.419375, "input_float32_sha256": "9e72c98aba531511cf767ae705faa2728fe7e771c0b1563b82decdb1820f7797", "internal_samples": 86710, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.802617399953306}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3040971824474088, "全帯域_10ms_rms_envelope_nrmse": 0.06610156423490912, "全帯域_10ms_envelope_correlation": 0.9963091893796194, "全帯域_10ms_modulation_mae_db": 0.5511711069591029, "全帯域_40ms_log_rms_mae_db": 0.7279766305042188, "全帯域_40ms_rms_envelope_nrmse": 0.037736191071442056, "全帯域_40ms_envelope_correlation": 0.9987372085962528, "全帯域_40ms_modulation_mae_db": 0.7641905477556362, "300–1000 Hz_10ms_log_rms_mae_db": 0.8699920561063945, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07637765712213199, "300–1000 Hz_10ms_envelope_correlation": 0.9954608836881967, "300–1000 Hz_10ms_modulation_mae_db": 0.29439239302937564, "300–1000 Hz_40ms_log_rms_mae_db": 0.615854604827332, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.049518027566472764, "300–1000 Hz_40ms_envelope_correlation": 0.9980316435047258, "300–1000 Hz_40ms_modulation_mae_db": 0.9979958365476732, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9520003322240239, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06773612820577037, "1000–3000 Hz_10ms_envelope_correlation": 0.9971233807065223, "1000–3000 Hz_10ms_modulation_mae_db": 0.35574847647066227, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5955168708704123, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03709529028182816, "1000–3000 Hz_40ms_envelope_correlation": 0.9991648830675931, "1000–3000 Hz_40ms_modulation_mae_db": 0.44295122042482954, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3932661125133454, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1390782635945491, "3000–6000 Hz_10ms_envelope_correlation": 0.9875020857881014, "3000–6000 Hz_10ms_modulation_mae_db": 1.398557466126473, "3000–6000 Hz_40ms_log_rms_mae_db": 0.952631017154478, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06733830752309589, "3000–6000 Hz_40ms_envelope_correlation": 0.9970270843552816, "3000–6000 Hz_40ms_modulation_mae_db": 0.8051780497861465, "mr_stft_db": 5.608411365400278, "band_mae_db": 1.394140949847879, "rms_gain_error_db": 0.015353531873617664, "output_peak": 0.2783661671822479}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1670065639847167, "全帯域_10ms_rms_envelope_nrmse": 0.06434407118260792, "全帯域_10ms_envelope_correlation": 0.9965684188296462, "全帯域_10ms_modulation_mae_db": 0.5888820157870999, "全帯域_40ms_log_rms_mae_db": 0.6375829252442118, "全帯域_40ms_rms_envelope_nrmse": 0.03867662742954316, "全帯域_40ms_envelope_correlation": 0.9987711878881531, "全帯域_40ms_modulation_mae_db": 1.0260759661835626, "300–1000 Hz_10ms_log_rms_mae_db": 0.8032696551410005, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06941051324805511, "300–1000 Hz_10ms_envelope_correlation": 0.9962076134451704, "300–1000 Hz_10ms_modulation_mae_db": 0.49042539457629064, "300–1000 Hz_40ms_log_rms_mae_db": 0.5617399718991692, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03764604665123545, "300–1000 Hz_40ms_envelope_correlation": 0.998854845797479, "300–1000 Hz_40ms_modulation_mae_db": 0.832775640364253, "1000–3000 Hz_10ms_log_rms_mae_db": 0.870579582359486, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05885957452498765, "1000–3000 Hz_10ms_envelope_correlation": 0.997896061527362, "1000–3000 Hz_10ms_modulation_mae_db": 0.3289710743833835, "1000–3000 Hz_40ms_log_rms_mae_db": 0.49264798294055706, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.029546725805196676, "1000–3000 Hz_40ms_envelope_correlation": 0.9995493098464839, "1000–3000 Hz_40ms_modulation_mae_db": 0.4755165367603773, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4058019870343519, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13209204703054864, "3000–6000 Hz_10ms_envelope_correlation": 0.9887896649287674, "3000–6000 Hz_10ms_modulation_mae_db": 1.2081122563225628, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9612298928552245, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0672327572810112, "3000–6000 Hz_40ms_envelope_correlation": 0.9969888864527154, "3000–6000 Hz_40ms_modulation_mae_db": 0.4892568452702004, "mr_stft_db": 5.613163074488081, "band_mae_db": 1.2828226946739683, "rms_gain_error_db": -0.09895710837680893, "output_peak": 0.21116794176533332}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2531713483505644, "全帯域_10ms_rms_envelope_nrmse": 0.0609646239090383, "全帯域_10ms_envelope_correlation": 0.9968909264979724, "全帯域_10ms_modulation_mae_db": 0.24348753645840207, "全帯域_40ms_log_rms_mae_db": 0.6670876271513014, "全帯域_40ms_rms_envelope_nrmse": 0.03373897141106975, "全帯域_40ms_envelope_correlation": 0.9990450488055164, "全帯域_40ms_modulation_mae_db": 0.5338499021566169, "300–1000 Hz_10ms_log_rms_mae_db": 0.8565456336609681, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07331541748778857, "300–1000 Hz_10ms_envelope_correlation": 0.9957303885092932, "300–1000 Hz_10ms_modulation_mae_db": 0.5276837892742477, "300–1000 Hz_40ms_log_rms_mae_db": 0.5936149312206445, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04642064941401697, "300–1000 Hz_40ms_envelope_correlation": 0.9982031158318856, "300–1000 Hz_40ms_modulation_mae_db": 1.0643191278770923, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8838486661499428, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06984081127094958, "1000–3000 Hz_10ms_envelope_correlation": 0.9970489371488986, "1000–3000 Hz_10ms_modulation_mae_db": 0.41407398340329843, "1000–3000 Hz_40ms_log_rms_mae_db": 0.545781287841686, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03722589132346014, "1000–3000 Hz_40ms_envelope_correlation": 0.999290125824838, "1000–3000 Hz_40ms_modulation_mae_db": 0.6870130580968512, "3000–6000 Hz_10ms_log_rms_mae_db": 1.350264621540806, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12091078598100441, "3000–6000 Hz_10ms_envelope_correlation": 0.9911208357267328, "3000–6000 Hz_10ms_modulation_mae_db": 0.8024635325844622, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9304996489102465, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06614195994108253, "3000–6000 Hz_40ms_envelope_correlation": 0.9978554996161686, "3000–6000 Hz_40ms_modulation_mae_db": 0.9611130666093993, "mr_stft_db": 5.629793468221362, "band_mae_db": 1.2019375053748045, "rms_gain_error_db": -0.07282521015324722, "output_peak": 0.2534367960185788}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.263582922880799, "全帯域_10ms_rms_envelope_nrmse": 0.06228309826910028, "全帯域_10ms_envelope_correlation": 0.9967187619660626, "全帯域_10ms_modulation_mae_db": 0.4229862878026065, "全帯域_40ms_log_rms_mae_db": 0.7303415934148043, "全帯域_40ms_rms_envelope_nrmse": 0.03149058787544802, "全帯域_40ms_envelope_correlation": 0.9991316521128643, "全帯域_40ms_modulation_mae_db": 0.7267274614359805, "300–1000 Hz_10ms_log_rms_mae_db": 0.8370195465237958, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07689458350974165, "300–1000 Hz_10ms_envelope_correlation": 0.9953662227821224, "300–1000 Hz_10ms_modulation_mae_db": 0.6174189895762753, "300–1000 Hz_40ms_log_rms_mae_db": 0.5888451279858414, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04339634870534757, "300–1000 Hz_40ms_envelope_correlation": 0.9984729197965005, "300–1000 Hz_40ms_modulation_mae_db": 1.2028419831942767, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9176149217303353, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.061322265585567096, "1000–3000 Hz_10ms_envelope_correlation": 0.9976783284633537, "1000–3000 Hz_10ms_modulation_mae_db": 0.402617504717454, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5729486084461525, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.035737710685579474, "1000–3000 Hz_40ms_envelope_correlation": 0.999253200872632, "1000–3000 Hz_40ms_modulation_mae_db": 0.4108771475944993, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4197581492404885, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13786768731660545, "3000–6000 Hz_10ms_envelope_correlation": 0.9882361370590456, "3000–6000 Hz_10ms_modulation_mae_db": 1.3471970740501764, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9789034485963664, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07325377772087635, "3000–6000 Hz_40ms_envelope_correlation": 0.9972367872605614, "3000–6000 Hz_40ms_modulation_mae_db": 0.7544448838512583, "mr_stft_db": 5.637849292753912, "band_mae_db": 1.4404698112488818, "rms_gain_error_db": -0.03896224382751705, "output_peak": 0.22455764600002498}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2484712773845577, "全帯域_10ms_rms_envelope_nrmse": 0.059343122264373625, "全帯域_10ms_envelope_correlation": 0.9971370813480688, "全帯域_10ms_modulation_mae_db": 0.3761156524857048, "全帯域_40ms_log_rms_mae_db": 0.6591724755024334, "全帯域_40ms_rms_envelope_nrmse": 0.032264612068058786, "全帯域_40ms_envelope_correlation": 0.9992290260643535, "全帯域_40ms_modulation_mae_db": 0.5480122694410706, "300–1000 Hz_10ms_log_rms_mae_db": 0.8924343046719907, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07737111331678553, "300–1000 Hz_10ms_envelope_correlation": 0.995251556757652, "300–1000 Hz_10ms_modulation_mae_db": 0.33939326078776794, "300–1000 Hz_40ms_log_rms_mae_db": 0.6201387120701235, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.041395202060747524, "300–1000 Hz_40ms_envelope_correlation": 0.9985989424923392, "300–1000 Hz_40ms_modulation_mae_db": 0.4999048641831862, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9199136073735819, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06506490953908299, "1000–3000 Hz_10ms_envelope_correlation": 0.9973717292655216, "1000–3000 Hz_10ms_modulation_mae_db": 0.5374488161656715, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5445692556132543, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03802729227087468, "1000–3000 Hz_40ms_envelope_correlation": 0.9991419642819912, "1000–3000 Hz_40ms_modulation_mae_db": 0.6614340501993609, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4378088371255988, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15008976703099747, "3000–6000 Hz_10ms_envelope_correlation": 0.9860878935139342, "3000–6000 Hz_10ms_modulation_mae_db": 0.7612787807888015, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9970966647381774, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08843170401418719, "3000–6000 Hz_40ms_envelope_correlation": 0.9958164243256236, "3000–6000 Hz_40ms_modulation_mae_db": 1.2418612097320134, "mr_stft_db": 5.627696934246031, "band_mae_db": 1.2038057870391508, "rms_gain_error_db": -0.12013898556526113, "output_peak": 0.24579582236792974}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2493502767980142, "全帯域_10ms_rms_envelope_nrmse": 0.06283391628890392, "全帯域_10ms_envelope_correlation": 0.9966519168057841, "全帯域_10ms_modulation_mae_db": 0.4537889777754715, "全帯域_40ms_log_rms_mae_db": 0.6819659179781639, "全帯域_40ms_rms_envelope_nrmse": 0.030500314702100104, "全帯域_40ms_envelope_correlation": 0.999173499841993, "全帯域_40ms_modulation_mae_db": 0.6580557963242001, "300–1000 Hz_10ms_log_rms_mae_db": 0.8420209269444342, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.078274224726984, "300–1000 Hz_10ms_envelope_correlation": 0.9951949210130557, "300–1000 Hz_10ms_modulation_mae_db": 0.38170272117918924, "300–1000 Hz_40ms_log_rms_mae_db": 0.5984820416539771, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04575798520678654, "300–1000 Hz_40ms_envelope_correlation": 0.998298017781081, "300–1000 Hz_40ms_modulation_mae_db": 0.4133282380104437, "1000–3000 Hz_10ms_log_rms_mae_db": 0.891368471472757, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0687952529649167, "1000–3000 Hz_10ms_envelope_correlation": 0.9970639348338158, "1000–3000 Hz_10ms_modulation_mae_db": 0.5136713392024256, "1000–3000 Hz_40ms_log_rms_mae_db": 0.533665212783512, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.037956863143731506, "1000–3000 Hz_40ms_envelope_correlation": 0.9991611190564029, "1000–3000 Hz_40ms_modulation_mae_db": 1.033919364145439, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3541902110278412, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13733978939897093, "3000–6000 Hz_10ms_envelope_correlation": 0.9878583974077888, "3000–6000 Hz_10ms_modulation_mae_db": 0.3314494146768285, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9188599602647168, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0842371068862678, "3000–6000 Hz_40ms_envelope_correlation": 0.9953841730239272, "3000–6000 Hz_40ms_modulation_mae_db": 0.5971013902704909, "mr_stft_db": 5.622071900822532, "band_mae_db": 1.3287588293162866, "rms_gain_error_db": -0.0210397009815985, "output_peak": 0.2234795053448928}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2366263251151768, "全帯域_10ms_rms_envelope_nrmse": 0.06328359583367749, "全帯域_10ms_envelope_correlation": 0.9967201168634592, "全帯域_10ms_modulation_mae_db": 0.517513027466162, "全帯域_40ms_log_rms_mae_db": 0.7061317273840858, "全帯域_40ms_rms_envelope_nrmse": 0.03393715983048129, "全帯域_40ms_envelope_correlation": 0.9991264454797619, "全帯域_40ms_modulation_mae_db": 0.6752778060405776, "300–1000 Hz_10ms_log_rms_mae_db": 0.8664213819490354, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08056332059533926, "300–1000 Hz_10ms_envelope_correlation": 0.9948421059331298, "300–1000 Hz_10ms_modulation_mae_db": 0.3958444837593129, "300–1000 Hz_40ms_log_rms_mae_db": 0.5810278045386111, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04475837916408168, "300–1000 Hz_40ms_envelope_correlation": 0.9983517371336188, "300–1000 Hz_40ms_modulation_mae_db": 0.9036054780431221, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8620958924765817, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0666948112992711, "1000–3000 Hz_10ms_envelope_correlation": 0.9971718904879449, "1000–3000 Hz_10ms_modulation_mae_db": 0.6489617744424622, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5373049795933995, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.036116214412817337, "1000–3000 Hz_40ms_envelope_correlation": 0.9991601656290264, "1000–3000 Hz_40ms_modulation_mae_db": 1.0844131677391238, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3255777285073271, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1353498142592133, "3000–6000 Hz_10ms_envelope_correlation": 0.9886179549135541, "3000–6000 Hz_10ms_modulation_mae_db": 0.6882381352230981, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9164599275746165, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08307831165494334, "3000–6000 Hz_40ms_envelope_correlation": 0.9960761942646078, "3000–6000 Hz_40ms_modulation_mae_db": 0.6069696864968392, "mr_stft_db": 5.623959003232598, "band_mae_db": 1.1523174302192574, "rms_gain_error_db": -0.11922570386549816, "output_peak": 0.2162057921905396}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2601603259957326, "全帯域_10ms_rms_envelope_nrmse": 0.06608726508284055, "全帯域_10ms_envelope_correlation": 0.9963035745188012, "全帯域_10ms_modulation_mae_db": 0.5204011479316552, "全帯域_40ms_log_rms_mae_db": 0.7337895717307488, "全帯域_40ms_rms_envelope_nrmse": 0.03336971878989926, "全帯域_40ms_envelope_correlation": 0.9990263734417123, "全帯域_40ms_modulation_mae_db": 0.5585079109901724, "300–1000 Hz_10ms_log_rms_mae_db": 0.8199232887318842, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07837386245435747, "300–1000 Hz_10ms_envelope_correlation": 0.9951434940197823, "300–1000 Hz_10ms_modulation_mae_db": 0.3351000188398599, "300–1000 Hz_40ms_log_rms_mae_db": 0.546111769854033, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04772897847384657, "300–1000 Hz_40ms_envelope_correlation": 0.9981268860999232, "300–1000 Hz_40ms_modulation_mae_db": 0.6349047233147626, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8860141543062529, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06354306804749092, "1000–3000 Hz_10ms_envelope_correlation": 0.9974337764407475, "1000–3000 Hz_10ms_modulation_mae_db": 0.4696992938629234, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5440409369349083, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.036660598432682295, "1000–3000 Hz_40ms_envelope_correlation": 0.9991302202157847, "1000–3000 Hz_40ms_modulation_mae_db": 0.21975632323186214, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3412546069503726, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13158290369764203, "3000–6000 Hz_10ms_envelope_correlation": 0.9897727995768749, "3000–6000 Hz_10ms_modulation_mae_db": 0.849298945570767, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9190924874225962, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07775688783340405, "3000–6000 Hz_40ms_envelope_correlation": 0.9972451496695357, "3000–6000 Hz_40ms_modulation_mae_db": 1.3122529563278404, "mr_stft_db": 5.624450772020807, "band_mae_db": 1.2387170786388464, "rms_gain_error_db": -0.04614158679230155, "output_peak": 0.25863438591873156}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 130065, "output_samples": 130065, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.7988004732296625, "spectral_convergence": 0.17845735751557204, "spectral_convergence_status": "ok", "amplitude_floor": 8.628776010687778e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.71509855619137, "spectral_convergence": 0.19274005370954134, "spectral_convergence_status": "ok", "amplitude_floor": 8.696913128358987e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.311335066779801, "spectral_convergence": 0.19240270038653962, "spectral_convergence_status": "ok", "amplitude_floor": 6.997748100750841e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.5012142154628568e-06, "output_power": 1.1828216443566406e-05, "delta_db": 8.9647659481642, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008569985031977355, "output_power": 0.0008563056215001661, "delta_db": -0.003512683007449252, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0002039561579698118, "output_power": 0.00020743502555886075, "delta_db": 0.07345266854788275, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00031755380447674584, "output_power": 0.0003091058305695032, "delta_db": -0.11710123097672653, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 8.391217397004902e-05, "output_power": 8.498069229478312e-05, "delta_db": 0.054952919447762906, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2641952404694477e-05, "output_power": 1.1977158573154965e-05, "delta_db": -0.23460351440692226, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.274471551779886e-06, "output_power": 2.4430945655016286e-06, "delta_db": 0.31059768438420854, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.394140949847879, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.015353531873617664, "pitch": null, "output_rms_dbfs": -28.28543963623893, "output_peak": 0.2783661671822479, "reference_rms_dbfs": -28.300793168112545, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.608411365400278}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 130065, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 0.0001318526099400404, "log_rms_mae_db": 1.3040971824474088, "rms_envelope_nrmse": 0.06610156423490912, "envelope_correlation": 0.9963091893796194, "rms_gain_error_db": 0.015353298836302105, "reference_mean_power": 0.0014814008893508253, "output_mean_power": 0.0014866472468841598}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 7.673423983742615e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002922132888675935, "output_power": 0.0002859221423615716, "reference_active": true, "delta_db": -0.09452173023167812}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.0438146457063534e-05, "output_power": 2.569167446924457e-05, "reference_active": true, "delta_db": -0.73625791795518}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.705913608511969e-06, "output_power": 4.721193761484601e-06, "reference_active": true, "delta_db": -0.8227336726904504}], "active_band_count": 3, "active_band_mae_db": 0.5511711069591029}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 0.00011771272815729935, "log_rms_mae_db": 0.7279766305042188, "rms_envelope_nrmse": 0.037736191071442056, "envelope_correlation": 0.9987372085962528, "rms_gain_error_db": 0.01535308023236606, "reference_mean_power": 0.001489661173505724, "output_mean_power": 0.0014949367094548875}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 7.348414354743223e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000259482167884596, "output_power": 0.0002535783748329186, "reference_active": true, "delta_db": -0.09995303505101862}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3907004138768798e-05, "output_power": 1.1687238403207318e-05, "reference_active": true, "delta_db": -0.7552168077426386}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.4011744172060643e-07, "output_power": 3.161028415102471e-07, "reference_active": true, "delta_db": -1.4374018004732514}], "active_band_count": 3, "active_band_mae_db": 0.7641905477556362}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 8.480086855572389e-05, "log_rms_mae_db": 0.8699920561063945, "rms_envelope_nrmse": 0.07637765712213199, "envelope_correlation": 0.9954608836881967, "rms_gain_error_db": 0.07149381275298643, "reference_mean_power": 0.0005471873658289661, "output_mean_power": 0.0005562697486423971}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 3.0613556922446793e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0001155073862142863, "output_power": 0.00011143326453392921, "reference_active": true, "delta_db": -0.1559490269438917}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3854221447460866e-05, "output_power": 1.1919437681218402e-05, "reference_active": true, "delta_db": -0.6532635782722218}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9357817767829245e-06, "output_power": 1.9690323642484917e-06, "reference_active": true, "delta_db": 0.07396457387201351}], "active_band_count": 3, "active_band_mae_db": 0.29439239302937564}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.44475219971024e-05, "log_rms_mae_db": 0.615854604827332, "rms_envelope_nrmse": 0.049518027566472764, "envelope_correlation": 0.9980316435047258, "rms_gain_error_db": 0.0714937729938389, "reference_mean_power": 0.0005502385876291546, "output_mean_power": 0.0005593716104317964}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.936750998626233e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.910211940271478e-05, "output_power": 9.598142035186648e-05, "reference_active": true, "delta_db": -0.1389577000856859}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.231208448817648e-06, "output_power": 5.421931156866178e-06, "reference_active": true, "delta_db": -0.604182807138855}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.518968227553501e-07, "output_power": 1.5001614096226642e-07, "reference_active": true, "delta_db": -2.2508470024184786}], "active_band_count": 3, "active_band_mae_db": 0.9979958365476732}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 7.92844222433349e-05, "log_rms_mae_db": 0.9520003322240239, "rms_envelope_nrmse": 0.06773612820577037, "envelope_correlation": 0.9971233807065223, "rms_gain_error_db": -0.09300034372287101, "reference_mean_power": 0.0003517587960046477, "output_mean_power": 0.0003443062701860639}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 1.184446345593241e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.4086641780542994e-05, "output_power": 3.245259936736923e-05, "reference_active": true, "delta_db": -0.2133472823052635}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.908924984845658e-06, "output_power": 7.853710225947395e-06, "reference_active": true, "delta_db": -0.5475042878945017}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.00669572393549e-07, "output_power": 5.59752764182212e-07, "reference_active": true, "delta_db": -0.3063938592122217}], "active_band_count": 3, "active_band_mae_db": 0.35574847647066227}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.287723098191666e-05, "log_rms_mae_db": 0.5955168708704123, "rms_envelope_nrmse": 0.03709529028182816, "envelope_correlation": 0.9991648830675931, "rms_gain_error_db": -0.09300035572455792, "reference_mean_power": 0.0003537202709185465, "output_mean_power": 0.0003462261874213356}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 1.1592322619199725e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.0388893978542697e-05, "output_power": 2.906202228186973e-05, "reference_active": true, "delta_db": -0.19389062556813855}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.277692934034562e-06, "output_power": 3.826994472191769e-06, "reference_active": true, "delta_db": -0.48351771440767655}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.6389202390485585e-08, "output_power": 4.8534596067299125e-08, "reference_active": true, "delta_db": -0.6514453212986735}], "active_band_count": 3, "active_band_mae_db": 0.44295122042482954}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 3.178621250284737e-05, "log_rms_mae_db": 1.3932661125133454, "rms_envelope_nrmse": 0.1390782635945491, "envelope_correlation": 0.9875020857881014, "rms_gain_error_db": -0.09836859919178341, "reference_mean_power": 4.4150646761510114e-05, "output_mean_power": 4.3161865792132854e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 2.2237128168975068e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.193805277966022e-06, "output_power": 8.820367682004923e-06, "reference_active": true, "delta_db": -0.18008611965279978}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0890347422283183e-06, "output_power": 7.266742822097199e-07, "reference_active": true, "delta_db": -1.7570194446340266}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8576888047519497e-07, "output_power": 3.1248533977431315e-07, "reference_active": true, "delta_db": 2.258566834092593}], "active_band_count": 3, "active_band_mae_db": 1.398557466126473}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 2.883918900864625e-05, "log_rms_mae_db": 0.952631017154478, "rms_envelope_nrmse": 0.06733830752309589, "envelope_correlation": 0.9970270843552816, "rms_gain_error_db": -0.09836863869227305, "reference_mean_power": 4.439683700027618e-05, "output_mean_power": 4.340254205387452e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.1738925168287815e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.247468496821311e-06, "output_power": 8.025038394746585e-06, "reference_active": true, "delta_db": -0.11873546421867943}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.957219370502507e-07, "output_power": 3.5162712093541524e-07, "reference_active": true, "delta_db": -1.4915577330048422}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6536836687109635e-08, "output_power": 1.3738152794288799e-08, "reference_active": true, "delta_db": -0.805240952134918}], "active_band_count": 3, "active_band_mae_db": 0.8051780497861465}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8755981320024091, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "1fa7e22d409ce69c767bf21f4b93c68eed919dc2785ef97a315d38ed5a57504e", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9973485048592707, "standard_deviation": 0.0003091478987311605, "minimum": 0.9970489371488986, "maximum": 0.997896061527362, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.8979294535116202, "standard_deviation": 0.029784534736840913, "minimum": 0.8620958924765817, "maximum": 0.9520003322240239, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4588990328310351, "standard_deviation": 0.1056333094930604, "minimum": 0.3289710743833835, "maximum": 0.6489617744424622, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06523210267975454, "standard_deviation": 0.0038008011917678515, "minimum": 0.05885957452498765, "maximum": 0.06984081127094958, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.999231373599344, "standard_deviation": 0.0001402370497169659, "minimum": 0.9991302202157847, "maximum": 0.9995493098464839, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5458093918779853, "standard_deviation": 0.02989978074165053, "minimum": 0.49264798294055706, "maximum": 0.5955168708704123, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6269851085240429, "standard_deviation": 0.3044843736587641, "minimum": 0.21975632323186214, "maximum": 1.0844131677391238, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03604582329452129, "standard_deviation": 0.0027461229567587314, "minimum": 0.029546725805196676, "maximum": 0.03802729227087468, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9884982211143498, "standard_deviation": 0.0015062707259462886, "minimum": 0.9860878935139342, "maximum": 0.9911208357267328, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.3784902817425164, "standard_deviation": 0.04098675294554834, "minimum": 1.3255777285073271, "maximum": 1.4378088371255988, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.9233244506678961, "standard_deviation": 0.366166645136705, "minimum": 0.3314494146768285, "maximum": 1.398557466126473, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.13553888228869143, "standard_deviation": 0.008232943010564129, "minimum": 0.12091078598100441, "maximum": 0.15008976703099747, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9967037748710528, "standard_deviation": 0.0008461740658399911, "minimum": 0.9953841730239272, "maximum": 0.9978554996161686, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9468466309395527, "standard_deviation": 0.030559460968834367, "minimum": 0.9164599275746165, "maximum": 0.9970966647381774, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.8460222610430236, "standard_deviation": 0.30325599484176385, "minimum": 0.4892568452702004, "maximum": 1.3122529563278404, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07593385160685855, "standard_deviation": 0.008719137346617027, "minimum": 0.06614195994108253, "maximum": 0.08843170401418719, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9953996482685503, "standard_deviation": 0.00041530998284071977, "minimum": 0.9948421059331298, "maximum": 0.9962076134451704, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8484533492161879, "standard_deviation": 0.028820166716431426, "minimum": 0.8032696551410005, "maximum": 0.8924343046719907, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4227451313777899, "standard_deviation": 0.11148504115863289, "minimum": 0.29439239302937564, "maximum": 0.6174189895762753, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07632258655764795, "standard_deviation": 0.003469250524736137, "minimum": 0.06941051324805511, "maximum": 0.08056332059533926, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9983672635546942, "standard_deviation": 0.0002685882338612339, "minimum": 0.9980316435047258, "maximum": 0.998854845797479, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5882268705062165, "standard_deviation": 0.02519439666482231, "minimum": 0.546111769854033, "maximum": 0.6201387120701235, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8187094864418512, "standard_deviation": 0.27958775446797196, "minimum": 0.4133282380104437, "maximum": 1.2028419831942767, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04457770215531689, "standard_deviation": 0.0037555915516204867, "minimum": 0.03764604665123545, "maximum": 0.049518027566472764, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.2803712607948845, "standard_deviation": 0.10076098628301375, "minimum": 1.1523174302192574, "maximum": 1.4404698112488818, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.623424476398201, "standard_deviation": 0.009263998004005304, "minimum": 5.608411365400278, "maximum": 5.637849292753912, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.23895550709853486, "standard_deviation": 0.023704910255825495, "minimum": 0.21116794176533332, "maximum": 0.2783661671822479, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06274212596107687, "standard_deviation": 0.04866367422022919, "minimum": -0.12013898556526113, "maximum": 0.015353531873617664, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9966624982761767, "standard_deviation": 0.0002794153075900377, "minimum": 0.9963035745188012, "maximum": 0.9971370813480688, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.2478082778696211, "standard_deviation": 0.03827603910109871, "minimum": 1.1670065639847167, "maximum": 1.3040971824474088, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4592932190832756, "standard_deviation": 0.11161004674287138, "minimum": 0.24348753645840207, "maximum": 0.5888820157870999, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.0631551571331814, "standard_deviation": 0.002357429379151623, "minimum": 0.059343122264373625, "maximum": 0.06610156423490912, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9990300552788259, "standard_deviation": 0.00018236093368204808, "minimum": 0.9987372085962528, "maximum": 0.9992290260643535, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6930060586137461, "standard_deviation": 0.036766728036238955, "minimum": 0.6375829252442118, "maximum": 0.7337895717307488, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.686337207540977, "standard_deviation": 0.16158305416748484, "minimum": 0.5338499021566169, "maximum": 1.0260759661835626, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0339642728972553, "standard_deviation": 0.00287465807443939, "minimum": 0.030500314702100104, "maximum": 0.03867662742954316, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_falset10_BASIC5000_1728", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 1.3344571590423584, "predicted_mos": 1.3344571590423584, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 130065, "input_sample_rate": 24000, "input_seconds": 5.419375, "input_float32_sha256": "b6bf1d473188df1d1fbb0fc9bba67bdacebe469b9b72e27da8bff09bf1b18331", "internal_samples": 86710, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.943765899632126}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2411331942516297, "全帯域_10ms_rms_envelope_nrmse": 0.06828860317917325, "全帯域_10ms_envelope_correlation": 0.996133223639591, "全帯域_10ms_modulation_mae_db": 0.7518804349670715, "全帯域_40ms_log_rms_mae_db": 0.6909482285669047, "全帯域_40ms_rms_envelope_nrmse": 0.037529763995703555, "全帯域_40ms_envelope_correlation": 0.9988647208847088, "全帯域_40ms_modulation_mae_db": 0.7743332532799302, "300–1000 Hz_10ms_log_rms_mae_db": 0.8161191932409517, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07273228521859923, "300–1000 Hz_10ms_envelope_correlation": 0.9958813258616334, "300–1000 Hz_10ms_modulation_mae_db": 0.6115851103315894, "300–1000 Hz_40ms_log_rms_mae_db": 0.5845814610089891, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04041792610004959, "300–1000 Hz_40ms_envelope_correlation": 0.998695794528871, "300–1000 Hz_40ms_modulation_mae_db": 1.0330606171167924, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7638519266394479, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06741658638827627, "1000–3000 Hz_10ms_envelope_correlation": 0.9973667626848982, "1000–3000 Hz_10ms_modulation_mae_db": 0.36500700467764763, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4719112618131823, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.048183835322655855, "1000–3000 Hz_40ms_envelope_correlation": 0.9987738291526645, "1000–3000 Hz_40ms_modulation_mae_db": 0.2576348112696277, "3000–6000 Hz_10ms_log_rms_mae_db": 1.064013161463481, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.10487798695206715, "3000–6000 Hz_10ms_envelope_correlation": 0.9932244787910091, "3000–6000 Hz_10ms_modulation_mae_db": 0.7267343751745917, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7415008279281753, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0593452181128332, "3000–6000 Hz_40ms_envelope_correlation": 0.9980931510280152, "3000–6000 Hz_40ms_modulation_mae_db": 0.9613808714377875, "mr_stft_db": 5.3533159542318245, "band_mae_db": 1.2934757011227322, "rms_gain_error_db": -0.10442998371940225, "output_peak": 0.21286396204416977}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.26657855349654, "全帯域_10ms_rms_envelope_nrmse": 0.05933634999007855, "全帯域_10ms_envelope_correlation": 0.9970519599086313, "全帯域_10ms_modulation_mae_db": 0.427367659914176, "全帯域_40ms_log_rms_mae_db": 0.7296346849704634, "全帯域_40ms_rms_envelope_nrmse": 0.03301280061904104, "全帯域_40ms_envelope_correlation": 0.9990825743198627, "全帯域_40ms_modulation_mae_db": 0.4246190924734529, "300–1000 Hz_10ms_log_rms_mae_db": 0.8042724554593017, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06961292332680735, "300–1000 Hz_10ms_envelope_correlation": 0.9961809827227458, "300–1000 Hz_10ms_modulation_mae_db": 0.6755170172240899, "300–1000 Hz_40ms_log_rms_mae_db": 0.5751381572686262, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03972937774483546, "300–1000 Hz_40ms_envelope_correlation": 0.9987078181753895, "300–1000 Hz_40ms_modulation_mae_db": 1.0918808165673695, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7770261929536465, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06395066442537592, "1000–3000 Hz_10ms_envelope_correlation": 0.9973968116631371, "1000–3000 Hz_10ms_modulation_mae_db": 0.44578194916466374, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5074316006598076, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03983017177935451, "1000–3000 Hz_40ms_envelope_correlation": 0.9989715007114888, "1000–3000 Hz_40ms_modulation_mae_db": 0.33005349727964256, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0841810962060372, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12672935446670366, "3000–6000 Hz_10ms_envelope_correlation": 0.9899482509540303, "3000–6000 Hz_10ms_modulation_mae_db": 1.3013151658847957, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7743972058829243, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07623633299252923, "3000–6000 Hz_40ms_envelope_correlation": 0.996614815302379, "3000–6000 Hz_40ms_modulation_mae_db": 0.7736049457522, "mr_stft_db": 5.342436080051833, "band_mae_db": 1.3285214464495685, "rms_gain_error_db": -0.07078274598877392, "output_peak": 0.20793401316135526}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2685633090039765, "全帯域_10ms_rms_envelope_nrmse": 0.05972367912282385, "全帯域_10ms_envelope_correlation": 0.9970583742573328, "全帯域_10ms_modulation_mae_db": 0.2612026432129551, "全帯域_40ms_log_rms_mae_db": 0.745041330968258, "全帯域_40ms_rms_envelope_nrmse": 0.033010686041560516, "全帯域_40ms_envelope_correlation": 0.9991380038659191, "全帯域_40ms_modulation_mae_db": 0.5880906109069075, "300–1000 Hz_10ms_log_rms_mae_db": 0.7657982951417378, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08052336131303736, "300–1000 Hz_10ms_envelope_correlation": 0.9948574274088308, "300–1000 Hz_10ms_modulation_mae_db": 0.4523898059828176, "300–1000 Hz_40ms_log_rms_mae_db": 0.5548540174877229, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04262411173049358, "300–1000 Hz_40ms_envelope_correlation": 0.9985109667644735, "300–1000 Hz_40ms_modulation_mae_db": 0.9066520749411943, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7612408439705186, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06970352725021178, "1000–3000 Hz_10ms_envelope_correlation": 0.9971819063637997, "1000–3000 Hz_10ms_modulation_mae_db": 0.7362077908388575, "1000–3000 Hz_40ms_log_rms_mae_db": 0.49450761093536433, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04280440326513575, "1000–3000 Hz_40ms_envelope_correlation": 0.9991276563889886, "1000–3000 Hz_40ms_modulation_mae_db": 0.7497740331745377, "3000–6000 Hz_10ms_log_rms_mae_db": 1.090622916764003, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.10992284102744718, "3000–6000 Hz_10ms_envelope_correlation": 0.9930320726619902, "3000–6000 Hz_10ms_modulation_mae_db": 0.8858398731158245, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7853277704862949, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.063760343719554, "3000–6000 Hz_40ms_envelope_correlation": 0.9983432062654533, "3000–6000 Hz_40ms_modulation_mae_db": 0.9640111714322727, "mr_stft_db": 5.347149235523254, "band_mae_db": 1.2906138805188851, "rms_gain_error_db": -0.10054887240817051, "output_peak": 0.23430051749120862}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.306924110064865, "全帯域_10ms_rms_envelope_nrmse": 0.05643781519452852, "全帯域_10ms_envelope_correlation": 0.9973270260562931, "全帯域_10ms_modulation_mae_db": 0.21377069092596615, "全帯域_40ms_log_rms_mae_db": 0.6920125214676109, "全帯域_40ms_rms_envelope_nrmse": 0.025765826329011022, "全帯域_40ms_envelope_correlation": 0.9994504680039531, "全帯域_40ms_modulation_mae_db": 0.25015031399043536, "300–1000 Hz_10ms_log_rms_mae_db": 0.8260190802990328, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07366113526603679, "300–1000 Hz_10ms_envelope_correlation": 0.9957403781669242, "300–1000 Hz_10ms_modulation_mae_db": 0.755826969107429, "300–1000 Hz_40ms_log_rms_mae_db": 0.5664955865705241, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03774415324019668, "300–1000 Hz_40ms_envelope_correlation": 0.9988668293129639, "300–1000 Hz_40ms_modulation_mae_db": 1.2461915443968552, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7577548177807736, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05811183672030368, "1000–3000 Hz_10ms_envelope_correlation": 0.9978611139072364, "1000–3000 Hz_10ms_modulation_mae_db": 0.5807408347750679, "1000–3000 Hz_40ms_log_rms_mae_db": 0.47380886755082785, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03342358082867459, "1000–3000 Hz_40ms_envelope_correlation": 0.9992877478755577, "1000–3000 Hz_40ms_modulation_mae_db": 0.660613754909758, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0357238937123094, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.10557486903701498, "3000–6000 Hz_10ms_envelope_correlation": 0.9936010751690518, "3000–6000 Hz_10ms_modulation_mae_db": 0.5817241894548668, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7586728442606879, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06558595633465805, "3000–6000 Hz_40ms_envelope_correlation": 0.9981108347968004, "3000–6000 Hz_40ms_modulation_mae_db": 0.5775214153866507, "mr_stft_db": 5.356662898356521, "band_mae_db": 1.1993818043649955, "rms_gain_error_db": -0.06134365640162658, "output_peak": 0.21231060988557768}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2698787056268601, "全帯域_10ms_rms_envelope_nrmse": 0.05221353800169228, "全帯域_10ms_envelope_correlation": 0.9976914019274176, "全帯域_10ms_modulation_mae_db": 0.4564942300915266, "全帯域_40ms_log_rms_mae_db": 0.7499364146707573, "全帯域_40ms_rms_envelope_nrmse": 0.025711430842947552, "全帯域_40ms_envelope_correlation": 0.9994178067903627, "全帯域_40ms_modulation_mae_db": 0.5301637504057541, "300–1000 Hz_10ms_log_rms_mae_db": 0.7795905740692974, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06960319373923884, "300–1000 Hz_10ms_envelope_correlation": 0.9962129629960693, "300–1000 Hz_10ms_modulation_mae_db": 0.5261935253141911, "300–1000 Hz_40ms_log_rms_mae_db": 0.5576585182750086, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038852688074453114, "300–1000 Hz_40ms_envelope_correlation": 0.9987819748029292, "300–1000 Hz_40ms_modulation_mae_db": 1.0300430809493992, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7515307261670908, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05950200531719552, "1000–3000 Hz_10ms_envelope_correlation": 0.9977497530065355, "1000–3000 Hz_10ms_modulation_mae_db": 0.3798028680097853, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4773752832032225, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.036400104859715586, "1000–3000 Hz_40ms_envelope_correlation": 0.9991476812594625, "1000–3000 Hz_40ms_modulation_mae_db": 0.67648539521569, "3000–6000 Hz_10ms_log_rms_mae_db": 1.055045701988192, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.09443281779105293, "3000–6000 Hz_10ms_envelope_correlation": 0.9944013104143138, "3000–6000 Hz_10ms_modulation_mae_db": 0.49699487503762924, "3000–6000 Hz_40ms_log_rms_mae_db": 0.734103541816603, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0508445094628945, "3000–6000 Hz_40ms_envelope_correlation": 0.998500424960176, "3000–6000 Hz_40ms_modulation_mae_db": 0.8283705501173166, "mr_stft_db": 5.361382312700711, "band_mae_db": 1.165290635487212, "rms_gain_error_db": -0.025961341652086883, "output_peak": 0.2296819939726988}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2085716166734217, "全帯域_10ms_rms_envelope_nrmse": 0.06514395115997436, "全帯域_10ms_envelope_correlation": 0.9965113173540767, "全帯域_10ms_modulation_mae_db": 0.6172994163580098, "全帯域_40ms_log_rms_mae_db": 0.6798728375030009, "全帯域_40ms_rms_envelope_nrmse": 0.03406754837670344, "全帯域_40ms_envelope_correlation": 0.9991125802333213, "全帯域_40ms_modulation_mae_db": 0.7892338690347743, "300–1000 Hz_10ms_log_rms_mae_db": 0.8036581214024134, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08374452460561299, "300–1000 Hz_10ms_envelope_correlation": 0.9944700399072216, "300–1000 Hz_10ms_modulation_mae_db": 1.0003882286295251, "300–1000 Hz_40ms_log_rms_mae_db": 0.546973399861266, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.047975368705595836, "300–1000 Hz_40ms_envelope_correlation": 0.9981191092385424, "300–1000 Hz_40ms_modulation_mae_db": 1.525867519687042, "1000–3000 Hz_10ms_log_rms_mae_db": 0.703516731293327, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.052239743260700196, "1000–3000 Hz_10ms_envelope_correlation": 0.9983143606365994, "1000–3000 Hz_10ms_modulation_mae_db": 0.3309275741863844, "1000–3000 Hz_40ms_log_rms_mae_db": 0.43011815818864035, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.02878192253851264, "1000–3000 Hz_40ms_envelope_correlation": 0.9995211293235463, "1000–3000 Hz_40ms_modulation_mae_db": 0.2375182620103685, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0706158417308285, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13482684700183928, "3000–6000 Hz_10ms_envelope_correlation": 0.9892151034822514, "3000–6000 Hz_10ms_modulation_mae_db": 1.4716660809856006, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7263946897579864, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0797440347632983, "3000–6000 Hz_40ms_envelope_correlation": 0.9970878063098477, "3000–6000 Hz_40ms_modulation_mae_db": 0.5980001458680061, "mr_stft_db": 5.340830331260662, "band_mae_db": 1.2879498066653707, "rms_gain_error_db": -0.11512829492633359, "output_peak": 0.22571576169612792}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1959169973434904, "全帯域_10ms_rms_envelope_nrmse": 0.04850641423693971, "全帯域_10ms_envelope_correlation": 0.9980377756980836, "全帯域_10ms_modulation_mae_db": 0.2281460213558509, "全帯域_40ms_log_rms_mae_db": 0.6336668307111946, "全帯域_40ms_rms_envelope_nrmse": 0.026911155937639375, "全帯域_40ms_envelope_correlation": 0.9993953674244689, "全帯域_40ms_modulation_mae_db": 0.6245691779186651, "300–1000 Hz_10ms_log_rms_mae_db": 0.7883533668037699, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07367921556984651, "300–1000 Hz_10ms_envelope_correlation": 0.9957371602458138, "300–1000 Hz_10ms_modulation_mae_db": 0.47490229444088156, "300–1000 Hz_40ms_log_rms_mae_db": 0.5779632460704003, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04425937348158325, "300–1000 Hz_40ms_envelope_correlation": 0.9984043547099486, "300–1000 Hz_40ms_modulation_mae_db": 0.9292915871782244, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7484818853840784, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05620531542459442, "1000–3000 Hz_10ms_envelope_correlation": 0.998020353121999, "1000–3000 Hz_10ms_modulation_mae_db": 0.3911215876127374, "1000–3000 Hz_40ms_log_rms_mae_db": 0.46246447773959376, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03174007831547576, "1000–3000 Hz_40ms_envelope_correlation": 0.9993883218442831, "1000–3000 Hz_40ms_modulation_mae_db": 0.9100504643755619, "3000–6000 Hz_10ms_log_rms_mae_db": 1.058426410406884, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12055457521710342, "3000–6000 Hz_10ms_envelope_correlation": 0.9906776423806086, "3000–6000 Hz_10ms_modulation_mae_db": 0.40156758631801703, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7361270572042093, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07265344084395663, "3000–6000 Hz_40ms_envelope_correlation": 0.9965081465140417, "3000–6000 Hz_40ms_modulation_mae_db": 0.4540467628433414, "mr_stft_db": 5.351378243736451, "band_mae_db": 1.1712778213364536, "rms_gain_error_db": -0.05864897918795287, "output_peak": 0.2562916206632534}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.235749624957798, "全帯域_10ms_rms_envelope_nrmse": 0.05941131535558332, "全帯域_10ms_envelope_correlation": 0.9971352923369773, "全帯域_10ms_modulation_mae_db": 0.27037585594013697, "全帯域_40ms_log_rms_mae_db": 0.7020065135698583, "全帯域_40ms_rms_envelope_nrmse": 0.03429640513940434, "全帯域_40ms_envelope_correlation": 0.9991096117127967, "全帯域_40ms_modulation_mae_db": 0.3699863845984363, "300–1000 Hz_10ms_log_rms_mae_db": 0.7813753881376764, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08080653481924215, "300–1000 Hz_10ms_envelope_correlation": 0.9948509015831996, "300–1000 Hz_10ms_modulation_mae_db": 0.5029194348443621, "300–1000 Hz_40ms_log_rms_mae_db": 0.5606746042515247, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0500978515673311, "300–1000 Hz_40ms_envelope_correlation": 0.9979594738395624, "300–1000 Hz_40ms_modulation_mae_db": 0.8603256583349795, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7583100388838023, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06033829131502339, "1000–3000 Hz_10ms_envelope_correlation": 0.9977668899002783, "1000–3000 Hz_10ms_modulation_mae_db": 0.8782200024081886, "1000–3000 Hz_40ms_log_rms_mae_db": 0.48358368264723745, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.035615279782835366, "1000–3000 Hz_40ms_envelope_correlation": 0.9992814006748038, "1000–3000 Hz_40ms_modulation_mae_db": 0.7371306048827674, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0200708744343208, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12270129783491893, "3000–6000 Hz_10ms_envelope_correlation": 0.9908496905824946, "3000–6000 Hz_10ms_modulation_mae_db": 1.2178461211682239, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7284314247722479, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07062113972404947, "3000–6000 Hz_40ms_envelope_correlation": 0.9974799422760511, "3000–6000 Hz_40ms_modulation_mae_db": 0.561957692845912, "mr_stft_db": 5.350173649123925, "band_mae_db": 1.2560488166724126, "rms_gain_error_db": -0.1197609491980409, "output_peak": 0.23800165311165475}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 130065, "output_samples": 130065, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.445792021173038, "spectral_convergence": 0.17926340153999815, "spectral_convergence_status": "ok", "amplitude_floor": 8.628776010687778e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.4252765242663505, "spectral_convergence": 0.1915465701164314, "spectral_convergence_status": "ok", "amplitude_floor": 8.696913128358987e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.1888793172560845, "spectral_convergence": 0.19177982227133752, "spectral_convergence_status": "ok", "amplitude_floor": 6.997748100750841e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.5012142154628568e-06, "output_power": 9.71815879536099e-06, "delta_db": 8.111413229560636, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008569985031977355, "output_power": 0.0008284420829077752, "delta_db": -0.14717911481817608, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0002039561579698118, "output_power": 0.00020778657103453444, "delta_db": 0.0808065392499429, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00031755380447674584, "output_power": 0.00030202057015284026, "delta_db": -0.2178079711488368, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 8.391217397004902e-05, "output_power": 8.127945395854791e-05, "delta_db": -0.1384419547412086, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2641952404694477e-05, "output_power": 1.2303868785398422e-05, "delta_db": -0.11772459983818467, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.274471551779886e-06, "output_power": 2.151715554610093e-06, "delta_db": -0.2409564985021394, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.2934757011227322, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.10442998371940225, "pitch": null, "output_rms_dbfs": -28.405223151831947, "output_peak": 0.21286396204416977, "reference_rms_dbfs": -28.300793168112545, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.3533159542318245}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 130065, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 0.0001318526099400404, "log_rms_mae_db": 1.2411331942516297, "rms_envelope_nrmse": 0.06828860317917325, "envelope_correlation": 0.996133223639591, "rms_gain_error_db": -0.10443023511939989, "reference_mean_power": 0.0014814008893508253, "output_mean_power": 0.0014462040637099943}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 7.673423983742615e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002922132888675935, "output_power": 0.00028512433312989204, "reference_active": true, "delta_db": -0.1066567975942738}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.0438146457063534e-05, "output_power": 2.777300801154431e-05, "reference_active": true, "delta_db": -0.3979528293409628}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.705913608511969e-06, "output_power": 3.8126068520504967e-06, "reference_active": true, "delta_db": -1.7510316779659776}], "active_band_count": 3, "active_band_mae_db": 0.7518804349670715}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 0.00011771272815729935, "log_rms_mae_db": 0.6909482285669047, "rms_envelope_nrmse": 0.037529763995703555, "envelope_correlation": 0.9988647208847088, "rms_gain_error_db": -0.10443011121888818, "reference_mean_power": 0.001489661173505724, "output_mean_power": 0.0014542681320253124}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 7.348414354743223e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000259482167884596, "output_power": 0.000253825235569886, "reference_active": true, "delta_db": -0.0957271973894667}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3907004138768798e-05, "output_power": 1.2842061001866275e-05, "reference_active": true, "delta_db": -0.3459885534622417}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.4011744172060643e-07, "output_power": 2.853909380595984e-07, "reference_active": true, "delta_db": -1.881284008988082}], "active_band_count": 3, "active_band_mae_db": 0.7743332532799302}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 8.480086855572389e-05, "log_rms_mae_db": 0.8161191932409517, "rms_envelope_nrmse": 0.07273228521859923, "envelope_correlation": 0.9958813258616334, "rms_gain_error_db": 0.05111502253769398, "reference_mean_power": 0.0005471873658289661, "output_mean_power": 0.0005536656286678162}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 3.0613556922446793e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0001155073862142863, "output_power": 0.00011342007778251504, "reference_active": true, "delta_db": -0.07919815646483501}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3854221447460866e-05, "output_power": 1.125073041078986e-05, "reference_active": true, "delta_db": -0.9040140689241969}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9357817767829245e-06, "output_power": 1.5911168925830473e-06, "reference_active": true, "delta_db": -0.8515431056057363}], "active_band_count": 3, "active_band_mae_db": 0.6115851103315894}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.44475219971024e-05, "log_rms_mae_db": 0.5845814610089891, "rms_envelope_nrmse": 0.04041792610004959, "envelope_correlation": 0.998695794528871, "rms_gain_error_db": 0.05111499890302163, "reference_mean_power": 0.0005502385876291546, "output_mean_power": 0.000556752971475386}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.936750998626233e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.910211940271478e-05, "output_power": 9.788957542335409e-05, "reference_active": true, "delta_db": -0.053464975820485275}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.231208448817648e-06, "output_power": 5.2840719743742955e-06, "reference_active": true, "delta_db": -0.7160355517594651}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.518968227553501e-07, "output_power": 1.4731757363442147e-07, "reference_active": true, "delta_db": -2.329681323770427}], "active_band_count": 3, "active_band_mae_db": 1.0330606171167924}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 7.92844222433349e-05, "log_rms_mae_db": 0.7638519266394479, "rms_envelope_nrmse": 0.06741658638827627, "envelope_correlation": 0.9973667626848982, "rms_gain_error_db": -0.19496623230952514, "reference_mean_power": 0.0003517587960046477, "output_mean_power": 0.0003363166302208887}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 1.184446345593241e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.4086641780542994e-05, "output_power": 3.2281258523948435e-05, "reference_active": true, "delta_db": -0.23633758723074866}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.908924984845658e-06, "output_power": 7.854210137442974e-06, "reference_active": true, "delta_db": -0.5472278556246402}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.00669572393549e-07, "output_power": 5.59100751110355e-07, "reference_active": true, "delta_db": -0.31145557117755385}], "active_band_count": 3, "active_band_mae_db": 0.36500700467764763}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.287723098191666e-05, "log_rms_mae_db": 0.4719112618131823, "rms_envelope_nrmse": 0.048183835322655855, "envelope_correlation": 0.9987738291526645, "rms_gain_error_db": -0.19496622856354562, "reference_mean_power": 0.0003537202709185465, "output_mean_power": 0.00033819199693071355}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 1.1592322619199725e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.0388893978542697e-05, "output_power": 2.8922348297396822e-05, "reference_active": true, "delta_db": -0.21481342163910516}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.277692934034562e-06, "output_power": 3.780008181692677e-06, "reference_active": true, "delta_db": -0.5371686650658093}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.6389202390485585e-08, "output_power": 5.666151551952823e-08, "reference_active": true, "delta_db": 0.020922347103968578}], "active_band_count": 3, "active_band_mae_db": 0.2576348112696277}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 3.178621250284737e-05, "log_rms_mae_db": 1.064013161463481, "rms_envelope_nrmse": 0.10487798695206715, "envelope_correlation": 0.9932244787910091, "rms_gain_error_db": -0.23898353667043382, "reference_mean_power": 4.4150646761510114e-05, "output_mean_power": 4.1786761683261686e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 2.2237128168975068e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.193805277966022e-06, "output_power": 8.721775686194626e-06, "reference_active": true, "delta_db": -0.22890388346915863}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0890347422283183e-06, "output_power": 9.464240622515122e-07, "reference_active": true, "delta_db": -0.6095596134514997}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8576888047519497e-07, "output_power": 1.3639517300168773e-07, "reference_active": true, "delta_db": -1.3417396286031167}], "active_band_count": 3, "active_band_mae_db": 0.7267343751745917}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 2.883918900864625e-05, "log_rms_mae_db": 0.7415008279281753, "rms_envelope_nrmse": 0.0593452181128332, "envelope_correlation": 0.9980931510280152, "rms_gain_error_db": -0.2389835084979662, "reference_mean_power": 4.439683700027618e-05, "output_mean_power": 4.201977083771924e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.1738925168287815e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.247468496821311e-06, "output_power": 7.882503370274394e-06, "reference_active": true, "delta_db": -0.19656500220241832}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.957219370502507e-07, "output_power": 4.478120027829276e-07, "reference_active": true, "delta_db": -0.44142408178435244}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6536836687109635e-08, "output_power": 9.859095749792875e-09, "reference_active": true, "delta_db": -2.2461535303265916}], "active_band_count": 3, "active_band_mae_db": 0.9613808714377875}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8790946673193699, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "5275e120fafda918111b92628f66432dce0f490c23811e8f7e01b10c4f790079", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9977072439105604, "standard_deviation": 0.0003749178812632416, "minimum": 0.9971819063637997, "maximum": 0.9983143606365994, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.7527141453840857, "standard_deviation": 0.02166053316300692, "minimum": 0.703516731293327, "maximum": 0.7770261929536465, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5134762014591665, "standard_deviation": 0.19998598495333272, "minimum": 0.3309275741863844, "maximum": 0.8782200024081886, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06093349626271015, "standard_deviation": 0.005810697498674717, "minimum": 0.052239743260700196, "maximum": 0.06970352725021178, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9991874084038495, "standard_deviation": 0.00023708072684343548, "minimum": 0.9987738291526645, "maximum": 0.9995211293235463, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.4751501178422345, "standard_deviation": 0.02297195508730948, "minimum": 0.43011815818864035, "maximum": 0.5074316006598076, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5699076028897442, "standard_deviation": 0.2566615407453759, "minimum": 0.2375182620103685, "maximum": 0.9100504643755619, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03709742208654501, "standard_deviation": 0.0062902973495944405, "minimum": 0.02878192253851264, "maximum": 0.048183835322655855, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9918687030544686, "standard_deviation": 0.0019195798937947737, "minimum": 0.9892151034822514, "maximum": 0.9944013104143138, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.0598374870882568, "standard_deviation": 0.023487882528788494, "minimum": 1.0200708744343208, "maximum": 1.090622916764003, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.8854610333924436, "standard_deviation": 0.40170352502678186, "minimum": 0.40156758631801703, "maximum": 1.4716660809856006, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.11495257366601844, "standard_deviation": 0.013421207564511026, "minimum": 0.09443281779105293, "maximum": 0.13482684700183928, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9975922909315955, "standard_deviation": 0.0007843363442721545, "minimum": 0.9965081465140417, "maximum": 0.998500424960176, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7481194202636411, "standard_deviation": 0.022135964815892487, "minimum": 0.7263946897579864, "maximum": 0.7853277704862949, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7148616944604359, "standard_deviation": 0.19387228212608812, "minimum": 0.4540467628433414, "maximum": 0.9640111714322727, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06734887199422168, "standard_deviation": 0.00944087673489943, "minimum": 0.0508445094628945, "maximum": 0.0797440347632983, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9954913973615548, "standard_deviation": 0.0006682539936010507, "minimum": 0.9944700399072216, "maximum": 0.9962129629960693, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.7956483093192727, "standard_deviation": 0.020304047723860328, "minimum": 0.7657982951417378, "maximum": 0.8260190802990328, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6249652982343608, "standard_deviation": 0.18429553936974696, "minimum": 0.4523898059828176, "maximum": 1.0003882286295251, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07554539673230265, "standard_deviation": 0.005413423660947794, "minimum": 0.06960319373923884, "maximum": 0.08374452460561299, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.998505790171585, "standard_deviation": 0.00032554214362063953, "minimum": 0.9979594738395624, "maximum": 0.9988668293129639, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5655423738492578, "standard_deviation": 0.012843290059033702, "minimum": 0.546973399861266, "maximum": 0.5845814610089891, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.0779141123964822, "standard_deviation": 0.21786042896324204, "minimum": 0.8603256583349795, "maximum": 1.525867519687042, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04271260633056733, "standard_deviation": 0.0044463233631365255, "minimum": 0.03774415324019668, "maximum": 0.0500978515673311, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.2490699890772037, "standard_deviation": 0.06223246472131784, "minimum": 1.165290635487212, "maximum": 1.3285214464495685, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.350416088123148, "standard_deviation": 0.006916998239043507, "minimum": 5.340830331260662, "maximum": 5.361382312700711, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.22713751650325578, "standard_deviation": 0.016125142951497813, "minimum": 0.20793401316135526, "maximum": 0.2562916206632534, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.08207560293529843, "standard_deviation": 0.0329688273562099, "minimum": -0.1197609491980409, "maximum": -0.025961341652086883, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9971182963973004, "standard_deviation": 0.0006052782306167178, "minimum": 0.996133223639591, "maximum": 0.9980377756980836, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.2491645139273229, "standard_deviation": 0.03619856623026969, "minimum": 1.1959169973434904, "maximum": 1.306924110064865, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.40331711909571166, "standard_deviation": 0.19826883192147274, "minimum": 0.21377069092596615, "maximum": 0.7518804349670715, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05863270828009923, "standard_deviation": 0.006397424503268898, "minimum": 0.04850641423693971, "maximum": 0.06828860317917325, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9991963916544242, "standard_deviation": 0.00020497210347838275, "minimum": 0.9988647208847088, "maximum": 0.9994504680039531, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.702889920303506, "standard_deviation": 0.03833819605664079, "minimum": 0.6336668307111946, "maximum": 0.7499364146707573, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5438933065760445, "standard_deviation": 0.18999998519502223, "minimum": 0.25015031399043536, "maximum": 0.7892338690347743, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.031288202160251355, "standard_deviation": 0.004510747198916733, "minimum": 0.025711430842947552, "maximum": 0.037529763995703555, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_falset10_BASIC5000_1728", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 1.6955037117004395, "predicted_mos": 1.6955037117004395, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 130065, "input_sample_rate": 24000, "input_seconds": 5.419375, "input_float32_sha256": "35e6b592746ea2dd77da55c7e07f5c0cf26afe81b8ab948d66fb5414580ff734", "internal_samples": 86710, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.4989590998739}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2478844696644837, "全帯域_10ms_rms_envelope_nrmse": 0.05306636444315696, "全帯域_10ms_envelope_correlation": 0.9977074547934219, "全帯域_10ms_modulation_mae_db": 0.22439377885116463, "全帯域_40ms_log_rms_mae_db": 0.6876085418751573, "全帯域_40ms_rms_envelope_nrmse": 0.028409018464918914, "全帯域_40ms_envelope_correlation": 0.9994010526671495, "全帯域_40ms_modulation_mae_db": 0.4881421051414699, "300–1000 Hz_10ms_log_rms_mae_db": 0.777268238526919, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07153504788182369, "300–1000 Hz_10ms_envelope_correlation": 0.9959988348446804, "300–1000 Hz_10ms_modulation_mae_db": 0.37922568049188804, "300–1000 Hz_40ms_log_rms_mae_db": 0.5488893702268496, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04207173061004382, "300–1000 Hz_40ms_envelope_correlation": 0.9986192605750406, "300–1000 Hz_40ms_modulation_mae_db": 0.9436645604959315, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8066479798627006, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05926094354966475, "1000–3000 Hz_10ms_envelope_correlation": 0.9978474098535495, "1000–3000 Hz_10ms_modulation_mae_db": 0.6656656640772908, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5298429116933819, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.033122581521538096, "1000–3000 Hz_40ms_envelope_correlation": 0.9993868331313291, "1000–3000 Hz_40ms_modulation_mae_db": 0.5792377461173418, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1129031476356581, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12874327264061855, "3000–6000 Hz_10ms_envelope_correlation": 0.9893536436050474, "3000–6000 Hz_10ms_modulation_mae_db": 0.5035039781961514, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7764974730077515, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06109823982157371, "3000–6000 Hz_40ms_envelope_correlation": 0.9976759695742, "3000–6000 Hz_40ms_modulation_mae_db": 0.5876779312125141, "mr_stft_db": 5.436527892286386, "band_mae_db": 0.996366155019277, "rms_gain_error_db": -0.1031907128552751, "output_peak": 0.21612622755915883}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.233255519635448, "全帯域_10ms_rms_envelope_nrmse": 0.061450211750261295, "全帯域_10ms_envelope_correlation": 0.9968680916176373, "全帯域_10ms_modulation_mae_db": 0.6548011764333838, "全帯域_40ms_log_rms_mae_db": 0.7112040185253389, "全帯域_40ms_rms_envelope_nrmse": 0.03336682895011881, "全帯域_40ms_envelope_correlation": 0.9991027605996067, "全帯域_40ms_modulation_mae_db": 0.8003537157121352, "300–1000 Hz_10ms_log_rms_mae_db": 0.8161199872795794, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08074370410360959, "300–1000 Hz_10ms_envelope_correlation": 0.9948334328955383, "300–1000 Hz_10ms_modulation_mae_db": 0.5190664996337578, "300–1000 Hz_40ms_log_rms_mae_db": 0.5621503931655523, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04881806432263362, "300–1000 Hz_40ms_envelope_correlation": 0.9980361980554722, "300–1000 Hz_40ms_modulation_mae_db": 1.0428821032435298, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7982595661112437, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06191490565811457, "1000–3000 Hz_10ms_envelope_correlation": 0.9976902482840501, "1000–3000 Hz_10ms_modulation_mae_db": 0.6894006815217347, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4883442594505817, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03744190583863893, "1000–3000 Hz_40ms_envelope_correlation": 0.9992359051696548, "1000–3000 Hz_40ms_modulation_mae_db": 0.7790389803854786, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1263938331142682, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11449987842401971, "3000–6000 Hz_10ms_envelope_correlation": 0.991763553525146, "3000–6000 Hz_10ms_modulation_mae_db": 0.36540993148382545, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7890055703959159, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06637025941271184, "3000–6000 Hz_40ms_envelope_correlation": 0.997410691040561, "3000–6000 Hz_40ms_modulation_mae_db": 0.6446789269887174, "mr_stft_db": 5.423552494612014, "band_mae_db": 1.2155638431499696, "rms_gain_error_db": -0.09435549278127167, "output_peak": 0.21032187309319186}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2540262168361893, "全帯域_10ms_rms_envelope_nrmse": 0.06540087792366647, "全帯域_10ms_envelope_correlation": 0.9964623531770859, "全帯域_10ms_modulation_mae_db": 0.4337357386971936, "全帯域_40ms_log_rms_mae_db": 0.7387331834549887, "全帯域_40ms_rms_envelope_nrmse": 0.03573410750060521, "全帯域_40ms_envelope_correlation": 0.9989841610865862, "全帯域_40ms_modulation_mae_db": 0.5968441076790798, "300–1000 Hz_10ms_log_rms_mae_db": 0.7930855715294032, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0722497448042838, "300–1000 Hz_10ms_envelope_correlation": 0.9959088745077186, "300–1000 Hz_10ms_modulation_mae_db": 0.4577822494770907, "300–1000 Hz_40ms_log_rms_mae_db": 0.5403047440232095, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.040712700037324925, "300–1000 Hz_40ms_envelope_correlation": 0.9986572270964359, "300–1000 Hz_40ms_modulation_mae_db": 0.8840283383026573, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8106406963948443, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06587640973584652, "1000–3000 Hz_10ms_envelope_correlation": 0.9973240395821806, "1000–3000 Hz_10ms_modulation_mae_db": 0.4308956666582621, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4855216406136007, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03901436115976246, "1000–3000 Hz_40ms_envelope_correlation": 0.9991159482716273, "1000–3000 Hz_40ms_modulation_mae_db": 0.7261040153390489, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1592653687615253, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13636355315555768, "3000–6000 Hz_10ms_envelope_correlation": 0.9902547721493389, "3000–6000 Hz_10ms_modulation_mae_db": 0.8262457142566667, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8085320277601173, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1017171202866515, "3000–6000 Hz_40ms_envelope_correlation": 0.9957783526374858, "3000–6000 Hz_40ms_modulation_mae_db": 1.361117351685414, "mr_stft_db": 5.426187819429941, "band_mae_db": 1.2112558156435898, "rms_gain_error_db": -0.10616768698201497, "output_peak": 0.22682464288431828}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1930960138416866, "全帯域_10ms_rms_envelope_nrmse": 0.07284451578761322, "全帯域_10ms_envelope_correlation": 0.9955968341839269, "全帯域_10ms_modulation_mae_db": 0.41015685569569377, "全帯域_40ms_log_rms_mae_db": 0.657732988699173, "全帯域_40ms_rms_envelope_nrmse": 0.03836536464825276, "全帯域_40ms_envelope_correlation": 0.9988345621233682, "全帯域_40ms_modulation_mae_db": 0.696470222485638, "300–1000 Hz_10ms_log_rms_mae_db": 0.8055000881475506, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07769765938940093, "300–1000 Hz_10ms_envelope_correlation": 0.9952689833707915, "300–1000 Hz_10ms_modulation_mae_db": 0.24470528454188356, "300–1000 Hz_40ms_log_rms_mae_db": 0.5607196154828364, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043803586074539054, "300–1000 Hz_40ms_envelope_correlation": 0.9984490782194246, "300–1000 Hz_40ms_modulation_mae_db": 0.5814797864373696, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7770628729822789, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06475897003484103, "1000–3000 Hz_10ms_envelope_correlation": 0.9975307719222374, "1000–3000 Hz_10ms_modulation_mae_db": 0.5456571912971789, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5121281421684218, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.039090858577165884, "1000–3000 Hz_40ms_envelope_correlation": 0.9992417054852016, "1000–3000 Hz_40ms_modulation_mae_db": 0.7784930087333738, "3000–6000 Hz_10ms_log_rms_mae_db": 1.120690031939464, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11762839637269024, "3000–6000 Hz_10ms_envelope_correlation": 0.991348572449573, "3000–6000 Hz_10ms_modulation_mae_db": 0.9311177787029402, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7923641036895716, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.059231896264117144, "3000–6000 Hz_40ms_envelope_correlation": 0.9981051801645843, "3000–6000 Hz_40ms_modulation_mae_db": 0.43001221002334716, "mr_stft_db": 5.429091788587797, "band_mae_db": 1.2633838580748866, "rms_gain_error_db": -0.11502458230278217, "output_peak": 0.21168867329501256}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.192185778151989, "全帯域_10ms_rms_envelope_nrmse": 0.05766901256818478, "全帯域_10ms_envelope_correlation": 0.9972915274728769, "全帯域_10ms_modulation_mae_db": 0.22555016122301144, "全帯域_40ms_log_rms_mae_db": 0.6407570443492986, "全帯域_40ms_rms_envelope_nrmse": 0.03288656864110602, "全帯域_40ms_envelope_correlation": 0.9991757898907874, "全帯域_40ms_modulation_mae_db": 0.15268343680246707, "300–1000 Hz_10ms_log_rms_mae_db": 0.8770913040118616, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06943004181823537, "300–1000 Hz_10ms_envelope_correlation": 0.9962065459853373, "300–1000 Hz_10ms_modulation_mae_db": 0.6160734792352404, "300–1000 Hz_40ms_log_rms_mae_db": 0.6606409297194917, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04244756957806542, "300–1000 Hz_40ms_envelope_correlation": 0.9985256149814983, "300–1000 Hz_40ms_modulation_mae_db": 0.721367132729274, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8058026844544004, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06599503830761795, "1000–3000 Hz_10ms_envelope_correlation": 0.9973103760266808, "1000–3000 Hz_10ms_modulation_mae_db": 0.7290816995194443, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5017895260910917, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03708377168732762, "1000–3000 Hz_40ms_envelope_correlation": 0.9992017746770432, "1000–3000 Hz_40ms_modulation_mae_db": 0.5275759173909482, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1062410237186981, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13611582952883627, "3000–6000 Hz_10ms_envelope_correlation": 0.9881732746116995, "3000–6000 Hz_10ms_modulation_mae_db": 1.465694710725714, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7657586074703185, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06327562520525698, "3000–6000 Hz_40ms_envelope_correlation": 0.9976649792615838, "3000–6000 Hz_40ms_modulation_mae_db": 0.896131474471928, "mr_stft_db": 5.430955596592763, "band_mae_db": 1.2177398916524467, "rms_gain_error_db": -0.10908448393145231, "output_peak": 0.23061971765601993}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1809894431927044, "全帯域_10ms_rms_envelope_nrmse": 0.057356600193903935, "全帯域_10ms_envelope_correlation": 0.9972212868026173, "全帯域_10ms_modulation_mae_db": 0.5843208159768943, "全帯域_40ms_log_rms_mae_db": 0.6045072784426359, "全帯域_40ms_rms_envelope_nrmse": 0.028609458178262114, "全帯域_40ms_envelope_correlation": 0.9992846375212521, "全帯域_40ms_modulation_mae_db": 0.7503324446545471, "300–1000 Hz_10ms_log_rms_mae_db": 0.7607698722210984, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07765688135473521, "300–1000 Hz_10ms_envelope_correlation": 0.9952717832260296, "300–1000 Hz_10ms_modulation_mae_db": 0.7104030275165852, "300–1000 Hz_40ms_log_rms_mae_db": 0.5034191347353539, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04298066514304407, "300–1000 Hz_40ms_envelope_correlation": 0.9985017371213278, "300–1000 Hz_40ms_modulation_mae_db": 1.1979891322763818, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7987764317554102, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06222542650831048, "1000–3000 Hz_10ms_envelope_correlation": 0.9975812681021914, "1000–3000 Hz_10ms_modulation_mae_db": 0.6313646502212517, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4991998054079394, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.035191264853805165, "1000–3000 Hz_40ms_envelope_correlation": 0.9992521103515154, "1000–3000 Hz_40ms_modulation_mae_db": 1.1024085764071374, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1242618210661928, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1396925712034076, "3000–6000 Hz_10ms_envelope_correlation": 0.9874481484238993, "3000–6000 Hz_10ms_modulation_mae_db": 0.6901643945385129, "3000–6000 Hz_40ms_log_rms_mae_db": 0.779800412478112, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08946592668861468, "3000–6000 Hz_40ms_envelope_correlation": 0.994696256514025, "3000–6000 Hz_40ms_modulation_mae_db": 0.45661475788941375, "mr_stft_db": 5.423069088448805, "band_mae_db": 1.0900426886817678, "rms_gain_error_db": -0.03374510332812435, "output_peak": 0.22674653834574526}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2381560320044669, "全帯域_10ms_rms_envelope_nrmse": 0.0744291166517725, "全帯域_10ms_envelope_correlation": 0.9954731191575101, "全帯域_10ms_modulation_mae_db": 0.0696908206365061, "全帯域_40ms_log_rms_mae_db": 0.6862022759302154, "全帯域_40ms_rms_envelope_nrmse": 0.05240905092040242, "全帯域_40ms_envelope_correlation": 0.9977696627569892, "全帯域_40ms_modulation_mae_db": 0.26481233163448603, "300–1000 Hz_10ms_log_rms_mae_db": 0.7978772910420288, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07046870755382523, "300–1000 Hz_10ms_envelope_correlation": 0.9961120115530173, "300–1000 Hz_10ms_modulation_mae_db": 0.5253850347732031, "300–1000 Hz_40ms_log_rms_mae_db": 0.5699943754974707, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038811137311729055, "300–1000 Hz_40ms_envelope_correlation": 0.998792889776142, "300–1000 Hz_40ms_modulation_mae_db": 0.4794626420547579, "1000–3000 Hz_10ms_log_rms_mae_db": 0.795274016342103, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05618458486633245, "1000–3000 Hz_10ms_envelope_correlation": 0.9980900379744517, "1000–3000 Hz_10ms_modulation_mae_db": 0.3446288189344738, "1000–3000 Hz_40ms_log_rms_mae_db": 0.496333530788804, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03370068518759012, "1000–3000 Hz_40ms_envelope_correlation": 0.9993770017153492, "1000–3000 Hz_40ms_modulation_mae_db": 0.6881332616178075, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0954815291165292, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12291297105044305, "3000–6000 Hz_10ms_envelope_correlation": 0.9908676031813684, "3000–6000 Hz_10ms_modulation_mae_db": 0.6592710780671324, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7427538343785894, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07531011388167366, "3000–6000 Hz_40ms_envelope_correlation": 0.9970644323039833, "3000–6000 Hz_40ms_modulation_mae_db": 0.33509700551408533, "mr_stft_db": 5.4313813134996245, "band_mae_db": 1.25603178966669, "rms_gain_error_db": -0.14703554672297886, "output_peak": 0.2388161857151247}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1827610424124593, "全帯域_10ms_rms_envelope_nrmse": 0.06566972884130225, "全帯域_10ms_envelope_correlation": 0.9964425440529724, "全帯域_10ms_modulation_mae_db": 0.5676198960948852, "全帯域_40ms_log_rms_mae_db": 0.651539807164336, "全帯域_40ms_rms_envelope_nrmse": 0.03322999504763501, "全帯域_40ms_envelope_correlation": 0.9991524683756288, "全帯域_40ms_modulation_mae_db": 0.7457776841258236, "300–1000 Hz_10ms_log_rms_mae_db": 0.8363697390944387, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06744972911407274, "300–1000 Hz_10ms_envelope_correlation": 0.9963935911312055, "300–1000 Hz_10ms_modulation_mae_db": 0.2217860319345766, "300–1000 Hz_40ms_log_rms_mae_db": 0.5602972379908393, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03695575764647342, "300–1000 Hz_40ms_envelope_correlation": 0.9988706486554892, "300–1000 Hz_40ms_modulation_mae_db": 0.7716116971017738, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7828962693439406, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05819326707175286, "1000–3000 Hz_10ms_envelope_correlation": 0.9980824698070665, "1000–3000 Hz_10ms_modulation_mae_db": 0.5855266456250298, "1000–3000 Hz_40ms_log_rms_mae_db": 0.49822933315652745, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03661951453318562, "1000–3000 Hz_40ms_envelope_correlation": 0.9993906622979541, "1000–3000 Hz_40ms_modulation_mae_db": 0.7152680420170915, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1145742336332867, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12296081283332964, "3000–6000 Hz_10ms_envelope_correlation": 0.9910271416271182, "3000–6000 Hz_10ms_modulation_mae_db": 0.460352136251074, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7682538840533081, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07279271138351893, "3000–6000 Hz_40ms_envelope_correlation": 0.997526231157184, "3000–6000 Hz_40ms_modulation_mae_db": 0.7773963948237718, "mr_stft_db": 5.429381574967223, "band_mae_db": 1.3031315823709273, "rms_gain_error_db": -0.1099690626637654, "output_peak": 0.22702025234201978}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 130065, "output_samples": 130065, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.564556337776826, "spectral_convergence": 0.16241046600044387, "spectral_convergence_status": "ok", "amplitude_floor": 8.628776010687778e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.4968633761758765, "spectral_convergence": 0.17733814243892834, "spectral_convergence_status": "ok", "amplitude_floor": 8.696913128358987e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.248163962906458, "spectral_convergence": 0.17367789497230143, "spectral_convergence_status": "ok", "amplitude_floor": 6.997748100750841e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.5012142154628568e-06, "output_power": 6.214128307001794e-06, "delta_db": 6.169375479322715, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008569985031977355, "output_power": 0.000827204482167334, "delta_db": -0.15367184441178758, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0002039561579698118, "output_power": 0.00020708914096607327, "delta_db": 0.0662050426183912, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00031755380447674584, "output_power": 0.0003096289700272323, "delta_db": -0.10975732099535716, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 8.391217397004902e-05, "output_power": 7.974093696016778e-05, "delta_db": -0.22143638461779974, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2641952404694477e-05, "output_power": 1.1971426836263613e-05, "delta_db": -0.23668235264192372, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.274471551779886e-06, "output_power": 2.2653590368663864e-06, "delta_db": -0.017434660526963755, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.996366155019277, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.1031907128552751, "pitch": null, "output_rms_dbfs": -28.40398388096782, "output_peak": 0.21612622755915883, "reference_rms_dbfs": -28.300793168112545, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.436527892286386}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 130065, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 0.0001318526099400404, "log_rms_mae_db": 1.2478844696644837, "rms_envelope_nrmse": 0.05306636444315696, "envelope_correlation": 0.9977074547934219, "rms_gain_error_db": -0.10319086074440938, "reference_mean_power": 0.0014814008893508253, "output_mean_power": 0.001446616835253115}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 7.673423983742615e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002922132888675935, "output_power": 0.0002838742424504767, "reference_active": true, "delta_db": -0.12573974017993017}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.0438146457063534e-05, "output_power": 3.002891996992801e-05, "reference_active": true, "delta_db": -0.058784898691022644}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.705913608511969e-06, "output_power": 5.098700735072448e-06, "reference_active": true, "delta_db": -0.48865669768254105}], "active_band_count": 3, "active_band_mae_db": 0.22439377885116463}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 0.00011771272815729935, "log_rms_mae_db": 0.6876085418751573, "rms_envelope_nrmse": 0.028409018464918914, "envelope_correlation": 0.9994010526671495, "rms_gain_error_db": -0.10319110929740201, "reference_mean_power": 0.001489661173505724, "output_mean_power": 0.0014546830804379092}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 7.348414354743223e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000259482167884596, "output_power": 0.00025283702730416094, "reference_active": true, "delta_db": -0.1126684212555744}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3907004138768798e-05, "output_power": 1.3502296258331822e-05, "reference_active": true, "delta_db": -0.12825951144923065}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.4011744172060643e-07, "output_power": 3.3206166531292184e-07, "reference_active": true, "delta_db": -1.2234983827196046}], "active_band_count": 3, "active_band_mae_db": 0.4881421051414699}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 8.480086855572389e-05, "log_rms_mae_db": 0.777268238526919, "rms_envelope_nrmse": 0.07153504788182369, "envelope_correlation": 0.9959988348446804, "rms_gain_error_db": -0.0750126146256579, "reference_mean_power": 0.0005471873658289661, "output_mean_power": 0.0005378173392859267}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 3.0613556922446793e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0001155073862142863, "output_power": 0.00011133237770646598, "reference_active": true, "delta_db": -0.15988272111852816}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3854221447460866e-05, "output_power": 1.1824218611798766e-05, "reference_active": true, "delta_db": -0.6880967460029415}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9357817767829245e-06, "output_power": 1.8108673552247443e-06, "reference_active": true, "delta_db": -0.28969757435419435}], "active_band_count": 3, "active_band_mae_db": 0.37922568049188804}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.44475219971024e-05, "log_rms_mae_db": 0.5488893702268496, "rms_envelope_nrmse": 0.04207173061004382, "envelope_correlation": 0.9986192605750406, "rms_gain_error_db": -0.07501272325965472, "reference_mean_power": 0.0005502385876291546, "output_mean_power": 0.0005408162984913396}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.936750998626233e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.910211940271478e-05, "output_power": 9.585098710175531e-05, "reference_active": true, "delta_db": -0.1448635269750322}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.231208448817648e-06, "output_power": 5.3858233005936595e-06, "reference_active": true, "delta_db": -0.6332017881654197}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.518968227553501e-07, "output_power": 1.5701091807769383e-07, "reference_active": true, "delta_db": -2.0529283663473423}], "active_band_count": 3, "active_band_mae_db": 0.9436645604959315}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 7.92844222433349e-05, "log_rms_mae_db": 0.8066479798627006, "rms_envelope_nrmse": 0.05926094354966475, "envelope_correlation": 0.9978474098535495, "rms_gain_error_db": -0.11601174819582313, "reference_mean_power": 0.0003517587960046477, "output_mean_power": 0.0003424867633803724}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 1.184446345593241e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.4086641780542994e-05, "output_power": 3.208618043915726e-05, "reference_active": true, "delta_db": -0.2626619513884517}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.908924984845658e-06, "output_power": 7.683904835574987e-06, "reference_active": true, "delta_db": -0.6424332456595948}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.00669572393549e-07, "output_power": 4.671382756595329e-07, "reference_active": true, "delta_db": -1.091901795183826}], "active_band_count": 3, "active_band_mae_db": 0.6656656640772908}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.287723098191666e-05, "log_rms_mae_db": 0.5298429116933819, "rms_envelope_nrmse": 0.033122581521538096, "envelope_correlation": 0.9993868331313291, "rms_gain_error_db": -0.11601177250908684, "reference_mean_power": 0.0003537202709185465, "output_mean_power": 0.00034439653372339026}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 1.1592322619199725e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.0388893978542697e-05, "output_power": 2.8648964555065154e-05, "reference_active": true, "delta_db": -0.25605963864725945}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.277692934034562e-06, "output_power": 3.646162161640271e-06, "reference_active": true, "delta_db": -0.6937362653350605}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.6389202390485585e-08, "output_power": 4.703316646616877e-08, "reference_active": true, "delta_db": -0.7879173343697053}], "active_band_count": 3, "active_band_mae_db": 0.5792377461173418}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 3.178621250284737e-05, "log_rms_mae_db": 1.1129031476356581, "rms_envelope_nrmse": 0.12874327264061855, "envelope_correlation": 0.9893536436050474, "rms_gain_error_db": -0.1525281978804213, "reference_mean_power": 4.4150646761510114e-05, "output_mean_power": 4.2626949074976386e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 2.2237128168975068e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.193805277966022e-06, "output_power": 8.357471181167125e-06, "reference_active": true, "delta_db": -0.41420413583294297}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0890347422283183e-06, "output_power": 1.0775584907870582e-06, "reference_active": true, "delta_db": -0.046008814316030495}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8576888047519497e-07, "output_power": 2.365935290581463e-07, "reference_active": true, "delta_db": 1.0502989844394808}], "active_band_count": 3, "active_band_mae_db": 0.5035039781961514}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 2.883918900864625e-05, "log_rms_mae_db": 0.7764974730077515, "rms_envelope_nrmse": 0.06109823982157371, "envelope_correlation": 0.9976759695742, "rms_gain_error_db": -0.15252824474773552, "reference_mean_power": 4.439683700027618e-05, "output_mean_power": 4.28646424977751e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.1738925168287815e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.247468496821311e-06, "output_power": 7.556084113100457e-06, "reference_active": true, "delta_db": -0.3802388155659169}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.957219370502507e-07, "output_power": 4.4007074773702434e-07, "reference_active": true, "delta_db": -0.5171563683015628}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6536836687109635e-08, "output_power": 1.354841766662696e-08, "reference_active": true, "delta_db": -0.8656386097700626}], "active_band_count": 3, "active_band_mae_db": 0.5876779312125141}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8753214065713, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "bec67606a475f3d0a7c66e3c8dbc0217ebe16f6ff74a9ae6441e267f86d36e39", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.997682077694051, "standard_deviation": 0.0003055571832214295, "minimum": 0.9973103760266808, "maximum": 0.9980900379744517, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.7969200646558653, "standard_deviation": 0.011715153423750943, "minimum": 0.7770628729822789, "maximum": 0.8106406963948443, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5777776272318332, "standard_deviation": 0.13254268931520205, "minimum": 0.3446288189344738, "maximum": 0.7290816995194443, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06180119321656007, "standard_deviation": 0.003667489667629835, "minimum": 0.05618458486633245, "maximum": 0.06599503830761795, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9992752426374594, "standard_deviation": 0.00010007751430422883, "minimum": 0.9991159482716273, "maximum": 0.9993906622979541, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5014236436712936, "standard_deviation": 0.014078236858022604, "minimum": 0.4855216406136007, "maximum": 0.5298429116933819, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7370324435010285, "standard_deviation": 0.17268414546433722, "minimum": 0.5275759173909482, "maximum": 1.1024085764071374, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.036408117919876734, "standard_deviation": 0.002241338505426827, "minimum": 0.033122581521538096, "maximum": 0.039090858577165884, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9900295886966488, "standard_deviation": 0.0015611844180717918, "minimum": 0.9874481484238993, "maximum": 0.991763553525146, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.1199763736232027, "standard_deviation": 0.018790400968976596, "minimum": 1.0954815291165292, "maximum": 1.1592653687615253, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7377199652777521, "standard_deviation": 0.3492864798700511, "minimum": 0.36540993148382545, "maximum": 1.465694710725714, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12736466065111285, "standard_deviation": 0.009342298985862274, "minimum": 0.11449987842401971, "maximum": 0.1396925712034076, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9969902615817009, "standard_deviation": 0.0011569165296683032, "minimum": 0.994696256514025, "maximum": 0.9981051801645843, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7778707391542106, "standard_deviation": 0.01982837374405155, "minimum": 0.7427538343785894, "maximum": 0.8085320277601173, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6860907565761489, "standard_deviation": 0.3297069737862714, "minimum": 0.33509700551408533, "maximum": 1.361117351685414, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07365773661801481, "standard_deviation": 0.014963994384380617, "minimum": 0.059231896264117144, "maximum": 0.1017171202866515, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9957492571892899, "standard_deviation": 0.0005530454848076734, "minimum": 0.9948334328955383, "maximum": 0.9963935911312055, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.80801026148161, "standard_deviation": 0.03615575204811733, "minimum": 0.7607698722210984, "maximum": 0.8770913040118616, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4593034109505282, "standard_deviation": 0.17090009511238596, "minimum": 0.2217860319345766, "maximum": 0.7104030275165852, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07340393950249832, "standard_deviation": 0.004706844276518556, "minimum": 0.06744972911407274, "maximum": 0.08074370410360959, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9985565818101039, "standard_deviation": 0.0002549119449850956, "minimum": 0.9980361980554722, "maximum": 0.9988706486554892, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5633019751052004, "standard_deviation": 0.04449596107401427, "minimum": 0.5034191347353539, "maximum": 0.6606409297194917, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8278106740802095, "standard_deviation": 0.2379628330687585, "minimum": 0.4794626420547579, "maximum": 1.1979891322763818, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.042075151340481676, "standard_deviation": 0.0035482647133916216, "minimum": 0.03695575764647342, "maximum": 0.04881806432263362, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.1941894530324444, "standard_deviation": 0.1012522183465988, "minimum": 0.996366155019277, "maximum": 1.3031315823709273, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.42876844605307, "standard_deviation": 0.004450499930010224, "minimum": 5.423069088448805, "maximum": 5.436527892286386, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.2235205138613239, "standard_deviation": 0.009905272645103987, "minimum": 0.21032187309319186, "maximum": 0.2388161857151247, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.10232158394595811, "standard_deviation": 0.031728008305931, "minimum": -0.14703554672297886, "maximum": -0.03374510332812435, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9966329014072561, "standard_deviation": 0.0007994478328192878, "minimum": 0.9954731191575101, "maximum": 0.9977074547934219, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.2152943144674284, "standard_deviation": 0.030867339377668664, "minimum": 1.1809894431927044, "maximum": 1.2540262168361893, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.39628365545109157, "standard_deviation": 0.2065012796421712, "minimum": 0.0696908206365061, "maximum": 0.6548011764333838, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.06348580351998268, "standard_deviation": 0.007558242164375641, "minimum": 0.05306636444315696, "maximum": 0.0744291166517725, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.998963136877671, "standard_deviation": 0.0005122847098848944, "minimum": 0.9977696627569892, "maximum": 0.9994010526671495, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.672285642305143, "standard_deviation": 0.04240705496354683, "minimum": 0.6045072784426359, "maximum": 0.7387331834549887, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5619270060294559, "standard_deviation": 0.2410298435599166, "minimum": 0.15268343680246707, "maximum": 0.8003537157121352, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03537629904391266, "standard_deviation": 0.007637816244686751, "minimum": 0.028409018464918914, "maximum": 0.05240905092040242, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_falset10_BASIC5000_1728", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 1.684023380279541, "predicted_mos": 1.684023380279541, "model": "UTMOSv2", "language": "ja", "style": "falsetto", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 130065, "input_sample_rate": 24000, "input_seconds": 5.419375, "input_float32_sha256": "1c89d3fe286b16dfbf9b358dac7cdae6c8485757cee35017cdf41ddcdab2d95f", "internal_samples": 86710, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 8.312421599868685}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2272082312124544, "全帯域_10ms_rms_envelope_nrmse": 0.07559511577551314, "全帯域_10ms_envelope_correlation": 0.9951880557937465, "全帯域_10ms_modulation_mae_db": 0.4043188402391629, "全帯域_40ms_log_rms_mae_db": 0.7243176567079267, "全帯域_40ms_rms_envelope_nrmse": 0.03396489943030817, "全帯域_40ms_envelope_correlation": 0.9990442524258738, "全帯域_40ms_modulation_mae_db": 0.97236466043298, "300–1000 Hz_10ms_log_rms_mae_db": 0.797163048079647, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09012771308786607, "300–1000 Hz_10ms_envelope_correlation": 0.9935554685072145, "300–1000 Hz_10ms_modulation_mae_db": 0.45904004813552296, "300–1000 Hz_40ms_log_rms_mae_db": 0.5504094496161982, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.052837229356785746, "300–1000 Hz_40ms_envelope_correlation": 0.9977047664855332, "300–1000 Hz_40ms_modulation_mae_db": 1.0714776458697666, "1000–3000 Hz_10ms_log_rms_mae_db": 0.822292369460996, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05793951690846307, "1000–3000 Hz_10ms_envelope_correlation": 0.997874176654186, "1000–3000 Hz_10ms_modulation_mae_db": 0.5453820075274514, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5115160116017611, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03008354924039449, "1000–3000 Hz_40ms_envelope_correlation": 0.9994296135964025, "1000–3000 Hz_40ms_modulation_mae_db": 0.4769572824893667, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1010423696365608, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12362914092622247, "3000–6000 Hz_10ms_envelope_correlation": 0.9902373498260587, "3000–6000 Hz_10ms_modulation_mae_db": 1.1864775667310488, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7563819053764081, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06138489812778192, "3000–6000 Hz_40ms_envelope_correlation": 0.9976972687322546, "3000–6000 Hz_40ms_modulation_mae_db": 0.3504724430505621, "mr_stft_db": 5.369532422803189, "band_mae_db": 1.2842080803563418, "rms_gain_error_db": -0.08088186863322369, "output_peak": 0.23370059656704806}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2748635505717005, "全帯域_10ms_rms_envelope_nrmse": 0.06035102633994242, "全帯域_10ms_envelope_correlation": 0.9970268160168871, "全帯域_10ms_modulation_mae_db": 0.1731696960826532, "全帯域_40ms_log_rms_mae_db": 0.7293546680035458, "全帯域_40ms_rms_envelope_nrmse": 0.0354061060060988, "全帯域_40ms_envelope_correlation": 0.9990301827901505, "全帯域_40ms_modulation_mae_db": 0.20643776583212645, "300–1000 Hz_10ms_log_rms_mae_db": 0.8145916766268213, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09819995151885134, "300–1000 Hz_10ms_envelope_correlation": 0.9923662035821597, "300–1000 Hz_10ms_modulation_mae_db": 0.29574016207628673, "300–1000 Hz_40ms_log_rms_mae_db": 0.5920604680320674, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.06342340965791646, "300–1000 Hz_40ms_envelope_correlation": 0.9967000264764497, "300–1000 Hz_40ms_modulation_mae_db": 0.7664498740937119, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7845341948641835, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06357091735531172, "1000–3000 Hz_10ms_envelope_correlation": 0.9977421217147461, "1000–3000 Hz_10ms_modulation_mae_db": 0.5667832444139268, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5091541141347755, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04066577570646611, "1000–3000 Hz_40ms_envelope_correlation": 0.9992766401465855, "1000–3000 Hz_40ms_modulation_mae_db": 0.8180994823718133, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0980565627700514, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1347455258514829, "3000–6000 Hz_10ms_envelope_correlation": 0.9890505530978669, "3000–6000 Hz_10ms_modulation_mae_db": 0.6002173007068355, "3000–6000 Hz_40ms_log_rms_mae_db": 0.777308483020483, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09118983415358946, "3000–6000 Hz_40ms_envelope_correlation": 0.9955017752355803, "3000–6000 Hz_40ms_modulation_mae_db": 0.9759016487972293, "mr_stft_db": 5.374931245839034, "band_mae_db": 1.1460552562146762, "rms_gain_error_db": -0.116332034568829, "output_peak": 0.2632891796488289}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2128202481610584, "全帯域_10ms_rms_envelope_nrmse": 0.058618456226819, "全帯域_10ms_envelope_correlation": 0.997151862166695, "全帯域_10ms_modulation_mae_db": 0.6633934423562229, "全帯域_40ms_log_rms_mae_db": 0.6528093002528236, "全帯域_40ms_rms_envelope_nrmse": 0.031871760963648396, "全帯域_40ms_envelope_correlation": 0.9991812327973638, "全帯域_40ms_modulation_mae_db": 0.9199627645317512, "300–1000 Hz_10ms_log_rms_mae_db": 0.8278158909551036, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08231838639053005, "300–1000 Hz_10ms_envelope_correlation": 0.9946472904094207, "300–1000 Hz_10ms_modulation_mae_db": 0.4056303661817562, "300–1000 Hz_40ms_log_rms_mae_db": 0.5715558452883365, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0491773913468998, "300–1000 Hz_40ms_envelope_correlation": 0.998006938487868, "300–1000 Hz_40ms_modulation_mae_db": 0.7983012411156049, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7633855182456316, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06006676963244951, "1000–3000 Hz_10ms_envelope_correlation": 0.9978711377632512, "1000–3000 Hz_10ms_modulation_mae_db": 0.4408767378843792, "1000–3000 Hz_40ms_log_rms_mae_db": 0.46644919293070547, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.035347027632060754, "1000–3000 Hz_40ms_envelope_correlation": 0.9993807579780667, "1000–3000 Hz_40ms_modulation_mae_db": 0.6913629413168819, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0976222385586996, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1312630904891219, "3000–6000 Hz_10ms_envelope_correlation": 0.9889699750372832, "3000–6000 Hz_10ms_modulation_mae_db": 1.0771080922988538, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7423550125339616, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07244858731278774, "3000–6000 Hz_40ms_envelope_correlation": 0.9967216782112465, "3000–6000 Hz_40ms_modulation_mae_db": 0.6129100095051188, "mr_stft_db": 5.379913370312667, "band_mae_db": 1.2942664358420244, "rms_gain_error_db": -0.09037950695357508, "output_peak": 0.26801993135105595}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.179228534861206, "全帯域_10ms_rms_envelope_nrmse": 0.059047838835605895, "全帯域_10ms_envelope_correlation": 0.9971423322508557, "全帯域_10ms_modulation_mae_db": 0.538628184918692, "全帯域_40ms_log_rms_mae_db": 0.6708558554451661, "全帯域_40ms_rms_envelope_nrmse": 0.030813446118828844, "全帯域_40ms_envelope_correlation": 0.9992814581969922, "全帯域_40ms_modulation_mae_db": 0.8073693011434383, "300–1000 Hz_10ms_log_rms_mae_db": 0.790401529345852, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.078886862694791, "300–1000 Hz_10ms_envelope_correlation": 0.9950690011804101, "300–1000 Hz_10ms_modulation_mae_db": 0.7653779067093097, "300–1000 Hz_40ms_log_rms_mae_db": 0.548790441249974, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04469625172694569, "300–1000 Hz_40ms_envelope_correlation": 0.9983592790625399, "300–1000 Hz_40ms_modulation_mae_db": 1.0891657191818551, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7630679426328885, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06481621541139296, "1000–3000 Hz_10ms_envelope_correlation": 0.9974579735009014, "1000–3000 Hz_10ms_modulation_mae_db": 0.8870510567292312, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4507328864167076, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04000134413727376, "1000–3000 Hz_40ms_envelope_correlation": 0.9991160138727153, "1000–3000 Hz_40ms_modulation_mae_db": 0.5463077662057255, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0686714743957768, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13673077155245095, "3000–6000 Hz_10ms_envelope_correlation": 0.9896748163911067, "3000–6000 Hz_10ms_modulation_mae_db": 0.9046910791094419, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7328419069615423, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09268458420904553, "3000–6000 Hz_40ms_envelope_correlation": 0.9964545259202803, "3000–6000 Hz_40ms_modulation_mae_db": 0.9341073828995713, "mr_stft_db": 5.392591995961638, "band_mae_db": 1.3028765013789985, "rms_gain_error_db": -0.10698196127093508, "output_peak": 0.23203415964116048}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.181757734499873, "全帯域_10ms_rms_envelope_nrmse": 0.05405165570357221, "全帯域_10ms_envelope_correlation": 0.9975482865442071, "全帯域_10ms_modulation_mae_db": 0.2387106748669461, "全帯域_40ms_log_rms_mae_db": 0.6765060468456069, "全帯域_40ms_rms_envelope_nrmse": 0.026040367853860977, "全帯域_40ms_envelope_correlation": 0.9994331511127797, "全帯域_40ms_modulation_mae_db": 0.25973758298765476, "300–1000 Hz_10ms_log_rms_mae_db": 0.7721960607228213, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07417486600872829, "300–1000 Hz_10ms_envelope_correlation": 0.9956508528061203, "300–1000 Hz_10ms_modulation_mae_db": 0.37272302726004797, "300–1000 Hz_40ms_log_rms_mae_db": 0.5479907300808027, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.041701776079797845, "300–1000 Hz_40ms_envelope_correlation": 0.9985784841504592, "300–1000 Hz_40ms_modulation_mae_db": 0.3558377385957838, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7894253317493072, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05828814078758537, "1000–3000 Hz_10ms_envelope_correlation": 0.9978939084477242, "1000–3000 Hz_10ms_modulation_mae_db": 0.34069671435959487, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5008902471248299, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03239616694398962, "1000–3000 Hz_40ms_envelope_correlation": 0.9993879932001544, "1000–3000 Hz_40ms_modulation_mae_db": 0.466012124774225, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1177009610676518, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11352718849856377, "3000–6000 Hz_10ms_envelope_correlation": 0.9917273695993654, "3000–6000 Hz_10ms_modulation_mae_db": 0.9756550606807867, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7210946983888117, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0453959099195522, "3000–6000 Hz_40ms_envelope_correlation": 0.9987417490136882, "3000–6000 Hz_40ms_modulation_mae_db": 0.3474787741351159, "mr_stft_db": 5.375236389836375, "band_mae_db": 1.1631300301523557, "rms_gain_error_db": -0.057251086498909906, "output_peak": 0.23743614940238542}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2537458822547833, "全帯域_10ms_rms_envelope_nrmse": 0.05325848256211175, "全帯域_10ms_envelope_correlation": 0.9976484932132367, "全帯域_10ms_modulation_mae_db": 0.36112396355486154, "全帯域_40ms_log_rms_mae_db": 0.7213949237797631, "全帯域_40ms_rms_envelope_nrmse": 0.028065851118809645, "全帯域_40ms_envelope_correlation": 0.9993655440864271, "全帯域_40ms_modulation_mae_db": 0.6566144310102915, "300–1000 Hz_10ms_log_rms_mae_db": 0.7478207261632898, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0661434521171977, "300–1000 Hz_10ms_envelope_correlation": 0.996552468762353, "300–1000 Hz_10ms_modulation_mae_db": 0.5908669016975391, "300–1000 Hz_40ms_log_rms_mae_db": 0.5030972925612857, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03685780741932431, "300–1000 Hz_40ms_envelope_correlation": 0.9988812260825849, "300–1000 Hz_40ms_modulation_mae_db": 1.1873339880154103, "1000–3000 Hz_10ms_log_rms_mae_db": 0.767572154036845, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.054912672102999466, "1000–3000 Hz_10ms_envelope_correlation": 0.9981471905192768, "1000–3000 Hz_10ms_modulation_mae_db": 0.7421695544881349, "1000–3000 Hz_40ms_log_rms_mae_db": 0.47664681868119413, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.030329661039299412, "1000–3000 Hz_40ms_envelope_correlation": 0.9994813061188875, "1000–3000 Hz_40ms_modulation_mae_db": 0.946918831702214, "3000–6000 Hz_10ms_log_rms_mae_db": 1.112892795162917, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11149913671188308, "3000–6000 Hz_10ms_envelope_correlation": 0.9926124956890215, "3000–6000 Hz_10ms_modulation_mae_db": 0.6318386288270291, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7461289865964182, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06482460892411894, "3000–6000 Hz_40ms_envelope_correlation": 0.9980279922927965, "3000–6000 Hz_40ms_modulation_mae_db": 0.33620918754668216, "mr_stft_db": 5.3738914019194866, "band_mae_db": 1.2120998097641333, "rms_gain_error_db": -0.0787647985154595, "output_peak": 0.2133851491051793}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2297149718368925, "全帯域_10ms_rms_envelope_nrmse": 0.06623945868599325, "全帯域_10ms_envelope_correlation": 0.996377691389451, "全帯域_10ms_modulation_mae_db": 0.5498630909222727, "全帯域_40ms_log_rms_mae_db": 0.7196907600233979, "全帯域_40ms_rms_envelope_nrmse": 0.042340552881028184, "全帯域_40ms_envelope_correlation": 0.9985310356459635, "全帯域_40ms_modulation_mae_db": 0.7727894801668773, "300–1000 Hz_10ms_log_rms_mae_db": 0.7840412032815511, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07197281419187347, "300–1000 Hz_10ms_envelope_correlation": 0.9958975800243114, "300–1000 Hz_10ms_modulation_mae_db": 0.3654192221815591, "300–1000 Hz_40ms_log_rms_mae_db": 0.5351103371035923, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03933725251726291, "300–1000 Hz_40ms_envelope_correlation": 0.9987293344688447, "300–1000 Hz_40ms_modulation_mae_db": 0.8487376657307822, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7835188646273613, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06284905240466047, "1000–3000 Hz_10ms_envelope_correlation": 0.9974838694988813, "1000–3000 Hz_10ms_modulation_mae_db": 0.4126586894798088, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5089850981139207, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03822243395758256, "1000–3000 Hz_40ms_envelope_correlation": 0.9990475456994887, "1000–3000 Hz_40ms_modulation_mae_db": 0.33571761163537445, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1516494282864502, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1266661928187332, "3000–6000 Hz_10ms_envelope_correlation": 0.9900489995035129, "3000–6000 Hz_10ms_modulation_mae_db": 1.189134846738367, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7806144716532218, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06269210738009204, "3000–6000 Hz_40ms_envelope_correlation": 0.9980307984441764, "3000–6000 Hz_40ms_modulation_mae_db": 0.554633231772734, "mr_stft_db": 5.3833536432351785, "band_mae_db": 1.3166310918765183, "rms_gain_error_db": -0.11203879500997257, "output_peak": 0.19558289653896552}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2436600869676921, "全帯域_10ms_rms_envelope_nrmse": 0.05173569801963576, "全帯域_10ms_envelope_correlation": 0.9977459998150762, "全帯域_10ms_modulation_mae_db": 0.47092515637778737, "全帯域_40ms_log_rms_mae_db": 0.7479916596291522, "全帯域_40ms_rms_envelope_nrmse": 0.026431523171171405, "全帯域_40ms_envelope_correlation": 0.9994008804767176, "全帯域_40ms_modulation_mae_db": 0.4060081415628804, "300–1000 Hz_10ms_log_rms_mae_db": 0.7916954750872871, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06883996825076201, "300–1000 Hz_10ms_envelope_correlation": 0.9962696814938432, "300–1000 Hz_10ms_modulation_mae_db": 0.32039256627485035, "300–1000 Hz_40ms_log_rms_mae_db": 0.5860548587882904, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.042119727402007846, "300–1000 Hz_40ms_envelope_correlation": 0.9985458647848489, "300–1000 Hz_40ms_modulation_mae_db": 0.6217391547146625, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7392335543089892, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05500422862136168, "1000–3000 Hz_10ms_envelope_correlation": 0.9981576615210952, "1000–3000 Hz_10ms_modulation_mae_db": 0.3371479689875239, "1000–3000 Hz_40ms_log_rms_mae_db": 0.44435818740818533, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03346674604545149, "1000–3000 Hz_40ms_envelope_correlation": 0.999366045315933, "1000–3000 Hz_40ms_modulation_mae_db": 0.5974794086068785, "3000–6000 Hz_10ms_log_rms_mae_db": 1.093635041398776, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12329607359383528, "3000–6000 Hz_10ms_envelope_correlation": 0.9915129192368765, "3000–6000 Hz_10ms_modulation_mae_db": 1.13733852819784, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7357488384966581, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07876455062043955, "3000–6000 Hz_40ms_envelope_correlation": 0.997521235081427, "3000–6000 Hz_40ms_modulation_mae_db": 0.7002651068780036, "mr_stft_db": 5.371985181031678, "band_mae_db": 1.2601238703307016, "rms_gain_error_db": -0.04764862434913843, "output_peak": 0.2463694059326455}, "full_scale": {"sample_count": 130065, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 130065, "output_samples": 130065, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.517307586605114, "spectral_convergence": 0.18008599922745605, "spectral_convergence_status": "ok", "amplitude_floor": 8.628776010687778e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.416707475339976, "spectral_convergence": 0.19102513895067239, "spectral_convergence_status": "ok", "amplitude_floor": 8.696913128358987e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.17458220646448, "spectral_convergence": 0.19132814484920993, "spectral_convergence_status": "ok", "amplitude_floor": 6.997748100750841e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.5012142154628568e-06, "output_power": 9.877435053405231e-06, "delta_db": 8.182015145389045, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008569985031977355, "output_power": 0.000829605179382564, "delta_db": -0.1410860862867854, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0002039561579698118, "output_power": 0.0002022106320115132, "delta_db": -0.037328357581612244, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00031755380447674584, "output_power": 0.0003139470776413203, "delta_db": -0.04960875395819768, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 8.391217397004902e-05, "output_power": 8.202793383747936e-05, "delta_db": -0.09863200348872032, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2641952404694477e-05, "output_power": 1.1679501346315748e-05, "delta_db": -0.34389849865692357, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.274471551779886e-06, "output_power": 2.203899251973757e-06, "delta_db": -0.13688771713310785, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.2842080803563418, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.08088186863322369, "pitch": null, "output_rms_dbfs": -28.38167503674577, "output_peak": 0.23370059656704806, "reference_rms_dbfs": -28.300793168112545, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.369532422803189}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 130065, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 0.0001318526099400404, "log_rms_mae_db": 1.2272082312124544, "rms_envelope_nrmse": 0.07559511577551314, "envelope_correlation": 0.9951880557937465, "rms_gain_error_db": -0.0808818020400094, "reference_mean_power": 0.0014814008893508253, "output_mean_power": 0.0014540670086442987}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 7.673423983742615e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0002922132888675935, "output_power": 0.0002769545536731075, "reference_active": true, "delta_db": -0.23291452095064394}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.0438146457063534e-05, "output_power": 2.707600393140325e-05, "reference_active": true, "delta_db": -0.5083363388566963}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.705913608511969e-06, "output_power": 5.118640466494971e-06, "reference_active": true, "delta_db": -0.47170566091014865}], "active_band_count": 3, "active_band_mae_db": 0.4043188402391629}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 0.00011771272815729935, "log_rms_mae_db": 0.7243176567079267, "rms_envelope_nrmse": 0.03396489943030817, "envelope_correlation": 0.9990442524258738, "rms_gain_error_db": -0.08088148030517847, "reference_mean_power": 0.001489661173505724, "output_mean_power": 0.0014621749875344142}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 7.348414354743223e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.000259482167884596, "output_power": 0.0002463502837708056, "reference_active": true, "delta_db": -0.22554450780045115}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3907004138768798e-05, "output_power": 1.2788817547578667e-05, "reference_active": true, "delta_db": -0.3640319237751336}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.4011744172060643e-07, "output_power": 2.575234754980995e-07, "reference_active": true, "delta_db": -2.327517549723355}], "active_band_count": 3, "active_band_mae_db": 0.97236466043298}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 8.480086855572389e-05, "log_rms_mae_db": 0.797163048079647, "rms_envelope_nrmse": 0.09012771308786607, "envelope_correlation": 0.9935554685072145, "rms_gain_error_db": -0.03700055003231774, "reference_mean_power": 0.0005471873658289661, "output_mean_power": 0.000542545300842355}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 3.0613556922446793e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0001155073862142863, "output_power": 0.00011182597706799396, "reference_active": true, "delta_db": -0.14067054967269804}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3854221447460866e-05, "output_power": 1.0575860749666886e-05, "reference_active": true, "delta_db": -1.1726640126205357}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9357817767829245e-06, "output_power": 1.9644227513539876e-06, "reference_active": true, "delta_db": 0.06378558211333511}], "active_band_count": 3, "active_band_mae_db": 0.45904004813552296}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.44475219971024e-05, "log_rms_mae_db": 0.5504094496161982, "rms_envelope_nrmse": 0.052837229356785746, "envelope_correlation": 0.9977047664855332, "rms_gain_error_db": -0.037000592251287046, "reference_mean_power": 0.0005502385876291546, "output_mean_power": 0.0005455706322933573}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.936750998626233e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.910211940271478e-05, "output_power": 9.595236199574084e-05, "reference_active": true, "delta_db": -0.14027272484689335}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.231208448817648e-06, "output_power": 4.900405541677489e-06, "reference_active": true, "delta_db": -1.0434025736703982}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.518968227553501e-07, "output_power": 1.5781450801346034e-07, "reference_active": true, "delta_db": -2.0307576390920086}], "active_band_count": 3, "active_band_mae_db": 1.0714776458697666}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 7.92844222433349e-05, "log_rms_mae_db": 0.822292369460996, "rms_envelope_nrmse": 0.05793951690846307, "envelope_correlation": 0.997874176654186, "rms_gain_error_db": -0.056708705408368136, "reference_mean_power": 0.0003517587960046477, "output_mean_power": 0.0003471955063353823}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 1.184446345593241e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.4086641780542994e-05, "output_power": 3.270863532088967e-05, "reference_active": true, "delta_db": -0.17921791855946181}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.908924984845658e-06, "output_power": 8.064599957825236e-06, "reference_active": true, "delta_db": -0.432424728876875}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.00669572393549e-07, "output_power": 4.744443676659721e-07, "reference_active": true, "delta_db": -1.0245033751460173}], "active_band_count": 3, "active_band_mae_db": 0.5453820075274514}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 7.287723098191666e-05, "log_rms_mae_db": 0.5115160116017611, "rms_envelope_nrmse": 0.03008354924039449, "envelope_correlation": 0.9994296135964025, "rms_gain_error_db": -0.056708726572361104, "reference_mean_power": 0.0003537202709185465, "output_mean_power": 0.0003491315337642726}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 1.1592322619199725e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.0388893978542697e-05, "output_power": 2.9342096522659692e-05, "reference_active": true, "delta_db": -0.15223752568866167}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.277692934034562e-06, "output_power": 3.934246312999795e-06, "reference_active": true, "delta_db": -0.3634805986945045}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.6389202390485585e-08, "output_power": 4.5675212794706685e-08, "reference_active": true, "delta_db": -0.915153723084934}], "active_band_count": 3, "active_band_mae_db": 0.4769572824893667}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1082, "rms_floor": 3.178621250284737e-05, "log_rms_mae_db": 1.1010423696365608, "rms_envelope_nrmse": 0.12362914092622247, "envelope_correlation": 0.9902373498260587, "rms_gain_error_db": -0.1669267386310067, "reference_mean_power": 4.4150646761510114e-05, "output_mean_power": 4.248585827672996e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 2.2237128168975068e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.193805277966022e-06, "output_power": 8.881912870859764e-06, "reference_active": true, "delta_db": -0.14988792736771064}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0890347422283183e-06, "output_power": 9.093511640988345e-07, "reference_active": true, "delta_db": -0.7831010768256923}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8576888047519497e-07, "output_power": 3.4010838056488293e-07, "reference_active": true, "delta_db": 2.6264436959997433}], "active_band_count": 3, "active_band_mae_db": 1.1864775667310488}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 129960, "uncovered_tail_samples": 105, "metrics": {"frame_count": 1076, "rms_floor": 2.883918900864625e-05, "log_rms_mae_db": 0.7563819053764081, "rms_envelope_nrmse": 0.06138489812778192, "envelope_correlation": 0.9976972687322546, "rms_gain_error_db": -0.16692677179159013, "reference_mean_power": 4.439683700027618e-05, "output_mean_power": 4.2722765093688926e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1076, "frequency_resolution_hz": 0.1858736059479554, "power_floor": 2.1738925168287815e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.247468496821311e-06, "output_power": 8.097644582834222e-06, "reference_active": true, "delta_db": -0.07961954282183674}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.957219370502507e-07, "output_power": 4.624272875600145e-07, "reference_active": true, "delta_db": -0.3019468441944798}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6536836687109635e-08, "output_power": 1.9294677842042757e-08, "reference_active": true, "delta_db": 0.6698509421353696}], "active_band_count": 3, "active_band_mae_db": 0.3504724430505621}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8770847811781259, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "e815db5452dd94ffe18809e9b5359d507fdab5a23ae3414dced3582a1bf3dd63", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9978285049525077, "standard_deviation": 0.0002623015798317899, "minimum": 0.9974579735009014, "maximum": 0.9981576615210952, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.7766287412407753, "standard_deviation": 0.024490784446925033, "minimum": 0.7392335543089892, "maximum": 0.822292369460996, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5340957467337564, "standard_deviation": 0.19592140110714312, "minimum": 0.3371479689875239, "maximum": 0.8870510567292312, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.05968093915302803, "standard_deviation": 0.003803555295021843, "minimum": 0.054912672102999466, "maximum": 0.06481621541139296, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9993107394910292, "standard_deviation": 0.00015376479694689042, "minimum": 0.9990475456994887, "maximum": 0.9994813061188875, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.48359156955150995, "standard_deviation": 0.027615564091501184, "minimum": 0.44435818740818533, "maximum": 0.5115160116017611, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6098569311378099, "standard_deviation": 0.20046967191549023, "minimum": 0.33571761163537445, "maximum": 0.946918831702214, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.035064088087814776, "standard_deviation": 0.004186721806787254, "minimum": 0.03008354924039449, "maximum": 0.04066577570646611, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9904793097976365, "standard_deviation": 0.0013302439160305132, "minimum": 0.9889699750372832, "maximum": 0.9926124956890215, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.1051588589096104, "standard_deviation": 0.02380518393988395, "minimum": 1.0686714743957768, "maximum": 1.1516494282864502, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.9628076379112753, "standard_deviation": 0.23583671601287282, "minimum": 0.6002173007068355, "maximum": 1.189134846738367, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1251696400552867, "standard_deviation": 0.009204345925428565, "minimum": 0.11149913671188308, "maximum": 0.13673077155245095, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9973371278664311, "standard_deviation": 0.0010434362021845586, "minimum": 0.9955017752355803, "maximum": 0.9987417490136882, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7490592878784381, "standard_deviation": 0.021122402195723044, "minimum": 0.7210946983888117, "maximum": 0.7806144716532218, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6014972230731271, "standard_deviation": 0.2565725536616821, "minimum": 0.33620918754668216, "maximum": 0.9759016487972293, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07117313508092593, "standard_deviation": 0.016014161538836287, "minimum": 0.0453959099195522, "maximum": 0.09268458420904553, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9950010683457291, "standard_deviation": 0.0014344845027659068, "minimum": 0.9923662035821597, "maximum": 0.996552468762353, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.7907157012827967, "standard_deviation": 0.024543308993127212, "minimum": 0.7478207261632898, "maximum": 0.8278158909551036, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.446898775064609, "standard_deviation": 0.15811387266603674, "minimum": 0.29574016207628673, "maximum": 0.7653779067093097, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07883300178257499, "standard_deviation": 0.010983402055346843, "minimum": 0.0661434521171977, "maximum": 0.09819995151885134, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9981882399998911, "standard_deviation": 0.0007135274195012904, "minimum": 0.9967000264764497, "maximum": 0.9988812260825849, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5543836778400684, "standard_deviation": 0.02880275557597923, "minimum": 0.5030972925612857, "maximum": 0.5920604680320674, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8423803784146973, "standard_deviation": 0.2740012179432783, "minimum": 0.3558377385957838, "maximum": 1.1873339880154103, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.046268855688367576, "standard_deviation": 0.008644100805670733, "minimum": 0.03685780741932431, "maximum": 0.06342340965791646, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.2474238844894687, "standard_deviation": 0.06568546754897098, "minimum": 1.1460552562146762, "maximum": 1.3166310918765183, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.377679456367406, "standard_deviation": 0.007428133051870384, "minimum": 5.369532422803189, "maximum": 5.392591995961638, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.23622718352340866, "standard_deviation": 0.024039070621392565, "minimum": 0.19558289653896552, "maximum": 0.26801993135105595, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.0862848344750054, "standard_deviation": 0.025164306786110376, "minimum": -0.116332034568829, "maximum": -0.04764862434913843, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9969786921487694, "standard_deviation": 0.0008441813117268123, "minimum": 0.9951880557937465, "maximum": 0.9977459998150762, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.2253749050457077, "standard_deviation": 0.03338123506963952, "minimum": 1.179228534861206, "maximum": 1.2748635505717005, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4250166311648248, "standard_deviation": 0.16478244534069542, "minimum": 0.1731696960826532, "maximum": 0.6633934423562229, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.059862216518649175, "standard_deviation": 0.0078745035623332, "minimum": 0.05173569801963576, "maximum": 0.07559511577551314, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9991584671915336, "standard_deviation": 0.0002966271355387793, "minimum": 0.9985310356459635, "maximum": 0.9994331511127797, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.7053651088359227, "standard_deviation": 0.03380563593307215, "minimum": 0.6528093002528236, "maximum": 0.7479916596291522, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6251605159585, "standard_deviation": 0.2976894857699021, "minimum": 0.20643776583212645, "maximum": 0.97236466043298, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03186681344296931, "standard_deviation": 0.005420523759653688, "minimum": 0.026040367853860977, "maximum": 0.042340552881028184, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "language": "ja", "style": "normal", "speaker": "jvs_jvs082", "source_utterance_id": "VOICEACTRESS100_079", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 144000, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs082_parallel100_VOICEACTRESS100_079.wav", "source_file_sha256": "b64d7a959a2691a86416c074b4f73bec7f6d8bee6f1830171b62cfa526f8b15a", "decoded_pcm_sha256": "a636d3ab3504b45a1258fe0a67c7b1329af515afc77a9c8ad32ba0146c5573fb", "original_source_sha256": "b64d7a959a2691a86416c074b4f73bec7f6d8bee6f1830171b62cfa526f8b15a", "corpus_entry_id": "jvs_jvs082_parallel100_VOICEACTRESS100_079"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 4.19839334487915, "predicted_mos": 4.19839334487915, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "5b158f7c5a397b2b64ddae8c857d0fba7a94e6c19358df34b14dfda40021c7fc", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 8.83438799995929}, "waveform_sha256": "4ec2fa88c32b7bc902aa7fdf6a3cee4d3a10c9d77654a01119f350529c29c37f"}, "rows": [{"case": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 2.3952198028564453, "predicted_mos": 2.3952198028564453, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "2cb8addf2a3e855a40e6b10e968aacfb0238b037d3f52c95cde5f66fdcb5baf9", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 8.98569229990244}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.059633742939385, "全帯域_10ms_rms_envelope_nrmse": 0.037353365771681434, "全帯域_10ms_envelope_correlation": 0.9986446705753732, "全帯域_10ms_modulation_mae_db": 0.1594411854381498, "全帯域_40ms_log_rms_mae_db": 0.5838044260693733, "全帯域_40ms_rms_envelope_nrmse": 0.020845462739975867, "全帯域_40ms_envelope_correlation": 0.9996132204229143, "全帯域_40ms_modulation_mae_db": 0.3149530207966091, "300–1000 Hz_10ms_log_rms_mae_db": 1.4637321478362628, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06543493317213052, "300–1000 Hz_10ms_envelope_correlation": 0.9961916675214424, "300–1000 Hz_10ms_modulation_mae_db": 0.21101333404623512, "300–1000 Hz_40ms_log_rms_mae_db": 1.163989728141247, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037814642041158135, "300–1000 Hz_40ms_envelope_correlation": 0.998709933096672, "300–1000 Hz_40ms_modulation_mae_db": 0.673784185829788, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2139682874979663, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10856237078305836, "1000–3000 Hz_10ms_envelope_correlation": 0.991891569997768, "1000–3000 Hz_10ms_modulation_mae_db": 0.8209002419257225, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8806826469411664, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06747679354987, "1000–3000 Hz_40ms_envelope_correlation": 0.9972316673714311, "1000–3000 Hz_40ms_modulation_mae_db": 0.6658088488599635, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5080991521454628, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14608198221158, "3000–6000 Hz_10ms_envelope_correlation": 0.9846128058796249, "3000–6000 Hz_10ms_modulation_mae_db": 0.5857575952399753, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9264193354546812, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08732802261063224, "3000–6000 Hz_40ms_envelope_correlation": 0.9954024416132218, "3000–6000 Hz_40ms_modulation_mae_db": 0.5610704960812737, "mr_stft_db": 5.472557851182217, "band_mae_db": 0.20236346418005705, "rms_gain_error_db": -0.07556268034266492, "output_peak": 0.1589409545327264}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1010362104975984, "全帯域_10ms_rms_envelope_nrmse": 0.041772561043871, "全帯域_10ms_envelope_correlation": 0.9983282796215751, "全帯域_10ms_modulation_mae_db": 0.4922680596281486, "全帯域_40ms_log_rms_mae_db": 0.5807670637671867, "全帯域_40ms_rms_envelope_nrmse": 0.02428834039055814, "全帯域_40ms_envelope_correlation": 0.9994948417025155, "全帯域_40ms_modulation_mae_db": 0.5524673487514359, "300–1000 Hz_10ms_log_rms_mae_db": 1.4344961083387904, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06224323648715591, "300–1000 Hz_10ms_envelope_correlation": 0.9965671128731907, "300–1000 Hz_10ms_modulation_mae_db": 0.748833362878805, "300–1000 Hz_40ms_log_rms_mae_db": 1.081894675942437, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0360674498504515, "300–1000 Hz_40ms_envelope_correlation": 0.9988232731196577, "300–1000 Hz_40ms_modulation_mae_db": 1.047246424820747, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2877011918174288, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.14534470013348585, "1000–3000 Hz_10ms_envelope_correlation": 0.9859788182798455, "1000–3000 Hz_10ms_modulation_mae_db": 1.381349048201261, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8806036899939428, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09059825311320009, "1000–3000 Hz_40ms_envelope_correlation": 0.9957960936398635, "1000–3000 Hz_40ms_modulation_mae_db": 1.1004403187751441, "3000–6000 Hz_10ms_log_rms_mae_db": 1.532231490886338, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1706153011065608, "3000–6000 Hz_10ms_envelope_correlation": 0.9777388129152531, "3000–6000 Hz_10ms_modulation_mae_db": 0.6422970835473291, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9576240171069729, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09038509274000411, "3000–6000 Hz_40ms_envelope_correlation": 0.9939138663443862, "3000–6000 Hz_40ms_modulation_mae_db": 0.4333512302901217, "mr_stft_db": 5.464918217404196, "band_mae_db": 0.17973462630984716, "rms_gain_error_db": -0.10123564175290584, "output_peak": 0.15089476584165473}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.126039682802268, "全帯域_10ms_rms_envelope_nrmse": 0.04041079463161015, "全帯域_10ms_envelope_correlation": 0.9983934741262959, "全帯域_10ms_modulation_mae_db": 0.6817179816531892, "全帯域_40ms_log_rms_mae_db": 0.5765066782339654, "全帯域_40ms_rms_envelope_nrmse": 0.020884358038444756, "全帯域_40ms_envelope_correlation": 0.9995973783646234, "全帯域_40ms_modulation_mae_db": 0.7437503065358961, "300–1000 Hz_10ms_log_rms_mae_db": 1.3739482329560702, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0614001784103233, "300–1000 Hz_10ms_envelope_correlation": 0.9966907409799728, "300–1000 Hz_10ms_modulation_mae_db": 0.713637011818943, "300–1000 Hz_40ms_log_rms_mae_db": 1.0108190459354767, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03833025908240155, "300–1000 Hz_40ms_envelope_correlation": 0.9986912584680993, "300–1000 Hz_40ms_modulation_mae_db": 0.8137881560032265, "1000–3000 Hz_10ms_log_rms_mae_db": 1.281269037818404, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13083934507177775, "1000–3000 Hz_10ms_envelope_correlation": 0.988518161835201, "1000–3000 Hz_10ms_modulation_mae_db": 0.3006052198708529, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8735433803011395, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08536106431261195, "1000–3000 Hz_40ms_envelope_correlation": 0.9958252077684951, "1000–3000 Hz_40ms_modulation_mae_db": 0.2592568301026685, "3000–6000 Hz_10ms_log_rms_mae_db": 1.548804062232219, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15925475437857398, "3000–6000 Hz_10ms_envelope_correlation": 0.9812097784624948, "3000–6000 Hz_10ms_modulation_mae_db": 0.4546441993610353, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0196261067376522, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10760516425822662, "3000–6000 Hz_40ms_envelope_correlation": 0.991752574444028, "3000–6000 Hz_40ms_modulation_mae_db": 0.22223840629247996, "mr_stft_db": 5.477669787642003, "band_mae_db": 0.20249912525328767, "rms_gain_error_db": -0.07119675790067187, "output_peak": 0.16049949634142946}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1459237335028458, "全帯域_10ms_rms_envelope_nrmse": 0.04607407883369207, "全帯域_10ms_envelope_correlation": 0.997858642225498, "全帯域_10ms_modulation_mae_db": 0.18940911861510887, "全帯域_40ms_log_rms_mae_db": 0.6323843122898511, "全帯域_40ms_rms_envelope_nrmse": 0.023567752671451454, "全帯域_40ms_envelope_correlation": 0.9994385765033923, "全帯域_40ms_modulation_mae_db": 0.1786037675536296, "300–1000 Hz_10ms_log_rms_mae_db": 1.353920678704946, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06689137927490064, "300–1000 Hz_10ms_envelope_correlation": 0.9960100482825966, "300–1000 Hz_10ms_modulation_mae_db": 0.3188794364608549, "300–1000 Hz_40ms_log_rms_mae_db": 1.0566689177160589, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037584466223675346, "300–1000 Hz_40ms_envelope_correlation": 0.998722381219378, "300–1000 Hz_40ms_modulation_mae_db": 0.36963631219294374, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2144260546909211, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12382068816206025, "1000–3000 Hz_10ms_envelope_correlation": 0.9891235928753485, "1000–3000 Hz_10ms_modulation_mae_db": 0.735733634427007, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8290171789445435, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06573607187388505, "1000–3000 Hz_40ms_envelope_correlation": 0.9972702432972913, "1000–3000 Hz_40ms_modulation_mae_db": 0.601437667727108, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5570456498711969, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17615686054033367, "3000–6000 Hz_10ms_envelope_correlation": 0.9778368629297902, "3000–6000 Hz_10ms_modulation_mae_db": 0.9742515073024358, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0090197862871446, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12342655417609989, "3000–6000 Hz_40ms_envelope_correlation": 0.9902545969293808, "3000–6000 Hz_40ms_modulation_mae_db": 0.7026621423798307, "mr_stft_db": 5.461610619271013, "band_mae_db": 0.2363335273543544, "rms_gain_error_db": -0.05704754129267276, "output_peak": 0.15270838106517115}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0997043364629573, "全帯域_10ms_rms_envelope_nrmse": 0.039805347911196984, "全帯域_10ms_envelope_correlation": 0.9984286785147245, "全帯域_10ms_modulation_mae_db": 0.3575710841864148, "全帯域_40ms_log_rms_mae_db": 0.5744783626203254, "全帯域_40ms_rms_envelope_nrmse": 0.02156103835791114, "全帯域_40ms_envelope_correlation": 0.9995569373958924, "全帯域_40ms_modulation_mae_db": 0.4431026100913733, "300–1000 Hz_10ms_log_rms_mae_db": 1.4039333141018564, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05988676775656944, "300–1000 Hz_10ms_envelope_correlation": 0.9968361874933788, "300–1000 Hz_10ms_modulation_mae_db": 0.6266617679640737, "300–1000 Hz_40ms_log_rms_mae_db": 1.0506079500274748, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.034186845590683385, "300–1000 Hz_40ms_envelope_correlation": 0.9989448211160756, "300–1000 Hz_40ms_modulation_mae_db": 0.8517358457932728, "1000–3000 Hz_10ms_log_rms_mae_db": 1.261980847156096, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13060391678631947, "1000–3000 Hz_10ms_envelope_correlation": 0.9877764314171364, "1000–3000 Hz_10ms_modulation_mae_db": 0.5842580524853421, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8748497299939404, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07698066418372838, "1000–3000 Hz_40ms_envelope_correlation": 0.9960090020664928, "1000–3000 Hz_40ms_modulation_mae_db": 0.4929139303215273, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5117684334103625, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16758307330326944, "3000–6000 Hz_10ms_envelope_correlation": 0.9784414798568833, "3000–6000 Hz_10ms_modulation_mae_db": 0.934786001268053, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9291908053740016, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0912860425905841, "3000–6000 Hz_40ms_envelope_correlation": 0.9934173583599387, "3000–6000 Hz_40ms_modulation_mae_db": 0.5733068191841085, "mr_stft_db": 5.455272797867541, "band_mae_db": 0.19539161661274093, "rms_gain_error_db": -0.06549931515705808, "output_peak": 0.15581677547320405}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0342330578518655, "全帯域_10ms_rms_envelope_nrmse": 0.041123408099174925, "全帯域_10ms_envelope_correlation": 0.9983203912209959, "全帯域_10ms_modulation_mae_db": 0.17985754171110357, "全帯域_40ms_log_rms_mae_db": 0.5421053842764884, "全帯域_40ms_rms_envelope_nrmse": 0.022912090202355354, "全帯域_40ms_envelope_correlation": 0.9994969884607914, "全帯域_40ms_modulation_mae_db": 0.6019776880270317, "300–1000 Hz_10ms_log_rms_mae_db": 1.3826767774589361, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05888032538076327, "300–1000 Hz_10ms_envelope_correlation": 0.9968996001678083, "300–1000 Hz_10ms_modulation_mae_db": 0.28692107769262115, "300–1000 Hz_40ms_log_rms_mae_db": 1.0685995422317462, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03342107376377352, "300–1000 Hz_40ms_envelope_correlation": 0.9989617354211573, "300–1000 Hz_40ms_modulation_mae_db": 0.635743155838849, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2832326961008294, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11586747406605424, "1000–3000 Hz_10ms_envelope_correlation": 0.9903280276262081, "1000–3000 Hz_10ms_modulation_mae_db": 0.5088454120818432, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8825556590982446, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06273207213303342, "1000–3000 Hz_40ms_envelope_correlation": 0.9972610143346811, "1000–3000 Hz_40ms_modulation_mae_db": 0.17624583375652214, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5251090048711882, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1605475888716718, "3000–6000 Hz_10ms_envelope_correlation": 0.9814745801114511, "3000–6000 Hz_10ms_modulation_mae_db": 0.832451260420697, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9774876959391382, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09643905476719573, "3000–6000 Hz_40ms_envelope_correlation": 0.9945306919489331, "3000–6000 Hz_40ms_modulation_mae_db": 0.4018037937108985, "mr_stft_db": 5.465868844484798, "band_mae_db": 0.1613436221657351, "rms_gain_error_db": -0.06856593842256392, "output_peak": 0.15408956256567413}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0711888602661306, "全帯域_10ms_rms_envelope_nrmse": 0.041101986659544516, "全帯域_10ms_envelope_correlation": 0.9983761054645477, "全帯域_10ms_modulation_mae_db": 0.3745150280790173, "全帯域_40ms_log_rms_mae_db": 0.5747252210220659, "全帯域_40ms_rms_envelope_nrmse": 0.024026097563866696, "全帯域_40ms_envelope_correlation": 0.9994941113141271, "全帯域_40ms_modulation_mae_db": 0.43102832932331586, "300–1000 Hz_10ms_log_rms_mae_db": 1.4349682130794015, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06944632023983428, "300–1000 Hz_10ms_envelope_correlation": 0.995732415853929, "300–1000 Hz_10ms_modulation_mae_db": 0.5354036946630069, "300–1000 Hz_40ms_log_rms_mae_db": 1.0611312833154165, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043453937434710446, "300–1000 Hz_40ms_envelope_correlation": 0.9982926739008442, "300–1000 Hz_40ms_modulation_mae_db": 0.8988742854807773, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2982484675558814, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1229385585209124, "1000–3000 Hz_10ms_envelope_correlation": 0.9897712899699878, "1000–3000 Hz_10ms_modulation_mae_db": 0.6163706999539672, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9169681600813054, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07194383718079128, "1000–3000 Hz_40ms_envelope_correlation": 0.997212029127625, "1000–3000 Hz_40ms_modulation_mae_db": 0.6569515091383066, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5252486027043048, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16983215775264068, "3000–6000 Hz_10ms_envelope_correlation": 0.9782451677448845, "3000–6000 Hz_10ms_modulation_mae_db": 0.5773023480621131, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9768590340963507, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10125727954608979, "3000–6000 Hz_40ms_envelope_correlation": 0.9926417857047326, "3000–6000 Hz_40ms_modulation_mae_db": 0.3237247964259679, "mr_stft_db": 5.470288235393567, "band_mae_db": 0.18820917777302842, "rms_gain_error_db": -0.09330438699512814, "output_peak": 0.1583538320936904}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0424283933598528, "全帯域_10ms_rms_envelope_nrmse": 0.04203760356204224, "全帯域_10ms_envelope_correlation": 0.9982355785894972, "全帯域_10ms_modulation_mae_db": 0.6110111061777432, "全帯域_40ms_log_rms_mae_db": 0.5404499745457139, "全帯域_40ms_rms_envelope_nrmse": 0.021894010381727787, "全帯域_40ms_envelope_correlation": 0.9995348607288531, "全帯域_40ms_modulation_mae_db": 0.6065957915112732, "300–1000 Hz_10ms_log_rms_mae_db": 1.4102097558520088, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0684877960584797, "300–1000 Hz_10ms_envelope_correlation": 0.9958388664270748, "300–1000 Hz_10ms_modulation_mae_db": 0.5157378468374899, "300–1000 Hz_40ms_log_rms_mae_db": 1.0874877032733747, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.040333776098366005, "300–1000 Hz_40ms_envelope_correlation": 0.9985251305103883, "300–1000 Hz_40ms_modulation_mae_db": 0.5182287184827586, "1000–3000 Hz_10ms_log_rms_mae_db": 1.255899157918034, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12145786720718416, "1000–3000 Hz_10ms_envelope_correlation": 0.9893040112252779, "1000–3000 Hz_10ms_modulation_mae_db": 0.40514663369033416, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8807308938879495, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07486255167382073, "1000–3000 Hz_40ms_envelope_correlation": 0.9957618444448612, "1000–3000 Hz_40ms_modulation_mae_db": 0.4340796759238555, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6252442464822956, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1599351685001327, "3000–6000 Hz_10ms_envelope_correlation": 0.9807697854536499, "3000–6000 Hz_10ms_modulation_mae_db": 0.1760902465431052, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0382958080361497, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0938542567825357, "3000–6000 Hz_40ms_envelope_correlation": 0.9937668115649391, "3000–6000 Hz_40ms_modulation_mae_db": 0.26130960712910345, "mr_stft_db": 5.474241652298666, "band_mae_db": 0.2020925307355835, "rms_gain_error_db": -0.06357134326885613, "output_peak": 0.1590878329080399}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.523643346058507, "spectral_convergence": 0.12677310730005917, "spectral_convergence_status": "ok", "amplitude_floor": 5.237444731722431e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.479432388083744, "spectral_convergence": 0.1324426371540462, "spectral_convergence_status": "ok", "amplitude_floor": 5.437369948912744e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.414597819404403, "spectral_convergence": 0.13205806203745127, "spectral_convergence_status": "ok", "amplitude_floor": 5.052721691674583e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 6.432970236988243e-05, "output_power": 6.624295646900406e-05, "delta_db": 0.12728164990213858, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008444430165469724, "output_power": 0.000825769284641482, "delta_db": -0.09711623680437903, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 6.039141474549642e-05, "output_power": 6.224424190501187e-05, "delta_db": 0.13123978252893356, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 3.556975687019485e-05, "output_power": 3.3087766234684036e-05, "delta_db": -0.31413447869828715, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.090392882810899e-05, "output_power": 1.0561203868242521e-05, "delta_db": -0.13869582009936451, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2355857763199668e-06, "output_power": 1.3767934232283805e-06, "delta_db": 0.46995882558638674, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.0422411240430348e-06, "output_power": 1.0759199263035815e-06, "delta_db": 0.13811745564090971, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.20236346418005705, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.07556268034266492, "pitch": null, "output_rms_dbfs": -29.99844478129061, "output_peak": 0.1589409545327264, "reference_rms_dbfs": -29.922882100947945, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.472557851182217}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 8.184761378594803e-05, "log_rms_mae_db": 1.059633742939385, "rms_envelope_nrmse": 0.037353365771681434, "envelope_correlation": 0.9986446705753732, "rms_gain_error_db": -0.07510447359647081, "reference_mean_power": 0.0010176842474405314, "output_mean_power": 0.0010002362842861968}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.21363647710693e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00013327602732153044, "output_power": 0.0001285281408985317, "reference_active": true, "delta_db": -0.15753813135821249}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5932863269435214e-05, "output_power": 1.5971815648697885e-05, "reference_active": true, "delta_db": 0.010604596159426076}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.59165062752131e-06, "output_power": 4.27514405122479e-06, "reference_active": true, "delta_db": -0.31018082879681086}], "active_band_count": 3, "active_band_mae_db": 0.1594411854381498}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.048620680965671e-05, "log_rms_mae_db": 0.5838044260693733, "rms_envelope_nrmse": 0.020845462739975867, "envelope_correlation": 0.9996132204229143, "rms_gain_error_db": -0.07432373499590875, "reference_mean_power": 0.0010161096570352637, "output_mean_power": 0.0009988682419810782}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.9042638692252304e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00011759425242544185, "output_power": 0.00011347317882932708, "reference_active": true, "delta_db": -0.15492874214843266}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 7.519272755909202e-06, "output_power": 7.920532636913191e-06, "reference_active": true, "delta_db": 0.22578549024862396}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.598733053895232e-07, "output_power": 3.160349764568453e-07, "reference_active": true, "delta_db": -0.5641448299927707}], "active_band_count": 3, "active_band_mae_db": 0.3149530207966091}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.667982083652557e-05, "log_rms_mae_db": 1.4637321478362628, "rms_envelope_nrmse": 0.06543493317213052, "envelope_correlation": 0.9961916675214424, "rms_gain_error_db": -0.019688148306851453, "reference_mean_power": 0.00027945110045850193, "output_mean_power": 0.00027818711420874706}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.93859363437704e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.295075151115005e-05, "output_power": 3.095613396145925e-05, "reference_active": true, "delta_db": -0.27118606657404776}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.807348843301933e-06, "output_power": 3.510544445659457e-06, "reference_active": true, "delta_db": -0.3524819445319073}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5906604704508056e-06, "output_power": 1.5940967914450479e-06, "reference_active": true, "delta_db": 0.009371991032750356}], "active_band_count": 3, "active_band_mae_db": 0.21101333404623512}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.254388131298964e-05, "log_rms_mae_db": 1.163989728141247, "rms_envelope_nrmse": 0.037814642041158135, "envelope_correlation": 0.998709933096672, "rms_gain_error_db": -0.016287245527346485, "reference_mean_power": 0.00027742187495382226, "output_mean_power": 0.0002763834145854421}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 9.236914065861651e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.9257092980847557e-05, "output_power": 2.7213268321281584e-05, "reference_active": true, "delta_db": -0.3145046811948576}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8979287936807737e-06, "output_power": 1.9164489698484276e-06, "reference_active": true, "delta_db": 0.04217345012978411}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.43591780871064e-08, "output_power": 6.431565644971114e-08, "reference_active": true, "delta_db": -1.6646744261647226}], "active_band_count": 3, "active_band_mae_db": 0.673784185829788}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.428909761907278e-05, "log_rms_mae_db": 1.2139682874979663, "rms_envelope_nrmse": 0.10856237078305836, "envelope_correlation": 0.991891569997768, "rms_gain_error_db": -0.2814023807922323, "reference_mean_power": 3.509769240032237e-05, "output_mean_power": 3.28956388757087e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.14178826098124e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0207730418969553e-05, "output_power": 9.430240235566055e-06, "reference_active": true, "delta_db": -0.3440643549031518}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.594184871691995e-06, "output_power": 2.568933485868713e-06, "reference_active": true, "delta_db": -0.042480625862531256}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.354712471534306e-07, "output_power": 2.079886943919691e-07, "reference_active": true, "delta_db": -2.0761557450114845}], "active_band_count": 3, "active_band_mae_db": 0.8209002419257225}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9506018028930777e-05, "log_rms_mae_db": 0.8806826469411664, "rms_envelope_nrmse": 0.06747679354987, "envelope_correlation": 0.9972316673714311, "rms_gain_error_db": -0.286262371307271, "reference_mean_power": 3.5141167460930974e-05, "output_mean_power": 3.289954929559364e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.01202004778774e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.499160468037956e-06, "output_power": 8.864781734349132e-06, "reference_active": true, "delta_db": -0.30017177197072487}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1261229797074577e-06, "output_power": 1.1444263318790208e-06, "reference_active": true, "delta_db": 0.07002021051653111}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7957517138182228e-08, "output_power": 1.9220963030267738e-08, "reference_active": true, "delta_db": -1.6272345640926345}], "active_band_count": 3, "active_band_mae_db": 0.6658088488599635}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0101884937381439e-05, "log_rms_mae_db": 1.5080991521454628, "rms_envelope_nrmse": 0.14608198221158, "envelope_correlation": 0.9846128058796249, "rms_gain_error_db": -0.41879827818283044, "reference_mean_power": 6.452617383104305e-06, "output_mean_power": 5.859439655528618e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.15273367532141e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.10173826656627e-06, "output_power": 1.910118814655009e-06, "reference_active": true, "delta_db": -0.41518249146130415}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.3061476096447684e-07, "output_power": 3.6294189255297273e-07, "reference_active": true, "delta_db": -0.7425181332711777}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.161739165108172e-08, "output_power": 9.370007261766048e-08, "reference_active": true, "delta_db": 0.5995721609874441}], "active_band_count": 3, "active_band_mae_db": 0.5857575952399753}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.618352616189344e-06, "log_rms_mae_db": 0.9264193354546812, "rms_envelope_nrmse": 0.08732802261063224, "envelope_correlation": 0.9954024416132218, "rms_gain_error_db": -0.42130972114776405, "reference_mean_power": 6.458260841661403e-06, "output_mean_power": 5.8611739345091045e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.76552281278155e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.8830611185238975e-06, "output_power": 1.7074765583137317e-06, "reference_active": true, "delta_db": -0.4250966611200571}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.769776726408418e-07, "output_power": 1.545327119454127e-07, "reference_active": true, "delta_db": -0.5889805333535683}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.816205310457936e-09, "output_power": 8.414536602418951e-09, "reference_active": true, "delta_db": -0.6691342937701955}], "active_band_count": 3, "active_band_mae_db": 0.5610704960812737}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.931760563150795, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "a18dd2339e324d0afd531c78022e2c3cadfb117152f793fdb43fbb3ebab12fcd", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9890864879033465, "standard_deviation": 0.0017576122801167481, "minimum": 0.9859788182798455, "maximum": 0.991891569997768, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.2620907175694451, "standard_deviation": 0.032522753232630035, "minimum": 1.2139682874979663, "maximum": 1.2982484675558814, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6691511178295413, "standard_deviation": 0.3329311149480535, "minimum": 0.3006052198708529, "maximum": 1.381349048201261, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12492936509135656, "standard_deviation": 0.011026943947355167, "minimum": 0.10856237078305836, "maximum": 0.14534470013348585, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9965458877563427, "standard_deviation": 0.0007497309993770866, "minimum": 0.9957618444448612, "maximum": 0.9972702432972913, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.877368917405279, "standard_deviation": 0.023864562503654287, "minimum": 0.8290171789445435, "maximum": 0.9169681600813054, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5483918268256369, "standard_deviation": 0.2857021705301838, "minimum": 0.17624583375652214, "maximum": 1.1004403187751441, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07446141350261762, "standard_deviation": 0.009669832751892576, "minimum": 0.06273207213303342, "maximum": 0.09059825311320009, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9800411591692539, "standard_deviation": 0.0024141101833145963, "minimum": 0.9777388129152531, "maximum": 0.9846128058796249, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5416938303254208, "standard_deviation": 0.037656483786571625, "minimum": 1.5080991521454628, "maximum": 1.6252442464822956, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.647197530218093, "standard_deviation": 0.26503192573014334, "minimum": 0.1760902465431052, "maximum": 0.9742515073024358, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16375086083309537, "standard_deviation": 0.009334437758530077, "minimum": 0.14608198221158, "maximum": 0.17615686054033367, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.993210015863695, "standard_deviation": 0.0016292354006346428, "minimum": 0.9902545969293808, "maximum": 0.9954024416132218, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9793153236290114, "standard_deviation": 0.041016287936537686, "minimum": 0.9264193354546812, "maximum": 1.0382958080361497, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.43493341143672304, "standard_deviation": 0.16715615412057422, "minimum": 0.22223840629247996, "maximum": 0.7026621423798307, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09894768343392102, "standard_deviation": 0.011824748571954237, "minimum": 0.08732802261063224, "maximum": 0.12342655417609989, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9963458299499242, "standard_deviation": 0.0004605657971531066, "minimum": 0.995732415853929, "maximum": 0.9968996001678083, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.407235653541034, "standard_deviation": 0.03640547281796464, "minimum": 1.353920678704946, "maximum": 1.4637321478362628, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4946359415452537, "standard_deviation": 0.20234112425936118, "minimum": 0.21101333404623512, "maximum": 0.748833362878805, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06408386709751963, "standard_deviation": 0.00402031614695433, "minimum": 0.05888032538076327, "maximum": 0.06944632023983428, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.998708900856534, "standard_deviation": 0.00022044602800413111, "minimum": 0.9982926739008442, "maximum": 0.9989617354211573, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.0726498558229038, "standard_deviation": 0.043690417859458625, "minimum": 1.0108190459354767, "maximum": 1.163989728141247, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7261296355552953, "standard_deviation": 0.21962230091927312, "minimum": 0.36963631219294374, "maximum": 1.047246424820747, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.037649056260652486, "standard_deviation": 0.0032461892254905802, "minimum": 0.03342107376377352, "maximum": 0.043453937434710446, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.19599596129807928, "standard_deviation": 0.021624518101115087, "minimum": 0.1613436221657351, "maximum": 0.2363335273543544, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.467803500693, "standard_deviation": 0.007319340497920242, "minimum": 5.455272797867541, "maximum": 5.477669787642003, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.15629895010269879, "standard_deviation": 0.003460727888206788, "minimum": 0.15089476584165473, "maximum": 0.16049949634142946, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.0744979506415652, "standard_deviation": 0.015216013377856108, "minimum": -0.10123564175290584, "maximum": -0.05704754129267276, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9983232275423135, "standard_deviation": 0.00022223912863009813, "minimum": 0.997858642225498, "maximum": 0.9986446705753732, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.085023502210363, "standard_deviation": 0.03980873682381381, "minimum": 1.0342330578518655, "maximum": 1.1459237335028458, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.38072388818610947, "standard_deviation": 0.20091256672266605, "minimum": 0.1594411854381498, "maximum": 0.6817179816531892, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.04120989331410167, "standard_deviation": 0.0024543033551815362, "minimum": 0.037353365771681434, "maximum": 0.04607407883369207, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9995283643616387, "standard_deviation": 5.875548776510513e-05, "minimum": 0.9994385765033923, "maximum": 0.9996132204229143, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5756526778531212, "standard_deviation": 0.028482340452783802, "minimum": 0.5404499745457139, "maximum": 0.6323843122898511, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4840598578238206, "standard_deviation": 0.18024933852115435, "minimum": 0.1786037675536296, "maximum": 0.7437503065358961, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0224973937932864, "standard_deviation": 0.001385313773957633, "minimum": 0.020845462739975867, "maximum": 0.02428834039055814, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 2.2230944633483887, "predicted_mos": 2.2230944633483887, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "cc33aae8ea7b52fc0c9b680ee0dbc3f2804d20376086e96aae70948862ff936b", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 8.96122800000012}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0843484773196224, "全帯域_10ms_rms_envelope_nrmse": 0.03837518302627169, "全帯域_10ms_envelope_correlation": 0.9985682797227412, "全帯域_10ms_modulation_mae_db": 0.19173595782402045, "全帯域_40ms_log_rms_mae_db": 0.5926225631581004, "全帯域_40ms_rms_envelope_nrmse": 0.021704378553530523, "全帯域_40ms_envelope_correlation": 0.9995765749609884, "全帯域_40ms_modulation_mae_db": 0.3347699120292987, "300–1000 Hz_10ms_log_rms_mae_db": 1.3987286973660222, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06690485040953496, "300–1000 Hz_10ms_envelope_correlation": 0.9960160674792793, "300–1000 Hz_10ms_modulation_mae_db": 0.21614291281765322, "300–1000 Hz_40ms_log_rms_mae_db": 1.0682237818410734, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038348788150353655, "300–1000 Hz_40ms_envelope_correlation": 0.9986703846237996, "300–1000 Hz_40ms_modulation_mae_db": 0.7551503452957329, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2006308655115405, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10905244808537502, "1000–3000 Hz_10ms_envelope_correlation": 0.9920247955337528, "1000–3000 Hz_10ms_modulation_mae_db": 1.1345026084359497, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8366613214890429, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06762422748205081, "1000–3000 Hz_40ms_envelope_correlation": 0.9974539810499644, "1000–3000 Hz_40ms_modulation_mae_db": 1.0159999871854362, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5011825116790727, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14823971375892037, "3000–6000 Hz_10ms_envelope_correlation": 0.9846777597905297, "3000–6000 Hz_10ms_modulation_mae_db": 0.5928561599026952, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8966095184794735, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09101606198559796, "3000–6000 Hz_40ms_envelope_correlation": 0.9955415993363879, "3000–6000 Hz_40ms_modulation_mae_db": 0.7570112898612745, "mr_stft_db": 5.441098047430434, "band_mae_db": 0.17636325121722107, "rms_gain_error_db": -0.07693690617832454, "output_peak": 0.15927304934234665}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1013005924846964, "全帯域_10ms_rms_envelope_nrmse": 0.041556491452195525, "全帯域_10ms_envelope_correlation": 0.9983403829057681, "全帯域_10ms_modulation_mae_db": 0.47183425485895025, "全帯域_40ms_log_rms_mae_db": 0.601233046861523, "全帯域_40ms_rms_envelope_nrmse": 0.02423735987479456, "全帯域_40ms_envelope_correlation": 0.9994917684035131, "全帯域_40ms_modulation_mae_db": 0.5273896889303847, "300–1000 Hz_10ms_log_rms_mae_db": 1.368602253145554, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06216133841761792, "300–1000 Hz_10ms_envelope_correlation": 0.9965730151705079, "300–1000 Hz_10ms_modulation_mae_db": 0.8120808692396527, "300–1000 Hz_40ms_log_rms_mae_db": 1.0068385781124882, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03623175706246252, "300–1000 Hz_40ms_envelope_correlation": 0.9988083395155838, "300–1000 Hz_40ms_modulation_mae_db": 1.2184560682343137, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2480499407822716, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.14056259115726882, "1000–3000 Hz_10ms_envelope_correlation": 0.9867501079631523, "1000–3000 Hz_10ms_modulation_mae_db": 1.1217904640280165, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8282207278718314, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08641439509078311, "1000–3000 Hz_40ms_envelope_correlation": 0.9960257377009809, "1000–3000 Hz_40ms_modulation_mae_db": 0.8727265487002561, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5241377238665332, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16660984882689966, "3000–6000 Hz_10ms_envelope_correlation": 0.9790906375936981, "3000–6000 Hz_10ms_modulation_mae_db": 0.5763046657242964, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9220877715189141, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09054152814802945, "3000–6000 Hz_40ms_envelope_correlation": 0.9943213768078193, "3000–6000 Hz_40ms_modulation_mae_db": 0.31159842873248317, "mr_stft_db": 5.434666021751912, "band_mae_db": 0.17953356517174618, "rms_gain_error_db": -0.09851121650521977, "output_peak": 0.15017120799282432}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1375203962657174, "全帯域_10ms_rms_envelope_nrmse": 0.040972036240132806, "全帯域_10ms_envelope_correlation": 0.9983516612139075, "全帯域_10ms_modulation_mae_db": 0.6377580119548759, "全帯域_40ms_log_rms_mae_db": 0.5869855273418463, "全帯域_40ms_rms_envelope_nrmse": 0.021096810057439668, "全帯域_40ms_envelope_correlation": 0.9995930743311952, "全帯域_40ms_modulation_mae_db": 0.760915578035598, "300–1000 Hz_10ms_log_rms_mae_db": 1.32632316332821, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06052571936812128, "300–1000 Hz_10ms_envelope_correlation": 0.9967880504311668, "300–1000 Hz_10ms_modulation_mae_db": 0.7747405994852447, "300–1000 Hz_40ms_log_rms_mae_db": 0.9447588349748168, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037275714228615524, "300–1000 Hz_40ms_envelope_correlation": 0.9987661547203748, "300–1000 Hz_40ms_modulation_mae_db": 0.9175863900718806, "1000–3000 Hz_10ms_log_rms_mae_db": 1.250431510251379, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13066362033830173, "1000–3000 Hz_10ms_envelope_correlation": 0.9884805188063731, "1000–3000 Hz_10ms_modulation_mae_db": 0.3528028841825564, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8224683403554065, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08449176137763235, "1000–3000 Hz_40ms_envelope_correlation": 0.9958463167513018, "1000–3000 Hz_40ms_modulation_mae_db": 0.22613700489060026, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5404238450804866, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.155078658392252, "3000–6000 Hz_10ms_envelope_correlation": 0.9827570924611965, "3000–6000 Hz_10ms_modulation_mae_db": 0.4377218381115071, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9905434512548893, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10307368185091885, "3000–6000 Hz_40ms_envelope_correlation": 0.9932087782172522, "3000–6000 Hz_40ms_modulation_mae_db": 0.29893264395828517, "mr_stft_db": 5.446906670508887, "band_mae_db": 0.21560107534224432, "rms_gain_error_db": -0.07396373341430834, "output_peak": 0.1602201344957705}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1381416324068443, "全帯域_10ms_rms_envelope_nrmse": 0.04572521198867139, "全帯域_10ms_envelope_correlation": 0.9978947855853675, "全帯域_10ms_modulation_mae_db": 0.22251989063631447, "全帯域_40ms_log_rms_mae_db": 0.6445153657050697, "全帯域_40ms_rms_envelope_nrmse": 0.023029299515739864, "全帯域_40ms_envelope_correlation": 0.9994687980004391, "全帯域_40ms_modulation_mae_db": 0.24172940987525213, "300–1000 Hz_10ms_log_rms_mae_db": 1.2904151616727668, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06575546146742625, "300–1000 Hz_10ms_envelope_correlation": 0.9961423872211759, "300–1000 Hz_10ms_modulation_mae_db": 0.26945443933104307, "300–1000 Hz_40ms_log_rms_mae_db": 0.9423972630797246, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03657619225174422, "300–1000 Hz_40ms_envelope_correlation": 0.9987863456029392, "300–1000 Hz_40ms_modulation_mae_db": 0.38133257032261314, "1000–3000 Hz_10ms_log_rms_mae_db": 1.202997677841719, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12670562435888397, "1000–3000 Hz_10ms_envelope_correlation": 0.9888283816895881, "1000–3000 Hz_10ms_modulation_mae_db": 0.9878438175924081, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8168676855506044, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06831815311240645, "1000–3000 Hz_40ms_envelope_correlation": 0.9973125725361356, "1000–3000 Hz_40ms_modulation_mae_db": 0.8262526120790373, "3000–6000 Hz_10ms_log_rms_mae_db": 1.558073914300514, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17823871509200975, "3000–6000 Hz_10ms_envelope_correlation": 0.9775875215899736, "3000–6000 Hz_10ms_modulation_mae_db": 1.038503174683146, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9657243289979478, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1251298597843482, "3000–6000 Hz_40ms_envelope_correlation": 0.9903014755459857, "3000–6000 Hz_40ms_modulation_mae_db": 0.9169733492102458, "mr_stft_db": 5.426348441846396, "band_mae_db": 0.2484061824899599, "rms_gain_error_db": -0.05911605944760396, "output_peak": 0.1525340980785118}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1376274037085847, "全帯域_10ms_rms_envelope_nrmse": 0.04019928745193961, "全帯域_10ms_envelope_correlation": 0.9983942217278443, "全帯域_10ms_modulation_mae_db": 0.3801561350365126, "全帯域_40ms_log_rms_mae_db": 0.5953783641216052, "全帯域_40ms_rms_envelope_nrmse": 0.0213949494760084, "全帯域_40ms_envelope_correlation": 0.9995620543781748, "全帯域_40ms_modulation_mae_db": 0.4924037982844382, "300–1000 Hz_10ms_log_rms_mae_db": 1.3569832174643033, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0643379876757443, "300–1000 Hz_10ms_envelope_correlation": 0.9963344845895709, "300–1000 Hz_10ms_modulation_mae_db": 0.5548287423435453, "300–1000 Hz_40ms_log_rms_mae_db": 0.9787007953317858, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03716202320595371, "300–1000 Hz_40ms_envelope_correlation": 0.9987446629243225, "300–1000 Hz_40ms_modulation_mae_db": 0.7986703046791429, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2386625340994701, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12484197242643769, "1000–3000 Hz_10ms_envelope_correlation": 0.9891355217176501, "1000–3000 Hz_10ms_modulation_mae_db": 0.38552351375429966, "1000–3000 Hz_40ms_log_rms_mae_db": 0.852093571292019, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07591928053341582, "1000–3000 Hz_40ms_envelope_correlation": 0.9964252723052076, "1000–3000 Hz_40ms_modulation_mae_db": 0.2104858650035514, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5304221088044774, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.157142610490897, "3000–6000 Hz_10ms_envelope_correlation": 0.9814137543890761, "3000–6000 Hz_10ms_modulation_mae_db": 0.6434371231556804, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9283339190293861, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08822494783144179, "3000–6000 Hz_40ms_envelope_correlation": 0.9944584982774888, "3000–6000 Hz_40ms_modulation_mae_db": 0.3394394909643794, "mr_stft_db": 5.4236653390762255, "band_mae_db": 0.1891065648501902, "rms_gain_error_db": -0.06338784841967149, "output_peak": 0.15401990674751276}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.050407850209364, "全帯域_10ms_rms_envelope_nrmse": 0.041502463942715194, "全帯域_10ms_envelope_correlation": 0.9982896473289432, "全帯域_10ms_modulation_mae_db": 0.17609474077418055, "全帯域_40ms_log_rms_mae_db": 0.5469208377998926, "全帯域_40ms_rms_envelope_nrmse": 0.023015197670173824, "全帯域_40ms_envelope_correlation": 0.9994938764225731, "全帯域_40ms_modulation_mae_db": 0.5126836539233753, "300–1000 Hz_10ms_log_rms_mae_db": 1.346961240629356, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.058537198601703956, "300–1000 Hz_10ms_envelope_correlation": 0.9969359827792305, "300–1000 Hz_10ms_modulation_mae_db": 0.3417744873316207, "300–1000 Hz_40ms_log_rms_mae_db": 1.0159155716309283, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03264082321705218, "300–1000 Hz_40ms_envelope_correlation": 0.9990081064438754, "300–1000 Hz_40ms_modulation_mae_db": 0.7864080020410372, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2664894917028353, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13309482533298866, "1000–3000 Hz_10ms_envelope_correlation": 0.987172553780308, "1000–3000 Hz_10ms_modulation_mae_db": 1.057616744918273, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8504104528801023, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06992300827420088, "1000–3000 Hz_40ms_envelope_correlation": 0.9965534246706271, "1000–3000 Hz_40ms_modulation_mae_db": 0.7519388762770784, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5610105165741461, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16232623027384036, "3000–6000 Hz_10ms_envelope_correlation": 0.981607701224818, "3000–6000 Hz_10ms_modulation_mae_db": 0.841172433061224, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9960162638375023, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10072115746349758, "3000–6000 Hz_40ms_envelope_correlation": 0.9945108577745724, "3000–6000 Hz_40ms_modulation_mae_db": 0.40408700887890686, "mr_stft_db": 5.4386127089297815, "band_mae_db": 0.16457142960258178, "rms_gain_error_db": -0.06969893742860442, "output_peak": 0.15675524847435313}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0976074017586792, "全帯域_10ms_rms_envelope_nrmse": 0.043422391232030566, "全帯域_10ms_envelope_correlation": 0.9981633748772148, "全帯域_10ms_modulation_mae_db": 0.38640240156567884, "全帯域_40ms_log_rms_mae_db": 0.5947084022303765, "全帯域_40ms_rms_envelope_nrmse": 0.0256363724703957, "全帯域_40ms_envelope_correlation": 0.9993958677552711, "全帯域_40ms_modulation_mae_db": 0.43214477445376254, "300–1000 Hz_10ms_log_rms_mae_db": 1.3670790674785283, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0710319525801131, "300–1000 Hz_10ms_envelope_correlation": 0.9955260062282487, "300–1000 Hz_10ms_modulation_mae_db": 0.4938782895777605, "300–1000 Hz_40ms_log_rms_mae_db": 0.9716670083459472, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04421824813410089, "300–1000 Hz_40ms_envelope_correlation": 0.9982242563246483, "300–1000 Hz_40ms_modulation_mae_db": 0.9245271233381401, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2930488785757999, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12090080649308216, "1000–3000 Hz_10ms_envelope_correlation": 0.9899629256375808, "1000–3000 Hz_10ms_modulation_mae_db": 0.4761457686474369, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8916557283483083, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06899679936908369, "1000–3000 Hz_40ms_envelope_correlation": 0.997280880653122, "1000–3000 Hz_40ms_modulation_mae_db": 0.49332044210196924, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5325467687013052, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16876864233663175, "3000–6000 Hz_10ms_envelope_correlation": 0.9788588567938126, "3000–6000 Hz_10ms_modulation_mae_db": 0.6519291964442185, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9553258099337257, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10323276288036838, "3000–6000 Hz_40ms_envelope_correlation": 0.9927007620604186, "3000–6000 Hz_40ms_modulation_mae_db": 0.4187875447428156, "mr_stft_db": 5.438552896613607, "band_mae_db": 0.18426929810934214, "rms_gain_error_db": -0.08873991433541514, "output_peak": 0.1588283711712269}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0629268041689097, "全帯域_10ms_rms_envelope_nrmse": 0.04190983896497123, "全帯域_10ms_envelope_correlation": 0.9982450407621927, "全帯域_10ms_modulation_mae_db": 0.5539085795745852, "全帯域_40ms_log_rms_mae_db": 0.558980617450092, "全帯域_40ms_rms_envelope_nrmse": 0.021756206392197115, "全帯域_40ms_envelope_correlation": 0.9995399317134549, "全帯域_40ms_modulation_mae_db": 0.5723912664808467, "300–1000 Hz_10ms_log_rms_mae_db": 1.3555319926762397, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06897425794781584, "300–1000 Hz_10ms_envelope_correlation": 0.9957757312103633, "300–1000 Hz_10ms_modulation_mae_db": 0.4915755554718522, "300–1000 Hz_40ms_log_rms_mae_db": 1.017217500652006, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04065001260217405, "300–1000 Hz_40ms_envelope_correlation": 0.998498580473386, "300–1000 Hz_40ms_modulation_mae_db": 0.5310774320238673, "1000–3000 Hz_10ms_log_rms_mae_db": 1.222375644512085, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12088569801429348, "1000–3000 Hz_10ms_envelope_correlation": 0.9893728683269296, "1000–3000 Hz_10ms_modulation_mae_db": 0.32725942070809894, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8166857599198728, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07171253450166246, "1000–3000 Hz_40ms_envelope_correlation": 0.99610823949773, "1000–3000 Hz_40ms_modulation_mae_db": 0.4028928332189195, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5896212728483685, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15650730818679987, "3000–6000 Hz_10ms_envelope_correlation": 0.9821087096904052, "3000–6000 Hz_10ms_modulation_mae_db": 0.2469007549819688, "3000–6000 Hz_40ms_log_rms_mae_db": 1.002267194850271, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09421589469225178, "3000–6000 Hz_40ms_envelope_correlation": 0.9943261478276084, "3000–6000 Hz_40ms_modulation_mae_db": 0.3421977861356546, "mr_stft_db": 5.444652427011171, "band_mae_db": 0.1900413642665956, "rms_gain_error_db": -0.06313791378556402, "output_peak": 0.15935381959744135}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.508669948633339, "spectral_convergence": 0.12695564006651047, "spectral_convergence_status": "ok", "amplitude_floor": 5.237444731722431e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.447989787910556, "spectral_convergence": 0.13270866809233905, "spectral_convergence_status": "ok", "amplitude_floor": 5.437369948912744e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.3666344057474085, "spectral_convergence": 0.1324570760062975, "spectral_convergence_status": "ok", "amplitude_floor": 5.052721691674583e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 6.432970236988243e-05, "output_power": 6.616486506700526e-05, "delta_db": 0.12215889076132248, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008444430165469724, "output_power": 0.0008260680775259488, "delta_db": -0.09554508815084739, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 6.039141474549642e-05, "output_power": 6.23068342808204e-05, "delta_db": 0.13560482320842238, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 3.556975687019485e-05, "output_power": 3.2629393001717e-05, "delta_db": -0.37471901897907345, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.090392882810899e-05, "output_power": 1.0497863774254422e-05, "delta_db": -0.16482075280822076, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2355857763199668e-06, "output_power": 1.3342958446994098e-06, "delta_db": 0.3337923334027532, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.0422411240430348e-06, "output_power": 1.0403465232748248e-06, "delta_db": -0.007901851209907915, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.17636325121722107, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.07693690617832454, "pitch": null, "output_rms_dbfs": -29.999819007126266, "output_peak": 0.15927304934234665, "reference_rms_dbfs": -29.922882100947945, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.441098047430434}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 8.184761378594803e-05, "log_rms_mae_db": 1.0843484773196224, "rms_envelope_nrmse": 0.03837518302627169, "envelope_correlation": 0.9985682797227412, "rms_gain_error_db": -0.07622885043559413, "reference_mean_power": 0.0010176842474405314, "output_mean_power": 0.0009999773592968986}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.21363647710693e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00013327602732153044, "output_power": 0.00012815095414462743, "reference_active": true, "delta_db": -0.1703019478856499}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5932863269435214e-05, "output_power": 1.6040395633184832e-05, "reference_active": true, "delta_db": 0.029212466845874537}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.59165062752131e-06, "output_power": 4.211138158114661e-06, "reference_active": true, "delta_db": -0.375693458740537}], "active_band_count": 3, "active_band_mae_db": 0.19173595782402045}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.048620680965671e-05, "log_rms_mae_db": 0.5926225631581004, "rms_envelope_nrmse": 0.021704378553530523, "envelope_correlation": 0.9995765749609884, "rms_gain_error_db": -0.07521782021539687, "reference_mean_power": 0.0010161096570352637, "output_mean_power": 0.0009986626254130443}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.9042638692252304e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00011759425242544185, "output_power": 0.00011306831320499956, "reference_active": true, "delta_db": -0.17045182290302258}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 7.519272755909202e-06, "output_power": 7.94370105865643e-06, "reference_active": true, "delta_db": 0.23847053393118417}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.598733053895232e-07, "output_power": 3.137696222832671e-07, "reference_active": true, "delta_db": -0.5953873792536892}], "active_band_count": 3, "active_band_mae_db": 0.3347699120292987}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.667982083652557e-05, "log_rms_mae_db": 1.3987286973660222, "rms_envelope_nrmse": 0.06690485040953496, "envelope_correlation": 0.9960160674792793, "rms_gain_error_db": -0.01630112791306508, "reference_mean_power": 0.00027945110045850193, "output_mean_power": 0.0002784041542541874}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.93859363437704e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.295075151115005e-05, "output_power": 3.0975818383843014e-05, "reference_active": true, "delta_db": -0.26842534743477947}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.807348843301933e-06, "output_power": 3.588452555203131e-06, "reference_active": true, "delta_db": -0.2571546172172854}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5906604704508056e-06, "output_power": 1.5462959242341804e-06, "reference_active": true, "delta_db": -0.12284877380089472}], "active_band_count": 3, "active_band_mae_db": 0.21614291281765322}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.254388131298964e-05, "log_rms_mae_db": 1.0682237818410734, "rms_envelope_nrmse": 0.038348788150353655, "envelope_correlation": 0.9986703846237996, "rms_gain_error_db": -0.01275813952904259, "reference_mean_power": 0.00027742187495382226, "output_mean_power": 0.00027660809687292555}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 9.236914065861651e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.9257092980847557e-05, "output_power": 2.7194994251281404e-05, "reference_active": true, "delta_db": -0.3174220057651228}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8979287936807737e-06, "output_power": 1.964537392715343e-06, "reference_active": true, "delta_db": 0.14980384947495312}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.43591780871064e-08, "output_power": 6.236797326288794e-08, "reference_active": true, "delta_db": -1.7982251806471228}], "active_band_count": 3, "active_band_mae_db": 0.7551503452957329}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.428909761907278e-05, "log_rms_mae_db": 1.2006308655115405, "rms_envelope_nrmse": 0.10905244808537502, "envelope_correlation": 0.9920247955337528, "rms_gain_error_db": -0.3260380077822058, "reference_mean_power": 3.509769240032237e-05, "output_mean_power": 3.255927776042461e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.14178826098124e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0207730418969553e-05, "output_power": 9.302345883119367e-06, "reference_active": true, "delta_db": -0.40336708462561544}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.594184871691995e-06, "output_power": 2.4533603345561864e-06, "reference_active": true, "delta_db": -0.24239582955254832}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.354712471534306e-07, "output_power": 1.777791445568404e-07, "reference_active": true, "delta_db": -2.7577449111296852}], "active_band_count": 3, "active_band_mae_db": 1.1345026084359497}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9506018028930777e-05, "log_rms_mae_db": 0.8366613214890429, "rms_envelope_nrmse": 0.06762422748205081, "envelope_correlation": 0.9974539810499644, "rms_gain_error_db": -0.32758888862130453, "reference_mean_power": 3.5141167460930974e-05, "output_mean_power": 3.258796916315529e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.01202004778774e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.499160468037956e-06, "output_power": 8.729013727002381e-06, "reference_active": true, "delta_db": -0.3672004776146275}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1261229797074577e-06, "output_power": 1.0818773391909225e-06, "reference_active": true, "delta_db": -0.17407796558086325}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7957517138182228e-08, "output_power": 1.5697353839308094e-08, "reference_active": true, "delta_db": -2.506721518360818}], "active_band_count": 3, "active_band_mae_db": 1.0159999871854362}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0101884937381439e-05, "log_rms_mae_db": 1.5011825116790727, "rms_envelope_nrmse": 0.14823971375892037, "envelope_correlation": 0.9846777597905297, "rms_gain_error_db": -0.4989464424635245, "reference_mean_power": 6.452617383104305e-06, "output_mean_power": 5.752296579870198e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.15273367532141e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.10173826656627e-06, "output_power": 1.8886906350207513e-06, "reference_active": true, "delta_db": -0.4641780465112977}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.3061476096447684e-07, "output_power": 3.556113345133782e-07, "reference_active": true, "delta_db": -0.8311331791839754}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.161739165108172e-08, "output_power": 9.122385831112587e-08, "reference_active": true, "delta_db": 0.4832572540128126}], "active_band_count": 3, "active_band_mae_db": 0.5928561599026952}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.618352616189344e-06, "log_rms_mae_db": 0.8966095184794735, "rms_envelope_nrmse": 0.09101606198559796, "envelope_correlation": 0.9955415993363879, "rms_gain_error_db": -0.49967182690323175, "reference_mean_power": 6.458260841661403e-06, "output_mean_power": 5.756365995179597e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.76552281278155e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.8830611185238975e-06, "output_power": 1.6871981731787449e-06, "reference_active": true, "delta_db": -0.47698319646118975}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.769776726408418e-07, "output_power": 1.4943813495661654e-07, "reference_active": true, "delta_db": -0.7345704081571637}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.816205310457936e-09, "output_power": 7.691226599965459e-09, "reference_active": true, "delta_db": -1.0594802649654704}], "active_band_count": 3, "active_band_mae_db": 0.7570112898612745}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9321498481865005, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "a6af867abddff1f9954df3467676f23eb0f18ac16c9c6e64787b962cd162749d", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9889659591819169, "standard_deviation": 0.0016442813423531604, "minimum": 0.9867501079631523, "maximum": 0.9920247955337528, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.2403358179096375, "standard_deviation": 0.03144178241284057, "minimum": 1.2006308655115405, "maximum": 1.2930488785757999, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7304356527833799, "standard_deviation": 0.3738831815555352, "minimum": 0.32725942070809894, "maximum": 1.1345026084359497, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12583844827582893, "standard_deviation": 0.00945033997438661, "minimum": 0.10905244808537502, "maximum": 0.14056259115726882, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9966258031456336, "standard_deviation": 0.0006400511526233926, "minimum": 0.9958463167513018, "maximum": 0.9974539810499644, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8393829484633986, "standard_deviation": 0.025229843792138565, "minimum": 0.8166857599198728, "maximum": 0.8916557283483083, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5999692711821061, "standard_deviation": 0.30785849775762464, "minimum": 0.2104858650035514, "maximum": 1.0159999871854362, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07417501996765444, "standard_deviation": 0.007439787630175413, "minimum": 0.06762422748205081, "maximum": 0.08641439509078311, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9810127541916887, "standard_deviation": 0.0023377916385343193, "minimum": 0.9775875215899736, "maximum": 0.9846777597905297, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.542177332731863, "standard_deviation": 0.026987637874251496, "minimum": 1.5011825116790727, "maximum": 1.5896212728483685, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.628603168258092, "standard_deviation": 0.23907956054359544, "minimum": 0.2469007549819688, "maximum": 1.038503174683146, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16161396591978133, "standard_deviation": 0.009416472528166145, "minimum": 0.14823971375892037, "maximum": 0.17823871509200975, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9936711869809416, "standard_deviation": 0.0016118122261415948, "minimum": 0.9903014755459857, "maximum": 0.9955415993363879, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9571135322377637, "standard_deviation": 0.03866150311511417, "minimum": 0.8966095184794735, "maximum": 1.002267194850271, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.47362844281050565, "standard_deviation": 0.23199664993813154, "minimum": 0.29893264395828517, "maximum": 0.9169733492102458, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09951948682955675, "standard_deviation": 0.011906556497387033, "minimum": 0.08822494783144179, "maximum": 0.1251298597843482, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9962614656386929, "standard_deviation": 0.0004907571700870151, "minimum": 0.9955260062282487, "maximum": 0.9969359827792305, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.3513280992201226, "standard_deviation": 0.032066140165090004, "minimum": 1.2904151616727668, "maximum": 1.3987286973660222, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4943094869497966, "standard_deviation": 0.21859743247046307, "minimum": 0.21614291281765322, "maximum": 0.8120808692396527, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.0647785958085097, "standard_deviation": 0.004247174619358931, "minimum": 0.058537198601703956, "maximum": 0.0710319525801131, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9986883538286162, "standard_deviation": 0.00023518615507148126, "minimum": 0.9982242563246483, "maximum": 0.9990081064438754, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.9932149167460963, "standard_deviation": 0.04227254363879003, "minimum": 0.9423972630797246, "maximum": 1.0682237818410734, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7891510295008409, "standard_deviation": 0.254473464683676, "minimum": 0.38133257032261314, "maximum": 1.2184560682343137, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.037887944856557096, "standard_deviation": 0.003397727420085435, "minimum": 0.03264082321705218, "maximum": 0.04421824813410089, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.19348659138123514, "standard_deviation": 0.026579280075750628, "minimum": 0.16457142960258178, "maximum": 0.2484061824899599, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.436812819146052, "standard_deviation": 0.008237060021610527, "minimum": 5.4236653390762255, "maximum": 5.446906670508887, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.15639447948749843, "standard_deviation": 0.003722589842427865, "minimum": 0.15017120799282432, "maximum": 0.1602201344957705, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07418656618933897, "standard_deviation": 0.013612214003327232, "minimum": -0.09851121650521977, "maximum": -0.05911605944760396, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9982809242654974, "standard_deviation": 0.00019575245890761242, "minimum": 0.9978947855853675, "maximum": 0.9985682797227412, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.1012350697903022, "standard_deviation": 0.03454266924235265, "minimum": 1.050407850209364, "maximum": 1.1381416324068443, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.37755124652813976, "standard_deviation": 0.1719346430142631, "minimum": 0.17609474077418055, "maximum": 0.6377580119548759, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.041707863037366004, "standard_deviation": 0.002174810118998412, "minimum": 0.03837518302627169, "maximum": 0.04572521198867139, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9995152432457013, "standard_deviation": 6.550391220808085e-05, "minimum": 0.9993958677552711, "maximum": 0.9995930743311952, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5901680905835631, "standard_deviation": 0.029235393053502964, "minimum": 0.5469208377998926, "maximum": 0.6445153657050697, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.48430351025161955, "standard_deviation": 0.1562617674408462, "minimum": 0.24172940987525213, "maximum": 0.760915578035598, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.022733821751284956, "standard_deviation": 0.0015738841138085585, "minimum": 0.021096810057439668, "maximum": 0.0256363724703957, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 2.3972227573394775, "predicted_mos": 2.3972227573394775, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "66332792b4ffc331d2a61a628c8fb5ad2f884531e0e75c587ac16883e4cf2438", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 8.389551000203937}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0465946044447691, "全帯域_10ms_rms_envelope_nrmse": 0.039248939848255525, "全帯域_10ms_envelope_correlation": 0.9984803625398163, "全帯域_10ms_modulation_mae_db": 0.5303377413052645, "全帯域_40ms_log_rms_mae_db": 0.5241807590674084, "全帯域_40ms_rms_envelope_nrmse": 0.020605285965172294, "全帯域_40ms_envelope_correlation": 0.99960649793845, "全帯域_40ms_modulation_mae_db": 0.45496924031281655, "300–1000 Hz_10ms_log_rms_mae_db": 1.5659612598319463, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06314321509200585, "300–1000 Hz_10ms_envelope_correlation": 0.9964531828212113, "300–1000 Hz_10ms_modulation_mae_db": 0.7243878679710773, "300–1000 Hz_40ms_log_rms_mae_db": 1.2127894067438036, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03556205107334563, "300–1000 Hz_40ms_envelope_correlation": 0.9988366161120698, "300–1000 Hz_40ms_modulation_mae_db": 0.8633614459082634, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5792440902123428, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13607803178919156, "1000–3000 Hz_10ms_envelope_correlation": 0.9874681048699421, "1000–3000 Hz_10ms_modulation_mae_db": 0.6128330472577371, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1259961840554646, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08006453777720227, "1000–3000 Hz_40ms_envelope_correlation": 0.9965607120983779, "1000–3000 Hz_40ms_modulation_mae_db": 0.4985815020422337, "3000–6000 Hz_10ms_log_rms_mae_db": 1.9417641093512967, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1838182225118643, "3000–6000 Hz_10ms_envelope_correlation": 0.9744226528653457, "3000–6000 Hz_10ms_modulation_mae_db": 0.528068845157161, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2648101756368264, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10437434381815935, "3000–6000 Hz_40ms_envelope_correlation": 0.9924399182478727, "3000–6000 Hz_40ms_modulation_mae_db": 0.933815621719388, "mr_stft_db": 5.683460514368041, "band_mae_db": 0.24895870175757975, "rms_gain_error_db": -0.07005225026357727, "output_peak": 0.15171780527873135}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1105954818277033, "全帯域_10ms_rms_envelope_nrmse": 0.047170514573117064, "全帯域_10ms_envelope_correlation": 0.9978870350937835, "全帯域_10ms_modulation_mae_db": 0.40476338355354874, "全帯域_40ms_log_rms_mae_db": 0.546575864046516, "全帯域_40ms_rms_envelope_nrmse": 0.026779039156824665, "全帯域_40ms_envelope_correlation": 0.9994126231600148, "全帯域_40ms_modulation_mae_db": 0.3944523852017561, "300–1000 Hz_10ms_log_rms_mae_db": 1.5457564187642328, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06418229994704623, "300–1000 Hz_10ms_envelope_correlation": 0.996355360319096, "300–1000 Hz_10ms_modulation_mae_db": 0.9452070522054591, "300–1000 Hz_40ms_log_rms_mae_db": 1.2106338627995203, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.036692316682961475, "300–1000 Hz_40ms_envelope_correlation": 0.9987916486015456, "300–1000 Hz_40ms_modulation_mae_db": 1.3011756429691006, "1000–3000 Hz_10ms_log_rms_mae_db": 1.526165502296774, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11592056824115413, "1000–3000 Hz_10ms_envelope_correlation": 0.9912595789061013, "1000–3000 Hz_10ms_modulation_mae_db": 1.0833069858333737, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0770998677643686, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06954736166667443, "1000–3000 Hz_40ms_envelope_correlation": 0.9977096118651902, "1000–3000 Hz_40ms_modulation_mae_db": 1.407426859263816, "3000–6000 Hz_10ms_log_rms_mae_db": 1.9162983281041406, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19642656047032428, "3000–6000 Hz_10ms_envelope_correlation": 0.97015405829523, "3000–6000 Hz_10ms_modulation_mae_db": 0.6651516411199587, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2354233709647822, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11428275283209552, "3000–6000 Hz_40ms_envelope_correlation": 0.9895893604387294, "3000–6000 Hz_40ms_modulation_mae_db": 0.47476123847024304, "mr_stft_db": 5.6791819194979185, "band_mae_db": 0.1985533511834194, "rms_gain_error_db": -0.11811899163813831, "output_peak": 0.15639842261889375}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0302204104471768, "全帯域_10ms_rms_envelope_nrmse": 0.03898780258881807, "全帯域_10ms_envelope_correlation": 0.9985257288232955, "全帯域_10ms_modulation_mae_db": 0.2430967952570251, "全帯域_40ms_log_rms_mae_db": 0.565752063495434, "全帯域_40ms_rms_envelope_nrmse": 0.022913314500392377, "全帯域_40ms_envelope_correlation": 0.999529589786182, "全帯域_40ms_modulation_mae_db": 0.08116168777183974, "300–1000 Hz_10ms_log_rms_mae_db": 1.494535001064376, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.059113447658182904, "300–1000 Hz_10ms_envelope_correlation": 0.9969218216316954, "300–1000 Hz_10ms_modulation_mae_db": 0.5144263002237867, "300–1000 Hz_40ms_log_rms_mae_db": 1.1434865303011512, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0366452623471297, "300–1000 Hz_40ms_envelope_correlation": 0.9987838075841841, "300–1000 Hz_40ms_modulation_mae_db": 0.5676363552657459, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5862281119101418, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.14202480806578974, "1000–3000 Hz_10ms_envelope_correlation": 0.9857282938358706, "1000–3000 Hz_10ms_modulation_mae_db": 0.39071029903693155, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1490419111750612, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0836251687953391, "1000–3000 Hz_40ms_envelope_correlation": 0.9955659146535007, "1000–3000 Hz_40ms_modulation_mae_db": 0.3255304364619347, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8963650140833426, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1718348613582663, "3000–6000 Hz_10ms_envelope_correlation": 0.9775759825025147, "3000–6000 Hz_10ms_modulation_mae_db": 0.26043787760615156, "3000–6000 Hz_40ms_log_rms_mae_db": 1.246827303403538, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10080262926396694, "3000–6000 Hz_40ms_envelope_correlation": 0.9926161016888979, "3000–6000 Hz_40ms_modulation_mae_db": 0.652568123441662, "mr_stft_db": 5.694127765112007, "band_mae_db": 0.20996303948798703, "rms_gain_error_db": -0.08220659989539791, "output_peak": 0.15432327665084422}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0798869220332423, "全帯域_10ms_rms_envelope_nrmse": 0.04189952176457903, "全帯域_10ms_envelope_correlation": 0.9982399227858314, "全帯域_10ms_modulation_mae_db": 0.6683155260672328, "全帯域_40ms_log_rms_mae_db": 0.5898602972981142, "全帯域_40ms_rms_envelope_nrmse": 0.020933750341372515, "全帯域_40ms_envelope_correlation": 0.9995704052168449, "全帯域_40ms_modulation_mae_db": 0.6636453139045675, "300–1000 Hz_10ms_log_rms_mae_db": 1.5259815498737719, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06640436059485814, "300–1000 Hz_10ms_envelope_correlation": 0.9960889781921051, "300–1000 Hz_10ms_modulation_mae_db": 0.8990280941902719, "300–1000 Hz_40ms_log_rms_mae_db": 1.207986146008049, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03973571691071961, "300–1000 Hz_40ms_envelope_correlation": 0.9985446017709306, "300–1000 Hz_40ms_modulation_mae_db": 1.0428338689553165, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5002175640426874, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1522205034777049, "1000–3000 Hz_10ms_envelope_correlation": 0.9831015375376385, "1000–3000 Hz_10ms_modulation_mae_db": 0.3946573685577315, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0454835570162557, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08655496492142149, "1000–3000 Hz_40ms_envelope_correlation": 0.9945599957239616, "1000–3000 Hz_40ms_modulation_mae_db": 0.5877581521820993, "3000–6000 Hz_10ms_log_rms_mae_db": 1.96011068293728, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1738722951036945, "3000–6000 Hz_10ms_envelope_correlation": 0.9767470892125272, "3000–6000 Hz_10ms_modulation_mae_db": 0.12370245283792304, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2369580449579423, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09532158287907459, "3000–6000 Hz_40ms_envelope_correlation": 0.9930113613772747, "3000–6000 Hz_40ms_modulation_mae_db": 0.524628988230418, "mr_stft_db": 5.697940834384123, "band_mae_db": 0.1716790921238284, "rms_gain_error_db": -0.054204377301654505, "output_peak": 0.15223257351062547}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0893664696934426, "全帯域_10ms_rms_envelope_nrmse": 0.04253391564904318, "全帯域_10ms_envelope_correlation": 0.9982664631234545, "全帯域_10ms_modulation_mae_db": 0.5868630591364025, "全帯域_40ms_log_rms_mae_db": 0.5394637130313757, "全帯域_40ms_rms_envelope_nrmse": 0.022898979160639595, "全帯域_40ms_envelope_correlation": 0.9995675720231331, "全帯域_40ms_modulation_mae_db": 0.7014969701497868, "300–1000 Hz_10ms_log_rms_mae_db": 1.4835856603014586, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05936091121993551, "300–1000 Hz_10ms_envelope_correlation": 0.9968729993660506, "300–1000 Hz_10ms_modulation_mae_db": 0.46847985875924586, "300–1000 Hz_40ms_log_rms_mae_db": 1.113102139850085, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03310338043983642, "300–1000 Hz_40ms_envelope_correlation": 0.9990195558115058, "300–1000 Hz_40ms_modulation_mae_db": 0.7076672142362946, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5219100623413775, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13410758494520963, "1000–3000 Hz_10ms_envelope_correlation": 0.9871289766646539, "1000–3000 Hz_10ms_modulation_mae_db": 0.4258250747815468, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0675685181059225, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08285870971140631, "1000–3000 Hz_40ms_envelope_correlation": 0.9952549085335665, "1000–3000 Hz_40ms_modulation_mae_db": 0.9478482042254738, "3000–6000 Hz_10ms_log_rms_mae_db": 1.9450680959473867, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1682701536153588, "3000–6000 Hz_10ms_envelope_correlation": 0.9783993012326966, "3000–6000 Hz_10ms_modulation_mae_db": 0.5356605030509394, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2526185104218641, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09137667847576769, "3000–6000 Hz_40ms_envelope_correlation": 0.9939349214012789, "3000–6000 Hz_40ms_modulation_mae_db": 0.46960491177272184, "mr_stft_db": 5.698223421569502, "band_mae_db": 0.24222221673619473, "rms_gain_error_db": -0.10205292577054838, "output_peak": 0.150662621858543}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0692311094070615, "全帯域_10ms_rms_envelope_nrmse": 0.04051938533841834, "全帯域_10ms_envelope_correlation": 0.9984186782750405, "全帯域_10ms_modulation_mae_db": 0.44872605450853786, "全帯域_40ms_log_rms_mae_db": 0.5718027827594299, "全帯域_40ms_rms_envelope_nrmse": 0.02361303192677529, "全帯域_40ms_envelope_correlation": 0.9995101425722797, "全帯域_40ms_modulation_mae_db": 0.29212072809636364, "300–1000 Hz_10ms_log_rms_mae_db": 1.5179520041221195, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06602890353782512, "300–1000 Hz_10ms_envelope_correlation": 0.996112039322653, "300–1000 Hz_10ms_modulation_mae_db": 0.6006037647972614, "300–1000 Hz_40ms_log_rms_mae_db": 1.2266389573977323, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.040442115751558816, "300–1000 Hz_40ms_envelope_correlation": 0.9984965229274152, "300–1000 Hz_40ms_modulation_mae_db": 0.43897266137017077, "1000–3000 Hz_10ms_log_rms_mae_db": 1.549670786958635, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12193674462433644, "1000–3000 Hz_10ms_envelope_correlation": 0.9902691320189535, "1000–3000 Hz_10ms_modulation_mae_db": 0.7302257723045176, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1063803721620362, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07437629125795184, "1000–3000 Hz_40ms_envelope_correlation": 0.997300938353867, "1000–3000 Hz_40ms_modulation_mae_db": 0.5755743344431091, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8768996124921538, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17642287294245435, "3000–6000 Hz_10ms_envelope_correlation": 0.9759748750589428, "3000–6000 Hz_10ms_modulation_mae_db": 0.6785828700902706, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2156146163123338, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09999816249738513, "3000–6000 Hz_40ms_envelope_correlation": 0.9921997262559918, "3000–6000 Hz_40ms_modulation_mae_db": 0.2608883739247418, "mr_stft_db": 5.687666516689229, "band_mae_db": 0.23471576299900754, "rms_gain_error_db": -0.090951356260256, "output_peak": 0.15590391859749408}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.13001257814701, "全帯域_10ms_rms_envelope_nrmse": 0.03817609165095955, "全帯域_10ms_envelope_correlation": 0.9986204781272805, "全帯域_10ms_modulation_mae_db": 0.3943202240824164, "全帯域_40ms_log_rms_mae_db": 0.5427362779919621, "全帯域_40ms_rms_envelope_nrmse": 0.02095422301895542, "全帯域_40ms_envelope_correlation": 0.9996483243872476, "全帯域_40ms_modulation_mae_db": 0.38378579269550356, "300–1000 Hz_10ms_log_rms_mae_db": 1.4841836613010557, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.062135474375682134, "300–1000 Hz_10ms_envelope_correlation": 0.9966022233661557, "300–1000 Hz_10ms_modulation_mae_db": 0.4466904374355746, "300–1000 Hz_40ms_log_rms_mae_db": 1.188447969408494, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037211028485163535, "300–1000 Hz_40ms_envelope_correlation": 0.9987713224229092, "300–1000 Hz_40ms_modulation_mae_db": 0.6232635519538957, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5482743859672716, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12041883593025605, "1000–3000 Hz_10ms_envelope_correlation": 0.9896842577180469, "1000–3000 Hz_10ms_modulation_mae_db": 0.34596429615422775, "1000–3000 Hz_40ms_log_rms_mae_db": 1.133428704204776, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.073133538073931, "1000–3000 Hz_40ms_envelope_correlation": 0.9963571116959916, "1000–3000 Hz_40ms_modulation_mae_db": 0.2337070676753136, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8925970727097328, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15682350622057542, "3000–6000 Hz_10ms_envelope_correlation": 0.9814436177994224, "3000–6000 Hz_10ms_modulation_mae_db": 0.2859443552434753, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2332404151200707, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09723592289841573, "3000–6000 Hz_40ms_envelope_correlation": 0.9931035516984823, "3000–6000 Hz_40ms_modulation_mae_db": 0.2500971898554188, "mr_stft_db": 5.690978424161905, "band_mae_db": 0.17748805296398978, "rms_gain_error_db": -0.09729383231291566, "output_peak": 0.15063529586760208}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.073723828752664, "全帯域_10ms_rms_envelope_nrmse": 0.03987436900514623, "全帯域_10ms_envelope_correlation": 0.998480578225447, "全帯域_10ms_modulation_mae_db": 0.6164848194510087, "全帯域_40ms_log_rms_mae_db": 0.5429762435032218, "全帯域_40ms_rms_envelope_nrmse": 0.023145266871470293, "全帯域_40ms_envelope_correlation": 0.999538622056471, "全帯域_40ms_modulation_mae_db": 0.8145142383349199, "300–1000 Hz_10ms_log_rms_mae_db": 1.5000390078663908, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06420524430325743, "300–1000 Hz_10ms_envelope_correlation": 0.9963465055466246, "300–1000 Hz_10ms_modulation_mae_db": 0.7190940136969507, "300–1000 Hz_40ms_log_rms_mae_db": 1.1691377544318005, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.039009248781411834, "300–1000 Hz_40ms_envelope_correlation": 0.9986216207802863, "300–1000 Hz_40ms_modulation_mae_db": 0.8681171944504396, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5346899622380892, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13167467482803932, "1000–3000 Hz_10ms_envelope_correlation": 0.9873710293919735, "1000–3000 Hz_10ms_modulation_mae_db": 0.16164417399795533, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0713969500918015, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06860969152588788, "1000–3000 Hz_40ms_envelope_correlation": 0.9965867237625639, "1000–3000 Hz_40ms_modulation_mae_db": 0.3881427616819604, "3000–6000 Hz_10ms_log_rms_mae_db": 1.9354396275251735, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1931300846709713, "3000–6000 Hz_10ms_envelope_correlation": 0.9717363625826706, "3000–6000 Hz_10ms_modulation_mae_db": 0.12978278124110407, "3000–6000 Hz_40ms_log_rms_mae_db": 1.268087663958904, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12456470573246739, "3000–6000 Hz_40ms_envelope_correlation": 0.9886861838211446, "3000–6000 Hz_40ms_modulation_mae_db": 0.3285218402315881, "mr_stft_db": 5.688182707491193, "band_mae_db": 0.20046398194625706, "rms_gain_error_db": -0.09393524211099541, "output_peak": 0.15115934243019188}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.77865667085599, "spectral_convergence": 0.1294888660745844, "spectral_convergence_status": "ok", "amplitude_floor": 5.237444731722431e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.7225117250764574, "spectral_convergence": 0.13354259591487883, "spectral_convergence_status": "ok", "amplitude_floor": 5.437369948912744e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.549213147171675, "spectral_convergence": 0.1353154002140073, "spectral_convergence_status": "ok", "amplitude_floor": 5.052721691674583e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 6.432970236988243e-05, "output_power": 6.781248181213445e-05, "delta_db": 0.2289809696475908, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008444430165469724, "output_power": 0.0008269317982546776, "delta_db": -0.09100656172956535, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 6.039141474549642e-05, "output_power": 6.230702634770489e-05, "delta_db": 0.13561821073813532, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 3.556975687019485e-05, "output_power": 3.1965886536779504e-05, "delta_db": -0.46394143074194116, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.090392882810899e-05, "output_power": 1.0208471441732574e-05, "delta_db": -0.2862228994104778, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2355857763199668e-06, "output_power": 1.3765082904561133e-06, "delta_db": 0.46905931218084396, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.0422411240430348e-06, "output_power": 1.0260772354996934e-06, "delta_db": -0.06788152785450369, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.24895870175757975, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.07005225026357727, "pitch": null, "output_rms_dbfs": -29.992934351211524, "output_peak": 0.15171780527873135, "reference_rms_dbfs": -29.922882100947945, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.683460514368041}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 8.184761378594803e-05, "log_rms_mae_db": 1.0465946044447691, "rms_envelope_nrmse": 0.039248939848255525, "envelope_correlation": 0.9984803625398163, "rms_gain_error_db": -0.06887157015745596, "reference_mean_power": 0.0010176842474405314, "output_mean_power": 0.0010016728330567068}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.21363647710693e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00013327602732153044, "output_power": 0.00012797226396579206, "reference_active": true, "delta_db": -0.17636185700300727}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5932863269435214e-05, "output_power": 1.4571558229572435e-05, "reference_active": true, "delta_db": -0.3878783305350242}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.59165062752131e-06, "output_power": 3.624862456385793e-06, "reference_active": true, "delta_db": -1.0267730363777618}], "active_band_count": 3, "active_band_mae_db": 0.5303377413052645}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.048620680965671e-05, "log_rms_mae_db": 0.5241807590674084, "rms_envelope_nrmse": 0.020605285965172294, "envelope_correlation": 0.99960649793845, "rms_gain_error_db": -0.06763444970733545, "reference_mean_power": 0.0010161096570352637, "output_mean_power": 0.0010004079491067854}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.9042638692252304e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00011759425242544185, "output_power": 0.000113618878066897, "reference_active": true, "delta_db": -0.14935599033657374}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 7.519272755909202e-06, "output_power": 6.797299601302017e-06, "reference_active": true, "delta_db": -0.43839426280970806}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.598733053895232e-07, "output_power": 3.0090810526415185e-07, "reference_active": true, "delta_db": -0.7771574677921679}], "active_band_count": 3, "active_band_mae_db": 0.45496924031281655}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.667982083652557e-05, "log_rms_mae_db": 1.5659612598319463, "rms_envelope_nrmse": 0.06314321509200585, "envelope_correlation": 0.9964531828212113, "rms_gain_error_db": 0.022537055015371333, "reference_mean_power": 0.00027945110045850193, "output_mean_power": 0.0002809050388950621}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.93859363437704e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.295075151115005e-05, "output_power": 3.2319187002948906e-05, "reference_active": true, "delta_db": -0.08404896585444024}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.807348843301933e-06, "output_power": 3.4573340887986444e-06, "reference_active": true, "delta_db": -0.41881322019131356}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5906604704508056e-06, "output_power": 1.082797755233711e-06, "reference_active": true, "delta_db": -1.6703014178674782}], "active_band_count": 3, "active_band_mae_db": 0.7243878679710773}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.254388131298964e-05, "log_rms_mae_db": 1.2127894067438036, "rms_envelope_nrmse": 0.03556205107334563, "envelope_correlation": 0.9988366161120698, "rms_gain_error_db": 0.02549877274287101, "reference_mean_power": 0.00027742187495382226, "output_mean_power": 0.0002790554956696596}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 9.236914065861651e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.9257092980847557e-05, "output_power": 2.8700002716413252e-05, "reference_active": true, "delta_db": -0.08349234083368873}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8979287936807737e-06, "output_power": 1.7541877775663223e-06, "reference_active": true, "delta_db": -0.3420383387233563}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.43591780871064e-08, "output_power": 5.732298315476013e-08, "reference_active": true, "delta_db": -2.164553658167745}], "active_band_count": 3, "active_band_mae_db": 0.8633614459082634}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.428909761907278e-05, "log_rms_mae_db": 1.5792440902123428, "rms_envelope_nrmse": 0.13607803178919156, "envelope_correlation": 0.9874681048699421, "rms_gain_error_db": -0.4066379677698664, "reference_mean_power": 3.509769240032237e-05, "output_mean_power": 3.1960588438515205e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.14178826098124e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0207730418969553e-05, "output_power": 9.296973113915944e-06, "reference_active": true, "delta_db": -0.40587617012800503}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.594184871691995e-06, "output_power": 2.108926093636945e-06, "reference_active": true, "delta_db": -0.8993956201078708}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.354712471534306e-07, "output_power": 3.792958040726664e-07, "reference_active": true, "delta_db": 0.5332273515373357}], "active_band_count": 3, "active_band_mae_db": 0.6128330472577371}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9506018028930777e-05, "log_rms_mae_db": 1.1259961840554646, "rms_envelope_nrmse": 0.08006453777720227, "envelope_correlation": 0.9965607120983779, "rms_gain_error_db": -0.4044829319188387, "reference_mean_power": 3.5141167460930974e-05, "output_mean_power": 3.20160605281966e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.01202004778774e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.499160468037956e-06, "output_power": 8.616231538886248e-06, "reference_active": true, "delta_db": -0.42367863229041647}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1261229797074577e-06, "output_power": 9.72066470614553e-07, "reference_active": true, "delta_db": -0.6388985747708094}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7957517138182228e-08, "output_power": 3.0889816592960784e-08, "reference_active": true, "delta_db": 0.43316729906547524}], "active_band_count": 3, "active_band_mae_db": 0.4985815020422337}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0101884937381439e-05, "log_rms_mae_db": 1.9417641093512967, "rms_envelope_nrmse": 0.1838182225118643, "envelope_correlation": 0.9744226528653457, "rms_gain_error_db": -0.39770009371293646, "reference_mean_power": 6.452617383104305e-06, "output_mean_power": 5.887974282283701e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.15273367532141e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.10173826656627e-06, "output_power": 1.9280334203180737e-06, "reference_active": true, "delta_db": -0.37464073903292067}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.3061476096447684e-07, "output_power": 3.7106936726558277e-07, "reference_active": true, "delta_db": -0.6463380914592831}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.161739165108172e-08, "output_power": 7.169022457859379e-08, "reference_active": true, "delta_db": -0.5632277049792794}], "active_band_count": 3, "active_band_mae_db": 0.528068845157161}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.618352616189344e-06, "log_rms_mae_db": 1.2648101756368264, "rms_envelope_nrmse": 0.10437434381815935, "envelope_correlation": 0.9924399182478727, "rms_gain_error_db": -0.3988780795141284, "reference_mean_power": 6.458260841661403e-06, "output_mean_power": 5.891525662481187e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.76552281278155e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.8830611185238975e-06, "output_power": 1.7252484714491693e-06, "reference_active": true, "delta_db": -0.38012764845382074}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.769776726408418e-07, "output_power": 1.6432803262356842e-07, "reference_active": true, "delta_db": -0.3220682378108919}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.816205310457936e-09, "output_power": 6.053667108430739e-09, "reference_active": true, "delta_db": -2.0992509788934512}], "active_band_count": 3, "active_band_mae_db": 0.933815621719388}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9248284503170189, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "0f7d952eee278d8f15c9dc7929e76fdcc93260f6a66179a76260aa487be987d9", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9877513638678976, "standard_deviation": 0.0026378768766082677, "minimum": 0.9831015375376385, "maximum": 0.9912595789061013, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.543300058245915, "standard_deviation": 0.028986404050417323, "minimum": 1.5002175640426874, "maximum": 1.5862281119101418, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5181458772405027, "standard_deviation": 0.2853826881669606, "minimum": 0.16164417399795533, "maximum": 1.0833069858333737, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.13179771898771023, "standard_deviation": 0.012095789624495134, "minimum": 0.11592056824115413, "maximum": 0.1522205034777049, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9962369895858774, "standard_deviation": 0.0010535162965917986, "minimum": 0.9945599957239616, "maximum": 0.9977096118651902, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.0970495080719607, "standard_deviation": 0.03690886251266431, "minimum": 1.0454835570162557, "maximum": 1.1490419111750612, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6205711647469925, "standard_deviation": 0.38451655257006573, "minimum": 0.2337070676753136, "maximum": 1.407426859263816, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0773462829662268, "standard_deviation": 0.00682138718770518, "minimum": 0.06860969152588788, "maximum": 0.08655496492142149, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9758067424436687, "standard_deviation": 0.0036444672374586463, "minimum": 0.97015405829523, "maximum": 0.9814436177994224, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.9205678178938133, "standard_deviation": 0.02958675934148534, "minimum": 1.8768996124921538, "maximum": 1.96011068293728, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.400916415793373, "standard_deviation": 0.22820931711619719, "minimum": 0.12370245283792304, "maximum": 0.6785828700902706, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17757481961168867, "standard_deviation": 0.013101314495724437, "minimum": 0.15682350622057542, "maximum": 0.19642656047032428, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9919476406162091, "standard_deviation": 0.0018271065208621691, "minimum": 0.9886861838211446, "maximum": 0.9939349214012789, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.2441975125970326, "standard_deviation": 0.01748421987294636, "minimum": 1.2156146163123338, "maximum": 1.268087663958904, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.4868607859557727, "standard_deviation": 0.22718460128460574, "minimum": 0.2500971898554188, "maximum": 0.933815621719388, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10349459729966655, "standard_deviation": 0.01091128248278015, "minimum": 0.09137667847576769, "maximum": 0.12456470573246739, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.996469138820699, "standard_deviation": 0.0003130535736892273, "minimum": 0.9960889781921051, "maximum": 0.9969218216316954, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.514749320390669, "standard_deviation": 0.02988302977385393, "minimum": 1.4835856603014586, "maximum": 1.5659612598319463, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6647396736599533, "standard_deviation": 0.1900512055776072, "minimum": 0.4466904374355746, "maximum": 0.9452070522054591, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06307173209109916, "standard_deviation": 0.0027435478106693583, "minimum": 0.059113447658182904, "maximum": 0.06640436059485814, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9987332120013558, "standard_deviation": 0.00017077992461557218, "minimum": 0.9984965229274152, "maximum": 0.9990195558115058, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.1840278458675795, "standard_deviation": 0.03935211166868936, "minimum": 1.113102139850085, "maximum": 1.2266389573977323, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8016284918886534, "standard_deviation": 0.27848401856305516, "minimum": 0.43897266137017077, "maximum": 1.3011756429691006, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03730014005901588, "standard_deviation": 0.0023953853864681776, "minimum": 0.03310338043983642, "maximum": 0.040442115751558816, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.21050552489978297, "standard_deviation": 0.02906239014680636, "minimum": 0.1716790921238284, "maximum": 0.24895870175757975, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.68997026290924, "standard_deviation": 0.006731733292336912, "minimum": 5.6791819194979185, "maximum": 5.698223421569502, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.15287915710161573, "standard_deviation": 0.002338876585716999, "minimum": 0.15063529586760208, "maximum": 0.15639842261889375, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.08860194694418544, "standard_deviation": 0.01974799049348619, "minimum": -0.11811899163813831, "maximum": -0.054204377301654505, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9983649058742436, "standard_deviation": 0.00023128684521889754, "minimum": 0.9978870350937835, "maximum": 0.9986204781272805, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.0787039255941338, "standard_deviation": 0.03220677362157148, "minimum": 1.0302204104471768, "maximum": 1.13001257814701, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4866134504201796, "standard_deviation": 0.14030441579155675, "minimum": 0.2430967952570251, "maximum": 0.6683155260672328, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.041051317552292126, "standard_deviation": 0.0028736204844579073, "minimum": 0.03817609165095955, "maximum": 0.047170514573117064, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.999547972142578, "standard_deviation": 7.02637871963853e-05, "minimum": 0.9994126231600148, "maximum": 0.9996483243872476, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5529185001491828, "standard_deviation": 0.021164853147650688, "minimum": 0.5241807590674084, "maximum": 0.5898602972981142, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4732682945584442, "standard_deviation": 0.24080118800599387, "minimum": 0.08116168777183974, "maximum": 0.8145142383349199, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.022730361367700305, "standard_deviation": 0.002010805582068939, "minimum": 0.020605285965172294, "maximum": 0.026779039156824665, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 2.873889923095703, "predicted_mos": 2.873889923095703, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "2a9e7a21a3c7906549863736a2f50fa217b673f18e5fd8b927478b0afaa97f46", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 9.355890600010753}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0969482128528827, "全帯域_10ms_rms_envelope_nrmse": 0.04089707118669061, "全帯域_10ms_envelope_correlation": 0.9983342279372369, "全帯域_10ms_modulation_mae_db": 0.653171694835795, "全帯域_40ms_log_rms_mae_db": 0.5426053700898948, "全帯域_40ms_rms_envelope_nrmse": 0.02083813734631426, "全帯域_40ms_envelope_correlation": 0.9995813975735246, "全帯域_40ms_modulation_mae_db": 0.7858684202613339, "300–1000 Hz_10ms_log_rms_mae_db": 1.414813524340979, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06140875605932435, "300–1000 Hz_10ms_envelope_correlation": 0.9966638087560914, "300–1000 Hz_10ms_modulation_mae_db": 1.071810924245552, "300–1000 Hz_40ms_log_rms_mae_db": 1.063865098263503, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.033663962059628634, "300–1000 Hz_40ms_envelope_correlation": 0.9989779357682123, "300–1000 Hz_40ms_modulation_mae_db": 1.5345312416699597, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1709099128122278, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11584232183763306, "1000–3000 Hz_10ms_envelope_correlation": 0.99050711608975, "1000–3000 Hz_10ms_modulation_mae_db": 0.5300351932151314, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8321007692154517, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06428655983358537, "1000–3000 Hz_40ms_envelope_correlation": 0.9973309096425222, "1000–3000 Hz_40ms_modulation_mae_db": 0.7096085367110812, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4366166702581438, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17106493226263295, "3000–6000 Hz_10ms_envelope_correlation": 0.9779240743894015, "3000–6000 Hz_10ms_modulation_mae_db": 0.8723195458121552, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9165173173014312, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10303621198200268, "3000–6000 Hz_40ms_envelope_correlation": 0.9922214078813879, "3000–6000 Hz_40ms_modulation_mae_db": 0.5393594369124525, "mr_stft_db": 5.42760464093089, "band_mae_db": 0.15756979160710305, "rms_gain_error_db": -0.06187610998354487, "output_peak": 0.16601412646813485}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1019789205774688, "全帯域_10ms_rms_envelope_nrmse": 0.04462660145854093, "全帯域_10ms_envelope_correlation": 0.9980557106392927, "全帯域_10ms_modulation_mae_db": 0.6971127083863328, "全帯域_40ms_log_rms_mae_db": 0.5524162784621569, "全帯域_40ms_rms_envelope_nrmse": 0.025856820953939652, "全帯域_40ms_envelope_correlation": 0.9993944072430361, "全帯域_40ms_modulation_mae_db": 0.9555785436446066, "300–1000 Hz_10ms_log_rms_mae_db": 1.3830166675362805, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06540338191497479, "300–1000 Hz_10ms_envelope_correlation": 0.9962146703525164, "300–1000 Hz_10ms_modulation_mae_db": 0.9804736492410034, "300–1000 Hz_40ms_log_rms_mae_db": 1.0426271358101782, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03457730152959442, "300–1000 Hz_40ms_envelope_correlation": 0.9989514502649544, "300–1000 Hz_40ms_modulation_mae_db": 1.2155431294505223, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1523003054275516, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1216524470861351, "1000–3000 Hz_10ms_envelope_correlation": 0.9892301742627495, "1000–3000 Hz_10ms_modulation_mae_db": 0.5178673809533917, "1000–3000 Hz_40ms_log_rms_mae_db": 0.785204401696905, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06966892068251572, "1000–3000 Hz_40ms_envelope_correlation": 0.9963476877888559, "1000–3000 Hz_40ms_modulation_mae_db": 0.20830358359701426, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4372603870926601, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1530462764730461, "3000–6000 Hz_10ms_envelope_correlation": 0.9828393844894799, "3000–6000 Hz_10ms_modulation_mae_db": 0.48142555213322247, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9130979151129829, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09528133442795153, "3000–6000 Hz_40ms_envelope_correlation": 0.9939662085543877, "3000–6000 Hz_40ms_modulation_mae_db": 0.1748758189026658, "mr_stft_db": 5.41397625744188, "band_mae_db": 0.18014696711715375, "rms_gain_error_db": -0.09073782319390696, "output_peak": 0.15648948399191884}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1489350263931941, "全帯域_10ms_rms_envelope_nrmse": 0.047225336469995355, "全帯域_10ms_envelope_correlation": 0.9977456821669123, "全帯域_10ms_modulation_mae_db": 0.7341937754203657, "全帯域_40ms_log_rms_mae_db": 0.5653895372828042, "全帯域_40ms_rms_envelope_nrmse": 0.024593481726418943, "全帯域_40ms_envelope_correlation": 0.9993838496859235, "全帯域_40ms_modulation_mae_db": 0.848172471006348, "300–1000 Hz_10ms_log_rms_mae_db": 1.3843334582234992, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06733760332121355, "300–1000 Hz_10ms_envelope_correlation": 0.9959430403046893, "300–1000 Hz_10ms_modulation_mae_db": 0.7850313355340158, "300–1000 Hz_40ms_log_rms_mae_db": 1.07318911982865, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04001248461220002, "300–1000 Hz_40ms_envelope_correlation": 0.998514806144331, "300–1000 Hz_40ms_modulation_mae_db": 0.8523388312583787, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1496075615860109, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12412064016619447, "1000–3000 Hz_10ms_envelope_correlation": 0.9894567331074565, "1000–3000 Hz_10ms_modulation_mae_db": 0.7838105385718516, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8018311710012157, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07189655197261673, "1000–3000 Hz_40ms_envelope_correlation": 0.9970656511642888, "1000–3000 Hz_40ms_modulation_mae_db": 0.8379160670287447, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4242266046464838, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16331743096861165, "3000–6000 Hz_10ms_envelope_correlation": 0.980674180477467, "3000–6000 Hz_10ms_modulation_mae_db": 0.3603225857647252, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9146674360502041, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10517165493461762, "3000–6000 Hz_40ms_envelope_correlation": 0.9929215119957729, "3000–6000 Hz_40ms_modulation_mae_db": 0.15611745162277121, "mr_stft_db": 5.417186530824666, "band_mae_db": 0.2169680421105368, "rms_gain_error_db": -0.05455191007099742, "output_peak": 0.15354012357139246}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1167870920097258, "全帯域_10ms_rms_envelope_nrmse": 0.040013107148175714, "全帯域_10ms_envelope_correlation": 0.9984115576116008, "全帯域_10ms_modulation_mae_db": 0.7342982681034531, "全帯域_40ms_log_rms_mae_db": 0.5472790874415082, "全帯域_40ms_rms_envelope_nrmse": 0.022532704873196197, "全帯域_40ms_envelope_correlation": 0.9995082395753292, "全帯域_40ms_modulation_mae_db": 0.8566096883433341, "300–1000 Hz_10ms_log_rms_mae_db": 1.4457678529171396, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07279346793006998, "300–1000 Hz_10ms_envelope_correlation": 0.9952879904388932, "300–1000 Hz_10ms_modulation_mae_db": 0.761900442162426, "300–1000 Hz_40ms_log_rms_mae_db": 1.1246074446507346, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.044310949441650885, "300–1000 Hz_40ms_envelope_correlation": 0.9982031336644788, "300–1000 Hz_40ms_modulation_mae_db": 1.1483372692852978, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1793396616391032, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11449099457100385, "1000–3000 Hz_10ms_envelope_correlation": 0.9914610928044031, "1000–3000 Hz_10ms_modulation_mae_db": 0.8658397638251193, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8175221338212919, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07244923496126664, "1000–3000 Hz_40ms_envelope_correlation": 0.9973350498267627, "1000–3000 Hz_40ms_modulation_mae_db": 0.7060011779828367, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4725080453695436, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14832742008900443, "3000–6000 Hz_10ms_envelope_correlation": 0.9834517697201106, "3000–6000 Hz_10ms_modulation_mae_db": 0.5602352063251027, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9135407334778574, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08846018029507785, "3000–6000 Hz_40ms_envelope_correlation": 0.9943263639055906, "3000–6000 Hz_40ms_modulation_mae_db": 0.10779419321724759, "mr_stft_db": 5.4282586762977125, "band_mae_db": 0.22239644163054745, "rms_gain_error_db": -0.06742109072333569, "output_peak": 0.15859546538615157}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0722532441692425, "全帯域_10ms_rms_envelope_nrmse": 0.039768435536168316, "全帯域_10ms_envelope_correlation": 0.9984882366442954, "全帯域_10ms_modulation_mae_db": 0.4752907695217301, "全帯域_40ms_log_rms_mae_db": 0.579556479491253, "全帯域_40ms_rms_envelope_nrmse": 0.02290992971657889, "全帯域_40ms_envelope_correlation": 0.9995519355397635, "全帯域_40ms_modulation_mae_db": 0.6171429015962729, "300–1000 Hz_10ms_log_rms_mae_db": 1.3250200052235317, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05791319499519928, "300–1000 Hz_10ms_envelope_correlation": 0.9970433578667527, "300–1000 Hz_10ms_modulation_mae_db": 0.7979619222744923, "300–1000 Hz_40ms_log_rms_mae_db": 1.002676652863462, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.030908690393979078, "300–1000 Hz_40ms_envelope_correlation": 0.9991501191884097, "300–1000 Hz_40ms_modulation_mae_db": 1.1244742030077115, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1627748535035056, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12585188582268608, "1000–3000 Hz_10ms_envelope_correlation": 0.9903864352010261, "1000–3000 Hz_10ms_modulation_mae_db": 1.1845950843420383, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7830513257375219, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08260912335757992, "1000–3000 Hz_40ms_envelope_correlation": 0.9972765974264212, "1000–3000 Hz_40ms_modulation_mae_db": 1.4323823978356482, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4419392868371141, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17022363164844065, "3000–6000 Hz_10ms_envelope_correlation": 0.9782598912003947, "3000–6000 Hz_10ms_modulation_mae_db": 0.8597187252041408, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9039912179570389, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0904161709331782, "3000–6000 Hz_40ms_envelope_correlation": 0.9946644493530651, "3000–6000 Hz_40ms_modulation_mae_db": 0.6813942830582119, "mr_stft_db": 5.41598527296923, "band_mae_db": 0.2238889325990844, "rms_gain_error_db": -0.09687598854125255, "output_peak": 0.15345179086513694}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.101825403900271, "全帯域_10ms_rms_envelope_nrmse": 0.0456786555493596, "全帯域_10ms_envelope_correlation": 0.9979183070074708, "全帯域_10ms_modulation_mae_db": 0.4085408640734723, "全帯域_40ms_log_rms_mae_db": 0.5344957114438098, "全帯域_40ms_rms_envelope_nrmse": 0.022317963953399418, "全帯域_40ms_envelope_correlation": 0.999527931605961, "全帯域_40ms_modulation_mae_db": 0.7545476359874902, "300–1000 Hz_10ms_log_rms_mae_db": 1.4066819996891073, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06228598850286446, "300–1000 Hz_10ms_envelope_correlation": 0.9965522522965571, "300–1000 Hz_10ms_modulation_mae_db": 0.47865012599355006, "300–1000 Hz_40ms_log_rms_mae_db": 1.1091169900196676, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03479929950039502, "300–1000 Hz_40ms_envelope_correlation": 0.9989089875286649, "300–1000 Hz_40ms_modulation_mae_db": 0.7293887113484359, "1000–3000 Hz_10ms_log_rms_mae_db": 1.195043159994269, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13415246813617007, "1000–3000 Hz_10ms_envelope_correlation": 0.9876768807671803, "1000–3000 Hz_10ms_modulation_mae_db": 0.6860010699551653, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8509242616029676, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07633718220681007, "1000–3000 Hz_40ms_envelope_correlation": 0.9967782595730932, "1000–3000 Hz_40ms_modulation_mae_db": 0.7224808493157, "3000–6000 Hz_10ms_log_rms_mae_db": 1.463402611517642, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16347705244218844, "3000–6000 Hz_10ms_envelope_correlation": 0.9805633187275291, "3000–6000 Hz_10ms_modulation_mae_db": 0.7737131031167754, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9331439489448035, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10186268172971247, "3000–6000 Hz_40ms_envelope_correlation": 0.993360252298132, "3000–6000 Hz_40ms_modulation_mae_db": 0.41319541760784045, "mr_stft_db": 5.4168627618153655, "band_mae_db": 0.2221254797304477, "rms_gain_error_db": -0.06499476714340811, "output_peak": 0.14983274187033382}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0285743476024078, "全帯域_10ms_rms_envelope_nrmse": 0.03723827298714446, "全帯域_10ms_envelope_correlation": 0.9986854943350673, "全帯域_10ms_modulation_mae_db": 0.2772357405289821, "全帯域_40ms_log_rms_mae_db": 0.5278031232899874, "全帯域_40ms_rms_envelope_nrmse": 0.020249898279543776, "全帯域_40ms_envelope_correlation": 0.9996731564960508, "全帯域_40ms_modulation_mae_db": 0.4283771430075734, "300–1000 Hz_10ms_log_rms_mae_db": 1.3823846735293956, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0613457326962449, "300–1000 Hz_10ms_envelope_correlation": 0.9966701048229114, "300–1000 Hz_10ms_modulation_mae_db": 0.8684755201474278, "300–1000 Hz_40ms_log_rms_mae_db": 1.0303058047999323, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.036890609393892645, "300–1000 Hz_40ms_envelope_correlation": 0.9987658199868225, "300–1000 Hz_40ms_modulation_mae_db": 1.3389600998534803, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2114380194692966, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1259500927667659, "1000–3000 Hz_10ms_envelope_correlation": 0.9892423319405004, "1000–3000 Hz_10ms_modulation_mae_db": 0.37143322439147997, "1000–3000 Hz_40ms_log_rms_mae_db": 0.845605168492915, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08629758596840419, "1000–3000 Hz_40ms_envelope_correlation": 0.9954083545088763, "1000–3000 Hz_40ms_modulation_mae_db": 0.4619833551442212, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4659893285447867, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17248886478924133, "3000–6000 Hz_10ms_envelope_correlation": 0.9774434426883231, "3000–6000 Hz_10ms_modulation_mae_db": 0.5736884611043963, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9995383522454357, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10930840476286487, "3000–6000 Hz_40ms_envelope_correlation": 0.9909704421745218, "3000–6000 Hz_40ms_modulation_mae_db": 0.30420628278453965, "mr_stft_db": 5.420082549820542, "band_mae_db": 0.21622228914191563, "rms_gain_error_db": -0.09243245277105133, "output_peak": 0.15161774148167323}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1666730280322521, "全帯域_10ms_rms_envelope_nrmse": 0.04284202382532352, "全帯域_10ms_envelope_correlation": 0.998193624419912, "全帯域_10ms_modulation_mae_db": 0.3202489404175078, "全帯域_40ms_log_rms_mae_db": 0.5849517318209049, "全帯域_40ms_rms_envelope_nrmse": 0.021921776595164266, "全帯域_40ms_envelope_correlation": 0.9995703478937056, "全帯域_40ms_modulation_mae_db": 0.25560072290523955, "300–1000 Hz_10ms_log_rms_mae_db": 1.3717269732088817, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06247404308918793, "300–1000 Hz_10ms_envelope_correlation": 0.99652779162341, "300–1000 Hz_10ms_modulation_mae_db": 1.154200644936995, "300–1000 Hz_40ms_log_rms_mae_db": 1.0559853237699242, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03563560757767165, "300–1000 Hz_40ms_envelope_correlation": 0.9988324376946844, "300–1000 Hz_40ms_modulation_mae_db": 1.2719086838174318, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1820190626096543, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12753419704254945, "1000–3000 Hz_10ms_envelope_correlation": 0.9884667253905995, "1000–3000 Hz_10ms_modulation_mae_db": 0.8486104260756783, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8358554853957479, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07626221141890464, "1000–3000 Hz_40ms_envelope_correlation": 0.9961224036840313, "1000–3000 Hz_40ms_modulation_mae_db": 0.893918732236477, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4748952142239984, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15560696115704992, "3000–6000 Hz_10ms_envelope_correlation": 0.9819288008043713, "3000–6000 Hz_10ms_modulation_mae_db": 1.037252097924277, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9673604895976091, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08549054997829136, "3000–6000 Hz_40ms_envelope_correlation": 0.9950299808757102, "3000–6000 Hz_40ms_modulation_mae_db": 0.47787618812825255, "mr_stft_db": 5.4257394538096415, "band_mae_db": 0.19252540534587145, "rms_gain_error_db": -0.08077074811582728, "output_peak": 0.16093896884372128}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.447327286162405, "spectral_convergence": 0.12702480504902558, "spectral_convergence_status": "ok", "amplitude_floor": 5.237444731722431e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.432642399567193, "spectral_convergence": 0.13039777114195245, "spectral_convergence_status": "ok", "amplitude_floor": 5.437369948912744e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.402844237063072, "spectral_convergence": 0.13063163212567017, "spectral_convergence_status": "ok", "amplitude_floor": 5.052721691674583e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 6.432970236988243e-05, "output_power": 6.599877148861171e-05, "delta_db": 0.11124309509606704, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008444430165469724, "output_power": 0.0008308530341593534, "delta_db": -0.07046138290636442, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 6.039141474549642e-05, "output_power": 6.036170470488246e-05, "delta_db": -0.0021370722371154343, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 3.556975687019485e-05, "output_power": 3.316028295867707e-05, "delta_db": -0.304626689099068, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.090392882810899e-05, "output_power": 1.0827265560423935e-05, "delta_db": -0.030642192643858, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2355857763199668e-06, "output_power": 1.3322485211001488e-06, "delta_db": 0.3271234661755944, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.0422411240430348e-06, "output_power": 9.824099240664401e-07, "delta_db": -0.256754643091654, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.15756979160710305, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.06187610998354487, "pitch": null, "output_rms_dbfs": -29.98475821093149, "output_peak": 0.16601412646813485, "reference_rms_dbfs": -29.922882100947945, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.42760464093089}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 8.184761378594803e-05, "log_rms_mae_db": 1.0969482128528827, "rms_envelope_nrmse": 0.04089707118669061, "envelope_correlation": 0.9983342279372369, "rms_gain_error_db": -0.06078692775999574, "reference_mean_power": 0.0010176842474405314, "output_mean_power": 0.0010035392415131692}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.21363647710693e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00013327602732153044, "output_power": 0.00012862332568252646, "reference_active": true, "delta_db": -0.15432304346564682}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5932863269435214e-05, "output_power": 1.431158926335912e-05, "reference_active": true, "delta_db": -0.4660596551540341}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.59165062752131e-06, "output_power": 3.373304900117967e-06, "reference_active": true, "delta_db": -1.3391323858877038}], "active_band_count": 3, "active_band_mae_db": 0.653171694835795}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.048620680965671e-05, "log_rms_mae_db": 0.5426053700898948, "rms_envelope_nrmse": 0.02083813734631426, "envelope_correlation": 0.9995813975735246, "rms_gain_error_db": -0.05860070710434652, "reference_mean_power": 0.0010161096570352637, "output_mean_power": 0.001002491059569172}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.9042638692252304e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00011759425242544185, "output_power": 0.0001139653831202037, "reference_active": true, "delta_db": -0.136131407221861}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 7.519272755909202e-06, "output_power": 6.804033955008572e-06, "reference_active": true, "delta_db": -0.4340936655472004}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.598733053895232e-07, "output_power": 2.3845784457297374e-07, "reference_active": true, "delta_db": -1.78738018801494}], "active_band_count": 3, "active_band_mae_db": 0.7858684202613339}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.667982083652557e-05, "log_rms_mae_db": 1.414813524340979, "rms_envelope_nrmse": 0.06140875605932435, "envelope_correlation": 0.9966638087560914, "rms_gain_error_db": -0.03134819622235246, "reference_mean_power": 0.00027945110045850193, "output_mean_power": 0.000277441232149448}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.93859363437704e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.295075151115005e-05, "output_power": 3.210409684187121e-05, "reference_active": true, "delta_db": -0.11304867266310199}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.807348843301933e-06, "output_power": 3.345799607584846e-06, "reference_active": true, "delta_db": -0.5612274440560656}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5906604704508056e-06, "output_power": 8.860573305453253e-07, "reference_active": true, "delta_db": -2.5411566560174883}], "active_band_count": 3, "active_band_mae_db": 1.071810924245552}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.254388131298964e-05, "log_rms_mae_db": 1.063865098263503, "rms_envelope_nrmse": 0.033663962059628634, "envelope_correlation": 0.9989779357682123, "rms_gain_error_db": -0.025389272327007592, "reference_mean_power": 0.00027742187495382226, "output_mean_power": 0.0002758047715174229}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 9.236914065861651e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.9257092980847557e-05, "output_power": 2.8448033831072383e-05, "reference_active": true, "delta_db": -0.12178916159038797}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8979287936807737e-06, "output_power": 1.693441549891625e-06, "reference_active": true, "delta_db": -0.49509703260505555}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.43591780871064e-08, "output_power": 3.7680217087920614e-08, "reference_active": true, "delta_db": -3.986707530814435}], "active_band_count": 3, "active_band_mae_db": 1.5345312416699597}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.428909761907278e-05, "log_rms_mae_db": 1.1709099128122278, "rms_envelope_nrmse": 0.11584232183763306, "envelope_correlation": 0.99050711608975, "rms_gain_error_db": -0.24148519155439221, "reference_mean_power": 3.509769240032237e-05, "output_mean_power": 3.319938542662463e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.14178826098124e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0207730418969553e-05, "output_power": 9.157000976916528e-06, "reference_active": true, "delta_db": -0.47175931509943947}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.594184871691995e-06, "output_power": 2.078550543344342e-06, "reference_active": true, "delta_db": -0.9624033281402826}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.354712471534306e-07, "output_power": 3.2363911848574283e-07, "reference_active": true, "delta_db": -0.15594293640567186}], "active_band_count": 3, "active_band_mae_db": 0.5300351932151314}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9506018028930777e-05, "log_rms_mae_db": 0.8321007692154517, "rms_envelope_nrmse": 0.06428655983358537, "envelope_correlation": 0.9973309096425222, "rms_gain_error_db": -0.23971187409888753, "reference_mean_power": 3.5141167460930974e-05, "output_mean_power": 3.3254084662516334e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.01202004778774e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.499160468037956e-06, "output_power": 8.450962007403681e-06, "reference_active": true, "delta_db": -0.5077907494178336}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1261229797074577e-06, "output_power": 9.414459326844359e-07, "reference_active": true, "delta_db": -0.777904372904713}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7957517138182228e-08, "output_power": 2.3024253116086004e-08, "reference_active": true, "delta_db": -0.8431304878106969}], "active_band_count": 3, "active_band_mae_db": 0.7096085367110812}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0101884937381439e-05, "log_rms_mae_db": 1.4366166702581438, "rms_envelope_nrmse": 0.17106493226263295, "envelope_correlation": 0.9779240743894015, "rms_gain_error_db": -0.33842931729328374, "reference_mean_power": 6.452617383104305e-06, "output_mean_power": 5.968881845024943e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.15273367532141e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.10173826656627e-06, "output_power": 1.9348730594337784e-06, "reference_active": true, "delta_db": -0.3592615387037099}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.3061476096447684e-07, "output_power": 3.820677117166625e-07, "reference_active": true, "delta_db": -0.5194857553672245}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.161739165108172e-08, "output_power": 1.2178781692298165e-07, "reference_active": true, "delta_db": 1.738211343365531}], "active_band_count": 3, "active_band_mae_db": 0.8723195458121552}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.618352616189344e-06, "log_rms_mae_db": 0.9165173173014312, "rms_envelope_nrmse": 0.10303621198200268, "envelope_correlation": 0.9922214078813879, "rms_gain_error_db": -0.33951795760787795, "reference_mean_power": 6.458260841661403e-06, "output_mean_power": 5.972604895785537e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.76552281278155e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.8830611185238975e-06, "output_power": 1.7618483838737448e-06, "reference_active": true, "delta_db": -0.2889588373613435}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.769776726408418e-07, "output_power": 1.652781868666832e-07, "reference_active": true, "delta_db": -0.29702939671089}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.816205310457936e-09, "output_power": 1.2449520966745131e-08, "reference_active": true, "delta_db": 1.032090076665124}], "active_band_count": 3, "active_band_mae_db": 0.5393594369124525}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9275111407619879, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "49e496464a0adc57ce382ad60c8725b88b856a3bd698888b05a3bded9c8ad5e7", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9895534361954581, "standard_deviation": 0.0012044905676153732, "minimum": 0.9876768807671803, "maximum": 0.9914610928044031, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1754290671302023, "standard_deviation": 0.02111979343107212, "minimum": 1.1496075615860109, "maximum": 1.2114380194692966, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.723524085166232, "standard_deviation": 0.25557494009368825, "minimum": 0.37143322439147997, "maximum": 1.1845950843420383, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12369938092864224, "standard_deviation": 0.006375925504413255, "minimum": 0.11449099457100385, "maximum": 0.13415246813617007, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9967081142018565, "standard_deviation": 0.0006968488191534368, "minimum": 0.9954083545088763, "maximum": 0.9973350498267627, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8190118396205021, "standard_deviation": 0.026495639300260557, "minimum": 0.7830513257375219, "maximum": 0.8509242616029676, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7465743374814653, "standard_deviation": 0.3534941821009383, "minimum": 0.20830358359701426, "maximum": 1.4323823978356482, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07497592130021041, "standard_deviation": 0.007053335598590967, "minimum": 0.06428655983358537, "maximum": 0.08629758596840419, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9803856078121347, "standard_deviation": 0.0023038111998709174, "minimum": 0.9774434426883231, "maximum": 0.9834517697201106, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.4521047685612964, "standard_deviation": 0.01926093853076099, "minimum": 1.4242266046464838, "maximum": 1.4748952142239984, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6898344096730994, "standard_deviation": 0.23058754760475006, "minimum": 0.3603225857647252, "maximum": 1.037252097924277, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16219407122877694, "standard_deviation": 0.009034955531464767, "minimum": 0.14832742008900443, "maximum": 0.17248886478924133, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9934325771298209, "standard_deviation": 0.0013600568863408034, "minimum": 0.9909704421745218, "maximum": 0.9950299808757102, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9327321763359203, "standard_deviation": 0.03344818947067746, "minimum": 0.9039912179570389, "maximum": 0.9995383522454357, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.3568523840292477, "standard_deviation": 0.20517210367994843, "minimum": 0.10779419321724759, "maximum": 0.6813942830582119, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09737839863046208, "standard_deviation": 0.008692405499788721, "minimum": 0.08549054997829136, "maximum": 0.10930840476286487, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9963628770577276, "standard_deviation": 0.0005430958983073652, "minimum": 0.9952879904388932, "maximum": 0.9970433578667527, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.3892181443336018, "standard_deviation": 0.03524270175934535, "minimum": 1.3250200052235317, "maximum": 1.4457678529171396, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8623130705669328, "standard_deviation": 0.21060494253564077, "minimum": 0.47865012599355006, "maximum": 1.154200644936995, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06387027106363491, "standard_deviation": 0.00457281990747014, "minimum": 0.05791319499519928, "maximum": 0.07279346793006998, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9987880862800697, "standard_deviation": 0.0002994590334986711, "minimum": 0.9982031336644788, "maximum": 0.9991501191884097, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.0627966962507562, "standard_deviation": 0.03999743883029977, "minimum": 1.002676652863462, "maximum": 1.1246074446507346, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.1519352712114022, "standard_deviation": 0.2588072146463822, "minimum": 0.7293887113484359, "maximum": 1.5345312416699597, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.036349863063626545, "standard_deviation": 0.004139753381182773, "minimum": 0.030908690393979078, "maximum": 0.044310949441650885, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.20398041866033254, "standard_deviation": 0.024601047806572355, "minimum": 0.15756979160710305, "maximum": 0.2238889325990844, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.420712017988741, "standard_deviation": 0.005670601696714915, "minimum": 5.41397625744188, "maximum": 5.4282586762977125, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.15631005530980788, "standard_deviation": 0.00535412694424168, "minimum": 0.14983274187033382, "maximum": 0.16601412646813485, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07620761131791552, "standard_deviation": 0.016034198797110454, "minimum": -0.09687598854125255, "maximum": -0.05455191007099742, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9982291050952236, "standard_deviation": 0.00031199764771339583, "minimum": 0.9977456821669123, "maximum": 0.9986854943350673, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.1042469094421805, "standard_deviation": 0.042871092366952024, "minimum": 1.0285743476024078, "maximum": 1.1666730280322521, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.5375115951609548, "standard_deviation": 0.18962749610372875, "minimum": 0.2772357405289821, "maximum": 0.7342982681034531, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.04228618802017481, "standard_deviation": 0.003393430161563031, "minimum": 0.03723827298714446, "maximum": 0.047225336469995355, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9995239082016618, "standard_deviation": 9.648896138381642e-05, "minimum": 0.9993838496859235, "maximum": 0.9996731564960508, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5543121649152899, "standard_deviation": 0.020647709601451306, "minimum": 0.5278031232899874, "maximum": 0.5849517318209049, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6877371908440248, "standard_deviation": 0.23877152216544167, "minimum": 0.25560072290523955, "maximum": 0.9555785436446066, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.022652589180569425, "standard_deviation": 0.001844915082559398, "minimum": 0.020249898279543776, "maximum": 0.025856820953939652, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 2.3216891288757324, "predicted_mos": 2.3216891288757324, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "c07f8649c19fae5c3ff3056278e9f8af926b5f16b9c5b5417331eb564125af8d", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 10.9794148998335}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0445917013496122, "全帯域_10ms_rms_envelope_nrmse": 0.03741550531574939, "全帯域_10ms_envelope_correlation": 0.9986397182965314, "全帯域_10ms_modulation_mae_db": 0.15997663634905734, "全帯域_40ms_log_rms_mae_db": 0.5711459729329538, "全帯域_40ms_rms_envelope_nrmse": 0.02088669197956057, "全帯域_40ms_envelope_correlation": 0.9996111634398727, "全帯域_40ms_modulation_mae_db": 0.314983599068913, "300–1000 Hz_10ms_log_rms_mae_db": 1.5458613627134041, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.065593148261404, "300–1000 Hz_10ms_envelope_correlation": 0.9961752621271898, "300–1000 Hz_10ms_modulation_mae_db": 0.21237902804506037, "300–1000 Hz_40ms_log_rms_mae_db": 1.2722811648080379, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037944193659293655, "300–1000 Hz_40ms_envelope_correlation": 0.9987029355083931, "300–1000 Hz_40ms_modulation_mae_db": 0.6738425940963254, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2643939407045304, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10859173802300905, "1000–3000 Hz_10ms_envelope_correlation": 0.9918764950847878, "1000–3000 Hz_10ms_modulation_mae_db": 0.8181628226474928, "1000–3000 Hz_40ms_log_rms_mae_db": 0.967838055981021, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06742169851122314, "1000–3000 Hz_40ms_envelope_correlation": 0.9972250535406445, "1000–3000 Hz_40ms_modulation_mae_db": 0.6697536707397598, "3000–6000 Hz_10ms_log_rms_mae_db": 1.57079762894494, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14613553767177756, "3000–6000 Hz_10ms_envelope_correlation": 0.9845821522252977, "3000–6000 Hz_10ms_modulation_mae_db": 0.5856255628865273, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0203771501192311, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08727602637063478, "3000–6000 Hz_40ms_envelope_correlation": 0.9953879558145536, "3000–6000 Hz_40ms_modulation_mae_db": 0.5558356065089872, "mr_stft_db": 5.487449036780071, "band_mae_db": 0.20106368859188756, "rms_gain_error_db": -0.07541097802643408, "output_peak": 0.15892683609633396}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.081129543673562, "全帯域_10ms_rms_envelope_nrmse": 0.04193713959926185, "全帯域_10ms_envelope_correlation": 0.9983151994090593, "全帯域_10ms_modulation_mae_db": 0.48705186734377265, "全帯域_40ms_log_rms_mae_db": 0.5704745097410417, "全帯域_40ms_rms_envelope_nrmse": 0.02445680070828804, "全帯域_40ms_envelope_correlation": 0.9994871826004843, "全帯域_40ms_modulation_mae_db": 0.5546356283089257, "300–1000 Hz_10ms_log_rms_mae_db": 1.5079120365270235, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.062379772462670964, "300–1000 Hz_10ms_envelope_correlation": 0.9965536646891638, "300–1000 Hz_10ms_modulation_mae_db": 0.7502518787281863, "300–1000 Hz_40ms_log_rms_mae_db": 1.1861797128307943, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.036162170641098466, "300–1000 Hz_40ms_envelope_correlation": 0.9988181919145731, "300–1000 Hz_40ms_modulation_mae_db": 1.0482729499224008, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3348836860179318, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.14526885021022867, "1000–3000 Hz_10ms_envelope_correlation": 0.9859841837654932, "1000–3000 Hz_10ms_modulation_mae_db": 1.3782752100125528, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9548308063036868, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09044581494485644, "1000–3000 Hz_40ms_envelope_correlation": 0.9958048435126063, "1000–3000 Hz_40ms_modulation_mae_db": 1.09742065020008, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5840506915881278, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17066392434280137, "3000–6000 Hz_10ms_envelope_correlation": 0.977712844730649, "3000–6000 Hz_10ms_modulation_mae_db": 0.6443530480342664, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0343762397644782, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09035207419930645, "3000–6000 Hz_40ms_envelope_correlation": 0.993902224492346, "3000–6000 Hz_40ms_modulation_mae_db": 0.4361982586560968, "mr_stft_db": 5.480600110017101, "band_mae_db": 0.17903739661601414, "rms_gain_error_db": -0.10172557613295762, "output_peak": 0.15088532426425055}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1157569953951385, "全帯域_10ms_rms_envelope_nrmse": 0.04045769463573832, "全帯域_10ms_envelope_correlation": 0.9983894635771671, "全帯域_10ms_modulation_mae_db": 0.6831538513158583, "全帯域_40ms_log_rms_mae_db": 0.5619139633530259, "全帯域_40ms_rms_envelope_nrmse": 0.020906206905648945, "全帯域_40ms_envelope_correlation": 0.9995961880601367, "全帯域_40ms_modulation_mae_db": 0.7440031206535543, "300–1000 Hz_10ms_log_rms_mae_db": 1.4396194043668957, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06156910853859697, "300–1000 Hz_10ms_envelope_correlation": 0.9966747720112192, "300–1000 Hz_10ms_modulation_mae_db": 0.7152913543295335, "300–1000 Hz_40ms_log_rms_mae_db": 1.1022154236556911, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03846478898671585, "300–1000 Hz_40ms_envelope_correlation": 0.9986839471897977, "300–1000 Hz_40ms_modulation_mae_db": 0.8149634909521861, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3262662522853954, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13094847726433312, "1000–3000 Hz_10ms_envelope_correlation": 0.988481499284409, "1000–3000 Hz_10ms_modulation_mae_db": 0.3000578653680574, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9513764446622336, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08538769874021215, "1000–3000 Hz_40ms_envelope_correlation": 0.9958045370869248, "1000–3000 Hz_40ms_modulation_mae_db": 0.25844668454800485, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5890201767210836, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15934670873602144, "3000–6000 Hz_10ms_envelope_correlation": 0.9811669964346986, "3000–6000 Hz_10ms_modulation_mae_db": 0.4574346445654552, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0840424559054798, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10761453477334924, "3000–6000 Hz_40ms_envelope_correlation": 0.9917276360942983, "3000–6000 Hz_40ms_modulation_mae_db": 0.2229760728198654, "mr_stft_db": 5.4916095061275945, "band_mae_db": 0.20373621363983602, "rms_gain_error_db": -0.07103804309665235, "output_peak": 0.16030096168212793}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1157358060565241, "全帯域_10ms_rms_envelope_nrmse": 0.0461352514386276, "全帯域_10ms_envelope_correlation": 0.9978527234051741, "全帯域_10ms_modulation_mae_db": 0.18784360621686344, "全帯域_40ms_log_rms_mae_db": 0.5984752508974756, "全帯域_40ms_rms_envelope_nrmse": 0.023623660043687492, "全帯域_40ms_envelope_correlation": 0.9994356132029092, "全帯域_40ms_modulation_mae_db": 0.17585167043380698, "300–1000 Hz_10ms_log_rms_mae_db": 1.4221588123074818, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06703924229502418, "300–1000 Hz_10ms_envelope_correlation": 0.9959937163619463, "300–1000 Hz_10ms_modulation_mae_db": 0.3184229819088958, "300–1000 Hz_40ms_log_rms_mae_db": 1.153275877415873, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03768955561797499, "300–1000 Hz_40ms_envelope_correlation": 0.9987163207964219, "300–1000 Hz_40ms_modulation_mae_db": 0.37105968848776527, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2597967414345461, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12384622900855963, "1000–3000 Hz_10ms_envelope_correlation": 0.9891104704451328, "1000–3000 Hz_10ms_modulation_mae_db": 0.7317620506334794, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8896277119378121, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0656935137652675, "1000–3000 Hz_40ms_envelope_correlation": 0.9972640830692722, "1000–3000 Hz_40ms_modulation_mae_db": 0.5964437235370315, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6176689433996974, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17617365932800097, "3000–6000 Hz_10ms_envelope_correlation": 0.9778047332156958, "3000–6000 Hz_10ms_modulation_mae_db": 0.9724857336142071, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1056475264314913, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12333430068768284, "3000–6000 Hz_40ms_envelope_correlation": 0.9902419836010787, "3000–6000 Hz_40ms_modulation_mae_db": 0.6974784376781975, "mr_stft_db": 5.475424113253607, "band_mae_db": 0.23572051371664113, "rms_gain_error_db": -0.05695221375485043, "output_peak": 0.15277599758653018}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0773965826741791, "全帯域_10ms_rms_envelope_nrmse": 0.03986003592349613, "全帯域_10ms_envelope_correlation": 0.9984242766665568, "全帯域_10ms_modulation_mae_db": 0.3535788189945624, "全帯域_40ms_log_rms_mae_db": 0.5546748771064804, "全帯域_40ms_rms_envelope_nrmse": 0.021588229705547798, "全帯域_40ms_envelope_correlation": 0.9995557108892691, "全帯域_40ms_modulation_mae_db": 0.4401722498494652, "300–1000 Hz_10ms_log_rms_mae_db": 1.477286188832895, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.060042809787043204, "300–1000 Hz_10ms_envelope_correlation": 0.9968219396366197, "300–1000 Hz_10ms_modulation_mae_db": 0.629214697986492, "300–1000 Hz_40ms_log_rms_mae_db": 1.1543255953301248, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03430728594405737, "300–1000 Hz_40ms_envelope_correlation": 0.9989390238026016, "300–1000 Hz_40ms_modulation_mae_db": 0.8542824899872051, "1000–3000 Hz_10ms_log_rms_mae_db": 1.300543671978078, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13060705717152307, "1000–3000 Hz_10ms_envelope_correlation": 0.9877687296110572, "1000–3000 Hz_10ms_modulation_mae_db": 0.5843016125875699, "1000–3000 Hz_40ms_log_rms_mae_db": 0.928968094289205, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07692062129211308, "1000–3000 Hz_40ms_envelope_correlation": 0.9960068483215273, "1000–3000 Hz_40ms_modulation_mae_db": 0.4926187116748207, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5628084171097434, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16766372766788462, "3000–6000 Hz_10ms_envelope_correlation": 0.9784110743549082, "3000–6000 Hz_10ms_modulation_mae_db": 0.9359499760194764, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0065042266620567, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09125563437463291, "3000–6000 Hz_40ms_envelope_correlation": 0.9934090091871923, "3000–6000 Hz_40ms_modulation_mae_db": 0.5774116371371504, "mr_stft_db": 5.470433427919571, "band_mae_db": 0.19559645223369126, "rms_gain_error_db": -0.06550467908442997, "output_peak": 0.15590319384115212}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0121730093826906, "全帯域_10ms_rms_envelope_nrmse": 0.04119001936551704, "全帯域_10ms_envelope_correlation": 0.9983146881031857, "全帯域_10ms_modulation_mae_db": 0.17575964951257747, "全帯域_40ms_log_rms_mae_db": 0.5374998347990382, "全帯域_40ms_rms_envelope_nrmse": 0.022946956663136026, "全帯域_40ms_envelope_correlation": 0.9994951809138019, "全帯域_40ms_modulation_mae_db": 0.6041050683556244, "300–1000 Hz_10ms_log_rms_mae_db": 1.4495756432943232, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.059004607661472905, "300–1000 Hz_10ms_envelope_correlation": 0.9968881126499137, "300–1000 Hz_10ms_modulation_mae_db": 0.2871363835611657, "300–1000 Hz_40ms_log_rms_mae_db": 1.1612463047054224, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03350829184483426, "300–1000 Hz_40ms_envelope_correlation": 0.9989575904471264, "300–1000 Hz_40ms_modulation_mae_db": 0.6360082022302775, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3333751797634488, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11600394123858836, "1000–3000 Hz_10ms_envelope_correlation": 0.9902982549721656, "1000–3000 Hz_10ms_modulation_mae_db": 0.5077908820160403, "1000–3000 Hz_40ms_log_rms_mae_db": 0.96937501017781, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0627682512322597, "1000–3000 Hz_40ms_envelope_correlation": 0.9972494603443384, "1000–3000 Hz_40ms_modulation_mae_db": 0.17394115213790773, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5735608231016, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16055051223783925, "3000–6000 Hz_10ms_envelope_correlation": 0.9814506583202346, "3000–6000 Hz_10ms_modulation_mae_db": 0.8308750503494373, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0425161398870644, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09633791087998952, "3000–6000 Hz_40ms_envelope_correlation": 0.9945198988324367, "3000–6000 Hz_40ms_modulation_mae_db": 0.39907481366492953, "mr_stft_db": 5.480370068599414, "band_mae_db": 0.16121103745885562, "rms_gain_error_db": -0.06853198290539113, "output_peak": 0.1539757093488175}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.040193314994463, "全帯域_10ms_rms_envelope_nrmse": 0.04119391938183429, "全帯域_10ms_envelope_correlation": 0.9983681749655695, "全帯域_10ms_modulation_mae_db": 0.37662090709621304, "全帯域_40ms_log_rms_mae_db": 0.5482945045878972, "全帯域_40ms_rms_envelope_nrmse": 0.024095716508505238, "全帯域_40ms_envelope_correlation": 0.9994903588042933, "全帯域_40ms_modulation_mae_db": 0.431104901918202, "300–1000 Hz_10ms_log_rms_mae_db": 1.5050548039749747, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06961598475087362, "300–1000 Hz_10ms_envelope_correlation": 0.9957135590408726, "300–1000 Hz_10ms_modulation_mae_db": 0.5357538971789056, "300–1000 Hz_40ms_log_rms_mae_db": 1.1588922421447512, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043568580024268104, "300–1000 Hz_40ms_envelope_correlation": 0.9982853362087728, "300–1000 Hz_40ms_modulation_mae_db": 0.8981152442772814, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3467888596492281, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12294559697833829, "1000–3000 Hz_10ms_envelope_correlation": 0.9897585560001547, "1000–3000 Hz_10ms_modulation_mae_db": 0.613957879404066, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9958545261391533, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07186320789726769, "1000–3000 Hz_40ms_envelope_correlation": 0.9972077143241598, "1000–3000 Hz_40ms_modulation_mae_db": 0.6547556607862771, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5781272826721473, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.169934849127386, "3000–6000 Hz_10ms_envelope_correlation": 0.9781993167162238, "3000–6000 Hz_10ms_modulation_mae_db": 0.5806677516478066, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0624226230415923, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.101266884714316, "3000–6000 Hz_40ms_envelope_correlation": 0.992617419217472, "3000–6000 Hz_40ms_modulation_mae_db": 0.3238112472092864, "mr_stft_db": 5.485366936187421, "band_mae_db": 0.18727617413520212, "rms_gain_error_db": -0.0933124163080549, "output_peak": 0.15844114541242704}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0315522583772838, "全帯域_10ms_rms_envelope_nrmse": 0.04218818626106023, "全帯域_10ms_envelope_correlation": 0.9982224449971918, "全帯域_10ms_modulation_mae_db": 0.6133252247059962, "全帯域_40ms_log_rms_mae_db": 0.5266933728795248, "全帯域_40ms_rms_envelope_nrmse": 0.021951636638744252, "全帯域_40ms_envelope_correlation": 0.9995319874635953, "全帯域_40ms_modulation_mae_db": 0.610532809808392, "300–1000 Hz_10ms_log_rms_mae_db": 1.480062095834995, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06866191026772049, "300–1000 Hz_10ms_envelope_correlation": 0.9958200605052916, "300–1000 Hz_10ms_modulation_mae_db": 0.5167648971708215, "300–1000 Hz_40ms_log_rms_mae_db": 1.1732201244394338, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04048176222600168, "300–1000 Hz_40ms_envelope_correlation": 0.9985163411110562, "300–1000 Hz_40ms_modulation_mae_db": 0.5189527391420603, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3030583694134281, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.121742696378826, "1000–3000 Hz_10ms_envelope_correlation": 0.9892547975904076, "1000–3000 Hz_10ms_modulation_mae_db": 0.41464241109588434, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9607942928963004, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07512149365693949, "1000–3000 Hz_40ms_envelope_correlation": 0.9957318368094494, "1000–3000 Hz_40ms_modulation_mae_db": 0.44319778790372677, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6826496584548207, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15999695814017093, "3000–6000 Hz_10ms_envelope_correlation": 0.9807365848354261, "3000–6000 Hz_10ms_modulation_mae_db": 0.17387079594541763, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1186638980286359, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09381657089913378, "3000–6000 Hz_40ms_envelope_correlation": 0.9937502492153969, "3000–6000 Hz_40ms_modulation_mae_db": 0.2622919696982409, "mr_stft_db": 5.488030167710099, "band_mae_db": 0.20318474321553232, "rms_gain_error_db": -0.0634514081750366, "output_peak": 0.15907628232296772}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.535477349505538, "spectral_convergence": 0.12667857158835957, "spectral_convergence_status": "ok", "amplitude_floor": 5.237444731722431e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.492784979604869, "spectral_convergence": 0.13231876702042583, "spectral_convergence_status": "ok", "amplitude_floor": 5.437369948912744e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.434084781229807, "spectral_convergence": 0.1319745461857312, "spectral_convergence_status": "ok", "amplitude_floor": 5.052721691674583e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 6.432970236988243e-05, "output_power": 6.620839131233822e-05, "delta_db": 0.12501493727167798, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008444430165469724, "output_power": 0.000825806714520721, "delta_db": -0.09691938737059182, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 6.039141474549642e-05, "output_power": 6.225376659474791e-05, "delta_db": 0.1319042943957691, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 3.556975687019485e-05, "output_power": 3.310265567228433e-05, "delta_db": -0.312180600626136, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.090392882810899e-05, "output_power": 1.0569111872542434e-05, "delta_db": -0.13544513247803935, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2355857763199668e-06, "output_power": 1.3780494952173462e-06, "delta_db": 0.47391916153026414, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.0422411240430348e-06, "output_power": 1.074420870625302e-06, "delta_db": 0.13206230647073455, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.20106368859188756, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.07541097802643408, "pitch": null, "output_rms_dbfs": -29.998293078974378, "output_peak": 0.15892683609633396, "reference_rms_dbfs": -29.922882100947945, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.487449036780071}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 8.184761378594803e-05, "log_rms_mae_db": 1.0445917013496122, "rms_envelope_nrmse": 0.03741550531574939, "envelope_correlation": 0.9986397182965314, "rms_gain_error_db": -0.0749577588807019, "reference_mean_power": 0.0010176842474405314, "output_mean_power": 0.001000270075150935}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.21363647710693e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00013327602732153044, "output_power": 0.00012859027935611242, "reference_active": true, "delta_db": -0.15543899044563658}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5932863269435214e-05, "output_power": 1.5980079232795878e-05, "reference_active": true, "delta_db": 0.012850991290499344}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.59165062752131e-06, "output_power": 4.273707972977278e-06, "reference_active": true, "delta_db": -0.3116399273110361}], "active_band_count": 3, "active_band_mae_db": 0.15997663634905734}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.048620680965671e-05, "log_rms_mae_db": 0.5711459729329538, "rms_envelope_nrmse": 0.02088669197956057, "envelope_correlation": 0.9996111634398727, "rms_gain_error_db": -0.07417954367980564, "reference_mean_power": 0.0010161096570352637, "output_mean_power": 0.0009989014062333106}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.9042638692252304e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00011759425242544185, "output_power": 0.00011351636732597864, "reference_active": true, "delta_db": -0.1532761086838963}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 7.519272755909202e-06, "output_power": 7.923449595964601e-06, "reference_active": true, "delta_db": 0.22738460746001357}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.598733053895232e-07, "output_power": 3.1602440675062423e-07, "reference_active": true, "delta_db": -0.5642900810628292}], "active_band_count": 3, "active_band_mae_db": 0.314983599068913}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.667982083652557e-05, "log_rms_mae_db": 1.5458613627134041, "rms_envelope_nrmse": 0.065593148261404, "envelope_correlation": 0.9961752621271898, "rms_gain_error_db": -0.019291782940053404, "reference_mean_power": 0.00027945110045850193, "output_mean_power": 0.0002782125045312131}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.93859363437704e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.295075151115005e-05, "output_power": 3.094779062577308e-05, "reference_active": true, "delta_db": -0.2723567402252801}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.807348843301933e-06, "output_power": 3.509538566981744e-06, "reference_active": true, "delta_db": -0.3537265097639642}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5906604704508056e-06, "output_power": 1.59471423882545e-06, "reference_active": true, "delta_db": 0.011053834145936718}], "active_band_count": 3, "active_band_mae_db": 0.21237902804506037}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.254388131298964e-05, "log_rms_mae_db": 1.2722811648080379, "rms_envelope_nrmse": 0.037944193659293655, "envelope_correlation": 0.9987029355083931, "rms_gain_error_db": -0.015885940811025304, "reference_mean_power": 0.00027742187495382226, "output_mean_power": 0.0002764089546503067}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 9.236914065861651e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.9257092980847557e-05, "output_power": 2.7205148774877456e-05, "reference_active": true, "delta_db": -0.31580066678694385}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8979287936807737e-06, "output_power": 1.916917528347581e-06, "reference_active": true, "delta_db": 0.043235140274675954}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.43591780871064e-08, "output_power": 6.434798498376383e-08, "reference_active": true, "delta_db": -1.6624919752273561}], "active_band_count": 3, "active_band_mae_db": 0.6738425940963254}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.428909761907278e-05, "log_rms_mae_db": 1.2643939407045304, "rms_envelope_nrmse": 0.10859173802300905, "envelope_correlation": 0.9918764950847878, "rms_gain_error_db": -0.27920052078676144, "reference_mean_power": 3.509769240032237e-05, "output_mean_power": 3.291232109457565e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.14178826098124e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0207730418969553e-05, "output_power": 9.438697677483267e-06, "reference_active": true, "delta_db": -0.34017116216643284}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.594184871691995e-06, "output_power": 2.5732496198580057e-06, "reference_active": true, "delta_db": -0.035190050725989686}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.354712471534306e-07, "output_power": 2.0784643398323257e-07, "reference_active": true, "delta_db": -2.079127255050056}], "active_band_count": 3, "active_band_mae_db": 0.8181628226474928}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9506018028930777e-05, "log_rms_mae_db": 0.967838055981021, "rms_envelope_nrmse": 0.06742169851122314, "envelope_correlation": 0.9972250535406445, "rms_gain_error_db": -0.28405862334930376, "reference_mean_power": 3.5141167460930974e-05, "output_mean_power": 3.2916247806787996e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.01202004778774e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.499160468037956e-06, "output_power": 8.873274788388525e-06, "reference_active": true, "delta_db": -0.29601293215537955}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1261229797074577e-06, "output_power": 1.1467878381237025e-06, "reference_active": true, "delta_db": 0.0789725774111995}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7957517138182228e-08, "output_power": 1.9189826559327383e-08, "reference_active": true, "delta_db": -1.6342755026527005}], "active_band_count": 3, "active_band_mae_db": 0.6697536707397598}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0101884937381439e-05, "log_rms_mae_db": 1.57079762894494, "rms_envelope_nrmse": 0.14613553767177756, "envelope_correlation": 0.9845821522252977, "rms_gain_error_db": -0.41569541504976637, "reference_mean_power": 6.452617383104305e-06, "output_mean_power": 5.863627490375924e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.15273367532141e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.10173826656627e-06, "output_power": 1.9109328071253345e-06, "reference_active": true, "delta_db": -0.4133321503588401}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.3061476096447684e-07, "output_power": 3.633599536786069e-07, "reference_active": true, "delta_db": -0.737518513321021}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.161739165108172e-08, "output_power": 9.383941978932255e-08, "reference_active": true, "delta_db": 0.606026024979721}], "active_band_count": 3, "active_band_mae_db": 0.5856255628865273}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.618352616189344e-06, "log_rms_mae_db": 1.0203771501192311, "rms_envelope_nrmse": 0.08727602637063478, "envelope_correlation": 0.9953879558145536, "rms_gain_error_db": -0.4182025258779375, "reference_mean_power": 6.458260841661403e-06, "output_mean_power": 5.86536885964233e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.76552281278155e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.8830611185238975e-06, "output_power": 1.7080950314252735e-06, "reference_active": true, "delta_db": -0.4235238674869761}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.769776726408418e-07, "output_power": 1.54757339265582e-07, "reference_active": true, "delta_db": -0.5826722526698255}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.816205310457936e-09, "output_power": 8.42970862422451e-09, "reference_active": true, "delta_db": -0.6613106993701601}], "active_band_count": 3, "active_band_mae_db": 0.5558356065089872}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9316464318768243, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "547ecfaa10beef96b6c3940eeca1221b7487376aedeb57e3c22b5acf60613fd7", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.989066623344201, "standard_deviation": 0.0017507847483501022, "minimum": 0.9859841837654932, "maximum": 0.9918764950847878, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.3086383376558233, "standard_deviation": 0.03274722062733881, "minimum": 1.2597967414345461, "maximum": 1.3467888596492281, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6686188417206429, "standard_deviation": 0.33085747843966756, "minimum": 0.3000578653680574, "maximum": 1.3782752100125528, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12499432328417577, "standard_deviation": 0.010980316307139507, "minimum": 0.10859173802300905, "maximum": 0.14526885021022867, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9965367971261153, "standard_deviation": 0.0007522754234140164, "minimum": 0.9957318368094494, "maximum": 0.9972640830692722, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.9523331177984028, "standard_deviation": 0.03158114173047716, "minimum": 0.8896277119378121, "maximum": 0.9958545261391533, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.548322255190951, "standard_deviation": 0.28491639796053814, "minimum": 0.17394115213790773, "maximum": 1.09742065020008, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0744527875050174, "standard_deviation": 0.009645739113146378, "minimum": 0.0627682512322597, "maximum": 0.09044581494485644, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9800080451041417, "standard_deviation": 0.0024148903897376426, "minimum": 0.977712844730649, "maximum": 0.9845821522252977, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.59483545274902, "standard_deviation": 0.039130098621032144, "minimum": 1.5628084171097434, "maximum": 1.6826496584548207, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6476578203828243, "standard_deviation": 0.2648988180190703, "minimum": 0.17387079594541763, "maximum": 0.9724857336142071, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16380823465648525, "standard_deviation": 0.009332527263830789, "minimum": 0.14613553767177756, "maximum": 0.17617365932800097, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9931945470568468, "standard_deviation": 0.0016312020471284487, "minimum": 0.9902419836010787, "maximum": 0.9953879558145536, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.0593187824800037, "standard_deviation": 0.040531075171447745, "minimum": 1.0065042266620567, "maximum": 1.1186638980286359, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.43438475542159427, "standard_deviation": 0.16570689409018338, "minimum": 0.2229760728198654, "maximum": 0.6974784376781975, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09890674211238068, "standard_deviation": 0.011817696308873178, "minimum": 0.08727602637063478, "maximum": 0.12333430068768284, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9963301358777771, "standard_deviation": 0.0004628261105311683, "minimum": 0.9957135590408726, "maximum": 0.9968881126499137, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.4784412934814992, "standard_deviation": 0.04076818290381683, "minimum": 1.4221588123074818, "maximum": 1.5458613627134041, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4956518898636326, "standard_deviation": 0.2028679791986181, "minimum": 0.21237902804506037, "maximum": 0.7502518787281863, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06423832300310078, "standard_deviation": 0.004030971061910572, "minimum": 0.059004607661472905, "maximum": 0.06961598475087362, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9987024608723429, "standard_deviation": 0.00022155793300868934, "minimum": 0.9982853362087728, "maximum": 0.9989575904471264, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.1702045556662661, "standard_deviation": 0.04788885306182447, "minimum": 1.1022154236556911, "maximum": 1.2722811648080379, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7269371748869378, "standard_deviation": 0.21958320803984444, "minimum": 0.37105968848776527, "maximum": 1.0482729499224008, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.037765828618030545, "standard_deviation": 0.003256515495582095, "minimum": 0.03350829184483426, "maximum": 0.043568580024268104, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1958532774509575, "standard_deviation": 0.021675948769293303, "minimum": 0.16121103745885562, "maximum": 0.23572051371664113, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.48241042082436, "standard_deviation": 0.007071375641600844, "minimum": 5.470433427919571, "maximum": 5.4916095061275945, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.15628568131932585, "standard_deviation": 0.0034329424648384646, "minimum": 0.15088532426425055, "maximum": 0.16030096168212793, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07449091218547588, "standard_deviation": 0.015373830170655424, "minimum": -0.10172557613295762, "maximum": -0.05695221375485043, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9983158361775545, "standard_deviation": 0.00022297225497258755, "minimum": 0.9978527234051741, "maximum": 0.9986397182965314, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.0648161514879317, "standard_deviation": 0.03873955945757321, "minimum": 1.0121730093826906, "maximum": 1.1157569953951385, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3796638201918626, "standard_deviation": 0.20197598665061897, "minimum": 0.15997663634905734, "maximum": 0.6831538513158583, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.04129721899016061, "standard_deviation": 0.002463158221345596, "minimum": 0.03741550531574939, "maximum": 0.0461352514386276, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9995254231717954, "standard_deviation": 5.975159841368914e-05, "minimum": 0.9994356132029092, "maximum": 0.9996111634398727, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5586465357871797, "standard_deviation": 0.02231036188526837, "minimum": 0.5266933728795248, "maximum": 0.5984752508974756, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4844236310496105, "standard_deviation": 0.1817636056276093, "minimum": 0.17585167043380698, "maximum": 0.7440031206535543, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.022556987394139794, "standard_deviation": 0.0014185882558513635, "minimum": 0.02088669197956057, "maximum": 0.02445680070828804, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 2.2762255668640137, "predicted_mos": 2.2762255668640137, "model": "UTMOSv2", "language": "ja", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "dcb4f3c6562543637e31b90b84b8027e9bbad170439d98bbbb261ce08d66f1c2", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 10.2008613999933}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0635331674705906, "全帯域_10ms_rms_envelope_nrmse": 0.04259243649973802, "全帯域_10ms_envelope_correlation": 0.9982440829381143, "全帯域_10ms_modulation_mae_db": 0.35574089814566995, "全帯域_40ms_log_rms_mae_db": 0.5414283407385139, "全帯域_40ms_rms_envelope_nrmse": 0.023898768940322848, "全帯域_40ms_envelope_correlation": 0.9995021417540296, "全帯域_40ms_modulation_mae_db": 0.5178047722302312, "300–1000 Hz_10ms_log_rms_mae_db": 1.384140343873778, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0750909838203286, "300–1000 Hz_10ms_envelope_correlation": 0.9949520881351402, "300–1000 Hz_10ms_modulation_mae_db": 0.12793862271197823, "300–1000 Hz_40ms_log_rms_mae_db": 1.0627623891053064, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04611354027492118, "300–1000 Hz_40ms_envelope_correlation": 0.9980383171145853, "300–1000 Hz_40ms_modulation_mae_db": 0.5613109105860521, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2457807815766473, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11353896490212699, "1000–3000 Hz_10ms_envelope_correlation": 0.9909605630689534, "1000–3000 Hz_10ms_modulation_mae_db": 0.3538418364885723, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8227077808242939, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06045359637402745, "1000–3000 Hz_40ms_envelope_correlation": 0.9978009904939528, "1000–3000 Hz_40ms_modulation_mae_db": 0.3056351449443963, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5501549276247446, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16827639804885902, "3000–6000 Hz_10ms_envelope_correlation": 0.9788497510241653, "3000–6000 Hz_10ms_modulation_mae_db": 0.40472666443101635, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0018330361112049, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09430456030006419, "3000–6000 Hz_40ms_envelope_correlation": 0.9939818084368336, "3000–6000 Hz_40ms_modulation_mae_db": 0.21702371430816328, "mr_stft_db": 5.435717115027733, "band_mae_db": 0.1734812578531259, "rms_gain_error_db": -0.093436779253784, "output_peak": 0.15179522072382454}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0542122602224004, "全帯域_10ms_rms_envelope_nrmse": 0.04137991011327181, "全帯域_10ms_envelope_correlation": 0.99837892507866, "全帯域_10ms_modulation_mae_db": 0.6192382387263994, "全帯域_40ms_log_rms_mae_db": 0.576262882269908, "全帯域_40ms_rms_envelope_nrmse": 0.023818648685210896, "全帯域_40ms_envelope_correlation": 0.9995316957722234, "全帯域_40ms_modulation_mae_db": 0.7441796005099347, "300–1000 Hz_10ms_log_rms_mae_db": 1.4172902681812254, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06260078107783706, "300–1000 Hz_10ms_envelope_correlation": 0.9965475125422776, "300–1000 Hz_10ms_modulation_mae_db": 0.7150697476538431, "300–1000 Hz_40ms_log_rms_mae_db": 1.07983483285243, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.036113931961340856, "300–1000 Hz_40ms_envelope_correlation": 0.9988460232106326, "300–1000 Hz_40ms_modulation_mae_db": 0.8270570726980443, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2206423422750539, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12752550938228888, "1000–3000 Hz_10ms_envelope_correlation": 0.9896212811106745, "1000–3000 Hz_10ms_modulation_mae_db": 0.3901915630781448, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8565238036866565, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08322236731845432, "1000–3000 Hz_40ms_envelope_correlation": 0.9966482680037189, "1000–3000 Hz_40ms_modulation_mae_db": 0.33174099749302605, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4947630386738953, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1818196979095958, "3000–6000 Hz_10ms_envelope_correlation": 0.9747857312297332, "3000–6000 Hz_10ms_modulation_mae_db": 1.4153609929289013, "3000–6000 Hz_40ms_log_rms_mae_db": 0.980263368815595, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11659186541263716, "3000–6000 Hz_40ms_envelope_correlation": 0.9896274038954991, "3000–6000 Hz_40ms_modulation_mae_db": 1.2726673064447516, "mr_stft_db": 5.4483235632377855, "band_mae_db": 0.21944153115988804, "rms_gain_error_db": -0.10386626586049705, "output_peak": 0.15090731443584215}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0702976219616969, "全帯域_10ms_rms_envelope_nrmse": 0.042887734436369, "全帯域_10ms_envelope_correlation": 0.9981685860729494, "全帯域_10ms_modulation_mae_db": 0.7603352724570213, "全帯域_40ms_log_rms_mae_db": 0.5376703895956344, "全帯域_40ms_rms_envelope_nrmse": 0.023537188293398365, "全帯域_40ms_envelope_correlation": 0.9994645834358469, "全帯域_40ms_modulation_mae_db": 0.9895901739205657, "300–1000 Hz_10ms_log_rms_mae_db": 1.3232210683634211, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05870202027675938, "300–1000 Hz_10ms_envelope_correlation": 0.9969311775612867, "300–1000 Hz_10ms_modulation_mae_db": 1.0362492006309783, "300–1000 Hz_40ms_log_rms_mae_db": 1.0320735483474477, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03785769882980415, "300–1000 Hz_40ms_envelope_correlation": 0.9986709161134295, "300–1000 Hz_40ms_modulation_mae_db": 1.0164979087873507, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2141175440495648, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12654325940297012, "1000–3000 Hz_10ms_envelope_correlation": 0.9896095964959984, "1000–3000 Hz_10ms_modulation_mae_db": 0.6580706262425191, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8299072867996877, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07673436401112516, "1000–3000 Hz_40ms_envelope_correlation": 0.9973094651165181, "1000–3000 Hz_40ms_modulation_mae_db": 0.5021632866310062, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5403714316325627, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.157896123537679, "3000–6000 Hz_10ms_envelope_correlation": 0.9817657654007694, "3000–6000 Hz_10ms_modulation_mae_db": 0.9321347462329544, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9919613600808591, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09390053747823739, "3000–6000 Hz_40ms_envelope_correlation": 0.9944130586414671, "3000–6000 Hz_40ms_modulation_mae_db": 0.5233710869420256, "mr_stft_db": 5.456807812722199, "band_mae_db": 0.2478700376138516, "rms_gain_error_db": -0.06853583645995477, "output_peak": 0.15357368759243173}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.047633759568046, "全帯域_10ms_rms_envelope_nrmse": 0.04341578387768585, "全帯域_10ms_envelope_correlation": 0.9981472712622982, "全帯域_10ms_modulation_mae_db": 0.5927366519162046, "全帯域_40ms_log_rms_mae_db": 0.5220269784694294, "全帯域_40ms_rms_envelope_nrmse": 0.02294361488460088, "全帯域_40ms_envelope_correlation": 0.9995197877673329, "全帯域_40ms_modulation_mae_db": 0.5663531269724302, "300–1000 Hz_10ms_log_rms_mae_db": 1.3564394768504988, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.056127521012061844, "300–1000 Hz_10ms_envelope_correlation": 0.997208434683597, "300–1000 Hz_10ms_modulation_mae_db": 0.5415398783077542, "300–1000 Hz_40ms_log_rms_mae_db": 1.038039143861933, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03393741279742395, "300–1000 Hz_40ms_envelope_correlation": 0.9989531950012888, "300–1000 Hz_40ms_modulation_mae_db": 0.7942020069504809, "1000–3000 Hz_10ms_log_rms_mae_db": 1.264759152681526, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1228917373867856, "1000–3000 Hz_10ms_envelope_correlation": 0.9893454556303293, "1000–3000 Hz_10ms_modulation_mae_db": 0.44881076723832924, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8522852128202448, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.066376052350873, "1000–3000 Hz_40ms_envelope_correlation": 0.9972466235937901, "1000–3000 Hz_40ms_modulation_mae_db": 0.6718789823164041, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5054979605100685, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15464417318535034, "3000–6000 Hz_10ms_envelope_correlation": 0.9821847034919744, "3000–6000 Hz_10ms_modulation_mae_db": 0.4011383730534536, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9528285420720898, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08852744054839684, "3000–6000 Hz_40ms_envelope_correlation": 0.9946861020968235, "3000–6000 Hz_40ms_modulation_mae_db": 0.3251458153907811, "mr_stft_db": 5.4396652648124215, "band_mae_db": 0.23329556579994795, "rms_gain_error_db": -0.08365615907060635, "output_peak": 0.16415371281168215}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.065488538356239, "全帯域_10ms_rms_envelope_nrmse": 0.0401783743606887, "全帯域_10ms_envelope_correlation": 0.998452876624306, "全帯域_10ms_modulation_mae_db": 0.5836843705065112, "全帯域_40ms_log_rms_mae_db": 0.5008610578024926, "全帯域_40ms_rms_envelope_nrmse": 0.02258849534407786, "全帯域_40ms_envelope_correlation": 0.9995650805635491, "全帯域_40ms_modulation_mae_db": 0.6014758796647179, "300–1000 Hz_10ms_log_rms_mae_db": 1.3794610824140268, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06254572841352234, "300–1000 Hz_10ms_envelope_correlation": 0.9965502496106252, "300–1000 Hz_10ms_modulation_mae_db": 0.4220046705484322, "300–1000 Hz_40ms_log_rms_mae_db": 0.999509253255531, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.036326810263443116, "300–1000 Hz_40ms_envelope_correlation": 0.9988335093305943, "300–1000 Hz_40ms_modulation_mae_db": 0.5576443276072817, "1000–3000 Hz_10ms_log_rms_mae_db": 1.231114911235624, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1257158733768094, "1000–3000 Hz_10ms_envelope_correlation": 0.9884971108398274, "1000–3000 Hz_10ms_modulation_mae_db": 1.0251333548142585, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8328355111852792, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06463515929941331, "1000–3000 Hz_40ms_envelope_correlation": 0.9969804826467774, "1000–3000 Hz_40ms_modulation_mae_db": 1.1718635802110071, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4882242778293546, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1580396812863945, "3000–6000 Hz_10ms_envelope_correlation": 0.9813986322480831, "3000–6000 Hz_10ms_modulation_mae_db": 0.154921950652397, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9651104213662955, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09843938784542954, "3000–6000 Hz_40ms_envelope_correlation": 0.9932048155737342, "3000–6000 Hz_40ms_modulation_mae_db": 0.6449128368436354, "mr_stft_db": 5.450925458911384, "band_mae_db": 0.17268040269581694, "rms_gain_error_db": -0.08981008216361595, "output_peak": 0.15688733900464047}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0366992092312983, "全帯域_10ms_rms_envelope_nrmse": 0.04074430336702626, "全帯域_10ms_envelope_correlation": 0.9984029237089923, "全帯域_10ms_modulation_mae_db": 0.3744751676481235, "全帯域_40ms_log_rms_mae_db": 0.544643538565714, "全帯域_40ms_rms_envelope_nrmse": 0.022554711225581458, "全帯域_40ms_envelope_correlation": 0.9995721935446824, "全帯域_40ms_modulation_mae_db": 0.4139097599907528, "300–1000 Hz_10ms_log_rms_mae_db": 1.3850716581267801, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0641752366430397, "300–1000 Hz_10ms_envelope_correlation": 0.996359746313501, "300–1000 Hz_10ms_modulation_mae_db": 0.5533474376556359, "300–1000 Hz_40ms_log_rms_mae_db": 1.089541653141982, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0380110742179905, "300–1000 Hz_40ms_envelope_correlation": 0.9986836608523929, "300–1000 Hz_40ms_modulation_mae_db": 0.7356528685320489, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2705084159255107, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11604715388477015, "1000–3000 Hz_10ms_envelope_correlation": 0.9914776255622954, "1000–3000 Hz_10ms_modulation_mae_db": 0.259376581204551, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8289760117286762, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07739735798419367, "1000–3000 Hz_40ms_envelope_correlation": 0.9970453481499492, "1000–3000 Hz_40ms_modulation_mae_db": 0.26868270489055696, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4934720573253661, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1631805263854323, "3000–6000 Hz_10ms_envelope_correlation": 0.9801692991947343, "3000–6000 Hz_10ms_modulation_mae_db": 0.4409840279836564, "3000–6000 Hz_40ms_log_rms_mae_db": 0.981481596411635, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10009013634514224, "3000–6000 Hz_40ms_envelope_correlation": 0.993007573343077, "3000–6000 Hz_40ms_modulation_mae_db": 0.08294732880704699, "mr_stft_db": 5.443197162980213, "band_mae_db": 0.23575876386575276, "rms_gain_error_db": -0.09214395088629852, "output_peak": 0.15462135864982418}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0637257951388281, "全帯域_10ms_rms_envelope_nrmse": 0.03959694105378989, "全帯域_10ms_envelope_correlation": 0.9984679735331297, "全帯域_10ms_modulation_mae_db": 0.39787562665291726, "全帯域_40ms_log_rms_mae_db": 0.5332585357381614, "全帯域_40ms_rms_envelope_nrmse": 0.020533674977600475, "全帯域_40ms_envelope_correlation": 0.9996261964412736, "全帯域_40ms_modulation_mae_db": 0.6898830550167685, "300–1000 Hz_10ms_log_rms_mae_db": 1.393952068935209, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06357440995662406, "300–1000 Hz_10ms_envelope_correlation": 0.9964044350088112, "300–1000 Hz_10ms_modulation_mae_db": 0.765678889701328, "300–1000 Hz_40ms_log_rms_mae_db": 1.0688664080988663, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04026167357553107, "300–1000 Hz_40ms_envelope_correlation": 0.9985012333348992, "300–1000 Hz_40ms_modulation_mae_db": 1.142852529025152, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2936476926835239, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11893754161786443, "1000–3000 Hz_10ms_envelope_correlation": 0.9899559250084251, "1000–3000 Hz_10ms_modulation_mae_db": 0.739124473394824, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9004423303238122, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0714233236037484, "1000–3000 Hz_40ms_envelope_correlation": 0.9965917096865639, "1000–3000 Hz_40ms_modulation_mae_db": 0.8195694676730669, "3000–6000 Hz_10ms_log_rms_mae_db": 1.55692473381292, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1588654828237721, "3000–6000 Hz_10ms_envelope_correlation": 0.9814241826381263, "3000–6000 Hz_10ms_modulation_mae_db": 0.3673213316047022, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9875640191056596, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10008482523647277, "3000–6000 Hz_40ms_envelope_correlation": 0.9932808040025097, "3000–6000 Hz_40ms_modulation_mae_db": 0.2885746812028289, "mr_stft_db": 5.440035049859262, "band_mae_db": 0.18504586715465715, "rms_gain_error_db": -0.07882591182616361, "output_peak": 0.15556125452138214}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0444771332822966, "全帯域_10ms_rms_envelope_nrmse": 0.03905369727069443, "全帯域_10ms_envelope_correlation": 0.9985646047937714, "全帯域_10ms_modulation_mae_db": 1.009528304794254, "全帯域_40ms_log_rms_mae_db": 0.544843707445269, "全帯域_40ms_rms_envelope_nrmse": 0.02251932752587161, "全帯域_40ms_envelope_correlation": 0.9995932014787302, "全帯域_40ms_modulation_mae_db": 1.0761514180338883, "300–1000 Hz_10ms_log_rms_mae_db": 1.4137118004699083, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06828624469627154, "300–1000 Hz_10ms_envelope_correlation": 0.9958511304435597, "300–1000 Hz_10ms_modulation_mae_db": 0.7232811174299013, "300–1000 Hz_40ms_log_rms_mae_db": 1.137686252177627, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04286582384635883, "300–1000 Hz_40ms_envelope_correlation": 0.9983254749508986, "300–1000 Hz_40ms_modulation_mae_db": 0.5554528659781911, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2206658025969945, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12028435758345932, "1000–3000 Hz_10ms_envelope_correlation": 0.9912436091524969, "1000–3000 Hz_10ms_modulation_mae_db": 1.1083362300245903, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8226994541125858, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07933896529289039, "1000–3000 Hz_40ms_envelope_correlation": 0.9974447277992892, "1000–3000 Hz_40ms_modulation_mae_db": 0.9841273150250988, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4561769606932042, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15744218221709116, "3000–6000 Hz_10ms_envelope_correlation": 0.9811330778720635, "3000–6000 Hz_10ms_modulation_mae_db": 0.8841920558262296, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9160501448505461, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09200968286997253, "3000–6000 Hz_40ms_envelope_correlation": 0.9936275525155955, "3000–6000 Hz_40ms_modulation_mae_db": 0.27333993078440716, "mr_stft_db": 5.4328188871504635, "band_mae_db": 0.2078821667721827, "rms_gain_error_db": -0.10399240044795449, "output_peak": 0.1630425960621305}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 5.5120776288549544, "spectral_convergence": 0.13193880156865212, "spectral_convergence_status": "ok", "amplitude_floor": 5.237444731722431e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.417188399834432, "spectral_convergence": 0.13370773851710074, "spectral_convergence_status": "ok", "amplitude_floor": 5.437369948912744e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.377885316393812, "spectral_convergence": 0.13285882074292824, "spectral_convergence_status": "ok", "amplitude_floor": 5.052721691674583e-07}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 6.432970236988243e-05, "output_power": 6.649049044434103e-05, "delta_db": 0.14347994305251793, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008444430165469724, "output_power": 0.0008216648798149606, "delta_db": -0.11875624032237152, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 6.039141474549642e-05, "output_power": 6.19896352542912e-05, "delta_db": 0.11343877352878301, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 3.556975687019485e-05, "output_power": 3.321756072866645e-05, "delta_db": -0.29713159006168327, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.090392882810899e-05, "output_power": 1.0549730978540806e-05, "delta_db": -0.14341622989232994, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2355857763199668e-06, "output_power": 1.3207255518626344e-06, "delta_db": 0.289396799519629, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.0422411240430348e-06, "output_power": 1.0164669970607318e-06, "delta_db": -0.10874922859456661, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.1734812578531259, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.093436779253784, "pitch": null, "output_rms_dbfs": -30.016318880201727, "output_peak": 0.15179522072382454, "reference_rms_dbfs": -29.922882100947945, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.435717115027733}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 8.184761378594803e-05, "log_rms_mae_db": 1.0635331674705906, "rms_envelope_nrmse": 0.04259243649973802, "envelope_correlation": 0.9982440829381143, "rms_gain_error_db": -0.09306853655187905, "reference_mean_power": 0.0010176842474405314, "output_mean_power": 0.0009961074736163295}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.21363647710693e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00013327602732153044, "output_power": 0.00012469451432707896, "reference_active": true, "delta_db": -0.28904690822845075}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5932863269435214e-05, "output_power": 1.484794504437017e-05, "reference_active": true, "delta_db": -0.30627477728267877}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.59165062752131e-06, "output_power": 4.118876163961234e-06, "reference_active": true, "delta_db": -0.47190100892588027}], "active_band_count": 3, "active_band_mae_db": 0.35574089814566995}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.048620680965671e-05, "log_rms_mae_db": 0.5414283407385139, "rms_envelope_nrmse": 0.023898768940322848, "envelope_correlation": 0.9995021417540296, "rms_gain_error_db": -0.09251597098745644, "reference_mean_power": 0.0010161096570352637, "output_mean_power": 0.0009946928170414767}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.9042638692252304e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00011759425242544185, "output_power": 0.00011060331666545044, "reference_active": true, "delta_db": -0.26617945174391094}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 7.519272755909202e-06, "output_power": 7.120180420763895e-06, "reference_active": true, "delta_db": -0.23684840296502135}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.598733053895232e-07, "output_power": 2.8256019827103915e-07, "reference_active": true, "delta_db": -1.0503864619817613}], "active_band_count": 3, "active_band_mae_db": 0.5178047722302312}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.667982083652557e-05, "log_rms_mae_db": 1.384140343873778, "rms_envelope_nrmse": 0.0750909838203286, "envelope_correlation": 0.9949520881351402, "rms_gain_error_db": -0.03850227311173045, "reference_mean_power": 0.00027945110045850193, "output_mean_power": 0.00027698458301165385}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.93859363437704e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.295075151115005e-05, "output_power": 3.146515417678388e-05, "reference_active": true, "delta_db": -0.20035459943955422}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.807348843301933e-06, "output_power": 3.7061136364649617e-06, "reference_active": true, "delta_db": -0.11703938816309682}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5906604704508056e-06, "output_power": 1.5665176789852235e-06, "reference_active": true, "delta_db": -0.06642188053328371}], "active_band_count": 3, "active_band_mae_db": 0.12793862271197823}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.254388131298964e-05, "log_rms_mae_db": 1.0627623891053064, "rms_envelope_nrmse": 0.04611354027492118, "envelope_correlation": 0.9980383171145853, "rms_gain_error_db": -0.03912136479187581, "reference_mean_power": 0.00027742187495382226, "output_mean_power": 0.00027493407309131404}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 9.236914065861651e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.9257092980847557e-05, "output_power": 2.7727144206227282e-05, "reference_active": true, "delta_db": -0.23326030774179607}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8979287936807737e-06, "output_power": 1.948497563637606e-06, "reference_active": true, "delta_db": 0.11419952519717652}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.43591780871064e-08, "output_power": 6.93644360074408e-08, "reference_active": true, "delta_db": -1.3364728988191836}], "active_band_count": 3, "active_band_mae_db": 0.5613109105860521}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 3.428909761907278e-05, "log_rms_mae_db": 1.2457807815766473, "rms_envelope_nrmse": 0.11353896490212699, "envelope_correlation": 0.9909605630689534, "rms_gain_error_db": -0.25837581638067086, "reference_mean_power": 3.509769240032237e-05, "output_mean_power": 3.307051680273571e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.14178826098124e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0207730418969553e-05, "output_power": 1.0015588380641499e-05, "reference_active": true, "delta_db": -0.08252724374971715}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.594184871691995e-06, "output_power": 2.2212272470373942e-06, "reference_active": true, "delta_db": -0.6740793018730096}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.354712471534306e-07, "output_power": 3.127255801325126e-07, "reference_active": true, "delta_db": -0.3049189638429903}], "active_band_count": 3, "active_band_mae_db": 0.3538418364885723}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 2.9506018028930777e-05, "log_rms_mae_db": 0.8227077808242939, "rms_envelope_nrmse": 0.06045359637402745, "envelope_correlation": 0.9978009904939528, "rms_gain_error_db": -0.25983627257032843, "reference_mean_power": 3.5141167460930974e-05, "output_mean_power": 3.3100347888592986e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.01202004778774e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.499160468037956e-06, "output_power": 9.315217425842535e-06, "reference_active": true, "delta_db": -0.08492228026247785}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1261229797074577e-06, "output_power": 9.634989829137667e-07, "reference_active": true, "delta_db": -0.6773456024940406}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.7957517138182228e-08, "output_power": 2.897092454508261e-08, "reference_active": true, "delta_db": 0.15463755207667046}], "active_band_count": 3, "active_band_mae_db": 0.3056351449443963}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 1.0101884937381439e-05, "log_rms_mae_db": 1.5501549276247446, "rms_envelope_nrmse": 0.16827639804885902, "envelope_correlation": 0.9788497510241653, "rms_gain_error_db": -0.37913510987335475, "reference_mean_power": 6.452617383104305e-06, "output_mean_power": 5.913197747412084e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.15273367532141e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.10173826656627e-06, "output_power": 2.0035865515621887e-06, "reference_active": true, "delta_db": -0.20770523584260306}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.3061476096447684e-07, "output_power": 4.2951890835938354e-07, "reference_active": true, "delta_db": -0.01106625664943044}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.161739165108172e-08, "output_power": 1.0264163501386564e-07, "reference_active": true, "delta_db": 0.9954085008010156}], "active_band_count": 3, "active_band_mae_db": 0.40472666443101635}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 8.618352616189344e-06, "log_rms_mae_db": 1.0018330361112049, "rms_envelope_nrmse": 0.09430456030006419, "envelope_correlation": 0.9939818084368336, "rms_gain_error_db": -0.37936526619691535, "reference_mean_power": 6.458260841661403e-06, "output_mean_power": 5.918055791254415e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.76552281278155e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.8830611185238975e-06, "output_power": 1.8491463677372737e-06, "reference_active": true, "delta_db": -0.07893127383082951}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.769776726408418e-07, "output_power": 1.881105175254936e-07, "reference_active": true, "delta_db": 0.26494598669638775}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.816205310457936e-09, "output_power": 9.145853595896719e-09, "reference_active": true, "delta_db": -0.30719388239727263}], "active_band_count": 3, "active_band_mae_db": 0.21702371430816328}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.9297284730328642, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "82d729ed96356589969e45e9f0a2a7b95f7ffed4b8caf6db50de584e175ac312", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.990088895858625, "standard_deviation": 0.0010402123618416536, "minimum": 0.9884971108398274, "maximum": 0.9914776255622954, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.2451545803780557, "standard_deviation": 0.028635867341736482, "minimum": 1.2141175440495648, "maximum": 1.2936476926835239, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6228606790607236, "standard_deviation": 0.3164957555314038, "minimum": 0.259376581204551, "maximum": 1.1083362300245903, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12143554969213435, "standard_deviation": 0.005107055473954019, "minimum": 0.11353896490212699, "maximum": 0.12752550938228888, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.99713345193632, "standard_deviation": 0.0004046760338826266, "minimum": 0.9965917096865639, "maximum": 0.9978009904939528, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8432971739351546, "standard_deviation": 0.026358294435303006, "minimum": 0.8226994541125858, "maximum": 0.9004423303238122, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6319576848980704, "standard_deviation": 0.3375850097383496, "minimum": 0.26868270489055696, "maximum": 1.1718635802110071, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07244764827934072, "standard_deviation": 0.008011297039707375, "minimum": 0.06045359637402745, "maximum": 0.08322236731845432, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9802138928874562, "standard_deviation": 0.0024299771606383744, "minimum": 0.9747857312297332, "maximum": 0.9821847034919744, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5106981735127647, "standard_deviation": 0.035111213147235074, "minimum": 1.4561769606932042, "maximum": 1.55692473381292, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6250975178391639, "standard_deviation": 0.4150818532317482, "minimum": 0.154921950652397, "maximum": 1.4153609929289013, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1625205331742718, "standard_deviation": 0.008853349788047395, "minimum": 0.15464417318535034, "maximum": 0.1818196979095958, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9932286398131924, "standard_deviation": 0.0015709186486566951, "minimum": 0.9896274038954991, "maximum": 0.9946861020968235, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9721365611017356, "standard_deviation": 0.027344722023787918, "minimum": 0.9160501448505461, "maximum": 1.0018330361112049, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.453497837590455, "standard_deviation": 0.3745319064529908, "minimum": 0.08294732880704699, "maximum": 1.2726673064447516, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09799355450454408, "standard_deviation": 0.0085409978045275, "minimum": 0.08852744054839684, "maximum": 0.11659186541263716, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9963505967873498, "standard_deviation": 0.000692807157510718, "minimum": 0.9949520881351402, "maximum": 0.997208434683597, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.381660970901856, "standard_deviation": 0.03052338482777464, "minimum": 1.3232210683634211, "maximum": 1.4172902681812254, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6106386955799814, "standard_deviation": 0.26870456803224607, "minimum": 0.12793862271197823, "maximum": 1.0362492006309783, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06388786573705557, "standard_deviation": 0.0058016043559956515, "minimum": 0.056127521012061844, "maximum": 0.0750909838203286, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9986065412385902, "standard_deviation": 0.0003052149565740912, "minimum": 0.9980383171145853, "maximum": 0.9989531950012888, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.0635391851051406, "standard_deviation": 0.04176228189655409, "minimum": 0.999509253255531, "maximum": 1.137686252177627, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7738338112705753, "standard_deviation": 0.22018179341050295, "minimum": 0.5554528659781911, "maximum": 1.142852529025152, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.038935995720851706, "standard_deviation": 0.00397301692715183, "minimum": 0.03393741279742395, "maximum": 0.04611354027492118, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.20943194911440288, "standard_deviation": 0.029472657889401968, "minimum": 0.17268040269581694, "maximum": 0.2478700376138516, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.443436289337683, "standard_deviation": 0.008079355201535469, "minimum": 5.4328188871504635, "maximum": 5.456807812722199, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.15631781047521973, "standard_deviation": 0.0048939655395611615, "minimum": 0.15090731443584215, "maximum": 0.16415371281168215, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.08928342324610934, "standard_deviation": 0.01210791752656545, "minimum": -0.10399240044795449, "maximum": -0.06853583645995477, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9983534055015277, "standard_deviation": 0.00015086879327874558, "minimum": 0.9981472712622982, "maximum": 0.9985646047937714, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.0557584356539245, "standard_deviation": 0.011885832046522491, "minimum": 1.0366992092312983, "maximum": 1.0702976219616969, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.5867018163558877, "standard_deviation": 0.22170552718256337, "minimum": 0.35574089814566995, "maximum": 1.009528304794254, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.041231147622407996, "standard_deviation": 0.0016102095311292218, "minimum": 0.03905369727069443, "maximum": 0.04341578387768585, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9995468600947085, "standard_deviation": 5.230077178365847e-05, "minimum": 0.9994645834358469, "maximum": 0.9996261964412736, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5376244288281402, "standard_deviation": 0.021456516683018387, "minimum": 0.5008610578024926, "maximum": 0.576262882269908, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6999184732924112, "standard_deviation": 0.2299123155941171, "minimum": 0.4139097599907528, "maximum": 1.0761514180338883, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.022799303734583047, "standard_deviation": 0.0010776239214148353, "minimum": 0.020533674977600475, "maximum": 0.023898768940322848, "valid_count": 8, "planned_count": 8}}}]}, {"case": {"id": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "language": "ja", "style": "whisper", "speaker": "jvs_jvs082", "source_utterance_id": "VOICEACTRESS100_001", "speaker_gender_as_distributed": null, "excerpt_start_sample": 0, "excerpt_samples": 144000, "kind": "natural_speech", "sr": 24000, "source_file": "audio/jvs_jvs082_whisper10_VOICEACTRESS100_001.wav", "source_file_sha256": "959dfe29d97ec4c67eb776ad4eebf28a8f34e92c64e82fd19b086f80ada75ca5", "decoded_pcm_sha256": "2e9752009fa4e3b6da1c72a2a24d8e0847c58184f65c69de675ab526188ca823", "original_source_sha256": "959dfe29d97ec4c67eb776ad4eebf28a8f34e92c64e82fd19b086f80ada75ca5", "corpus_entry_id": "jvs_jvs082_whisper10_VOICEACTRESS100_001"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 3.9916911125183105, "predicted_mos": 3.9916911125183105, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "d0c5684665aded3672ca9a285fc5ba6164649856eab5a6701aaf39f0a1b42d7a", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.421715000178665}, "waveform_sha256": "037b087a7a93c17686e2293a5bee2cd3483e44fd19cb08fb05cc85c4fe142bc8"}, "rows": [{"case": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 2.8367226123809814, "predicted_mos": 2.8367226123809814, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "ec263e22ff05c573420a23459c75ba6e4e6e2ce3bb3e56a0ffef56903917c0f3", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.889041000045836}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7970231990323762, "全帯域_10ms_rms_envelope_nrmse": 0.20203205345195277, "全帯域_10ms_envelope_correlation": 0.9650210066990967, "全帯域_10ms_modulation_mae_db": 0.5626225600262282, "全帯域_40ms_log_rms_mae_db": 1.0083383783659434, "全帯域_40ms_rms_envelope_nrmse": 0.11169244568299773, "全帯域_40ms_envelope_correlation": 0.9883433382975486, "全帯域_40ms_modulation_mae_db": 0.6701611298690269, "300–1000 Hz_10ms_log_rms_mae_db": 2.3899944005261506, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.32550719277991713, "300–1000 Hz_10ms_envelope_correlation": 0.92964474883058, "300–1000 Hz_10ms_modulation_mae_db": 0.8950807648885292, "300–1000 Hz_40ms_log_rms_mae_db": 1.820134694839904, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2406383929363215, "300–1000 Hz_40ms_envelope_correlation": 0.960850861985086, "300–1000 Hz_40ms_modulation_mae_db": 1.3071922667898137, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4591327512261723, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18489945932562274, "1000–3000 Hz_10ms_envelope_correlation": 0.9793769110817071, "1000–3000 Hz_10ms_modulation_mae_db": 0.270059465713879, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8912879165395741, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09908270449144047, "1000–3000 Hz_40ms_envelope_correlation": 0.9942122579172193, "1000–3000 Hz_40ms_modulation_mae_db": 0.4419674388308236, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3108086877845302, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24225837447838067, "3000–6000 Hz_10ms_envelope_correlation": 0.9635461780038664, "3000–6000 Hz_10ms_modulation_mae_db": 0.9282515676772868, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7929704718053817, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14415254716304993, "3000–6000 Hz_40ms_envelope_correlation": 0.9872872226748816, "3000–6000 Hz_40ms_modulation_mae_db": 1.3877276470028626, "mr_stft_db": 5.965629876950996, "band_mae_db": 0.4833292918155265, "rms_gain_error_db": 0.13159276812373974, "output_peak": 0.01424913917589817}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8529674014007511, "全帯域_10ms_rms_envelope_nrmse": 0.2063295046050789, "全帯域_10ms_envelope_correlation": 0.9624997350676023, "全帯域_10ms_modulation_mae_db": 0.6065641760711866, "全帯域_40ms_log_rms_mae_db": 0.8891890031780251, "全帯域_40ms_rms_envelope_nrmse": 0.09738529013095298, "全帯域_40ms_envelope_correlation": 0.9908292968264366, "全帯域_40ms_modulation_mae_db": 0.49236016438521113, "300–1000 Hz_10ms_log_rms_mae_db": 2.3073666658823653, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2913816768877124, "300–1000 Hz_10ms_envelope_correlation": 0.9420215675743436, "300–1000 Hz_10ms_modulation_mae_db": 0.7197455596840999, "300–1000 Hz_40ms_log_rms_mae_db": 1.6519831468693482, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20366401067322062, "300–1000 Hz_40ms_envelope_correlation": 0.9712423611231147, "300–1000 Hz_40ms_modulation_mae_db": 0.5929926864180216, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4154636281717135, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21496823822642083, "1000–3000 Hz_10ms_envelope_correlation": 0.9710730440019587, "1000–3000 Hz_10ms_modulation_mae_db": 0.7579256620895284, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8994334567795199, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10018179748496564, "1000–3000 Hz_40ms_envelope_correlation": 0.9935519681247977, "1000–3000 Hz_40ms_modulation_mae_db": 0.7390324975822679, "3000–6000 Hz_10ms_log_rms_mae_db": 1.310670588574632, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.22376536461869584, "3000–6000 Hz_10ms_envelope_correlation": 0.969855077248989, "3000–6000 Hz_10ms_modulation_mae_db": 0.8394857716648595, "3000–6000 Hz_40ms_log_rms_mae_db": 0.743757257103388, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12017942462562818, "3000–6000 Hz_40ms_envelope_correlation": 0.9908771637667658, "3000–6000 Hz_40ms_modulation_mae_db": 0.8855054893576314, "mr_stft_db": 5.960646826848451, "band_mae_db": 0.6914160210900953, "rms_gain_error_db": -0.06483002293665008, "output_peak": 0.01348450375585317}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.770932449126317, "全帯域_10ms_rms_envelope_nrmse": 0.196604158636653, "全帯域_10ms_envelope_correlation": 0.965718275336261, "全帯域_10ms_modulation_mae_db": 0.31732536176250986, "全帯域_40ms_log_rms_mae_db": 0.960434738233879, "全帯域_40ms_rms_envelope_nrmse": 0.10486163948666369, "全帯域_40ms_envelope_correlation": 0.989245218932197, "全帯域_40ms_modulation_mae_db": 0.5528710619791068, "300–1000 Hz_10ms_log_rms_mae_db": 2.3215207062831027, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3022534569608855, "300–1000 Hz_10ms_envelope_correlation": 0.9284168432012073, "300–1000 Hz_10ms_modulation_mae_db": 1.0193027503042138, "300–1000 Hz_40ms_log_rms_mae_db": 1.6547428258931975, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20872624650748042, "300–1000 Hz_40ms_envelope_correlation": 0.9629468987471239, "300–1000 Hz_40ms_modulation_mae_db": 2.030153464710002, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4134457517960097, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20272946788496798, "1000–3000 Hz_10ms_envelope_correlation": 0.9745099748585235, "1000–3000 Hz_10ms_modulation_mae_db": 0.3917533315612249, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8608670379040028, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09191364797955318, "1000–3000 Hz_40ms_envelope_correlation": 0.9947223070788261, "1000–3000 Hz_40ms_modulation_mae_db": 0.4750227890559926, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2824187009868588, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2489628781170274, "3000–6000 Hz_10ms_envelope_correlation": 0.9610518562723372, "3000–6000 Hz_10ms_modulation_mae_db": 0.867956018950979, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7787987947315371, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12843457356085788, "3000–6000 Hz_40ms_envelope_correlation": 0.9896110833834716, "3000–6000 Hz_40ms_modulation_mae_db": 1.5215315932653937, "mr_stft_db": 5.977113707851582, "band_mae_db": 0.40083112038916674, "rms_gain_error_db": -0.07065686202382933, "output_peak": 0.018040455796409966}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7181081536087883, "全帯域_10ms_rms_envelope_nrmse": 0.2018105622657649, "全帯域_10ms_envelope_correlation": 0.9637496037695266, "全帯域_10ms_modulation_mae_db": 0.4414066306785857, "全帯域_40ms_log_rms_mae_db": 0.8949479583446651, "全帯域_40ms_rms_envelope_nrmse": 0.10239920241217741, "全帯域_40ms_envelope_correlation": 0.9898101044050166, "全帯域_40ms_modulation_mae_db": 0.5397343923389589, "300–1000 Hz_10ms_log_rms_mae_db": 2.4329304041188458, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3040234141859943, "300–1000 Hz_10ms_envelope_correlation": 0.9372048239889771, "300–1000 Hz_10ms_modulation_mae_db": 0.6449818185138758, "300–1000 Hz_40ms_log_rms_mae_db": 1.8637973750019572, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.213287019120999, "300–1000 Hz_40ms_envelope_correlation": 0.9688845255806185, "300–1000 Hz_40ms_modulation_mae_db": 1.0421689188170953, "1000–3000 Hz_10ms_log_rms_mae_db": 1.44167339861026, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19834814253914237, "1000–3000 Hz_10ms_envelope_correlation": 0.9747062219943702, "1000–3000 Hz_10ms_modulation_mae_db": 0.5978418892507859, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7969513928583332, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10255909202497099, "1000–3000 Hz_40ms_envelope_correlation": 0.993350714531649, "1000–3000 Hz_40ms_modulation_mae_db": 0.32969152781632666, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3060068773553657, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.22798526164229516, "3000–6000 Hz_10ms_envelope_correlation": 0.9674809546963294, "3000–6000 Hz_10ms_modulation_mae_db": 0.9636764961010797, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7902806097259927, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11740356171207822, "3000–6000 Hz_40ms_envelope_correlation": 0.991060262720958, "3000–6000 Hz_40ms_modulation_mae_db": 1.3901227217730365, "mr_stft_db": 5.951465727676973, "band_mae_db": 0.405896097986093, "rms_gain_error_db": -0.12683282439523674, "output_peak": 0.013869141401446837}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.70971520396168, "全帯域_10ms_rms_envelope_nrmse": 0.17589030376840978, "全帯域_10ms_envelope_correlation": 0.972721111828769, "全帯域_10ms_modulation_mae_db": 0.43635618384801833, "全帯域_40ms_log_rms_mae_db": 0.8451025657909407, "全帯域_40ms_rms_envelope_nrmse": 0.08691488900252022, "全帯域_40ms_envelope_correlation": 0.9926558103853332, "全帯域_40ms_modulation_mae_db": 0.7231712505493771, "300–1000 Hz_10ms_log_rms_mae_db": 2.4371731475887213, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.29838683584554454, "300–1000 Hz_10ms_envelope_correlation": 0.9321532527674028, "300–1000 Hz_10ms_modulation_mae_db": 0.7426677411814477, "300–1000 Hz_40ms_log_rms_mae_db": 1.8119075844235446, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19218337462504664, "300–1000 Hz_40ms_envelope_correlation": 0.9709456953179343, "300–1000 Hz_40ms_modulation_mae_db": 0.901452768575839, "1000–3000 Hz_10ms_log_rms_mae_db": 1.407509525659505, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15280941617605867, "1000–3000 Hz_10ms_envelope_correlation": 0.9850938120595822, "1000–3000 Hz_10ms_modulation_mae_db": 0.3704364444216495, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8335780621729164, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0759119899549565, "1000–3000 Hz_40ms_envelope_correlation": 0.9962580378478231, "1000–3000 Hz_40ms_modulation_mae_db": 0.7625384440800723, "3000–6000 Hz_10ms_log_rms_mae_db": 1.280761760565418, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.26168645300697835, "3000–6000 Hz_10ms_envelope_correlation": 0.9575121004270208, "3000–6000 Hz_10ms_modulation_mae_db": 0.7166507942959477, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7887902399045885, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.15281590944459383, "3000–6000 Hz_40ms_envelope_correlation": 0.9864470419703879, "3000–6000 Hz_40ms_modulation_mae_db": 1.191739940001865, "mr_stft_db": 5.959428539021984, "band_mae_db": 0.382118984310231, "rms_gain_error_db": 0.004208480930748683, "output_peak": 0.016047006625443474}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.784609032217928, "全帯域_10ms_rms_envelope_nrmse": 0.1939518316595531, "全帯域_10ms_envelope_correlation": 0.9677587361993443, "全帯域_10ms_modulation_mae_db": 0.5247309499458727, "全帯域_40ms_log_rms_mae_db": 0.8463295452754238, "全帯域_40ms_rms_envelope_nrmse": 0.09041662238153651, "全帯域_40ms_envelope_correlation": 0.9924633720609799, "全帯域_40ms_modulation_mae_db": 0.5489835983882283, "300–1000 Hz_10ms_log_rms_mae_db": 2.3638939179545955, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3335981024591786, "300–1000 Hz_10ms_envelope_correlation": 0.9102058298475011, "300–1000 Hz_10ms_modulation_mae_db": 0.6295085032384037, "300–1000 Hz_40ms_log_rms_mae_db": 1.7827233234961366, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.21058892297308948, "300–1000 Hz_40ms_envelope_correlation": 0.9617509682027, "300–1000 Hz_40ms_modulation_mae_db": 1.265620349917355, "1000–3000 Hz_10ms_log_rms_mae_db": 1.432728636059607, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20276818562735374, "1000–3000 Hz_10ms_envelope_correlation": 0.9760575378082917, "1000–3000 Hz_10ms_modulation_mae_db": 0.5719332252581785, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8765667160681387, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10655068023102533, "1000–3000 Hz_40ms_envelope_correlation": 0.9939720135581455, "1000–3000 Hz_40ms_modulation_mae_db": 0.6019030604869081, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2752809494301653, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2525650419330177, "3000–6000 Hz_10ms_envelope_correlation": 0.9600733954797837, "3000–6000 Hz_10ms_modulation_mae_db": 0.931281755636936, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7521034908391717, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14086029441825043, "3000–6000 Hz_40ms_envelope_correlation": 0.9878716352444336, "3000–6000 Hz_40ms_modulation_mae_db": 1.4453608656279595, "mr_stft_db": 5.95946942514043, "band_mae_db": 0.45866450446292334, "rms_gain_error_db": 0.13209400414303235, "output_peak": 0.014013863210890293}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7754095378208217, "全帯域_10ms_rms_envelope_nrmse": 0.19498844652737327, "全帯域_10ms_envelope_correlation": 0.9672637528989126, "全帯域_10ms_modulation_mae_db": 0.5093234792115972, "全帯域_40ms_log_rms_mae_db": 0.9030949790426077, "全帯域_40ms_rms_envelope_nrmse": 0.09134795416810985, "全帯域_40ms_envelope_correlation": 0.99217455959075, "全帯域_40ms_modulation_mae_db": 0.4583257178337139, "300–1000 Hz_10ms_log_rms_mae_db": 2.3959581445801827, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3132850108636543, "300–1000 Hz_10ms_envelope_correlation": 0.9256516091772667, "300–1000 Hz_10ms_modulation_mae_db": 0.8212376225755795, "300–1000 Hz_40ms_log_rms_mae_db": 1.7614599997439986, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20834056050069427, "300–1000 Hz_40ms_envelope_correlation": 0.9650234391107952, "300–1000 Hz_40ms_modulation_mae_db": 1.0044804294037533, "1000–3000 Hz_10ms_log_rms_mae_db": 1.408056400265845, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18992763791944287, "1000–3000 Hz_10ms_envelope_correlation": 0.9769733293655163, "1000–3000 Hz_10ms_modulation_mae_db": 0.7863520990682057, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8359025084270609, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09471509366216073, "1000–3000 Hz_40ms_envelope_correlation": 0.9941554143755498, "1000–3000 Hz_40ms_modulation_mae_db": 0.31876190387032943, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2845472755580016, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.23434489765566713, "3000–6000 Hz_10ms_envelope_correlation": 0.9657523024645551, "3000–6000 Hz_10ms_modulation_mae_db": 0.7659388129377162, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7556426465418339, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1340272115539877, "3000–6000 Hz_40ms_envelope_correlation": 0.9879882720435589, "3000–6000 Hz_40ms_modulation_mae_db": 1.3744584801300055, "mr_stft_db": 5.969027501912194, "band_mae_db": 0.3020957467779882, "rms_gain_error_db": 0.10815620896395814, "output_peak": 0.014156859283418883}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.711868194333848, "全帯域_10ms_rms_envelope_nrmse": 0.19434457330750018, "全帯域_10ms_envelope_correlation": 0.9670977505080146, "全帯域_10ms_modulation_mae_db": 0.4928388225802147, "全帯域_40ms_log_rms_mae_db": 0.8815484334326614, "全帯域_40ms_rms_envelope_nrmse": 0.09401633877256904, "全帯域_40ms_envelope_correlation": 0.9915064664756515, "全帯域_40ms_modulation_mae_db": 0.5661881060681776, "300–1000 Hz_10ms_log_rms_mae_db": 2.427800479496336, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2897541988561794, "300–1000 Hz_10ms_envelope_correlation": 0.9418421762071201, "300–1000 Hz_10ms_modulation_mae_db": 0.6061027313414283, "300–1000 Hz_40ms_log_rms_mae_db": 1.8743680475764475, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1991997496427284, "300–1000 Hz_40ms_envelope_correlation": 0.9723371410167205, "300–1000 Hz_40ms_modulation_mae_db": 0.6420839771230432, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4458862110358137, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19419344454538054, "1000–3000 Hz_10ms_envelope_correlation": 0.9758299569150207, "1000–3000 Hz_10ms_modulation_mae_db": 0.52839207369037, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8977085105689908, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09635161913444495, "1000–3000 Hz_40ms_envelope_correlation": 0.9939393071685018, "1000–3000 Hz_40ms_modulation_mae_db": 0.6470132728585368, "3000–6000 Hz_10ms_log_rms_mae_db": 1.284653424232368, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2534086516957661, "3000–6000 Hz_10ms_envelope_correlation": 0.9639490706210478, "3000–6000 Hz_10ms_modulation_mae_db": 0.9379161340675454, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7688899705623564, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.15060666368156964, "3000–6000 Hz_40ms_envelope_correlation": 0.9876538116344566, "3000–6000 Hz_40ms_modulation_mae_db": 1.16233770533884, "mr_stft_db": 5.9610674512202335, "band_mae_db": 0.6226393894425539, "rms_gain_error_db": 0.0666814897411296, "output_peak": 0.013725957337543239}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.158067517126765, "spectral_convergence": 0.6844556861957306, "spectral_convergence_status": "ok", "amplitude_floor": 3.772168230462137e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.821915924633525, "spectral_convergence": 0.6388655190568765, "spectral_convergence_status": "ok", "amplitude_floor": 1.9872090073495523e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.9169061890927015, "spectral_convergence": 0.6763583477120855, "spectral_convergence_status": "ok", "amplitude_floor": 8.414272539865191e-09}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0228756868362371e-07, "output_power": 1.0013347266119665e-07, "delta_db": -0.09243577902918505, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 3.789702976182104e-08, "output_power": 5.2358521448688727e-08, "delta_db": 1.4038220121627734, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.1288069701978556e-08, "output_power": 5.558691088909071e-08, "delta_db": 0.34956185727084754, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.8766557699122943e-07, "output_power": 2.9654222866142507e-07, "delta_db": 0.13198651279484364, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 6.379889954922647e-08, "output_power": 6.982018537912356e-08, "delta_db": 0.39167809819974375, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 5.958002892412794e-08, "output_power": 4.9013045468931424e-08, "delta_db": -0.8478902109184219, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.518375636706213e-08, "output_power": 3.386484931297872e-08, "delta_db": -0.16593057233287026, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.4833292918155265, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.13159276812373974, "pitch": null, "output_rms_dbfs": -61.82223672854779, "output_peak": 0.01424913917589817, "reference_rms_dbfs": -61.95382949667153, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.965629876950996}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.024359572707954e-06, "log_rms_mae_db": 1.7970231990323762, "rms_envelope_nrmse": 0.20203205345195277, "envelope_correlation": 0.9650210066990967, "rms_gain_error_db": 0.1316123990508548, "reference_mean_power": 6.381840334285008e-07, "output_mean_power": 6.578201529691564e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.836855714370683e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.3707173350027986e-08, "output_power": 4.660366531203097e-08, "reference_active": true, "delta_db": -0.6161222104638643}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8108171988414046e-08, "output_power": 2.0771050381036253e-08, "reference_active": true, "delta_db": 0.59583848433005}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5077869163047108e-08, "output_power": 1.3512922062074586e-08, "reference_active": true, "delta_db": -0.4759069852847705}], "active_band_count": 3, "active_band_mae_db": 0.5626225600262282}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.11576902582373e-06, "log_rms_mae_db": 1.0083383783659434, "rms_envelope_nrmse": 0.11169244568299773, "envelope_correlation": 0.9883433382975486, "rms_gain_error_db": 0.13162409621786644, "reference_mean_power": 6.411560082425094e-07, "output_mean_power": 6.608853517157621e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.631066262241422e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.1382633554527724e-08, "output_power": 4.3101789640384754e-08, "reference_active": true, "delta_db": -0.763210567505207}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.770301277631505e-09, "output_power": 1.0668939483444859e-08, "reference_active": true, "delta_db": 0.38213295865147456}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.622703760150784e-10, "output_power": 7.884662888990284e-10, "reference_active": true, "delta_db": -0.8651398634503993}], "active_band_count": 3, "active_band_mae_db": 0.6701611298690269}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.2104964131871903e-06, "log_rms_mae_db": 2.3899944005261506, "rms_envelope_nrmse": 0.32550719277991713, "envelope_correlation": 0.92964474883058, "rms_gain_error_db": 0.8531743357937376, "reference_mean_power": 5.88463135957351e-08, "output_mean_power": 7.16203922797261e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.019969626272171e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.669218221395915e-09, "output_power": 6.58125680368543e-09, "reference_active": true, "delta_db": 0.6478566318475929}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.997554044063276e-09, "output_power": 4.802420908767332e-09, "reference_active": true, "delta_db": -0.17297278138640554}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.156278331683346e-09, "output_power": 3.3565650177852668e-09, "reference_active": true, "delta_db": -1.8644128814315892}], "active_band_count": 3, "active_band_mae_db": 0.8950807648885292}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.1954716835574657e-06, "log_rms_mae_db": 1.820134694839904, "rms_envelope_nrmse": 0.2406383929363215, "envelope_correlation": 0.960850861985086, "rms_gain_error_db": 0.8527113438489485, "reference_mean_power": 5.913056575013843e-08, "output_mean_power": 7.195867677610623e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.690703802813698e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.971603141472601e-09, "output_power": 6.9484351076819785e-09, "reference_active": true, "delta_db": -0.014456509878009728}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1694216774888265e-09, "output_power": 2.421026020208025e-09, "reference_active": true, "delta_db": -1.1698056689970702}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5180140726512066e-10, "output_power": 2.4055595764367587e-10, "reference_active": true, "delta_db": -2.7373146214943613}], "active_band_count": 3, "active_band_mae_db": 1.3071922667898137}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.597874045564372e-06, "log_rms_mae_db": 1.4591327512261723, "rms_envelope_nrmse": 0.18489945932562274, "envelope_correlation": 0.9793769110817071, "rms_gain_error_db": 0.2517764018173956, "reference_mean_power": 3.0019112356646434e-07, "output_mean_power": 3.1810865579907317e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1704248469151792e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.917571308133626e-08, "output_power": 4.263986739197172e-08, "reference_active": true, "delta_db": -0.6193482081811312}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.373644839895842e-09, "output_power": 6.360756186530823e-09, "reference_active": true, "delta_db": -0.008791105188655496}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.9583662339560916e-09, "output_power": 4.127811737930834e-09, "reference_active": true, "delta_db": 0.18203908377185024}], "active_band_count": 3, "active_band_mae_db": 0.270059465713879}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6957143825373563e-06, "log_rms_mae_db": 0.8912879165395741, "rms_envelope_nrmse": 0.09908270449144047, "envelope_correlation": 0.9942122579172193, "rms_gain_error_db": 0.2517714291372658, "reference_mean_power": 3.016958800523271e-07, "output_mean_power": 3.197028607482241e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.1236901446499244e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.541853281346178e-08, "output_power": 3.924853949927168e-08, "reference_active": true, "delta_db": -0.6340960020092017}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5898805602165613e-09, "output_power": 3.72439148574073e-09, "reference_active": true, "delta_db": 0.15975325843145544}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.01076242530766e-10, "output_power": 2.663613342862952e-10, "reference_active": true, "delta_db": -0.5320530560518137}], "active_band_count": 3, "active_band_mae_db": 0.4419674388308236}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.0353597876360997e-06, "log_rms_mae_db": 1.3108086877845302, "rms_envelope_nrmse": 0.24225837447838067, "envelope_correlation": 0.9635461780038664, "rms_gain_error_db": -0.4186872688762377, "reference_mean_power": 5.358047115055493e-08, "output_mean_power": 4.865615667997405e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.7539255872910824e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.2466604070258255e-09, "output_power": 5.581178406930749e-09, "reference_active": true, "delta_db": 0.26842950157390055}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.042126892400446e-09, "output_power": 3.0573281512826172e-09, "reference_active": true, "delta_db": 0.021647299543128964}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.488177427019359e-09, "output_power": 1.4009207101452147e-09, "reference_active": true, "delta_db": -2.4946779019148306}], "active_band_count": 3, "active_band_mae_db": 0.9282515676772868}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.4732086031870805e-06, "log_rms_mae_db": 0.7929704718053817, "rms_envelope_nrmse": 0.14415254716304993, "envelope_correlation": 0.9872872226748816, "rms_gain_error_db": -0.4187083970135536, "reference_mean_power": 5.3847422411461674e-08, "output_mean_power": 4.8898335891195984e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.6457241300858348e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.316794721929917e-09, "output_power": 6.194366683206871e-09, "reference_active": true, "delta_db": -0.0849985339254593}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0867827772247918e-09, "output_power": 1.7152241032739737e-09, "reference_active": true, "delta_db": -0.8515637271600005}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.2900642849732037e-10, "output_power": 1.0893955720464707e-10, "reference_active": true, "delta_db": -3.226620679923128}], "active_band_count": 3, "active_band_mae_db": 1.3877276470028626}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.463734074433335, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "ffacc0c8936660380e29344c0e2a1a6c25f1521b25487930f7b847188a41d1ab", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9767025985106212, "standard_deviation": 0.00412830501455446, "minimum": 0.9710730440019587, "maximum": 0.9850938120595822, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4279870378531159, "standard_deviation": 0.019585266681815157, "minimum": 1.407509525659505, "maximum": 1.4591327512261723, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5343367738817277, "standard_deviation": 0.1836227884188053, "minimum": 0.270059465713879, "maximum": 0.7863520990682057, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.19258049903054872, "standard_deviation": 0.018484139041054705, "minimum": 0.15280941617605867, "maximum": 0.21496823822642083, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.994270252575314, "standard_deviation": 0.0009049190094379102, "minimum": 0.993350714531649, "maximum": 0.9962580378478231, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8615369501648171, "standard_deviation": 0.03677364715388287, "minimum": 0.7969513928583332, "maximum": 0.8994334567795199, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5394913668226571, "standard_deviation": 0.17379274341009351, "minimum": 0.31876190387032943, "maximum": 0.7625384440800723, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09590832812043973, "standard_deviation": 0.00928334029758753, "minimum": 0.0759119899549565, "maximum": 0.10655068023102533, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9636526169017412, "standard_deviation": 0.004051724545586987, "minimum": 0.9575121004270208, "maximum": 0.969855077248989, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2918935330609176, "standard_deviation": 0.014665804692341038, "minimum": 1.2752809494301653, "maximum": 1.3108086877845302, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.8688946689165438, "standard_deviation": 0.08928831100679566, "minimum": 0.7166507942959477, "maximum": 0.9636764961010797, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.24312211539347853, "standard_deviation": 0.013391492889023372, "minimum": 0.22376536461869584, "maximum": 0.26168645300697835, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9885995616798642, "standard_deviation": 0.0017079338755890288, "minimum": 0.9864470419703879, "maximum": 0.991060262720958, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7714041851517812, "standard_deviation": 0.019160957630602302, "minimum": 0.743757257103388, "maximum": 0.7929704718053817, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.2948480553121993, "standard_deviation": 0.20488074768537434, "minimum": 0.8855054893576314, "maximum": 1.5215315932653937, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.136060023270002, "standard_deviation": 0.013327912668644033, "minimum": 0.11740356171207822, "maximum": 0.15281590944459383, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9308926064492998, "standard_deviation": 0.010339090205118577, "minimum": 0.9102058298475011, "maximum": 0.9420215675743436, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.384579733303787, "standard_deviation": 0.049995536924007586, "minimum": 2.3073666658823653, "maximum": 2.4371731475887213, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7598284364659473, "standard_deviation": 0.14397269064725132, "minimum": 0.6061027313414283, "maximum": 1.0193027503042138, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.3072737361048833, "standard_deviation": 0.01574712288256956, "minimum": 0.2897541988561794, "maximum": 0.3335981024591786, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9667477363855117, "standard_deviation": 0.0046413084783437485, "minimum": 0.960850861985086, "maximum": 0.9723371410167205, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.7776396247305668, "standard_deviation": 0.0853065628140235, "minimum": 1.6519831468693482, "maximum": 1.8743680475764475, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.0982681077193652, "standard_deviation": 0.45578082663337743, "minimum": 0.5929926864180216, "maximum": 2.030153464710002, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.20957853462244752, "standard_deviation": 0.014278054478646983, "minimum": 0.19218337462504664, "maximum": 0.2406383929363215, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.46837389453432227, "standard_deviation": 0.12951414851611995, "minimum": 0.3020957467779882, "maximum": 0.6914160210900953, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.962981132077855, "standard_deviation": 0.007652943714269333, "minimum": 5.951465727676973, "maximum": 5.977113707851582, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.014698365823363004, "standard_deviation": 0.001561072326739803, "minimum": 0.01348450375585317, "maximum": 0.018040455796409966, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": 0.022551655318361546, "standard_deviation": 0.10151752317746676, "minimum": -0.12683282439523674, "maximum": 0.13209400414303235, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9664787465384409, "standard_deviation": 0.0031073409228787713, "minimum": 0.9624997350676023, "maximum": 0.972721111828769, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.765079146437814, "standard_deviation": 0.04981395121753924, "minimum": 1.70971520396168, "maximum": 1.8529674014007511, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.48639602051552666, "standard_deviation": 0.08896269997938175, "minimum": 0.31732536176250986, "maximum": 0.6065641760711866, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.19574392927778572, "standard_deviation": 0.009173299391306422, "minimum": 0.17589030376840978, "maximum": 0.2063295046050789, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9908785208717392, "standard_deviation": 0.0016028236696979876, "minimum": 0.9883433382975486, "maximum": 0.9926558103853332, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.9036232002080182, "standard_deviation": 0.05564071883675609, "minimum": 0.8451025657909407, "maximum": 1.0083383783659434, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.568974427676475, "standard_deviation": 0.08754589499333724, "minimum": 0.4583257178337139, "maximum": 0.7231712505493771, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.09737929775469092, "standard_deviation": 0.008381275197466816, "minimum": 0.08691488900252022, "maximum": 0.11169244568299773, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 2.9782867431640625, "predicted_mos": 2.9782867431640625, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "d3e11d924c9eb64dd9f5ad9f34f9c2cdb93b8fcb9d85e066a784a048da3b3bfc", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 11.373334399890155}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8008610581470408, "全帯域_10ms_rms_envelope_nrmse": 0.2036818768178941, "全帯域_10ms_envelope_correlation": 0.9648122081859766, "全帯域_10ms_modulation_mae_db": 0.5326783141269077, "全帯域_40ms_log_rms_mae_db": 1.0152587209465034, "全帯域_40ms_rms_envelope_nrmse": 0.11300810182492177, "全帯域_40ms_envelope_correlation": 0.9883084629419743, "全帯域_40ms_modulation_mae_db": 0.6651749839134384, "300–1000 Hz_10ms_log_rms_mae_db": 2.2458607568111972, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.328882049588916, "300–1000 Hz_10ms_envelope_correlation": 0.929398096698844, "300–1000 Hz_10ms_modulation_mae_db": 0.8333008146325213, "300–1000 Hz_40ms_log_rms_mae_db": 1.6197007856887222, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.24491950877677662, "300–1000 Hz_40ms_envelope_correlation": 0.9601931439839321, "300–1000 Hz_40ms_modulation_mae_db": 1.184465868065255, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4223230190245773, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18755014795600453, "1000–3000 Hz_10ms_envelope_correlation": 0.9793411931565176, "1000–3000 Hz_10ms_modulation_mae_db": 0.22077020200497102, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7855894857444147, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10098632965437489, "1000–3000 Hz_40ms_envelope_correlation": 0.99442286396269, "1000–3000 Hz_40ms_modulation_mae_db": 0.4622509035744147, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2751316690191599, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24095371466437432, "3000–6000 Hz_10ms_envelope_correlation": 0.9639637527072044, "3000–6000 Hz_10ms_modulation_mae_db": 1.0387289023029675, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7043848345141647, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13431774035363503, "3000–6000 Hz_40ms_envelope_correlation": 0.9893209093164379, "3000–6000 Hz_40ms_modulation_mae_db": 1.488478732672293, "mr_stft_db": 5.963233022489682, "band_mae_db": 0.48357947963019987, "rms_gain_error_db": 0.1701238837101044, "output_peak": 0.014532251879260116}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8536576565427274, "全帯域_10ms_rms_envelope_nrmse": 0.206581445462707, "全帯域_10ms_envelope_correlation": 0.9624397192201022, "全帯域_10ms_modulation_mae_db": 0.6038831999255475, "全帯域_40ms_log_rms_mae_db": 0.9195846200237829, "全帯域_40ms_rms_envelope_nrmse": 0.09717845522458057, "全帯域_40ms_envelope_correlation": 0.9908537381290863, "全帯域_40ms_modulation_mae_db": 0.5164782541762946, "300–1000 Hz_10ms_log_rms_mae_db": 2.2224410670654433, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3121509113365994, "300–1000 Hz_10ms_envelope_correlation": 0.9344944264604688, "300–1000 Hz_10ms_modulation_mae_db": 0.8322664454641551, "300–1000 Hz_40ms_log_rms_mae_db": 1.534886923368087, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.22473108835778627, "300–1000 Hz_40ms_envelope_correlation": 0.965121978212358, "300–1000 Hz_40ms_modulation_mae_db": 0.6484336519393248, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3665166813670468, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21554578520551948, "1000–3000 Hz_10ms_envelope_correlation": 0.9709348578756213, "1000–3000 Hz_10ms_modulation_mae_db": 0.7402565167224453, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7737518448328206, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09957047739286935, "1000–3000 Hz_40ms_envelope_correlation": 0.9936252786600039, "1000–3000 Hz_40ms_modulation_mae_db": 0.7636607009425256, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3158349522234363, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.23530775891338643, "3000–6000 Hz_10ms_envelope_correlation": 0.9673993742962887, "3000–6000 Hz_10ms_modulation_mae_db": 1.0187087352869784, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6990816420179004, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11763601052672586, "3000–6000 Hz_40ms_envelope_correlation": 0.9918140398775726, "3000–6000 Hz_40ms_modulation_mae_db": 0.9690038584410039, "mr_stft_db": 5.962352446017434, "band_mae_db": 0.7309456758571946, "rms_gain_error_db": -0.05864136102741882, "output_peak": 0.01322311197207108}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7767068700139277, "全帯域_10ms_rms_envelope_nrmse": 0.20650593632833444, "全帯域_10ms_envelope_correlation": 0.9620431770399187, "全帯域_10ms_modulation_mae_db": 0.26186317356874717, "全帯域_40ms_log_rms_mae_db": 0.9774128217332396, "全帯域_40ms_rms_envelope_nrmse": 0.1114479776567959, "全帯域_40ms_envelope_correlation": 0.9878653881362941, "全帯域_40ms_modulation_mae_db": 0.5252353054111667, "300–1000 Hz_10ms_log_rms_mae_db": 2.2050693721523653, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3029220877910174, "300–1000 Hz_10ms_envelope_correlation": 0.9273762451397829, "300–1000 Hz_10ms_modulation_mae_db": 1.0402779150341572, "300–1000 Hz_40ms_log_rms_mae_db": 1.43490433121009, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19344882346659395, "300–1000 Hz_40ms_envelope_correlation": 0.9679729756633926, "300–1000 Hz_40ms_modulation_mae_db": 2.000667091720835, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3813042116346768, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20688863033537136, "1000–3000 Hz_10ms_envelope_correlation": 0.973324903617125, "1000–3000 Hz_10ms_modulation_mae_db": 0.4116328874067974, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7602375462352475, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09049289696885557, "1000–3000 Hz_40ms_envelope_correlation": 0.9948134370594482, "1000–3000 Hz_40ms_modulation_mae_db": 0.4894169653959683, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2489917290816273, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.25484095976066956, "3000–6000 Hz_10ms_envelope_correlation": 0.9590487337655048, "3000–6000 Hz_10ms_modulation_mae_db": 0.92640441066788, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7075323949774511, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12726372535551878, "3000–6000 Hz_40ms_envelope_correlation": 0.9895161070012937, "3000–6000 Hz_40ms_modulation_mae_db": 1.5692362332789218, "mr_stft_db": 5.97693397607605, "band_mae_db": 0.44926434232323553, "rms_gain_error_db": -0.11067733957372657, "output_peak": 0.016529951555906933}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7306153499772048, "全帯域_10ms_rms_envelope_nrmse": 0.19181107514793, "全帯域_10ms_envelope_correlation": 0.9672265988346679, "全帯域_10ms_modulation_mae_db": 0.4317928820322046, "全帯域_40ms_log_rms_mae_db": 0.9065556164611009, "全帯域_40ms_rms_envelope_nrmse": 0.09460978991368653, "全帯域_40ms_envelope_correlation": 0.9915011056503044, "全帯域_40ms_modulation_mae_db": 0.5632779867968452, "300–1000 Hz_10ms_log_rms_mae_db": 2.325172300004274, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.30678049050252587, "300–1000 Hz_10ms_envelope_correlation": 0.9350077705412554, "300–1000 Hz_10ms_modulation_mae_db": 0.7313523630016571, "300–1000 Hz_40ms_log_rms_mae_db": 1.69666861867122, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20422227994474842, "300–1000 Hz_40ms_envelope_correlation": 0.9711558791341002, "300–1000 Hz_40ms_modulation_mae_db": 1.0316110593728247, "1000–3000 Hz_10ms_log_rms_mae_db": 1.406516456388437, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1950300435050054, "1000–3000 Hz_10ms_envelope_correlation": 0.9755135441956154, "1000–3000 Hz_10ms_modulation_mae_db": 0.6120811001254469, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7529248313149187, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09137936564726842, "1000–3000 Hz_40ms_envelope_correlation": 0.994587302645534, "1000–3000 Hz_40ms_modulation_mae_db": 0.2845724531307247, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2562682732275094, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2443233962784597, "3000–6000 Hz_10ms_envelope_correlation": 0.9624509731846805, "3000–6000 Hz_10ms_modulation_mae_db": 1.074010750257113, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7031422375781762, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12377267353416324, "3000–6000 Hz_40ms_envelope_correlation": 0.989994189999115, "3000–6000 Hz_40ms_modulation_mae_db": 1.485183359227026, "mr_stft_db": 5.951315546682101, "band_mae_db": 0.4842227508365326, "rms_gain_error_db": -0.18295118847549086, "output_peak": 0.013758875644251621}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7023318900172477, "全帯域_10ms_rms_envelope_nrmse": 0.17314333271809076, "全帯域_10ms_envelope_correlation": 0.9734533193842798, "全帯域_10ms_modulation_mae_db": 0.5117573819157392, "全帯域_40ms_log_rms_mae_db": 0.8165097989280273, "全帯域_40ms_rms_envelope_nrmse": 0.08588994728291974, "全帯域_40ms_envelope_correlation": 0.9928498298065965, "全帯域_40ms_modulation_mae_db": 0.8169628270921351, "300–1000 Hz_10ms_log_rms_mae_db": 2.318221444780104, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2902357372758857, "300–1000 Hz_10ms_envelope_correlation": 0.9355314969961761, "300–1000 Hz_10ms_modulation_mae_db": 0.8196314251414877, "300–1000 Hz_40ms_log_rms_mae_db": 1.615399007094264, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.176806582939946, "300–1000 Hz_40ms_envelope_correlation": 0.9751850542958791, "300–1000 Hz_40ms_modulation_mae_db": 0.9408492343661331, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4019172464202425, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15679524285597518, "1000–3000 Hz_10ms_envelope_correlation": 0.984301217782692, "1000–3000 Hz_10ms_modulation_mae_db": 0.35360416155619134, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7948629174507384, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07521930092484509, "1000–3000 Hz_40ms_envelope_correlation": 0.9962610244638627, "1000–3000 Hz_40ms_modulation_mae_db": 0.7393075440654924, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2723009376732364, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2727782019669229, "3000–6000 Hz_10ms_envelope_correlation": 0.9535970967581647, "3000–6000 Hz_10ms_modulation_mae_db": 0.8890076638262568, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7067179170754734, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.15649077370871872, "3000–6000 Hz_40ms_envelope_correlation": 0.9858746392625694, "3000–6000 Hz_40ms_modulation_mae_db": 1.4978999370542374, "mr_stft_db": 5.962591379711326, "band_mae_db": 0.3516455903960062, "rms_gain_error_db": -0.03872193734746367, "output_peak": 0.014574589261358998}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8009557760026729, "全帯域_10ms_rms_envelope_nrmse": 0.19264988740537375, "全帯域_10ms_envelope_correlation": 0.9680012187126241, "全帯域_10ms_modulation_mae_db": 0.49960360256478853, "全帯域_40ms_log_rms_mae_db": 0.8587091330261687, "全帯域_40ms_rms_envelope_nrmse": 0.09069870963200563, "全帯域_40ms_envelope_correlation": 0.9922892048716764, "全帯域_40ms_modulation_mae_db": 0.49303671960789136, "300–1000 Hz_10ms_log_rms_mae_db": 2.282216179970105, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3464152059927193, "300–1000 Hz_10ms_envelope_correlation": 0.903113478005704, "300–1000 Hz_10ms_modulation_mae_db": 0.7837070472518125, "300–1000 Hz_40ms_log_rms_mae_db": 1.6237838166659397, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2091196654496072, "300–1000 Hz_40ms_envelope_correlation": 0.961826683786632, "300–1000 Hz_40ms_modulation_mae_db": 1.148712658736934, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3944219789189853, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2113961354931062, "1000–3000 Hz_10ms_envelope_correlation": 0.974135747997109, "1000–3000 Hz_10ms_modulation_mae_db": 0.5559591925671906, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8018781767016024, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11250467622100885, "1000–3000 Hz_40ms_envelope_correlation": 0.9933474736644706, "1000–3000 Hz_40ms_modulation_mae_db": 0.6898421542575885, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2584475118896112, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.27230725376101755, "3000–6000 Hz_10ms_envelope_correlation": 0.9531947232546577, "3000–6000 Hz_10ms_modulation_mae_db": 0.9772179803508868, "3000–6000 Hz_40ms_log_rms_mae_db": 0.689311772085537, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.15239206078862344, "3000–6000 Hz_40ms_envelope_correlation": 0.9855367018598347, "3000–6000 Hz_40ms_modulation_mae_db": 1.5504004422739726, "mr_stft_db": 5.95862346516549, "band_mae_db": 0.46206477596495293, "rms_gain_error_db": 0.11597530309460298, "output_peak": 0.015124758684052794}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8024824380147089, "全帯域_10ms_rms_envelope_nrmse": 0.20256355505526238, "全帯域_10ms_envelope_correlation": 0.9647829183228321, "全帯域_10ms_modulation_mae_db": 0.6440800111876946, "全帯域_40ms_log_rms_mae_db": 0.9185274463798607, "全帯域_40ms_rms_envelope_nrmse": 0.094968342777497, "全帯域_40ms_envelope_correlation": 0.9915928577141533, "全帯域_40ms_modulation_mae_db": 0.4435627513456431, "300–1000 Hz_10ms_log_rms_mae_db": 2.312498395917902, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.31512319602860084, "300–1000 Hz_10ms_envelope_correlation": 0.9242361669291187, "300–1000 Hz_10ms_modulation_mae_db": 0.9130343934894448, "300–1000 Hz_40ms_log_rms_mae_db": 1.5684529571939296, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.200392385953416, "300–1000 Hz_40ms_envelope_correlation": 0.9671777028952973, "300–1000 Hz_40ms_modulation_mae_db": 0.9342128065328731, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3817077983906763, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1919063564982712, "1000–3000 Hz_10ms_envelope_correlation": 0.9764619797653418, "1000–3000 Hz_10ms_modulation_mae_db": 0.7280181363688302, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7765226793765118, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0973054896591793, "1000–3000 Hz_40ms_envelope_correlation": 0.9937527689517694, "1000–3000 Hz_40ms_modulation_mae_db": 0.2724438973687276, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2512141932151775, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.23789755332514, "3000–6000 Hz_10ms_envelope_correlation": 0.9648141407036888, "3000–6000 Hz_10ms_modulation_mae_db": 0.8421390082140738, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6764346916837181, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1273661492162417, "3000–6000 Hz_40ms_envelope_correlation": 0.9891757735017067, "3000–6000 Hz_40ms_modulation_mae_db": 1.2830346151792844, "mr_stft_db": 5.973394496667855, "band_mae_db": 0.3647740354331402, "rms_gain_error_db": 0.12213525366390598, "output_peak": 0.014076165215926084}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7427435938131761, "全帯域_10ms_rms_envelope_nrmse": 0.19202040491406688, "全帯域_10ms_envelope_correlation": 0.9674359419807003, "全帯域_10ms_modulation_mae_db": 0.5016751470270591, "全帯域_40ms_log_rms_mae_db": 0.8932916671572279, "全帯域_40ms_rms_envelope_nrmse": 0.0949475619422502, "全帯域_40ms_envelope_correlation": 0.991175170161667, "全帯域_40ms_modulation_mae_db": 0.6015291584438831, "300–1000 Hz_10ms_log_rms_mae_db": 2.3332534653553223, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2795982840438963, "300–1000 Hz_10ms_envelope_correlation": 0.9444581191022241, "300–1000 Hz_10ms_modulation_mae_db": 0.6860085813038661, "300–1000 Hz_40ms_log_rms_mae_db": 1.6819493077529846, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.18058593368954923, "300–1000 Hz_40ms_envelope_correlation": 0.9767437292772936, "300–1000 Hz_40ms_modulation_mae_db": 0.6794206443512669, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3982951333050662, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19692897667231934, "1000–3000 Hz_10ms_envelope_correlation": 0.9750909218820305, "1000–3000 Hz_10ms_modulation_mae_db": 0.5562595990527833, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7883621313689376, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0983607479278895, "1000–3000 Hz_40ms_envelope_correlation": 0.9936634939117851, "1000–3000 Hz_40ms_modulation_mae_db": 0.7119924698435499, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2625912772428907, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2568261371920995, "3000–6000 Hz_10ms_envelope_correlation": 0.9619517817711338, "3000–6000 Hz_10ms_modulation_mae_db": 1.113906877771187, "3000–6000 Hz_40ms_log_rms_mae_db": 0.693805014519771, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13725012470463777, "3000–6000 Hz_40ms_envelope_correlation": 0.9893250999578013, "3000–6000 Hz_40ms_modulation_mae_db": 1.4795331351301835, "mr_stft_db": 5.961715682759043, "band_mae_db": 0.6585020584131581, "rms_gain_error_db": -0.017998541079533283, "output_peak": 0.013182131888985685}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.171810829591114, "spectral_convergence": 0.6859932243843668, "spectral_convergence_status": "ok", "amplitude_floor": 3.772168230462137e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.821031929110686, "spectral_convergence": 0.6333352666789118, "spectral_convergence_status": "ok", "amplitude_floor": 1.9872090073495523e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.896856308767248, "spectral_convergence": 0.6719953991010652, "spectral_convergence_status": "ok", "amplitude_floor": 8.414272539865191e-09}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0228756868362371e-07, "output_power": 1.009756448641003e-07, "delta_db": -0.05606220402376679, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 3.789702976182104e-08, "output_power": 5.074232472129148e-08, "delta_db": 1.267651874134378, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.1288069701978556e-08, "output_power": 5.5193763528338434e-08, "delta_db": 0.318736544632511, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.8766557699122943e-07, "output_power": 2.991030568470479e-07, "delta_db": 0.1693295566981644, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 6.379889954922647e-08, "output_power": 7.348958165304593e-08, "delta_db": 0.6141258736876928, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 5.958002892412794e-08, "output_power": 5.016878285215206e-08, "delta_db": -0.7466714500353799, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.518375636706213e-08, "output_power": 3.350381942521354e-08, "delta_db": -0.21247885419950638, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.48357947963019987, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.1701238837101044, "pitch": null, "output_rms_dbfs": -61.78370561296143, "output_peak": 0.014532251879260116, "reference_rms_dbfs": -61.95382949667153, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.963233022489682}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.024359572707954e-06, "log_rms_mae_db": 1.8008610581470408, "rms_envelope_nrmse": 0.2036818768178941, "envelope_correlation": 0.9648122081859766, "rms_gain_error_db": 0.17014692169543205, "reference_mean_power": 6.381840334285008e-07, "output_mean_power": 6.636828978655524e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.836855714370683e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.3707173350027986e-08, "output_power": 4.6884008352283306e-08, "reference_active": true, "delta_db": -0.5900756108228082}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8108171988414046e-08, "output_power": 2.0056355367923397e-08, "reference_active": true, "delta_db": 0.4437740535216084}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5077869163047108e-08, "output_power": 1.3241020033165928e-08, "reference_active": true, "delta_db": -0.5641852780363066}], "active_band_count": 3, "active_band_mae_db": 0.5326783141269077}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.11576902582373e-06, "log_rms_mae_db": 1.0152587209465034, "rms_envelope_nrmse": 0.11300810182492177, "envelope_correlation": 0.9883084629419743, "rms_gain_error_db": 0.17023423731118614, "reference_mean_power": 6.411560082425094e-07, "output_mean_power": 6.667870246916144e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.631066262241422e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.1382633554527724e-08, "output_power": 4.3330953673512856e-08, "reference_active": true, "delta_db": -0.7401811218500922}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.770301277631505e-09, "output_power": 1.0312529521627661e-08, "reference_active": true, "delta_db": 0.23457248954927487}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.622703760150784e-10, "output_power": 7.607115004711221e-10, "reference_active": true, "delta_db": -1.0207713403409482}], "active_band_count": 3, "active_band_mae_db": 0.6651749839134384}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.2104964131871903e-06, "log_rms_mae_db": 2.2458607568111972, "rms_envelope_nrmse": 0.328882049588916, "envelope_correlation": 0.929398096698844, "rms_gain_error_db": 0.9038691165475481, "reference_mean_power": 5.88463135957351e-08, "output_mean_power": 7.246130870978834e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.019969626272171e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.669218221395915e-09, "output_power": 6.768215240850148e-09, "reference_active": true, "delta_db": 0.7695098724230286}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.997554044063276e-09, "output_power": 5.0394754669495775e-09, "reference_active": true, "delta_db": 0.03627836000921921}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.156278331683346e-09, "output_power": 3.4907997084948135e-09, "reference_active": true, "delta_db": -1.6941142114653158}], "active_band_count": 3, "active_band_mae_db": 0.8333008146325213}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.1954716835574657e-06, "log_rms_mae_db": 1.6197007856887222, "rms_envelope_nrmse": 0.24491950877677662, "envelope_correlation": 0.9601931439839321, "rms_gain_error_db": 0.9035217018907604, "reference_mean_power": 5.913056575013843e-08, "output_mean_power": 7.280550262741192e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.690703802813698e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.971603141472601e-09, "output_power": 7.210560377494578e-09, "reference_active": true, "delta_db": 0.14636360829356848}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1694216774888265e-09, "output_power": 2.5887591502209455e-09, "reference_active": true, "delta_db": -0.8788837702758346}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5180140726512066e-10, "output_power": 2.524251114955476e-10, "reference_active": true, "delta_db": -2.5281502256263617}], "active_band_count": 3, "active_band_mae_db": 1.184465868065255}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.597874045564372e-06, "log_rms_mae_db": 1.4223230190245773, "rms_envelope_nrmse": 0.18755014795600453, "envelope_correlation": 0.9793411931565176, "rms_gain_error_db": 0.32360125111279564, "reference_mean_power": 3.0019112356646434e-07, "output_mean_power": 3.234133712197701e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1704248469151792e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.917571308133626e-08, "output_power": 4.345267264131493e-08, "reference_active": true, "delta_db": -0.5373417246813855}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.373644839895842e-09, "output_power": 6.353742444405431e-09, "reference_active": true, "delta_db": -0.013582532518880037}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.9583662339560916e-09, "output_power": 4.0612021570816205e-09, "reference_active": true, "delta_db": 0.11138634881464746}], "active_band_count": 3, "active_band_mae_db": 0.22077020200497102}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6957143825373563e-06, "log_rms_mae_db": 0.7855894857444147, "rms_envelope_nrmse": 0.10098632965437489, "envelope_correlation": 0.99442286396269, "rms_gain_error_db": 0.3236022103192858, "reference_mean_power": 3.016958800523271e-07, "output_mean_power": 3.25034604761151e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.1236901446499244e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.541853281346178e-08, "output_power": 4.00354085605156e-08, "reference_active": true, "delta_db": -0.5478883596080467}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5898805602165613e-09, "output_power": 3.741172893915771e-09, "reference_active": true, "delta_db": 0.17927779769850657}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.01076242530766e-10, "output_power": 2.5865318584418667e-10, "reference_active": true, "delta_db": -0.6595865534166907}], "active_band_count": 3, "active_band_mae_db": 0.4622509035744147}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.0353597876360997e-06, "log_rms_mae_db": 1.2751316690191599, "rms_envelope_nrmse": 0.24095371466437432, "envelope_correlation": 0.9639637527072044, "rms_gain_error_db": -0.4441249100444203, "reference_mean_power": 5.358047115055493e-08, "output_mean_power": 4.837199921775828e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.7539255872910824e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.2466604070258255e-09, "output_power": 5.56936128148612e-09, "reference_active": true, "delta_db": 0.2592243609487434}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.042126892400446e-09, "output_power": 3.1662896246640465e-09, "reference_active": true, "delta_db": 0.1737331255656593}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.488177427019359e-09, "output_power": 1.3414003760814062e-09, "reference_active": true, "delta_db": -2.6832292203945}], "active_band_count": 3, "active_band_mae_db": 1.0387289023029675}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.4732086031870805e-06, "log_rms_mae_db": 0.7043848345141647, "rms_envelope_nrmse": 0.13431774035363503, "envelope_correlation": 0.9893209093164379, "rms_gain_error_db": -0.4441338235868167, "reference_mean_power": 5.3847422411461674e-08, "output_mean_power": 4.861290079926747e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.6457241300858348e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.316794721929917e-09, "output_power": 6.182104416139411e-09, "reference_active": true, "delta_db": -0.09360427723114224}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0867827772247918e-09, "output_power": 1.7382127537403986e-09, "reference_active": true, "delta_db": -0.793743115808641}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.2900642849732037e-10, "output_power": 1.0047055312421697e-10, "reference_active": true, "delta_db": -3.578088804977096}], "active_band_count": 3, "active_band_mae_db": 1.488478732672293}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.4669249586199842, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "5fc824b3f1f1cc723c664e3a4fdb10eba146ca52401a3a646b06f0db6281537c", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9761380457840065, "standard_deviation": 0.004096776847768271, "minimum": 0.9709348578756213, "maximum": 0.984301217782692, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.3941253156812135, "standard_deviation": 0.017352037953292453, "minimum": 1.3665166813670468, "maximum": 1.4223230190245773, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5223227244755819, "standard_deviation": 0.18197234759724487, "minimum": 0.22077020200497102, "maximum": 0.7402565167224453, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1952551648151966, "standard_deviation": 0.01836214061225321, "minimum": 0.15679524285597518, "maximum": 0.21554578520551948, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9943092054149455, "standard_deviation": 0.0009466747921791533, "minimum": 0.9933474736644706, "maximum": 0.9962610244638627, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.779266201628149, "standard_deviation": 0.016780819758153372, "minimum": 0.7529248313149187, "maximum": 0.8018781767016024, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5516858860723739, "standard_deviation": 0.2021747026764677, "minimum": 0.2724438973687276, "maximum": 0.7636607009425256, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09572741054953637, "standard_deviation": 0.010691886262997203, "minimum": 0.07521930092484509, "maximum": 0.11250467622100885, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9608025720551654, "standard_deviation": 0.005161888380560339, "minimum": 0.9531947232546577, "maximum": 0.9673993742962887, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.267597567946581, "standard_deviation": 0.02157200966323788, "minimum": 1.2489917290816273, "maximum": 1.3158349522234363, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.9850155410846679, "standard_deviation": 0.09386979062230358, "minimum": 0.8421390082140738, "maximum": 1.113906877771187, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2519043719827587, "standard_deviation": 0.01480283904350003, "minimum": 0.23530775891338643, "maximum": 0.2727782019669229, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9888196825970413, "standard_deviation": 0.0021015425810513005, "minimum": 0.9855367018598347, "maximum": 0.9918140398775726, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.697551313056524, "standard_deviation": 0.010635402276916258, "minimum": 0.6764346916837181, "maximum": 0.7075323949774511, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.4153462891571151, "standard_deviation": 0.1999322422121517, "minimum": 0.9690038584410039, "maximum": 1.5692362332789218, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.13456115727353307, "standard_deviation": 0.013700946902309911, "minimum": 0.11763601052672586, "maximum": 0.15649077370871872, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9292019749841967, "standard_deviation": 0.012207554829212772, "minimum": 0.903113478005704, "maximum": 0.9444581191022241, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.280591622757089, "standard_deviation": 0.04998388572875678, "minimum": 2.2050693721523653, "maximum": 2.3332534653553223, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8299473731648878, "standard_deviation": 0.10944206021655407, "minimum": 0.6860085813038661, "maximum": 1.0402779150341572, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.31026349532002007, "standard_deviation": 0.021004318058683212, "minimum": 0.2795982840438963, "maximum": 0.3464152059927193, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9681721434061106, "standard_deviation": 0.005925936446544639, "minimum": 0.9601931439839321, "maximum": 0.9767437292772936, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.5969682184556546, "standard_deviation": 0.0842355592585835, "minimum": 1.43490433121009, "maximum": 1.69666861867122, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.0710466268856809, "standard_deviation": 0.422964504015399, "minimum": 0.6484336519393248, "maximum": 2.000667091720835, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.20427828357230296, "standard_deviation": 0.02249402368150356, "minimum": 0.176806582939946, "maximum": 0.24491950877677662, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.49812483860680257, "standard_deviation": 0.13269595401367296, "minimum": 0.3516455903960062, "maximum": 0.7309456758571946, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.963770001946123, "standard_deviation": 0.008066054087013079, "minimum": 5.951315546682101, "maximum": 5.97693397607605, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.014375229512726663, "standard_deviation": 0.0011012466771196773, "minimum": 0.013182131888985685, "maximum": 0.016529951555906933, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -9.449087937747624e-05, "standard_deviation": 0.1243796673160872, "minimum": -0.18295118847549086, "maximum": 0.1701238837101044, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9662743877101376, "standard_deviation": 0.003659531502034542, "minimum": 0.9620431770399187, "maximum": 0.9734533193842798, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.7762943290660882, "standard_deviation": 0.04864660636821175, "minimum": 1.7023318900172477, "maximum": 1.8536576565427274, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.498416714043586, "standard_deviation": 0.11594404132515145, "minimum": 0.26186317356874717, "maximum": 0.6440800111876946, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.19611968923120743, "standard_deviation": 0.011284333834533158, "minimum": 0.17314333271809076, "maximum": 0.206581445462707, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9908044696764691, "standard_deviation": 0.0017929580581660196, "minimum": 0.9878653881362941, "maximum": 0.9928498298065965, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.913231228081989, "standard_deviation": 0.0625267318472707, "minimum": 0.8165097989280273, "maximum": 1.0152587209465034, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5781572483484122, "standard_deviation": 0.11791888419626884, "minimum": 0.4435627513456431, "maximum": 0.8169628270921351, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.09784361078183217, "standard_deviation": 0.009535906312842558, "minimum": 0.08588994728291974, "maximum": 0.11300810182492177, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 2.1412057876586914, "predicted_mos": 2.1412057876586914, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "5b45b4eb97943e1d10297e0dd8e6085748a58a38e1f9356dc4dd397db5f9876a", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 10.06828900007531}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6943754131621447, "全帯域_10ms_rms_envelope_nrmse": 0.21018865371763173, "全帯域_10ms_envelope_correlation": 0.9630173665067846, "全帯域_10ms_modulation_mae_db": 0.30781308435203075, "全帯域_40ms_log_rms_mae_db": 0.8983733625611698, "全帯域_40ms_rms_envelope_nrmse": 0.12396982398511747, "全帯域_40ms_envelope_correlation": 0.9863178720548639, "全帯域_40ms_modulation_mae_db": 0.39282927646335225, "300–1000 Hz_10ms_log_rms_mae_db": 2.6182362803623613, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.31424952858655286, "300–1000 Hz_10ms_envelope_correlation": 0.9343869208469495, "300–1000 Hz_10ms_modulation_mae_db": 0.30482056518022344, "300–1000 Hz_40ms_log_rms_mae_db": 2.0713347559995587, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.22211834322958704, "300–1000 Hz_40ms_envelope_correlation": 0.9678190594279618, "300–1000 Hz_40ms_modulation_mae_db": 0.436640948580381, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7474732314966361, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.23190313441338173, "1000–3000 Hz_10ms_envelope_correlation": 0.9678147409107949, "1000–3000 Hz_10ms_modulation_mae_db": 0.200996873368241, "1000–3000 Hz_40ms_log_rms_mae_db": 1.188161057533721, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12713183678823398, "1000–3000 Hz_40ms_envelope_correlation": 0.9905397656701104, "1000–3000 Hz_40ms_modulation_mae_db": 0.8540215377092912, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7013320363859556, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2561136936618055, "3000–6000 Hz_10ms_envelope_correlation": 0.9601066227472327, "3000–6000 Hz_10ms_modulation_mae_db": 1.2448959967989977, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0832742943055655, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13171872411624475, "3000–6000 Hz_40ms_envelope_correlation": 0.9888093477836081, "3000–6000 Hz_40ms_modulation_mae_db": 1.9339331990092425, "mr_stft_db": 6.127791699349835, "band_mae_db": 0.48244087286702736, "rms_gain_error_db": 0.20327038119162233, "output_peak": 0.017710029564695997}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6742651468081446, "全帯域_10ms_rms_envelope_nrmse": 0.21086136893427318, "全帯域_10ms_envelope_correlation": 0.9602357478851568, "全帯域_10ms_modulation_mae_db": 0.9378984769293983, "全帯域_40ms_log_rms_mae_db": 0.9472450394699974, "全帯域_40ms_rms_envelope_nrmse": 0.1191848608879857, "全帯域_40ms_envelope_correlation": 0.9864628961282111, "全帯域_40ms_modulation_mae_db": 0.8887182285343118, "300–1000 Hz_10ms_log_rms_mae_db": 2.498189428715057, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3185505541710069, "300–1000 Hz_10ms_envelope_correlation": 0.9225337375517934, "300–1000 Hz_10ms_modulation_mae_db": 0.9104796506279841, "300–1000 Hz_40ms_log_rms_mae_db": 1.905781432252501, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19863301481565013, "300–1000 Hz_40ms_envelope_correlation": 0.9689247405997621, "300–1000 Hz_40ms_modulation_mae_db": 1.876651882061932, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7596070934338846, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.24224933679924784, "1000–3000 Hz_10ms_envelope_correlation": 0.9624744531744739, "1000–3000 Hz_10ms_modulation_mae_db": 1.0824531741825278, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1080065045660872, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.14236260418976365, "1000–3000 Hz_40ms_envelope_correlation": 0.9864767859943759, "1000–3000 Hz_40ms_modulation_mae_db": 1.338458489514241, "3000–6000 Hz_10ms_log_rms_mae_db": 1.693581599459674, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2480209112093264, "3000–6000 Hz_10ms_envelope_correlation": 0.9620876284712065, "3000–6000 Hz_10ms_modulation_mae_db": 1.087502380117337, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1019593559570815, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14228106897941653, "3000–6000 Hz_40ms_envelope_correlation": 0.9879852529211385, "3000–6000 Hz_40ms_modulation_mae_db": 1.5511834591911509, "mr_stft_db": 6.131918419962129, "band_mae_db": 0.46063590816156885, "rms_gain_error_db": -0.23766526305515276, "output_peak": 0.015038656837492713}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6736507821296829, "全帯域_10ms_rms_envelope_nrmse": 0.17213058910151552, "全帯域_10ms_envelope_correlation": 0.9737735971722434, "全帯域_10ms_modulation_mae_db": 0.5298139889287733, "全帯域_40ms_log_rms_mae_db": 0.845138272716618, "全帯域_40ms_rms_envelope_nrmse": 0.08501329923869931, "全帯域_40ms_envelope_correlation": 0.9929299700047083, "全帯域_40ms_modulation_mae_db": 0.5837147307774063, "300–1000 Hz_10ms_log_rms_mae_db": 2.4849995907056446, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.34010533825399486, "300–1000 Hz_10ms_envelope_correlation": 0.9114452308811812, "300–1000 Hz_10ms_modulation_mae_db": 0.7857639664949186, "300–1000 Hz_40ms_log_rms_mae_db": 1.8035887884644883, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.21342549060483718, "300–1000 Hz_40ms_envelope_correlation": 0.9625212505125055, "300–1000 Hz_40ms_modulation_mae_db": 0.9901278416014555, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6928680936166567, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20074761398779817, "1000–3000 Hz_10ms_envelope_correlation": 0.9741750032785048, "1000–3000 Hz_10ms_modulation_mae_db": 0.7166053015506432, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0542470908074095, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08612169690016368, "1000–3000 Hz_40ms_envelope_correlation": 0.9954420281209944, "1000–3000 Hz_40ms_modulation_mae_db": 1.091996651797328, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6839841062915035, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.25342744131721534, "3000–6000 Hz_10ms_envelope_correlation": 0.9596913287131286, "3000–6000 Hz_10ms_modulation_mae_db": 1.2414508468215353, "3000–6000 Hz_40ms_log_rms_mae_db": 1.106794165010167, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.17133584402600957, "3000–6000 Hz_40ms_envelope_correlation": 0.9804513613495153, "3000–6000 Hz_40ms_modulation_mae_db": 1.9607231407205508, "mr_stft_db": 6.127735531621983, "band_mae_db": 0.3145468354068149, "rms_gain_error_db": -0.03857446523887061, "output_peak": 0.013670498368876597}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.760976813407013, "全帯域_10ms_rms_envelope_nrmse": 0.1979456936100137, "全帯域_10ms_envelope_correlation": 0.9653109128236378, "全帯域_10ms_modulation_mae_db": 0.4694875545013666, "全帯域_40ms_log_rms_mae_db": 0.9094803765049662, "全帯域_40ms_rms_envelope_nrmse": 0.09979257382486018, "全帯域_40ms_envelope_correlation": 0.9914700389846407, "全帯域_40ms_modulation_mae_db": 0.8628150540039524, "300–1000 Hz_10ms_log_rms_mae_db": 2.6062646694714338, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.34080984786641405, "300–1000 Hz_10ms_envelope_correlation": 0.9100241780258282, "300–1000 Hz_10ms_modulation_mae_db": 1.0410518589549853, "300–1000 Hz_40ms_log_rms_mae_db": 1.993528342058045, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.22097706654473215, "300–1000 Hz_40ms_envelope_correlation": 0.9602571484384731, "300–1000 Hz_40ms_modulation_mae_db": 1.9332230792735938, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7078041386925202, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2128102083830173, "1000–3000 Hz_10ms_envelope_correlation": 0.971323082314111, "1000–3000 Hz_10ms_modulation_mae_db": 0.5457027728884344, "1000–3000 Hz_40ms_log_rms_mae_db": 1.121449526306571, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11409394258727232, "1000–3000 Hz_40ms_envelope_correlation": 0.9926730345551855, "1000–3000 Hz_40ms_modulation_mae_db": 0.4389667598220328, "3000–6000 Hz_10ms_log_rms_mae_db": 1.697158558579532, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24638852977421527, "3000–6000 Hz_10ms_envelope_correlation": 0.962010163811304, "3000–6000 Hz_10ms_modulation_mae_db": 1.0467987718672338, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0656596431036072, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1323473923810091, "3000–6000 Hz_40ms_envelope_correlation": 0.9885051760029154, "3000–6000 Hz_40ms_modulation_mae_db": 1.6821725973286694, "mr_stft_db": 6.130396757766115, "band_mae_db": 0.5593631853547821, "rms_gain_error_db": -0.3145436412139146, "output_peak": 0.01752374529057576}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6976503610691684, "全帯域_10ms_rms_envelope_nrmse": 0.19333069434683892, "全帯域_10ms_envelope_correlation": 0.9666678387172463, "全帯域_10ms_modulation_mae_db": 0.6542425597073556, "全帯域_40ms_log_rms_mae_db": 0.9123286534896164, "全帯域_40ms_rms_envelope_nrmse": 0.09391018124520828, "全帯域_40ms_envelope_correlation": 0.9916759766592288, "全帯域_40ms_modulation_mae_db": 0.8753070139722675, "300–1000 Hz_10ms_log_rms_mae_db": 2.555745513689542, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.32108825730437796, "300–1000 Hz_10ms_envelope_correlation": 0.9221684653352026, "300–1000 Hz_10ms_modulation_mae_db": 1.1324808445310264, "300–1000 Hz_40ms_log_rms_mae_db": 1.9053823808532666, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19473317003152227, "300–1000 Hz_40ms_envelope_correlation": 0.970979018975615, "300–1000 Hz_40ms_modulation_mae_db": 2.0472089700488496, "1000–3000 Hz_10ms_log_rms_mae_db": 1.742998728406462, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2193644765943152, "1000–3000 Hz_10ms_envelope_correlation": 0.9690106423629139, "1000–3000 Hz_10ms_modulation_mae_db": 0.6769872763783376, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1335899255942146, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09918483378391012, "1000–3000 Hz_40ms_envelope_correlation": 0.993675284669318, "1000–3000 Hz_40ms_modulation_mae_db": 0.8524277169271709, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6858185390550242, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.25530748468264713, "3000–6000 Hz_10ms_envelope_correlation": 0.9595576473764541, "3000–6000 Hz_10ms_modulation_mae_db": 1.2348970628867943, "3000–6000 Hz_40ms_log_rms_mae_db": 1.061716112197306, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14288335681126535, "3000–6000 Hz_40ms_envelope_correlation": 0.9874905683706485, "3000–6000 Hz_40ms_modulation_mae_db": 1.742374639451101, "mr_stft_db": 6.125748137663514, "band_mae_db": 0.5538847710677455, "rms_gain_error_db": -0.1878324035404882, "output_peak": 0.012099231742855095}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.770195201713127, "全帯域_10ms_rms_envelope_nrmse": 0.18774095211451575, "全帯域_10ms_envelope_correlation": 0.9697133768349808, "全帯域_10ms_modulation_mae_db": 0.4121682201539803, "全帯域_40ms_log_rms_mae_db": 0.9151384342510217, "全帯域_40ms_rms_envelope_nrmse": 0.09745435595485306, "全帯域_40ms_envelope_correlation": 0.9911917434080372, "全帯域_40ms_modulation_mae_db": 0.5335840170362465, "300–1000 Hz_10ms_log_rms_mae_db": 2.532115203908727, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.34463055102879897, "300–1000 Hz_10ms_envelope_correlation": 0.907421326523253, "300–1000 Hz_10ms_modulation_mae_db": 0.8523583439316798, "300–1000 Hz_40ms_log_rms_mae_db": 1.9664362121585204, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.234172034966976, "300–1000 Hz_40ms_envelope_correlation": 0.9538798609158651, "300–1000 Hz_40ms_modulation_mae_db": 1.2999952320010428, "1000–3000 Hz_10ms_log_rms_mae_db": 1.684461328004443, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17269800291901177, "1000–3000 Hz_10ms_envelope_correlation": 0.9816905923796538, "1000–3000 Hz_10ms_modulation_mae_db": 0.20018689258675806, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0515295297389338, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08007891065474848, "1000–3000 Hz_40ms_envelope_correlation": 0.9961271480873287, "1000–3000 Hz_40ms_modulation_mae_db": 0.6700751819147269, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6703037857270036, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2639865051691767, "3000–6000 Hz_10ms_envelope_correlation": 0.9562930274082747, "3000–6000 Hz_10ms_modulation_mae_db": 1.1851116900732286, "3000–6000 Hz_40ms_log_rms_mae_db": 1.068255582105445, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14088425556513748, "3000–6000 Hz_40ms_envelope_correlation": 0.9869500078521789, "3000–6000 Hz_40ms_modulation_mae_db": 1.9301951856791149, "mr_stft_db": 6.126147581317251, "band_mae_db": 0.22853559336767246, "rms_gain_error_db": 0.07957987417749965, "output_peak": 0.015038083642205236}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.74244749960458, "全帯域_10ms_rms_envelope_nrmse": 0.19960095968086822, "全帯域_10ms_envelope_correlation": 0.96485624639431, "全帯域_10ms_modulation_mae_db": 0.6437365398976747, "全帯域_40ms_log_rms_mae_db": 0.9228315501625208, "全帯域_40ms_rms_envelope_nrmse": 0.10959903062324698, "全帯域_40ms_envelope_correlation": 0.988251105053238, "全帯域_40ms_modulation_mae_db": 0.7461612428380442, "300–1000 Hz_10ms_log_rms_mae_db": 2.579255691548216, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3574438966368859, "300–1000 Hz_10ms_envelope_correlation": 0.8977031471522123, "300–1000 Hz_10ms_modulation_mae_db": 0.747594928716158, "300–1000 Hz_40ms_log_rms_mae_db": 1.9609683031627796, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.274529238067326, "300–1000 Hz_40ms_envelope_correlation": 0.932666947923058, "300–1000 Hz_40ms_modulation_mae_db": 1.341010299155445, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7388456632154914, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2203138670073338, "1000–3000 Hz_10ms_envelope_correlation": 0.9687739991915245, "1000–3000 Hz_10ms_modulation_mae_db": 0.5385364471499569, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1675522544343917, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11316390818498977, "1000–3000 Hz_40ms_envelope_correlation": 0.9917670870148834, "1000–3000 Hz_40ms_modulation_mae_db": 0.5583679008991548, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7270504616313926, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2656712062243396, "3000–6000 Hz_10ms_envelope_correlation": 0.9570198077796523, "3000–6000 Hz_10ms_modulation_mae_db": 1.1066224314727708, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0915992571891338, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13502798274154923, "3000–6000 Hz_40ms_envelope_correlation": 0.9882427873314716, "3000–6000 Hz_40ms_modulation_mae_db": 1.5443767788239653, "mr_stft_db": 6.1351685827592854, "band_mae_db": 0.5673751982335943, "rms_gain_error_db": 0.00021754854425189136, "output_peak": 0.01878240864872372}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8224699195874627, "全帯域_10ms_rms_envelope_nrmse": 0.18280941297722264, "全帯域_10ms_envelope_correlation": 0.9708709321554952, "全帯域_10ms_modulation_mae_db": 0.39948725067592, "全帯域_40ms_log_rms_mae_db": 0.9147926798477238, "全帯域_40ms_rms_envelope_nrmse": 0.08912446421581766, "全帯域_40ms_envelope_correlation": 0.9923835265166029, "全帯域_40ms_modulation_mae_db": 0.8867650272162392, "300–1000 Hz_10ms_log_rms_mae_db": 2.628236819879201, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.31910003153273836, "300–1000 Hz_10ms_envelope_correlation": 0.924326319711993, "300–1000 Hz_10ms_modulation_mae_db": 0.6605310331415892, "300–1000 Hz_40ms_log_rms_mae_db": 1.9398320216841876, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2145350813780761, "300–1000 Hz_40ms_envelope_correlation": 0.9637758822230691, "300–1000 Hz_40ms_modulation_mae_db": 1.4578385498917834, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7461854718992236, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20580988106548226, "1000–3000 Hz_10ms_envelope_correlation": 0.9736980672423754, "1000–3000 Hz_10ms_modulation_mae_db": 0.5132892969311832, "1000–3000 Hz_40ms_log_rms_mae_db": 1.126462745540081, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10219063726507982, "1000–3000 Hz_40ms_envelope_correlation": 0.9934713285117974, "1000–3000 Hz_40ms_modulation_mae_db": 0.745045134708262, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6604450692120223, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2818664815080126, "3000–6000 Hz_10ms_envelope_correlation": 0.9498971642444044, "3000–6000 Hz_10ms_modulation_mae_db": 1.3125416526260636, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0608851450557375, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.15080354504035554, "3000–6000 Hz_40ms_envelope_correlation": 0.9849461601948691, "3000–6000 Hz_40ms_modulation_mae_db": 2.007431733243812, "mr_stft_db": 6.128587632709093, "band_mae_db": 0.3365112558474582, "rms_gain_error_db": 0.05756906291305878, "output_peak": 0.017102110822562168}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.3800363469494625, "spectral_convergence": 0.681340777432625, "spectral_convergence_status": "ok", "amplitude_floor": 3.772168230462137e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.023640656923392, "spectral_convergence": 0.6401696437040854, "spectral_convergence_status": "ok", "amplitude_floor": 1.9872090073495523e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.979698094176651, "spectral_convergence": 0.6726389310613133, "spectral_convergence_status": "ok", "amplitude_floor": 8.414272539865191e-09}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0228756868362371e-07, "output_power": 9.540642420665082e-08, "delta_db": -0.30245236826212385, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 3.789702976182104e-08, "output_power": 5.168508575356823e-08, "delta_db": 1.3476006837019094, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.1288069701978556e-08, "output_power": 5.578626830420463e-08, "delta_db": 0.3651095714345933, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.8766557699122943e-07, "output_power": 3.047662619979321e-07, "delta_db": 0.25078992498437247, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 6.379889954922647e-08, "output_power": 7.242872213602498e-08, "delta_db": 0.5509763523440473, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 5.958002892412794e-08, "output_power": 5.4170761172267274e-08, "delta_db": -0.4133577166126035, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.518375636706213e-08, "output_power": 3.401435620730996e-08, "delta_db": -0.14679949272954182, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.48244087286702736, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.20327038119162233, "pitch": null, "output_rms_dbfs": -61.750559115479916, "output_peak": 0.017710029564695997, "reference_rms_dbfs": -61.95382949667153, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.127791699349835}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.024359572707954e-06, "log_rms_mae_db": 1.6943754131621447, "rms_envelope_nrmse": 0.21018865371763173, "envelope_correlation": 0.9630173665067846, "rms_gain_error_db": 0.20327339541041042, "reference_mean_power": 6.381840334285008e-07, "output_mean_power": 6.687645964284922e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.836855714370683e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.3707173350027986e-08, "output_power": 5.1705359712951646e-08, "reference_active": true, "delta_db": -0.16496731872838183}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8108171988414046e-08, "output_power": 2.151924624957405e-08, "reference_active": true, "delta_db": 0.7495244461319615}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5077869163047108e-08, "output_power": 1.510896514277241e-08, "reference_active": true, "delta_db": 0.008947488195749125}], "active_band_count": 3, "active_band_mae_db": 0.30781308435203075}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.11576902582373e-06, "log_rms_mae_db": 0.8983733625611698, "rms_envelope_nrmse": 0.12396982398511747, "envelope_correlation": 0.9863178720548639, "rms_gain_error_db": 0.20342147738309654, "reference_mean_power": 6.411560082425094e-07, "output_mean_power": 6.719018921517839e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.631066262241422e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.1382633554527724e-08, "output_power": 5.0222540995868546e-08, "reference_active": true, "delta_db": -0.09917677792868006}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.770301277631505e-09, "output_power": 1.1023226030215137e-08, "reference_active": true, "delta_db": 0.5240075681500005}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.622703760150784e-10, "output_power": 8.467725436230854e-10, "reference_active": true, "delta_db": -0.555303483311376}], "active_band_count": 3, "active_band_mae_db": 0.39282927646335225}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.2104964131871903e-06, "log_rms_mae_db": 2.6182362803623613, "rms_envelope_nrmse": 0.31424952858655286, "envelope_correlation": 0.9343869208469495, "rms_gain_error_db": 0.8087768082302448, "reference_mean_power": 5.88463135957351e-08, "output_mean_power": 7.089195328829927e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.019969626272171e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.669218221395915e-09, "output_power": 6.248789652619613e-09, "reference_active": true, "delta_db": 0.42272731331812907}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.997554044063276e-09, "output_power": 5.345405666461801e-09, "reference_active": true, "delta_db": 0.2922317037757916}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.156278331683346e-09, "output_power": 4.924771493923955e-09, "reference_active": true, "delta_db": -0.19950267844674974}], "active_band_count": 3, "active_band_mae_db": 0.30482056518022344}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.1954716835574657e-06, "log_rms_mae_db": 2.0713347559995587, "rms_envelope_nrmse": 0.22211834322958704, "envelope_correlation": 0.9678190594279618, "rms_gain_error_db": 0.8086067261260977, "reference_mean_power": 5.913056575013843e-08, "output_mean_power": 7.123160120197806e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.690703802813698e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.971603141472601e-09, "output_power": 7.2158812519129686e-09, "reference_active": true, "delta_db": 0.14956720702283569}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1694216774888265e-09, "output_power": 3.0551668972435697e-09, "reference_active": true, "delta_db": -0.15945084181123306}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5180140726512066e-10, "output_power": 3.588038543057729e-10, "reference_active": true, "delta_db": -1.0009047969070741}], "active_band_count": 3, "active_band_mae_db": 0.436640948580381}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.597874045564372e-06, "log_rms_mae_db": 1.7474732314966361, "rms_envelope_nrmse": 0.23190313441338173, "envelope_correlation": 0.9678147409107949, "rms_gain_error_db": 0.3178856633930114, "reference_mean_power": 3.0019112356646434e-07, "output_mean_power": 3.2298801889915477e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1704248469151792e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.917571308133626e-08, "output_power": 4.4364409129760525e-08, "reference_active": true, "delta_db": -0.4471596448838835}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.373644839895842e-09, "output_power": 6.482580917263208e-09, "reference_active": true, "delta_db": 0.07360086933226014}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.9583662339560916e-09, "output_power": 3.884122895292343e-09, "reference_active": true, "delta_db": -0.08223010588857937}], "active_band_count": 3, "active_band_mae_db": 0.200996873368241}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6957143825373563e-06, "log_rms_mae_db": 1.188161057533721, "rms_envelope_nrmse": 0.12713183678823398, "envelope_correlation": 0.9905397656701104, "rms_gain_error_db": 0.3178800806291629, "reference_mean_power": 3.016958800523271e-07, "output_mean_power": 3.2460663122919097e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.1236901446499244e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.541853281346178e-08, "output_power": 4.144478549617295e-08, "reference_active": true, "delta_db": -0.39763204572320193}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5898805602165613e-09, "output_power": 3.3090539710820105e-09, "reference_active": true, "delta_db": -0.3537614868739912}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.01076242530766e-10, "output_power": 1.984309352399405e-10, "reference_active": true, "delta_db": -1.8106710805306805}], "active_band_count": 3, "active_band_mae_db": 0.8540215377092912}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.0353597876360997e-06, "log_rms_mae_db": 1.7013320363859556, "rms_envelope_nrmse": 0.2561136936618055, "envelope_correlation": 0.9601066227472327, "rms_gain_error_db": 0.13646468277728746, "reference_mean_power": 5.358047115055493e-08, "output_mean_power": 5.529081561975096e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.7539255872910824e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.2466604070258255e-09, "output_power": 5.07514583810133e-09, "reference_active": true, "delta_db": -0.14434428618886866}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.042126892400446e-09, "output_power": 2.8263299094366767e-09, "reference_active": true, "delta_db": -0.31954470843722727}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.488177427019359e-09, "output_power": 1.171659575604729e-09, "reference_active": true, "delta_db": -3.270798995770897}], "active_band_count": 3, "active_band_mae_db": 1.2448959967989977}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.4732086031870805e-06, "log_rms_mae_db": 1.0832742943055655, "rms_envelope_nrmse": 0.13171872411624475, "envelope_correlation": 0.9888093477836081, "rms_gain_error_db": 0.1364155808693854, "reference_mean_power": 5.3847422411461674e-08, "output_mean_power": 5.5565660006820495e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.6457241300858348e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.316794721929917e-09, "output_power": 5.5553794865213146e-09, "reference_active": true, "delta_db": -0.5578303294116994}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0867827772247918e-09, "output_power": 1.5752808630095675e-09, "reference_active": true, "delta_db": -1.2211924661938098}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.2900642849732037e-10, "output_power": 9.069221179298692e-11, "reference_active": true, "delta_db": -4.022776801422218}], "active_band_count": 3, "active_band_mae_db": 1.9339331990092425}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.4262229068395079, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "32f1deb886726ebdf7783c38fc7d59d697c1f2b84a212eeeb7c57240c9e3f03b", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9711200726067941, "standard_deviation": 0.005649038709278008, "minimum": 0.9624744531744739, "maximum": 0.9816905923796538, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.7275304685956647, "standard_deviation": 0.02825266787440593, "minimum": 1.684461328004443, "maximum": 1.7596070934338846, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5593447543795103, "standard_deviation": 0.28594725525871884, "minimum": 0.20018689258675806, "maximum": 1.0824531741825278, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2132370651461985, "standard_deviation": 0.02115422136378727, "minimum": 0.17269800291901177, "maximum": 0.24224933679924784, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9925215578279992, "standard_deviation": 0.0030430603935366176, "minimum": 0.9864767859943759, "maximum": 0.9961271480873287, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.1188748293151762, "standard_deviation": 0.0482272406355251, "minimum": 1.0515295297389338, "maximum": 1.188161057533721, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.818669921661526, "standard_deviation": 0.28950934384963084, "minimum": 0.4389667598220328, "maximum": 1.338458489514241, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10804104629427022, "standard_deviation": 0.02063390960380084, "minimum": 0.08007891065474848, "maximum": 0.14236260418976365, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9583329238189571, "standard_deviation": 0.003984946875834356, "minimum": 0.9498971642444044, "maximum": 0.9620876284712065, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.6899592695427634, "standard_deviation": 0.02028483488060231, "minimum": 1.6604450692120223, "maximum": 1.7270504616313926, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.1824776040829952, "standard_deviation": 0.09275801066102461, "minimum": 1.0467987718672338, "maximum": 1.3125416526260636, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2588477816933423, "standard_deviation": 0.011493285340284164, "minimum": 0.24638852977421527, "maximum": 0.2818664815080126, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9866725827257932, "standard_deviation": 0.002791389924161515, "minimum": 0.9804513613495153, "maximum": 0.9888093477836081, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.0800179443655056, "standard_deviation": 0.01847259440166329, "minimum": 1.0608851450557375, "maximum": 1.106794165010167, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.7940488416809508, "standard_deviation": 0.1881952978731431, "minimum": 1.5443767788239653, "maximum": 2.007431733243812, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.14341027120762345, "standard_deviation": 0.012938171254806268, "minimum": 0.13171872411624475, "maximum": 0.17133584402600957, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9162511657535517, "standard_deviation": 0.01166475955313108, "minimum": 0.8977031471522123, "maximum": 0.9343869208469495, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.5628803997850227, "standard_deviation": 0.054424031241864776, "minimum": 2.4849995907056446, "maximum": 2.628236819879201, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8043851489473206, "standard_deviation": 0.25384079525469583, "minimum": 0.30482056518022344, "maximum": 1.1324808445310264, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.3319972506725962, "standard_deviation": 0.01572838519614722, "minimum": 0.31424952858655286, "maximum": 0.3574438966368859, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9601029886270387, "standard_deviation": 0.012343156830511641, "minimum": 0.932666947923058, "maximum": 0.970979018975615, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.9433565295791684, "standard_deviation": 0.07758852183576763, "minimum": 1.8035887884644883, "maximum": 2.0713347559995587, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.4228371003268103, "standard_deviation": 0.5397238631411997, "minimum": 0.436640948580381, "maximum": 2.0472089700488496, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.22164042995483835, "standard_deviation": 0.024860320060981732, "minimum": 0.19473317003152227, "maximum": 0.274529238067326, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.437911702538333, "standard_deviation": 0.1291729431390216, "minimum": 0.22853559336767246, "maximum": 0.5673751982335943, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.129186792893651, "standard_deviation": 0.0031663454921523953, "minimum": 6.125748137663514, "maximum": 6.1351685827592854, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.01587059561474841, "standard_deviation": 0.0022853732929797965, "minimum": 0.012099231742855095, "maximum": 0.01878240864872372, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.05474736327774919, "standard_deviation": 0.176950089399109, "minimum": -0.3145436412139146, "maximum": 0.20327038119162233, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9668057523112319, "standard_deviation": 0.004425603966524326, "minimum": 0.9602357478851568, "maximum": 0.9737735971722434, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.7295038921851655, "standard_deviation": 0.053286413494912296, "minimum": 1.6736507821296829, "maximum": 1.8224699195874627, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.5443309593933123, "standard_deviation": 0.1989461853574997, "minimum": 0.30781308435203075, "maximum": 0.9378984769293983, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.19432604056035996, "standard_deviation": 0.013285820157559624, "minimum": 0.17213058910151552, "maximum": 0.21086136893427318, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9900853911011914, "standard_deviation": 0.0026652675564101313, "minimum": 0.9863178720548639, "maximum": 0.9929299700047083, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.9081660461254543, "standard_deviation": 0.029086626374202663, "minimum": 0.845138272716618, "maximum": 0.9472450394699974, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7212368238552276, "standard_deviation": 0.19340197649790536, "minimum": 0.39282927646335225, "maximum": 0.8887182285343118, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.10225607374697358, "standard_deviation": 0.01404340967984313, "minimum": 0.08501329923869931, "maximum": 0.12396982398511747, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "method": "C", "status": "measured", "mos": {"status": "measured", "value": 2.5364372730255127, "predicted_mos": 2.5364372730255127, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "8a8c857cb57ad08477e79fdc3508205562f342a0ecc64c7c35b4939c7d34c484", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 11.645169900264591}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7135117794849164, "全帯域_10ms_rms_envelope_nrmse": 0.21572819590521314, "全帯域_10ms_envelope_correlation": 0.9590932501299925, "全帯域_10ms_modulation_mae_db": 0.6733260926010405, "全帯域_40ms_log_rms_mae_db": 0.9125305897221277, "全帯域_40ms_rms_envelope_nrmse": 0.11268948433841294, "全帯域_40ms_envelope_correlation": 0.9876440990600672, "全帯域_40ms_modulation_mae_db": 1.1683802939429964, "300–1000 Hz_10ms_log_rms_mae_db": 2.441867795522022, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3141744013472946, "300–1000 Hz_10ms_envelope_correlation": 0.9272269079586845, "300–1000 Hz_10ms_modulation_mae_db": 0.781553375607018, "300–1000 Hz_40ms_log_rms_mae_db": 1.8276901192471524, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2058919870857485, "300–1000 Hz_40ms_envelope_correlation": 0.9676138695974625, "300–1000 Hz_40ms_modulation_mae_db": 1.0486375875064073, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3828490601474703, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.22646143404581717, "1000–3000 Hz_10ms_envelope_correlation": 0.9673920044687996, "1000–3000 Hz_10ms_modulation_mae_db": 0.774885463190618, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8548090024459586, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12997559399965497, "1000–3000 Hz_40ms_envelope_correlation": 0.9887975965742176, "1000–3000 Hz_40ms_modulation_mae_db": 1.0799346988944611, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2379064867480873, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.23530325146170525, "3000–6000 Hz_10ms_envelope_correlation": 0.9653240595883331, "3000–6000 Hz_10ms_modulation_mae_db": 0.7996357960748347, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7599286772439313, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13457599999277134, "3000–6000 Hz_40ms_envelope_correlation": 0.9884754450959208, "3000–6000 Hz_40ms_modulation_mae_db": 1.3685100572190239, "mr_stft_db": 5.93987653811012, "band_mae_db": 0.3454947857624416, "rms_gain_error_db": 0.010172567434025826, "output_peak": 0.017080680716990322}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7891940975598923, "全帯域_10ms_rms_envelope_nrmse": 0.20970352194865347, "全帯域_10ms_envelope_correlation": 0.962254891626967, "全帯域_10ms_modulation_mae_db": 0.32383968012071945, "全帯域_40ms_log_rms_mae_db": 0.9867294014649323, "全帯域_40ms_rms_envelope_nrmse": 0.10658834015764165, "全帯域_40ms_envelope_correlation": 0.9894160575308504, "全帯域_40ms_modulation_mae_db": 0.6510070821734837, "300–1000 Hz_10ms_log_rms_mae_db": 2.3291035901659507, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.31077691672128005, "300–1000 Hz_10ms_envelope_correlation": 0.926907432525426, "300–1000 Hz_10ms_modulation_mae_db": 0.876012932399992, "300–1000 Hz_40ms_log_rms_mae_db": 1.747069068094388, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2104094104594861, "300–1000 Hz_40ms_envelope_correlation": 0.9639119767963672, "300–1000 Hz_40ms_modulation_mae_db": 1.2042685435565352, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4105283103023307, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2209223151232847, "1000–3000 Hz_10ms_envelope_correlation": 0.9698792437431865, "1000–3000 Hz_10ms_modulation_mae_db": 0.4042900934722093, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7997676388630846, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11934014623766162, "1000–3000 Hz_40ms_envelope_correlation": 0.9910233407964696, "1000–3000 Hz_40ms_modulation_mae_db": 0.2673978403106574, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1881753225241685, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.23345982516795707, "3000–6000 Hz_10ms_envelope_correlation": 0.9660608078152161, "3000–6000 Hz_10ms_modulation_mae_db": 0.6967790057238514, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6996935167747776, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11934357699735297, "3000–6000 Hz_40ms_envelope_correlation": 0.9917474109279127, "3000–6000 Hz_40ms_modulation_mae_db": 1.1497867257104402, "mr_stft_db": 5.939386173566754, "band_mae_db": 0.40991769260327743, "rms_gain_error_db": 0.1314340788565463, "output_peak": 0.015166561287385623}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8079934518449692, "全帯域_10ms_rms_envelope_nrmse": 0.1968065759405145, "全帯域_10ms_envelope_correlation": 0.9660270638645174, "全帯域_10ms_modulation_mae_db": 0.3105726603105489, "全帯域_40ms_log_rms_mae_db": 1.0008626115380004, "全帯域_40ms_rms_envelope_nrmse": 0.10876336966115872, "全帯域_40ms_envelope_correlation": 0.9884714760818781, "全帯域_40ms_modulation_mae_db": 0.6484049626047131, "300–1000 Hz_10ms_log_rms_mae_db": 2.41331164279192, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3023251903835391, "300–1000 Hz_10ms_envelope_correlation": 0.926940250198146, "300–1000 Hz_10ms_modulation_mae_db": 1.0515546136211142, "300–1000 Hz_40ms_log_rms_mae_db": 1.719331181208041, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19911744822365393, "300–1000 Hz_40ms_envelope_correlation": 0.9663546480791916, "300–1000 Hz_40ms_modulation_mae_db": 1.9932247817997284, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3464841005921449, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18399895775840547, "1000–3000 Hz_10ms_envelope_correlation": 0.9782659211786165, "1000–3000 Hz_10ms_modulation_mae_db": 0.20431786366420948, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7348099119157213, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08617520739735748, "1000–3000 Hz_40ms_envelope_correlation": 0.9950883861547798, "1000–3000 Hz_40ms_modulation_mae_db": 0.3142385913000447, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1835549007760782, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.25654044479873406, "3000–6000 Hz_10ms_envelope_correlation": 0.9633002049048526, "3000–6000 Hz_10ms_modulation_mae_db": 0.7947517215145203, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6683066194225372, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14922049195410048, "3000–6000 Hz_40ms_envelope_correlation": 0.9880505239115202, "3000–6000 Hz_40ms_modulation_mae_db": 0.7127543237675229, "mr_stft_db": 5.921891546946591, "band_mae_db": 0.34348637697474516, "rms_gain_error_db": -0.02983534575396381, "output_peak": 0.01523958636223677}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8320871208120795, "全帯域_10ms_rms_envelope_nrmse": 0.20635936356480264, "全帯域_10ms_envelope_correlation": 0.9624782824557809, "全帯域_10ms_modulation_mae_db": 0.6587812169364909, "全帯域_40ms_log_rms_mae_db": 0.910661792692002, "全帯域_40ms_rms_envelope_nrmse": 0.1124010386635415, "全帯域_40ms_envelope_correlation": 0.9877165660525478, "全帯域_40ms_modulation_mae_db": 1.0023872736158321, "300–1000 Hz_10ms_log_rms_mae_db": 2.2601688555057535, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2937048040110789, "300–1000 Hz_10ms_envelope_correlation": 0.9401927452042896, "300–1000 Hz_10ms_modulation_mae_db": 0.6377788183448009, "300–1000 Hz_40ms_log_rms_mae_db": 1.7763041763899006, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2113653033090811, "300–1000 Hz_40ms_envelope_correlation": 0.9681601243454535, "300–1000 Hz_40ms_modulation_mae_db": 1.0668684864041844, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4224295714017736, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17877707550221744, "1000–3000 Hz_10ms_envelope_correlation": 0.9794791258598917, "1000–3000 Hz_10ms_modulation_mae_db": 0.44188304098064846, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8505099743285923, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0975126612210135, "1000–3000 Hz_40ms_envelope_correlation": 0.9938678935202336, "1000–3000 Hz_40ms_modulation_mae_db": 0.6325742380824685, "3000–6000 Hz_10ms_log_rms_mae_db": 1.210022301324692, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24466220235042338, "3000–6000 Hz_10ms_envelope_correlation": 0.9623236341458549, "3000–6000 Hz_10ms_modulation_mae_db": 1.0384724119494242, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6842531913762683, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1414738082577501, "3000–6000 Hz_40ms_envelope_correlation": 0.9866525911326465, "3000–6000 Hz_40ms_modulation_mae_db": 1.8148804135201668, "mr_stft_db": 5.9317713974569335, "band_mae_db": 0.5028148850204234, "rms_gain_error_db": -0.05647098108301214, "output_peak": 0.015352413445813793}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8215748315307279, "全帯域_10ms_rms_envelope_nrmse": 0.21242556625646963, "全帯域_10ms_envelope_correlation": 0.9628823866142278, "全帯域_10ms_modulation_mae_db": 0.5332731030681525, "全帯域_40ms_log_rms_mae_db": 0.9716412405673025, "全帯域_40ms_rms_envelope_nrmse": 0.12208522012356209, "全帯域_40ms_envelope_correlation": 0.987157782279301, "全帯域_40ms_modulation_mae_db": 0.651382972147695, "300–1000 Hz_10ms_log_rms_mae_db": 2.2594512956827266, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.303849535476965, "300–1000 Hz_10ms_envelope_correlation": 0.9421718250589962, "300–1000 Hz_10ms_modulation_mae_db": 0.8670019743982952, "300–1000 Hz_40ms_log_rms_mae_db": 1.6551701433459005, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20650516810015207, "300–1000 Hz_40ms_envelope_correlation": 0.9756118607285923, "300–1000 Hz_40ms_modulation_mae_db": 0.7155225509006328, "1000–3000 Hz_10ms_log_rms_mae_db": 1.351558554344328, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2118187574842277, "1000–3000 Hz_10ms_envelope_correlation": 0.9718969255781285, "1000–3000 Hz_10ms_modulation_mae_db": 0.7022505930550267, "1000–3000 Hz_40ms_log_rms_mae_db": 0.765357611468724, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10942385689632751, "1000–3000 Hz_40ms_envelope_correlation": 0.9922710064958374, "1000–3000 Hz_40ms_modulation_mae_db": 0.5663134247688585, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1903054568010987, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24711522661864735, "3000–6000 Hz_10ms_envelope_correlation": 0.9630305925496264, "3000–6000 Hz_10ms_modulation_mae_db": 0.8480160323860853, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6746714071809444, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1304531654044683, "3000–6000 Hz_40ms_envelope_correlation": 0.9891370635103861, "3000–6000 Hz_40ms_modulation_mae_db": 0.9383117531845079, "mr_stft_db": 5.934850156001546, "band_mae_db": 0.6996232857572646, "rms_gain_error_db": 0.2696733503057731, "output_peak": 0.016061181382392358}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7218091933806399, "全帯域_10ms_rms_envelope_nrmse": 0.19373881418123912, "全帯域_10ms_envelope_correlation": 0.9680016467177428, "全帯域_10ms_modulation_mae_db": 0.4680840601481515, "全帯域_40ms_log_rms_mae_db": 0.9133682261288386, "全帯域_40ms_rms_envelope_nrmse": 0.10368448357767752, "全帯域_40ms_envelope_correlation": 0.9900974257814319, "全帯域_40ms_modulation_mae_db": 0.5610398412105954, "300–1000 Hz_10ms_log_rms_mae_db": 2.4072649987798975, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3195570924549012, "300–1000 Hz_10ms_envelope_correlation": 0.9201757429425176, "300–1000 Hz_10ms_modulation_mae_db": 0.4769298661057228, "300–1000 Hz_40ms_log_rms_mae_db": 1.793302997704588, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.22187969408870892, "300–1000 Hz_40ms_envelope_correlation": 0.9579505355999871, "300–1000 Hz_40ms_modulation_mae_db": 0.9367181382256623, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3541376044572462, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19399023915333338, "1000–3000 Hz_10ms_envelope_correlation": 0.9764758031393799, "1000–3000 Hz_10ms_modulation_mae_db": 0.38500478123390386, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7740852593307664, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08456926438459193, "1000–3000 Hz_40ms_envelope_correlation": 0.9954276171293045, "1000–3000 Hz_40ms_modulation_mae_db": 0.6301506994799269, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2245043744058162, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2253786246726415, "3000–6000 Hz_10ms_envelope_correlation": 0.9686460099234632, "3000–6000 Hz_10ms_modulation_mae_db": 0.884479177515875, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7149839148117401, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12212937347224148, "3000–6000 Hz_40ms_envelope_correlation": 0.990185083271857, "3000–6000 Hz_40ms_modulation_mae_db": 1.4777827181784098, "mr_stft_db": 5.926195395347154, "band_mae_db": 0.4167839515774485, "rms_gain_error_db": 0.15971138183627048, "output_peak": 0.013587905135095925}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.733130487444192, "全帯域_10ms_rms_envelope_nrmse": 0.19140296849769278, "全帯域_10ms_envelope_correlation": 0.9692048086630667, "全帯域_10ms_modulation_mae_db": 0.22460437324845292, "全帯域_40ms_log_rms_mae_db": 0.8980779332056866, "全帯域_40ms_rms_envelope_nrmse": 0.10225888834060183, "全帯域_40ms_envelope_correlation": 0.9906664586607994, "全帯域_40ms_modulation_mae_db": 0.46796260858685157, "300–1000 Hz_10ms_log_rms_mae_db": 2.2874123765670693, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2923807615314136, "300–1000 Hz_10ms_envelope_correlation": 0.9378642805539361, "300–1000 Hz_10ms_modulation_mae_db": 0.5981290008340673, "300–1000 Hz_40ms_log_rms_mae_db": 1.673943329890609, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2110041059735917, "300–1000 Hz_40ms_envelope_correlation": 0.9653399832751031, "300–1000 Hz_40ms_modulation_mae_db": 0.45319010680199406, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3746867637316713, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2029370279274777, "1000–3000 Hz_10ms_envelope_correlation": 0.9743591121991623, "1000–3000 Hz_10ms_modulation_mae_db": 0.5932107096255446, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7858055143036115, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09195954808131017, "1000–3000 Hz_40ms_envelope_correlation": 0.994630964585604, "1000–3000 Hz_40ms_modulation_mae_db": 0.29406779094498087, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2207641851564865, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24060866933316538, "3000–6000 Hz_10ms_envelope_correlation": 0.9648089350481017, "3000–6000 Hz_10ms_modulation_mae_db": 1.0383489577307967, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6857054066823125, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13573876000717483, "3000–6000 Hz_40ms_envelope_correlation": 0.988145080689404, "3000–6000 Hz_40ms_modulation_mae_db": 1.7337436191307842, "mr_stft_db": 5.915165396611336, "band_mae_db": 0.33276323460749463, "rms_gain_error_db": 0.1351502985239762, "output_peak": 0.01564471394408785}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7678825798577351, "全帯域_10ms_rms_envelope_nrmse": 0.18340039293223825, "全帯域_10ms_envelope_correlation": 0.9715187460457896, "全帯域_10ms_modulation_mae_db": 0.4175141578214235, "全帯域_40ms_log_rms_mae_db": 0.9431266693370157, "全帯域_40ms_rms_envelope_nrmse": 0.10193003516336485, "全帯域_40ms_envelope_correlation": 0.9905721570582354, "全帯域_40ms_modulation_mae_db": 0.4686524460167572, "300–1000 Hz_10ms_log_rms_mae_db": 2.3814029496908393, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3163436788839744, "300–1000 Hz_10ms_envelope_correlation": 0.9360431925484074, "300–1000 Hz_10ms_modulation_mae_db": 1.0029331973522242, "300–1000 Hz_40ms_log_rms_mae_db": 1.8272989366609622, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.21392680626340999, "300–1000 Hz_40ms_envelope_correlation": 0.9732224310886114, "300–1000 Hz_40ms_modulation_mae_db": 0.8146594842433986, "1000–3000 Hz_10ms_log_rms_mae_db": 1.401333213669935, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18833184978664427, "1000–3000 Hz_10ms_envelope_correlation": 0.979055281167622, "1000–3000 Hz_10ms_modulation_mae_db": 0.41932297050619627, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8139263022553301, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10138467192260361, "1000–3000 Hz_40ms_envelope_correlation": 0.9942654734805199, "1000–3000 Hz_40ms_modulation_mae_db": 0.33394216919451924, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2289918512253246, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2323070301056381, "3000–6000 Hz_10ms_envelope_correlation": 0.966212829890189, "3000–6000 Hz_10ms_modulation_mae_db": 0.927591339962803, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7246995323918708, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14078448460554252, "3000–6000 Hz_40ms_envelope_correlation": 0.9867634415585603, "3000–6000 Hz_40ms_modulation_mae_db": 1.5176321853525192, "mr_stft_db": 5.923373608030453, "band_mae_db": 0.5083285756363402, "rms_gain_error_db": 0.14158367497939467, "output_peak": 0.01481746427642709}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.07848847671138, "spectral_convergence": 0.6829417368155283, "spectral_convergence_status": "ok", "amplitude_floor": 3.772168230462137e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.795187167833405, "spectral_convergence": 0.6560656726883866, "spectral_convergence_status": "ok", "amplitude_floor": 1.9872090073495523e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.945953969785576, "spectral_convergence": 0.6940051861080236, "spectral_convergence_status": "ok", "amplitude_floor": 8.414272539865191e-09}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0228756868362371e-07, "output_power": 9.946224981683688e-08, "delta_db": -0.12164577138049908, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 3.789702976182104e-08, "output_power": 4.219642603346511e-08, "delta_db": 0.46670495703096343, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.1288069701978556e-08, "output_power": 5.55284249513438e-08, "delta_db": 0.3449900090761784, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.8766557699122943e-07, "output_power": 2.829523911814421e-07, "delta_db": -0.07174527459853652, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 6.379889954922647e-08, "output_power": 6.842498024802882e-08, "delta_db": 0.3040149296389912, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 5.958002892412794e-08, "output_power": 6.218698615556787e-08, "delta_db": 0.18598799861012977, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.518375636706213e-08, "output_power": 2.8444922098838093e-08, "delta_db": -0.9233745600017924, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.3454947857624416, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.010172567434025826, "pitch": null, "output_rms_dbfs": -61.943656929237505, "output_peak": 0.017080680716990322, "reference_rms_dbfs": -61.95382949667153, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.93987653811012}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.024359572707954e-06, "log_rms_mae_db": 1.7135117794849164, "rms_envelope_nrmse": 0.21572819590521314, "envelope_correlation": 0.9590932501299925, "rms_gain_error_db": 0.010149570647032815, "reference_mean_power": 6.381840334285008e-07, "output_mean_power": 6.396772296126259e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.836855714370683e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.3707173350027986e-08, "output_power": 5.035794879153068e-08, "reference_active": true, "delta_db": -0.27964263855831345}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8108171988414046e-08, "output_power": 1.7665502386706322e-08, "reference_active": true, "delta_db": -0.10748617914353695}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5077869163047108e-08, "output_power": 1.0352733258735837e-08, "reference_active": true, "delta_db": -1.632849460101271}], "active_band_count": 3, "active_band_mae_db": 0.6733260926010405}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.11576902582373e-06, "log_rms_mae_db": 0.9125305897221277, "rms_envelope_nrmse": 0.11268948433841294, "envelope_correlation": 0.9876440990600672, "rms_gain_error_db": 0.01021797743430394, "reference_mean_power": 6.411560082425094e-07, "output_mean_power": 6.426662808426501e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.631066262241422e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.1382633554527724e-08, "output_power": 4.7610775384088645e-08, "reference_active": true, "delta_db": -0.33111105330980745}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.770301277631505e-09, "output_power": 8.085228987078097e-09, "reference_active": true, "delta_db": -0.8221563150177907}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.622703760150784e-10, "output_power": 5.598990939095942e-10, "reference_active": true, "delta_db": -2.3518735135013906}], "active_band_count": 3, "active_band_mae_db": 1.1683802939429964}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.2104964131871903e-06, "log_rms_mae_db": 2.441867795522022, "rms_envelope_nrmse": 0.3141744013472946, "envelope_correlation": 0.9272269079586845, "rms_gain_error_db": 0.5002686761967713, "reference_mean_power": 5.88463135957351e-08, "output_mean_power": 6.603073468581623e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.019969626272171e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.669218221395915e-09, "output_power": 6.379063036428124e-09, "reference_active": true, "delta_db": 0.5123371945197311}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.997554044063276e-09, "output_power": 5.416578539017784e-09, "reference_active": true, "delta_db": 0.34967545367491815}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.156278331683346e-09, "output_power": 3.664979960317118e-09, "reference_active": true, "delta_db": -1.4826474786264046}], "active_band_count": 3, "active_band_mae_db": 0.781553375607018}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.1954716835574657e-06, "log_rms_mae_db": 1.8276901192471524, "rms_envelope_nrmse": 0.2058919870857485, "envelope_correlation": 0.9676138695974625, "rms_gain_error_db": 0.5000324790317331, "reference_mean_power": 5.913056575013843e-08, "output_mean_power": 6.634608215716284e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.690703802813698e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.971603141472601e-09, "output_power": 7.041143854891338e-09, "reference_active": true, "delta_db": 0.043105603847177106}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1694216774888265e-09, "output_power": 2.6923415067880533e-09, "reference_active": true, "delta_db": -0.7084987738586892}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5180140726512066e-10, "output_power": 2.603255177659944e-10, "reference_active": true, "delta_db": -2.394308384813356}], "active_band_count": 3, "active_band_mae_db": 1.0486375875064073}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.597874045564372e-06, "log_rms_mae_db": 1.3828490601474703, "rms_envelope_nrmse": 0.22646143404581717, "envelope_correlation": 0.9673920044687996, "rms_gain_error_db": 0.010190543164829032, "reference_mean_power": 3.0019112356646434e-07, "output_mean_power": 3.00896336867134e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1704248469151792e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.917571308133626e-08, "output_power": 4.364340330549357e-08, "reference_active": true, "delta_db": -0.5183205675294775}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.373644839895842e-09, "output_power": 8.216502182641819e-09, "reference_active": true, "delta_db": 1.1029911543326305}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.9583662339560916e-09, "output_power": 3.3665223847428972e-09, "reference_active": true, "delta_db": -0.7033446677097459}], "active_band_count": 3, "active_band_mae_db": 0.774885463190618}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6957143825373563e-06, "log_rms_mae_db": 0.8548090024459586, "rms_envelope_nrmse": 0.12997559399965497, "envelope_correlation": 0.9887975965742176, "rms_gain_error_db": 0.01017530626921632, "reference_mean_power": 3.016958800523271e-07, "output_mean_power": 3.024035673864961e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.1236901446499244e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.541853281346178e-08, "output_power": 4.0841267009011e-08, "reference_active": true, "delta_db": -0.4613389415347899}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5898805602165613e-09, "output_power": 4.403197638794626e-09, "reference_active": true, "delta_db": 0.8868818002791118}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.01076242530766e-10, "output_power": 1.947682453968975e-10, "reference_active": true, "delta_db": -1.8915833548694818}], "active_band_count": 3, "active_band_mae_db": 1.0799346988944611}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.0353597876360997e-06, "log_rms_mae_db": 1.2379064867480873, "rms_envelope_nrmse": 0.23530325146170525, "envelope_correlation": 0.9653240595883331, "rms_gain_error_db": -0.3051855468218096, "reference_mean_power": 5.358047115055493e-08, "output_mean_power": 4.9944534935611224e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.7539255872910824e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.2466604070258255e-09, "output_power": 5.305140172704482e-09, "reference_active": true, "delta_db": 0.048139081822310754}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.042126892400446e-09, "output_power": 2.932210099625325e-09, "reference_active": true, "delta_db": -0.1598223998593682}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.488177427019359e-09, "output_power": 1.5024040828930883e-09, "reference_active": true, "delta_db": -2.190945906542825}], "active_band_count": 3, "active_band_mae_db": 0.7996357960748347}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.4732086031870805e-06, "log_rms_mae_db": 0.7599286772439313, "rms_envelope_nrmse": 0.13457599999277134, "envelope_correlation": 0.9884754450959208, "rms_gain_error_db": -0.3052123402160602, "reference_mean_power": 5.3847422411461674e-08, "output_mean_power": 5.0193061393745596e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.6457241300858348e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.316794721929917e-09, "output_power": 5.877808191889267e-09, "reference_active": true, "delta_db": -0.312813539603315}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0867827772247918e-09, "output_power": 1.681599697141035e-09, "reference_active": true, "delta_db": -0.9375462324985984}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.2900642849732037e-10, "output_power": 1.1866718322612285e-10, "reference_active": true, "delta_db": -2.8551703995551585}], "active_band_count": 3, "active_band_mae_db": 1.3685100572190239}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.43131887695723825, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "72ea18201d3802978ff7c0907e355c111a49495e6f9f8991ab3af8bd7cdb37c4", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9746004271668484, "standard_deviation": 0.004507428645530045, "minimum": 0.9673920044687996, "maximum": 0.9794791258598917, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.3805008973308626, "standard_deviation": 0.02884140760962322, "minimum": 1.3464841005921449, "maximum": 1.4224295714017736, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4906456894660446, "standard_deviation": 0.1867596270065278, "minimum": 0.20431786366420948, "maximum": 0.774885463190618, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.200904707097676, "standard_deviation": 0.017559778699499123, "minimum": 0.17877707550221744, "maximum": 0.22646143404581717, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9931715348421208, "standard_deviation": 0.002303190442543757, "minimum": 0.9887975965742176, "maximum": 0.9954276171293045, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7973839018639737, "standard_deviation": 0.04143398926014529, "minimum": 0.7348099119157213, "maximum": 0.8548090024459586, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5148274316219896, "standard_deviation": 0.2756997280140239, "minimum": 0.2673978403106574, "maximum": 1.0799346988944611, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1025426187675651, "standard_deviation": 0.01608749656046812, "minimum": 0.08456926438459193, "maximum": 0.12997559399965497, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9649633842332046, "standard_deviation": 0.002068514163053479, "minimum": 0.9623236341458549, "maximum": 0.9686460099234632, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2105281098702192, "standard_deviation": 0.020794955168923233, "minimum": 1.1835549007760782, "maximum": 1.2379064867480873, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.8785093053572739, "standard_deviation": 0.11998434436873152, "minimum": 0.6967790057238514, "maximum": 1.0384724119494242, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.239421909313614, "standard_deviation": 0.009866578494227903, "minimum": 0.2253786246726415, "maximum": 0.25654044479873406, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9886445800122758, "standard_deviation": 0.0017063310850502882, "minimum": 0.9866525911326465, "maximum": 0.9917474109279127, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7015302832355478, "standard_deviation": 0.030485819007628354, "minimum": 0.6683066194225372, "maximum": 0.7599286772439313, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.3391752245079218, "standard_deviation": 0.3822605268057685, "minimum": 0.7127543237675229, "maximum": 1.8148804135201668, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.13421495758642527, "standard_deviation": 0.010034500271178212, "minimum": 0.11934357699735297, "maximum": 0.14922049195410048, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9321902971238004, "standard_deviation": 0.007884572291924952, "minimum": 0.9201757429425176, "maximum": 0.9421718250589962, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.3474979380882726, "standard_deviation": 0.07298333637283422, "minimum": 2.2594512956827266, "maximum": 2.441867795522022, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7864867223329044, "standard_deviation": 0.20179557150327698, "minimum": 0.4769298661057228, "maximum": 1.0515546136211142, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.3066390476013059, "standard_deviation": 0.010225621804304027, "minimum": 0.2923807615314136, "maximum": 0.3195570924549012, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9672706786888461, "standard_deviation": 0.005459202067308411, "minimum": 0.9579505355999871, "maximum": 0.9756118607285923, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.7525137440676928, "standard_deviation": 0.06574178260273732, "minimum": 1.6551701433459005, "maximum": 1.8276901192471524, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.0291362099298178, "standard_deviation": 0.4545878736022502, "minimum": 0.45319010680199406, "maximum": 1.9932247817997284, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.21001249043797904, "standard_deviation": 0.006623606517777003, "minimum": 0.19911744822365393, "maximum": 0.22187969408870892, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.4449015984924294, "standard_deviation": 0.12364483590154196, "minimum": 0.33276323460749463, "maximum": 0.6996232857572646, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.92906377650886, "standard_deviation": 0.008859962606899436, "minimum": 5.915165396611336, "maximum": 5.93987653811012, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.015368813318803716, "standard_deviation": 0.0010013903799333372, "minimum": 0.013587905135095925, "maximum": 0.017080680716990322, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": 0.09517737813737633, "standard_deviation": 0.11053805606211964, "minimum": -0.05647098108301214, "maximum": 0.2696733503057731, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9651826345147606, "standard_deviation": 0.004195933848135954, "minimum": 0.9590932501299925, "maximum": 0.9715187460457896, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.773397942739394, "standard_deviation": 0.04646264057937424, "minimum": 1.7135117794849164, "maximum": 1.8320871208120795, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4512494180318726, "standard_deviation": 0.16385011557183196, "minimum": 0.22460437324845292, "maximum": 0.6733260926010405, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.20119567490335294, "standard_deviation": 0.01148781894706896, "minimum": 0.18340039293223825, "maximum": 0.21572819590521314, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9889677528131389, "standard_deviation": 0.0014028880501627309, "minimum": 0.987157782279301, "maximum": 0.9906664586607994, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.9421248080819882, "standard_deviation": 0.03954153351330675, "minimum": 0.8980779332056866, "maximum": 1.0008626115380004, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7024021850373656, "standard_deviation": 0.2520971852883348, "minimum": 0.46796260858685157, "maximum": 1.1683802939429964, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.10880010750324513, "standard_deviation": 0.006820520397180816, "minimum": 0.10193003516336485, "maximum": 0.12208522012356209, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "method": "D", "status": "measured", "mos": {"status": "measured", "value": 2.921024799346924, "predicted_mos": 2.921024799346924, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "fe3b8d3586779b869ac955894eca90a943dd947c3246e7e9e1744add3c593a30", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 9.908447700086981}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7509932188687405, "全帯域_10ms_rms_envelope_nrmse": 0.19737342863875743, "全帯域_10ms_envelope_correlation": 0.966478380124814, "全帯域_10ms_modulation_mae_db": 0.5863177027141763, "全帯域_40ms_log_rms_mae_db": 0.9670103933931705, "全帯域_40ms_rms_envelope_nrmse": 0.10849016566820166, "全帯域_40ms_envelope_correlation": 0.9889337537841091, "全帯域_40ms_modulation_mae_db": 0.7103101771284778, "300–1000 Hz_10ms_log_rms_mae_db": 2.543628749320293, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3318212921202283, "300–1000 Hz_10ms_envelope_correlation": 0.9289873172803824, "300–1000 Hz_10ms_modulation_mae_db": 0.8733307747233162, "300–1000 Hz_40ms_log_rms_mae_db": 2.0299041200151033, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.24823688553633447, "300–1000 Hz_40ms_envelope_correlation": 0.9601944166893449, "300–1000 Hz_40ms_modulation_mae_db": 1.2904379528570582, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5498271084484483, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1863303609073616, "1000–3000 Hz_10ms_envelope_correlation": 0.9791936732275698, "1000–3000 Hz_10ms_modulation_mae_db": 0.27808481205138535, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0303937446634372, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10010298040286614, "1000–3000 Hz_40ms_envelope_correlation": 0.9941965117135552, "1000–3000 Hz_40ms_modulation_mae_db": 0.44629173494584135, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4186651255857554, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24349955673401522, "3000–6000 Hz_10ms_envelope_correlation": 0.9632116867148142, "3000–6000 Hz_10ms_modulation_mae_db": 0.9372396617565851, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9551961337509007, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14462539194895532, "3000–6000 Hz_40ms_envelope_correlation": 0.9871282223608767, "3000–6000 Hz_40ms_modulation_mae_db": 1.3662677636541893, "mr_stft_db": 5.9845695637687335, "band_mae_db": 0.5632219697266633, "rms_gain_error_db": 0.11847352073206807, "output_peak": 0.014186597797462687}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8037986505929902, "全帯域_10ms_rms_envelope_nrmse": 0.2030835539817062, "全帯域_10ms_envelope_correlation": 0.9636576936019963, "全帯域_10ms_modulation_mae_db": 0.609654388109672, "全帯域_40ms_log_rms_mae_db": 0.8526212202182386, "全帯域_40ms_rms_envelope_nrmse": 0.09531284765978149, "全帯域_40ms_envelope_correlation": 0.9912098740125478, "全帯域_40ms_modulation_mae_db": 0.5078378770126825, "300–1000 Hz_10ms_log_rms_mae_db": 2.448764892712035, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.29788385998608496, "300–1000 Hz_10ms_envelope_correlation": 0.9411821839077523, "300–1000 Hz_10ms_modulation_mae_db": 0.7287489374693527, "300–1000 Hz_40ms_log_rms_mae_db": 1.8397935574308173, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.21130253581326353, "300–1000 Hz_40ms_envelope_correlation": 0.9706035094007374, "300–1000 Hz_40ms_modulation_mae_db": 0.5787973567799586, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5318710335292671, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2161419203453625, "1000–3000 Hz_10ms_envelope_correlation": 0.9708863535026123, "1000–3000 Hz_10ms_modulation_mae_db": 0.7522769806664308, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0726352416861467, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10145721435512119, "1000–3000 Hz_40ms_envelope_correlation": 0.9934857996213269, "1000–3000 Hz_40ms_modulation_mae_db": 0.7401738767929352, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4036515121798239, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.22526946026374448, "3000–6000 Hz_10ms_envelope_correlation": 0.9696832557840898, "3000–6000 Hz_10ms_modulation_mae_db": 0.8450732622261975, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8913551385489262, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12179585454495777, "3000–6000 Hz_40ms_envelope_correlation": 0.9907763907952861, "3000–6000 Hz_40ms_modulation_mae_db": 0.8733931429466528, "mr_stft_db": 5.979152290968341, "band_mae_db": 0.7401774616362761, "rms_gain_error_db": -0.06008308751201668, "output_peak": 0.013503897550018186}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.722248862683111, "全帯域_10ms_rms_envelope_nrmse": 0.19446856271655127, "全帯域_10ms_envelope_correlation": 0.9664709550677001, "全帯域_10ms_modulation_mae_db": 0.3290807482628952, "全帯域_40ms_log_rms_mae_db": 0.9315781659112822, "全帯域_40ms_rms_envelope_nrmse": 0.10218223122681587, "全帯域_40ms_envelope_correlation": 0.9897935593688779, "全帯域_40ms_modulation_mae_db": 0.5956890542711575, "300–1000 Hz_10ms_log_rms_mae_db": 2.4543259479672823, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.30635313677310627, "300–1000 Hz_10ms_envelope_correlation": 0.9279406947761755, "300–1000 Hz_10ms_modulation_mae_db": 0.9915374211209391, "300–1000 Hz_40ms_log_rms_mae_db": 1.8691873182602639, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.21292940327482612, "300–1000 Hz_40ms_envelope_correlation": 0.9627505320947333, "300–1000 Hz_40ms_modulation_mae_db": 2.0062760600235996, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5151878364155607, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20362726549548152, "1000–3000 Hz_10ms_envelope_correlation": 0.9744162518855063, "1000–3000 Hz_10ms_modulation_mae_db": 0.39860751032295577, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0248965010627662, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09242288838864918, "1000–3000 Hz_40ms_envelope_correlation": 0.9947693754223824, "1000–3000 Hz_40ms_modulation_mae_db": 0.4815096409338377, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3878718110665493, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2498423713564119, "3000–6000 Hz_10ms_envelope_correlation": 0.9608651955170638, "3000–6000 Hz_10ms_modulation_mae_db": 0.8507165913327183, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9429457067760638, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1286169674573221, "3000–6000 Hz_40ms_envelope_correlation": 0.9895660226057672, "3000–6000 Hz_40ms_modulation_mae_db": 1.5035867897650341, "mr_stft_db": 5.994097987503945, "band_mae_db": 0.4437563476633098, "rms_gain_error_db": -0.06527428135199508, "output_peak": 0.018005124366914427}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6909633610185548, "全帯域_10ms_rms_envelope_nrmse": 0.20073686075535244, "全帯域_10ms_envelope_correlation": 0.9641366519045914, "全帯域_10ms_modulation_mae_db": 0.4299601064734416, "全帯域_40ms_log_rms_mae_db": 0.8607801991778754, "全帯域_40ms_rms_envelope_nrmse": 0.10052458824675006, "全帯域_40ms_envelope_correlation": 0.9901617246425581, "全帯域_40ms_modulation_mae_db": 0.5296315009366862, "300–1000 Hz_10ms_log_rms_mae_db": 2.591149517086126, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3108496201039081, "300–1000 Hz_10ms_envelope_correlation": 0.9362751246541834, "300–1000 Hz_10ms_modulation_mae_db": 0.6531394676025625, "300–1000 Hz_40ms_log_rms_mae_db": 2.0705111221340986, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.22101070682235227, "300–1000 Hz_40ms_envelope_correlation": 0.968265757977819, "300–1000 Hz_40ms_modulation_mae_db": 1.0299052529450894, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5173258600902992, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1992587120066963, "1000–3000 Hz_10ms_envelope_correlation": 0.9745038450188277, "1000–3000 Hz_10ms_modulation_mae_db": 0.6056326384154707, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9328402122428595, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10281768993595304, "1000–3000 Hz_40ms_envelope_correlation": 0.993322282059351, "1000–3000 Hz_40ms_modulation_mae_db": 0.3256442547134181, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4148212997974936, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.22908612009301288, "3000–6000 Hz_10ms_envelope_correlation": 0.9672929302933694, "3000–6000 Hz_10ms_modulation_mae_db": 0.9673518364954444, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9535822264991928, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11777672565152879, "3000–6000 Hz_40ms_envelope_correlation": 0.9910376499493884, "3000–6000 Hz_40ms_modulation_mae_db": 1.381188512008592, "mr_stft_db": 5.970643970383056, "band_mae_db": 0.4548265923080181, "rms_gain_error_db": -0.11461674053940142, "output_peak": 0.014051439871973066}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.668676305816319, "全帯域_10ms_rms_envelope_nrmse": 0.1756420914478044, "全帯域_10ms_envelope_correlation": 0.9728131380403857, "全帯域_10ms_modulation_mae_db": 0.4264122155208532, "全帯域_40ms_log_rms_mae_db": 0.8051199313214942, "全帯域_40ms_rms_envelope_nrmse": 0.08840864587464423, "全帯域_40ms_envelope_correlation": 0.9924081787132749, "全帯域_40ms_modulation_mae_db": 0.7046887974609765, "300–1000 Hz_10ms_log_rms_mae_db": 2.5831026520471134, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3029027398292706, "300–1000 Hz_10ms_envelope_correlation": 0.9317592095301189, "300–1000 Hz_10ms_modulation_mae_db": 0.7561180390060837, "300–1000 Hz_40ms_log_rms_mae_db": 2.011883110081525, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19661097588672424, "300–1000 Hz_40ms_envelope_correlation": 0.9711516721098072, "300–1000 Hz_40ms_modulation_mae_db": 0.8847619615891936, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4855359614206898, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1540045282537163, "1000–3000 Hz_10ms_envelope_correlation": 0.9849211280298847, "1000–3000 Hz_10ms_modulation_mae_db": 0.37323950535513833, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9620641104735217, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07658822936786695, "1000–3000 Hz_40ms_envelope_correlation": 0.9962265171552113, "1000–3000 Hz_40ms_modulation_mae_db": 0.7523094988991255, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3894622650781323, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2630917693033837, "3000–6000 Hz_10ms_envelope_correlation": 0.9570437735909815, "3000–6000 Hz_10ms_modulation_mae_db": 0.7036066673469549, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9514150739005013, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.15344343989989304, "3000–6000 Hz_40ms_envelope_correlation": 0.9862011389823667, "3000–6000 Hz_40ms_modulation_mae_db": 1.1768278159728915, "mr_stft_db": 5.975943863828648, "band_mae_db": 0.37639888585029996, "rms_gain_error_db": 0.00926113242565647, "output_peak": 0.01610314963114345}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7520120871081657, "全帯域_10ms_rms_envelope_nrmse": 0.19163605463308953, "全帯域_10ms_envelope_correlation": 0.9684291360376271, "全帯域_10ms_modulation_mae_db": 0.5450533595239425, "全帯域_40ms_log_rms_mae_db": 0.8308149216333622, "全帯域_40ms_rms_envelope_nrmse": 0.08918681648391487, "全帯域_40ms_envelope_correlation": 0.9926181167192116, "全帯域_40ms_modulation_mae_db": 0.5738462154231249, "300–1000 Hz_10ms_log_rms_mae_db": 2.513987662021218, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3370574521079373, "300–1000 Hz_10ms_envelope_correlation": 0.9097159706580773, "300–1000 Hz_10ms_modulation_mae_db": 0.6433890915862981, "300–1000 Hz_40ms_log_rms_mae_db": 1.9899404514780497, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2138284174034108, "300–1000 Hz_40ms_envelope_correlation": 0.9617387512109228, "300–1000 Hz_40ms_modulation_mae_db": 1.250521275231901, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5321353659641428, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20417312607768748, "1000–3000 Hz_10ms_envelope_correlation": 0.9758906728893533, "1000–3000 Hz_10ms_modulation_mae_db": 0.5891059219629459, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0202581595718607, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10799591251661887, "1000–3000 Hz_40ms_envelope_correlation": 0.9939239266987151, "1000–3000 Hz_40ms_modulation_mae_db": 0.6024306174204761, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3692660662859517, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2535271424884058, "3000–6000 Hz_10ms_envelope_correlation": 0.9598189130094366, "3000–6000 Hz_10ms_modulation_mae_db": 0.9042476787435335, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8963040018019599, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1411644641302153, "3000–6000 Hz_40ms_envelope_correlation": 0.9877613559725043, "3000–6000 Hz_40ms_modulation_mae_db": 1.4291259157028504, "mr_stft_db": 5.974930947559835, "band_mae_db": 0.46518237381182953, "rms_gain_error_db": 0.12518069095194786, "output_peak": 0.014098924205269222}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7455910895445728, "全帯域_10ms_rms_envelope_nrmse": 0.19596027368485938, "全帯域_10ms_envelope_correlation": 0.9669875588247288, "全帯域_10ms_modulation_mae_db": 0.48933084168756064, "全帯域_40ms_log_rms_mae_db": 0.8980625771859992, "全帯域_40ms_rms_envelope_nrmse": 0.09167257691949965, "全帯域_40ms_envelope_correlation": 0.9921569576275091, "全帯域_40ms_modulation_mae_db": 0.45168853125427316, "300–1000 Hz_10ms_log_rms_mae_db": 2.541039275041499, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3185899867211537, "300–1000 Hz_10ms_envelope_correlation": 0.9247622909019194, "300–1000 Hz_10ms_modulation_mae_db": 0.833233149973351, "300–1000 Hz_40ms_log_rms_mae_db": 1.9670021428858957, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2135681688170502, "300–1000 Hz_40ms_envelope_correlation": 0.9647765746173754, "300–1000 Hz_40ms_modulation_mae_db": 0.9952062207260512, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4963209178214942, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1914861155487167, "1000–3000 Hz_10ms_envelope_correlation": 0.976700375041929, "1000–3000 Hz_10ms_modulation_mae_db": 0.7954163104895778, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9703864932600729, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09612283517065473, "1000–3000 Hz_40ms_envelope_correlation": 0.9940553744198818, "1000–3000 Hz_40ms_modulation_mae_db": 0.32252971915240497, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3829072141714052, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.23569957366878527, "3000–6000 Hz_10ms_envelope_correlation": 0.9655038001438382, "3000–6000 Hz_10ms_modulation_mae_db": 0.7397934395368164, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9188346830311503, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1350099362541549, "3000–6000 Hz_40ms_envelope_correlation": 0.9878697987605276, "3000–6000 Hz_40ms_modulation_mae_db": 1.353454511698151, "mr_stft_db": 5.985853822594531, "band_mae_db": 0.30262208187377865, "rms_gain_error_db": 0.12029871171299814, "output_peak": 0.01416609384156172}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6950057443669322, "全帯域_10ms_rms_envelope_nrmse": 0.19320284401339807, "全帯域_10ms_envelope_correlation": 0.9674897980707291, "全帯域_10ms_modulation_mae_db": 0.5198000789488739, "全帯域_40ms_log_rms_mae_db": 0.8693066716566029, "全帯域_40ms_rms_envelope_nrmse": 0.09398527863809733, "全帯域_40ms_envelope_correlation": 0.9915242263052708, "全帯域_40ms_modulation_mae_db": 0.5854372091045709, "300–1000 Hz_10ms_log_rms_mae_db": 2.5721598518395443, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.29632750538054364, "300–1000 Hz_10ms_envelope_correlation": 0.941009360346199, "300–1000 Hz_10ms_modulation_mae_db": 0.6185152757310619, "300–1000 Hz_40ms_log_rms_mae_db": 2.0827270642765967, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20671492902021024, "300–1000 Hz_40ms_envelope_correlation": 0.971840709442796, "300–1000 Hz_40ms_modulation_mae_db": 0.618528727832691, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5460077855780519, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1956695205177933, "1000–3000 Hz_10ms_envelope_correlation": 0.9755502784388767, "1000–3000 Hz_10ms_modulation_mae_db": 0.5298777500838795, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0600098488586533, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09756686655239644, "1000–3000 Hz_40ms_envelope_correlation": 0.9938370413534148, "1000–3000 Hz_40ms_modulation_mae_db": 0.6507387750521055, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3946685120983053, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2548369096484115, "3000–6000 Hz_10ms_envelope_correlation": 0.9638392895134495, "3000–6000 Hz_10ms_modulation_mae_db": 0.9461698901065899, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9339732743988406, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.15126316316692962, "3000–6000 Hz_40ms_envelope_correlation": 0.9877522276209401, "3000–6000 Hz_40ms_modulation_mae_db": 1.1535219974855095, "mr_stft_db": 5.97977005264202, "band_mae_db": 0.6545575261995268, "rms_gain_error_db": 0.07350860286427936, "output_peak": 0.013663897044291863}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.179183341341919, "spectral_convergence": 0.6791865272133423, "spectral_convergence_status": "ok", "amplitude_floor": 3.772168230462137e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.842076500878915, "spectral_convergence": 0.633299197860805, "spectral_convergence_status": "ok", "amplitude_floor": 1.9872090073495523e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.932448849085367, "spectral_convergence": 0.6685882565256587, "spectral_convergence_status": "ok", "amplitude_floor": 8.414272539865191e-09}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0228756868362371e-07, "output_power": 9.261457575830094e-08, "delta_db": -0.4314351411784078, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 3.789702976182104e-08, "output_power": 5.433220582577756e-08, "delta_db": 1.5645216445197383, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.1288069701978556e-08, "output_power": 5.641155510427431e-08, "delta_db": 0.4135171804487814, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.8766557699122943e-07, "output_power": 2.980911372827126e-07, "delta_db": 0.15461168074283962, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 6.379889954922647e-08, "output_power": 7.03974518339597e-08, "delta_db": 0.4274375158198324, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 5.958002892412794e-08, "output_power": 4.940241572834442e-08, "delta_db": -0.8135252370924552, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.518375636706213e-08, "output_power": 3.408722646090478e-08, "delta_db": -0.1375053882845882, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.5632219697266633, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.11847352073206807, "pitch": null, "output_rms_dbfs": -61.835355975939464, "output_peak": 0.014186597797462687, "reference_rms_dbfs": -61.95382949667153, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.9845695637687335}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.024359572707954e-06, "log_rms_mae_db": 1.7509932188687405, "rms_envelope_nrmse": 0.19737342863875743, "envelope_correlation": 0.966478380124814, "rms_gain_error_db": 0.11844370519656736, "reference_mean_power": 6.381840334285008e-07, "output_mean_power": 6.558285292214017e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.836855714370683e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.3707173350027986e-08, "output_power": 4.637022841581292e-08, "reference_active": true, "delta_db": -0.6379306052444433}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8108171988414046e-08, "output_power": 2.0631402333413817e-08, "reference_active": true, "delta_db": 0.5665413763039508}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5077869163047108e-08, "output_power": 1.3270639688100032e-08, "reference_active": true, "delta_db": -0.5544811265941346}], "active_band_count": 3, "active_band_mae_db": 0.5863177027141763}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.11576902582373e-06, "log_rms_mae_db": 0.9670103933931705, "rms_envelope_nrmse": 0.10849016566820166, "envelope_correlation": 0.9889337537841091, "rms_gain_error_db": 0.11831097139420273, "reference_mean_power": 6.411560082425094e-07, "output_mean_power": 6.588625359378255e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.631066262241422e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.1382633554527724e-08, "output_power": 4.279087762717454e-08, "reference_active": true, "delta_db": -0.7946516592162021}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.770301277631505e-09, "output_power": 1.0597543980754735e-08, "reference_active": true, "delta_db": 0.35297271747400105}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.622703760150784e-10, "output_power": 7.673023009649524e-10, "reference_active": true, "delta_db": -0.9833061546952302}], "active_band_count": 3, "active_band_mae_db": 0.7103101771284778}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.2104964131871903e-06, "log_rms_mae_db": 2.543628749320293, "rms_envelope_nrmse": 0.3318212921202283, "envelope_correlation": 0.9289873172803824, "rms_gain_error_db": 0.933931611464498, "reference_mean_power": 5.88463135957351e-08, "output_mean_power": 7.2964636458906e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.019969626272171e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.669218221395915e-09, "output_power": 6.591173550748706e-09, "reference_active": true, "delta_db": 0.6543957278621921}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.997554044063276e-09, "output_power": 4.8570709616583675e-09, "reference_active": true, "delta_db": -0.12383050772230078}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.156278331683346e-09, "output_power": 3.3741139336562057e-09, "reference_active": true, "delta_db": -1.8417660885854557}], "active_band_count": 3, "active_band_mae_db": 0.8733307747233162}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.1954716835574657e-06, "log_rms_mae_db": 2.0299041200151033, "rms_envelope_nrmse": 0.24823688553633447, "envelope_correlation": 0.9601944166893449, "rms_gain_error_db": 0.9333760778473082, "reference_mean_power": 5.913056575013843e-08, "output_mean_power": 7.33077081274004e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.690703802813698e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.971603141472601e-09, "output_power": 6.963711478907865e-09, "reference_active": true, "delta_db": -0.004918878352811418}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1694216774888265e-09, "output_power": 2.4421165765027266e-09, "reference_active": true, "delta_db": -1.132136324693393}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5180140726512066e-10, "output_power": 2.4072528733896014e-10, "reference_active": true, "delta_db": -2.7342586555249704}], "active_band_count": 3, "active_band_mae_db": 1.2904379528570582}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.597874045564372e-06, "log_rms_mae_db": 1.5498271084484483, "rms_envelope_nrmse": 0.1863303609073616, "envelope_correlation": 0.9791936732275698, "rms_gain_error_db": 0.27518124703444286, "reference_mean_power": 3.0019112356646434e-07, "output_mean_power": 3.1982762349969997e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1704248469151792e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.917571308133626e-08, "output_power": 4.262800597829629e-08, "reference_active": true, "delta_db": -0.6205564819040305}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.373644839895842e-09, "output_power": 6.387738858566427e-09, "reference_active": true, "delta_db": 0.009592936267425238}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.9583662339560916e-09, "output_power": 4.148837979671795e-09, "reference_active": true, "delta_db": 0.20410501798270045}], "active_band_count": 3, "active_band_mae_db": 0.27808481205138535}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6957143825373563e-06, "log_rms_mae_db": 1.0303937446634372, "rms_envelope_nrmse": 0.10010298040286614, "envelope_correlation": 0.9941965117135552, "rms_gain_error_db": 0.27516938028468224, "reference_mean_power": 3.016958800523271e-07, "output_mean_power": 3.2142993282983744e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.1236901446499244e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.541853281346178e-08, "output_power": 3.923462024127445e-08, "reference_active": true, "delta_db": -0.6356364743917484}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5898805602165613e-09, "output_power": 3.742261109886906e-09, "reference_active": true, "delta_db": 0.18054087075954792}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.01076242530766e-10, "output_power": 2.6693572528043924e-10, "reference_active": true, "delta_db": -0.5226978596862276}], "active_band_count": 3, "active_band_mae_db": 0.44629173494584135}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.0353597876360997e-06, "log_rms_mae_db": 1.4186651255857554, "rms_envelope_nrmse": 0.24349955673401522, "envelope_correlation": 0.9632116867148142, "rms_gain_error_db": -0.38286278995704554, "reference_mean_power": 5.358047115055493e-08, "output_mean_power": 4.9059175964211104e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.7539255872910824e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.2466604070258255e-09, "output_power": 5.603136233401906e-09, "reference_active": true, "delta_db": 0.28548226775557217}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.042126892400446e-09, "output_power": 3.0867454866673024e-09, "reference_active": true, "delta_db": 0.0632349653455453}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.488177427019359e-09, "output_power": 1.4111759636844098e-09, "reference_active": true, "delta_db": -2.463001752168638}], "active_band_count": 3, "active_band_mae_db": 0.9372396617565851}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.4732086031870805e-06, "log_rms_mae_db": 0.9551961337509007, "rms_envelope_nrmse": 0.14462539194895532, "envelope_correlation": 0.9871282223608767, "rms_gain_error_db": -0.38290356435691075, "reference_mean_power": 5.3847422411461674e-08, "output_mean_power": 4.930313811347079e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.6457241300858348e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.316794721929917e-09, "output_power": 6.221014659783373e-09, "reference_active": true, "delta_db": -0.06635539017761447}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0867827772247918e-09, "output_power": 1.7303188850711232e-09, "reference_active": true, "delta_db": -0.8135109592643465}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.2900642849732037e-10, "output_power": 1.0913246870049811e-10, "reference_active": true, "delta_db": -3.2189369415206066}], "active_band_count": 3, "active_band_mae_db": 1.3662677636541893}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.4633148204227246, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "c78d959c1a3eeeb77200b6f299ae0a6388c50051b1b366a7e218e925a8b1f461", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.97650782225432, "standard_deviation": 0.0041287122151956995, "minimum": 0.9708863535026123, "maximum": 0.9849211280298847, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.5217764836584942, "standard_deviation": 0.022702358374430652, "minimum": 1.4855359614206898, "maximum": 1.5498271084484483, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.540280178668473, "standard_deviation": 0.18264733360623686, "minimum": 0.27808481205138535, "maximum": 0.7954163104895778, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.19383644364410196, "standard_deviation": 0.01844470290208457, "minimum": 0.1540045282537163, "maximum": 0.2161419203453625, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9942271035554798, "standard_deviation": 0.0009207480241502111, "minimum": 0.993322282059351, "maximum": 0.9962265171552113, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.009185538977415, "standard_deviation": 0.04925531788643602, "minimum": 0.9328402122428595, "maximum": 1.0726352416861467, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.540203514738768, "standard_deviation": 0.17185928664841285, "minimum": 0.32252971915240497, "maximum": 0.7523094988991255, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09688432708626582, "standard_deviation": 0.009432655288456755, "minimum": 0.07658822936786695, "maximum": 0.10799591251661887, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9634073555708803, "standard_deviation": 0.004122052554953053, "minimum": 0.9570437735909815, "maximum": 0.9696832557840898, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.3951642257829273, "standard_deviation": 0.016551276515497523, "minimum": 1.3692660662859517, "maximum": 1.4186651255857554, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.861774878443105, "standard_deviation": 0.09714919931164298, "minimum": 0.7036066673469549, "maximum": 0.9673518364954444, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.24435661294452132, "standard_deviation": 0.013353550004283713, "minimum": 0.22526946026374448, "maximum": 0.2630917693033837, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9885116008809571, "standard_deviation": 0.0017495059659006684, "minimum": 0.9862011389823667, "maximum": 0.9910376499493884, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.930450779838442, "standard_deviation": 0.02559250582451453, "minimum": 0.8913551385489262, "maximum": 0.9551961337509007, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.279670806154234, "standard_deviation": 0.20258185383407173, "minimum": 0.8733931429466528, "maximum": 1.5035867897650341, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1367119928817446, "standard_deviation": 0.013221120669770152, "minimum": 0.11777672565152879, "maximum": 0.15344343989989304, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.930204019006851, "standard_deviation": 0.010229704485118559, "minimum": 0.9097159706580773, "maximum": 0.9411821839077523, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.531019818504389, "standard_deviation": 0.05505581082520072, "minimum": 2.448764892712035, "maximum": 2.591149517086126, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7622515196516206, "standard_deviation": 0.12972657205778793, "minimum": 0.6185152757310619, "maximum": 0.9915374211209391, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.31272319912777913, "standard_deviation": 0.015216844021987485, "minimum": 0.29632750538054364, "maximum": 0.3370574521079373, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.966415240442942, "standard_deviation": 0.004621672911230305, "minimum": 0.9601944166893449, "maximum": 0.971840709442796, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.982618610820294, "standard_deviation": 0.08815754057707684, "minimum": 1.8397935574308173, "maximum": 2.0827270642765967, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.081804350998193, "standard_deviation": 0.45407678962877973, "minimum": 0.5787973567799586, "maximum": 2.0062760600235996, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.21552525282177148, "standard_deviation": 0.01496086322925743, "minimum": 0.19661097588672424, "maximum": 0.24823688553633447, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.5000929048837128, "standard_deviation": 0.144529641376771, "minimum": 0.30262208187377865, "maximum": 0.7401774616362761, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.980620312406138, "standard_deviation": 0.007380257580494452, "minimum": 5.970643970383056, "maximum": 5.994097987503945, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.014722390538579327, "standard_deviation": 0.0015456573101227924, "minimum": 0.013503897550018186, "maximum": 0.018005124366914427, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": 0.025843568660442094, "standard_deviation": 0.09660806673250606, "minimum": -0.11461674053940142, "maximum": 0.12518069095194786, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9670579139590716, "standard_deviation": 0.0028276688687355013, "minimum": 0.9636576936019963, "maximum": 0.9728131380403857, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.7286611649999233, "standard_deviation": 0.04337438841877788, "minimum": 1.668676305816319, "maximum": 1.8037986505929902, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4919511801551769, "standard_deviation": 0.0933705224364644, "minimum": 0.3290807482628952, "maximum": 0.609654388109672, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.1940129587339398, "standard_deviation": 0.008337296999802988, "minimum": 0.1756420914478044, "maximum": 0.2030835539817062, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9911007988966699, "standard_deviation": 0.001341905624374008, "minimum": 0.9889337537841091, "maximum": 0.9926181167192116, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8769117600622531, "standard_deviation": 0.05310450190866461, "minimum": 0.8051199313214942, "maximum": 0.9670103933931705, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5823911703239937, "standard_deviation": 0.09024099982536844, "minimum": 0.45168853125427316, "maximum": 0.7103101771284778, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.09622039383971315, "standard_deviation": 0.006985838028363767, "minimum": 0.08840864587464423, "maximum": 0.10849016566820166, "valid_count": 8, "planned_count": 8}}}, {"case": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "method": "E", "status": "measured", "mos": {"status": "measured", "value": 2.8208303451538086, "predicted_mos": 2.8208303451538086, "model": "UTMOSv2", "language": "ja", "style": "whisper", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 144000, "input_sample_rate": 24000, "input_seconds": 6.0, "input_float32_sha256": "fbaba708a2c371ac56d85e4aea9414f60da943b663f52f4d154d16b03908495a", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 10.119563499931246}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7548187977831595, "全帯域_10ms_rms_envelope_nrmse": 0.1923438774099815, "全帯域_10ms_envelope_correlation": 0.9670078224241982, "全帯域_10ms_modulation_mae_db": 0.5640779013695498, "全帯域_40ms_log_rms_mae_db": 0.9044238658118355, "全帯域_40ms_rms_envelope_nrmse": 0.08990314673007356, "全帯域_40ms_envelope_correlation": 0.9923413328309502, "全帯域_40ms_modulation_mae_db": 0.9343332207223156, "300–1000 Hz_10ms_log_rms_mae_db": 2.312424798065714, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2736387454730204, "300–1000 Hz_10ms_envelope_correlation": 0.9460884302465113, "300–1000 Hz_10ms_modulation_mae_db": 0.8278701801955576, "300–1000 Hz_40ms_log_rms_mae_db": 1.6137000344427066, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1658659499156304, "300–1000 Hz_40ms_envelope_correlation": 0.9803097647280306, "300–1000 Hz_40ms_modulation_mae_db": 1.042272840269407, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3595514364765475, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16170564414374106, "1000–3000 Hz_10ms_envelope_correlation": 0.9835697565981524, "1000–3000 Hz_10ms_modulation_mae_db": 0.3686103198968967, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7997825361424044, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08388575559404265, "1000–3000 Hz_40ms_envelope_correlation": 0.9959922954465967, "1000–3000 Hz_40ms_modulation_mae_db": 0.992106080128558, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2482409126377625, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24323833758720287, "3000–6000 Hz_10ms_envelope_correlation": 0.9649002432016226, "3000–6000 Hz_10ms_modulation_mae_db": 0.8950995725081056, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7129170756187816, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12909144362817448, "3000–6000 Hz_40ms_envelope_correlation": 0.9898272114791996, "3000–6000 Hz_40ms_modulation_mae_db": 1.1445670486690318, "mr_stft_db": 5.907247346811708, "band_mae_db": 0.4677324708002635, "rms_gain_error_db": -0.16742139849638943, "output_peak": 0.016213082420562182}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7263080640823676, "全帯域_10ms_rms_envelope_nrmse": 0.20029665761164783, "全帯域_10ms_envelope_correlation": 0.9682239660871286, "全帯域_10ms_modulation_mae_db": 0.6293843706237902, "全帯域_40ms_log_rms_mae_db": 0.8785312542307914, "全帯域_40ms_rms_envelope_nrmse": 0.12286075261352693, "全帯域_40ms_envelope_correlation": 0.9881359015615894, "全帯域_40ms_modulation_mae_db": 0.9061376118832585, "300–1000 Hz_10ms_log_rms_mae_db": 2.3566919878387846, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2980398611620395, "300–1000 Hz_10ms_envelope_correlation": 0.9369050625211303, "300–1000 Hz_10ms_modulation_mae_db": 1.007193502531577, "300–1000 Hz_40ms_log_rms_mae_db": 1.8201354224147661, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2038899408750847, "300–1000 Hz_40ms_envelope_correlation": 0.9697987033356517, "300–1000 Hz_40ms_modulation_mae_db": 1.3941260892244498, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3823371942313825, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19773343380464325, "1000–3000 Hz_10ms_envelope_correlation": 0.9802822308629076, "1000–3000 Hz_10ms_modulation_mae_db": 0.23710599265265322, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7977607171103676, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.13147697554179394, "1000–3000 Hz_40ms_envelope_correlation": 0.9929872321141416, "1000–3000 Hz_40ms_modulation_mae_db": 0.27373954963072433, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2778977362690034, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24365002861334992, "3000–6000 Hz_10ms_envelope_correlation": 0.9645081196366427, "3000–6000 Hz_10ms_modulation_mae_db": 1.0849553555793818, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7517237846834388, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13451816345600567, "3000–6000 Hz_40ms_envelope_correlation": 0.9887126593519427, "3000–6000 Hz_40ms_modulation_mae_db": 1.54301483197579, "mr_stft_db": 5.919324995533674, "band_mae_db": 0.5894496188507021, "rms_gain_error_db": 0.35054666373785565, "output_peak": 0.01782986205192422}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.647349199875526, "全帯域_10ms_rms_envelope_nrmse": 0.16873278769147776, "全帯域_10ms_envelope_correlation": 0.9758546344836542, "全帯域_10ms_modulation_mae_db": 0.49110125272515304, "全帯域_40ms_log_rms_mae_db": 0.8292344491571384, "全帯域_40ms_rms_envelope_nrmse": 0.08119062402687872, "全帯域_40ms_envelope_correlation": 0.9940934652423401, "全帯域_40ms_modulation_mae_db": 0.46982355299725426, "300–1000 Hz_10ms_log_rms_mae_db": 2.341171244430936, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3043631231581506, "300–1000 Hz_10ms_envelope_correlation": 0.9471110139589641, "300–1000 Hz_10ms_modulation_mae_db": 0.5705944507365285, "300–1000 Hz_40ms_log_rms_mae_db": 1.7616470054817217, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.22186315354208339, "300–1000 Hz_40ms_envelope_correlation": 0.9752720726209029, "300–1000 Hz_40ms_modulation_mae_db": 0.6204043516372928, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4006301195329516, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16709256578371554, "1000–3000 Hz_10ms_envelope_correlation": 0.9821249848601576, "1000–3000 Hz_10ms_modulation_mae_db": 0.28409031331657314, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8170248486169327, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08027737692180012, "1000–3000 Hz_40ms_envelope_correlation": 0.9958663384132577, "1000–3000 Hz_40ms_modulation_mae_db": 0.5576835818869972, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2482802141642093, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.21474655598216477, "3000–6000 Hz_10ms_envelope_correlation": 0.9729156860906619, "3000–6000 Hz_10ms_modulation_mae_db": 0.6543290954352767, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7065213700834605, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11354675781589466, "3000–6000 Hz_40ms_envelope_correlation": 0.9923896139851224, "3000–6000 Hz_40ms_modulation_mae_db": 0.9869701945091004, "mr_stft_db": 5.914694151124256, "band_mae_db": 0.5606993621768691, "rms_gain_error_db": 0.16679785568966352, "output_peak": 0.015047439725355572}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6859752168388757, "全帯域_10ms_rms_envelope_nrmse": 0.1780414355694681, "全帯域_10ms_envelope_correlation": 0.9718540485101395, "全帯域_10ms_modulation_mae_db": 0.40229511805598656, "全帯域_40ms_log_rms_mae_db": 0.8212993768491849, "全帯域_40ms_rms_envelope_nrmse": 0.08377806784777399, "全帯域_40ms_envelope_correlation": 0.9931989960748139, "全帯域_40ms_modulation_mae_db": 0.8399370120679558, "300–1000 Hz_10ms_log_rms_mae_db": 2.2309863973924142, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3353717402090139, "300–1000 Hz_10ms_envelope_correlation": 0.9221255943686906, "300–1000 Hz_10ms_modulation_mae_db": 0.7916626805801791, "300–1000 Hz_40ms_log_rms_mae_db": 1.725508106489246, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.22289550911717235, "300–1000 Hz_40ms_envelope_correlation": 0.9654593877006418, "300–1000 Hz_40ms_modulation_mae_db": 0.82011717550352, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3663378612440067, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17019104419683645, "1000–3000 Hz_10ms_envelope_correlation": 0.9816046034864155, "1000–3000 Hz_10ms_modulation_mae_db": 0.3539355953077616, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7845039807804225, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08394776834932643, "1000–3000 Hz_40ms_envelope_correlation": 0.9958301794896925, "1000–3000 Hz_40ms_modulation_mae_db": 0.5447660112513663, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2463914230455568, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.21734893652656298, "3000–6000 Hz_10ms_envelope_correlation": 0.9706147328938818, "3000–6000 Hz_10ms_modulation_mae_db": 0.7221036718149185, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7242476006095312, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11099080952183171, "3000–6000 Hz_40ms_envelope_correlation": 0.9918284676619897, "3000–6000 Hz_40ms_modulation_mae_db": 1.1292890775154747, "mr_stft_db": 5.9017686784017735, "band_mae_db": 0.5452967382278128, "rms_gain_error_db": -0.1026564602809589, "output_peak": 0.01564045478757316}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6651410885386881, "全帯域_10ms_rms_envelope_nrmse": 0.19620684616993095, "全帯域_10ms_envelope_correlation": 0.9656708625618411, "全帯域_10ms_modulation_mae_db": 0.4151129426411613, "全帯域_40ms_log_rms_mae_db": 0.8707933006092402, "全帯域_40ms_rms_envelope_nrmse": 0.10379155196702908, "全帯域_40ms_envelope_correlation": 0.9896921308499793, "全帯域_40ms_modulation_mae_db": 0.5079398881114155, "300–1000 Hz_10ms_log_rms_mae_db": 2.31583280364866, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.30907485093687065, "300–1000 Hz_10ms_envelope_correlation": 0.9258360989198708, "300–1000 Hz_10ms_modulation_mae_db": 1.1305006141464453, "300–1000 Hz_40ms_log_rms_mae_db": 1.73745039221504, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20327249137554523, "300–1000 Hz_40ms_envelope_correlation": 0.9654489845701785, "300–1000 Hz_40ms_modulation_mae_db": 2.3371155122434737, "1000–3000 Hz_10ms_log_rms_mae_db": 1.335700227968051, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17777036972734547, "1000–3000 Hz_10ms_envelope_correlation": 0.9800183356519708, "1000–3000 Hz_10ms_modulation_mae_db": 0.17754604858246106, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7612916091571071, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08904108816884206, "1000–3000 Hz_40ms_envelope_correlation": 0.9955082571180907, "1000–3000 Hz_40ms_modulation_mae_db": 0.6716967831174993, "3000–6000 Hz_10ms_log_rms_mae_db": 1.259391706152736, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.23987398396650422, "3000–6000 Hz_10ms_envelope_correlation": 0.9642536643542392, "3000–6000 Hz_10ms_modulation_mae_db": 1.1583813192784995, "3000–6000 Hz_40ms_log_rms_mae_db": 0.761625749900147, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14272044024669253, "3000–6000 Hz_40ms_envelope_correlation": 0.9875002624504573, "3000–6000 Hz_40ms_modulation_mae_db": 1.7230019983026985, "mr_stft_db": 5.907999566475836, "band_mae_db": 0.36481344946871996, "rms_gain_error_db": -0.18715471993811084, "output_peak": 0.01739905534659156}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7518912604015524, "全帯域_10ms_rms_envelope_nrmse": 0.18407613174210002, "全帯域_10ms_envelope_correlation": 0.9699598595940924, "全帯域_10ms_modulation_mae_db": 0.5085319362029715, "全帯域_40ms_log_rms_mae_db": 0.8618941609562607, "全帯域_40ms_rms_envelope_nrmse": 0.09373230690945525, "全帯域_40ms_envelope_correlation": 0.9920660383296017, "全帯域_40ms_modulation_mae_db": 0.48321396835293057, "300–1000 Hz_10ms_log_rms_mae_db": 2.2699841228238555, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3040267345020439, "300–1000 Hz_10ms_envelope_correlation": 0.932415930703657, "300–1000 Hz_10ms_modulation_mae_db": 0.9625712080619103, "300–1000 Hz_40ms_log_rms_mae_db": 1.6696625331357344, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19925282944462555, "300–1000 Hz_40ms_envelope_correlation": 0.970045646001946, "300–1000 Hz_40ms_modulation_mae_db": 0.6639581696355998, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3529421121998542, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18943947015935256, "1000–3000 Hz_10ms_envelope_correlation": 0.9774363760297036, "1000–3000 Hz_10ms_modulation_mae_db": 0.5538344731590291, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7849879747608421, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10113776302555498, "1000–3000 Hz_40ms_envelope_correlation": 0.994389642183984, "1000–3000 Hz_40ms_modulation_mae_db": 0.9240107290786806, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2399713725370842, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.23244734519765797, "3000–6000 Hz_10ms_envelope_correlation": 0.9681337393563161, "3000–6000 Hz_10ms_modulation_mae_db": 0.8964349656955658, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7197389189338698, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12752562990533972, "3000–6000 Hz_40ms_envelope_correlation": 0.9901893420962907, "3000–6000 Hz_40ms_modulation_mae_db": 1.0110068417215363, "mr_stft_db": 5.910906379243848, "band_mae_db": 0.6287400471425044, "rms_gain_error_db": -0.25733847227763945, "output_peak": 0.015399687450491922}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6955511250035613, "全帯域_10ms_rms_envelope_nrmse": 0.18236126365323221, "全帯域_10ms_envelope_correlation": 0.9706445422183249, "全帯域_10ms_modulation_mae_db": 0.8192874856537861, "全帯域_40ms_log_rms_mae_db": 0.8088548787819171, "全帯域_40ms_rms_envelope_nrmse": 0.08126012622857264, "全帯域_40ms_envelope_correlation": 0.9935580945478898, "全帯域_40ms_modulation_mae_db": 0.7087608007611657, "300–1000 Hz_10ms_log_rms_mae_db": 2.2351511392405023, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.30984530419133244, "300–1000 Hz_10ms_envelope_correlation": 0.9349778507213554, "300–1000 Hz_10ms_modulation_mae_db": 0.7531192235248613, "300–1000 Hz_40ms_log_rms_mae_db": 1.662402449866484, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.21909938134912854, "300–1000 Hz_40ms_envelope_correlation": 0.96695186098712, "300–1000 Hz_40ms_modulation_mae_db": 0.6077982080568486, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3799856844783505, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16895883283248928, "1000–3000 Hz_10ms_envelope_correlation": 0.9817531678315052, "1000–3000 Hz_10ms_modulation_mae_db": 0.8201031908489708, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8042857424617172, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.077415404702572, "1000–3000 Hz_40ms_envelope_correlation": 0.9961091233661618, "1000–3000 Hz_40ms_modulation_mae_db": 0.9142545397863887, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3320361066754862, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24060764727628334, "3000–6000 Hz_10ms_envelope_correlation": 0.9640345296484006, "3000–6000 Hz_10ms_modulation_mae_db": 0.8995158585837121, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7887819968233718, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12776229771003808, "3000–6000 Hz_40ms_envelope_correlation": 0.989125045397505, "3000–6000 Hz_40ms_modulation_mae_db": 1.2986732029679127, "mr_stft_db": 5.912160644459289, "band_mae_db": 0.3889830978320927, "rms_gain_error_db": -0.01992438320676139, "output_peak": 0.016853337660596317}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7147174791931863, "全帯域_10ms_rms_envelope_nrmse": 0.1750467125621308, "全帯域_10ms_envelope_correlation": 0.9727965502279176, "全帯域_10ms_modulation_mae_db": 0.5987647335404369, "全帯域_40ms_log_rms_mae_db": 0.906785811089593, "全帯域_40ms_rms_envelope_nrmse": 0.07948278006625377, "全帯域_40ms_envelope_correlation": 0.9939027327929831, "全帯域_40ms_modulation_mae_db": 0.6589318499862395, "300–1000 Hz_10ms_log_rms_mae_db": 2.282610003736766, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2877817791927667, "300–1000 Hz_10ms_envelope_correlation": 0.9473780917046973, "300–1000 Hz_10ms_modulation_mae_db": 0.7534353152665956, "300–1000 Hz_40ms_log_rms_mae_db": 1.779610821764914, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1947863504021756, "300–1000 Hz_40ms_envelope_correlation": 0.9783221181061108, "300–1000 Hz_40ms_modulation_mae_db": 0.7357405436984252, "1000–3000 Hz_10ms_log_rms_mae_db": 1.346149971620882, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17361948684376, "1000–3000 Hz_10ms_envelope_correlation": 0.9806447144078366, "1000–3000 Hz_10ms_modulation_mae_db": 0.8360708402805418, "1000–3000 Hz_40ms_log_rms_mae_db": 0.835476328577318, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08260741620592207, "1000–3000 Hz_40ms_envelope_correlation": 0.9955257697457028, "1000–3000 Hz_40ms_modulation_mae_db": 0.8770276851709954, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2339956611693952, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.23424380223275695, "3000–6000 Hz_10ms_envelope_correlation": 0.9659138472776488, "3000–6000 Hz_10ms_modulation_mae_db": 0.9986930105381426, "3000–6000 Hz_40ms_log_rms_mae_db": 0.71359612523782, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12709642467147303, "3000–6000 Hz_40ms_envelope_correlation": 0.9904578788494695, "3000–6000 Hz_40ms_modulation_mae_db": 1.6448151392322596, "mr_stft_db": 5.918179995029644, "band_mae_db": 0.5095271026839793, "rms_gain_error_db": -0.10710833019932442, "output_peak": 0.011977878914050338}, "full_scale": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 144000, "output_samples": 144000, "length_delta_samples": 0, "sample_rate": 24000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 120, "hop_samples": 30, "log_magnitude_mae_db": 6.121708720723887, "spectral_convergence": 0.651737823638639, "spectral_convergence_status": "ok", "amplitude_floor": 3.772168230462137e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.724284567265626, "spectral_convergence": 0.6085866517093975, "spectral_convergence_status": "ok", "amplitude_floor": 1.9872090073495523e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.875748752445611, "spectral_convergence": 0.6537159502565698, "spectral_convergence_status": "ok", "amplitude_floor": 8.414272539865191e-09}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 1.0228756868362371e-07, "output_power": 8.282764241300287e-08, "delta_db": -0.9164755592604257, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 3.789702976182104e-08, "output_power": 4.311155244610372e-08, "delta_db": 0.5598848926888214, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.1288069701978556e-08, "output_power": 5.243313249429037e-08, "delta_db": 0.09589450297173084, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.8766557699122943e-07, "output_power": 2.5907545552784017e-07, "delta_db": -0.45461625454283205, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 6.379889954922647e-08, "output_power": 8.210043778519883e-08, "delta_db": 1.0953228516736047, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 5.958002892412794e-08, "output_power": 5.988751787169133e-08, "delta_db": 0.02235603754160173, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.518375636706213e-08, "output_power": 3.414951066922089e-08, "delta_db": -0.12957719692282788, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.4677324708002635, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.16742139849638943, "pitch": null, "output_rms_dbfs": -62.121250895167925, "output_peak": 0.016213082420562182, "reference_rms_dbfs": -61.95382949667153, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.907247346811708}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 24000, "samples": 144000, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 5.024359572707954e-06, "log_rms_mae_db": 1.7548187977831595, "rms_envelope_nrmse": 0.1923438774099815, "envelope_correlation": 0.9670078224241982, "rms_gain_error_db": -0.16728101587101502, "reference_mean_power": 6.381840334285008e-07, "output_mean_power": 6.14069932383295e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.836855714370683e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.3707173350027986e-08, "output_power": 5.410641655499174e-08, "reference_active": true, "delta_db": 0.03216476022475361}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8108171988414046e-08, "output_power": 1.7182156443283e-08, "reference_active": true, "delta_db": -0.22796941737347226}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5077869163047108e-08, "output_power": 1.0842514654087266e-08, "reference_active": true, "delta_db": -1.4320995265104237}], "active_band_count": 3, "active_band_mae_db": 0.5640779013695498}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 4.11576902582373e-06, "log_rms_mae_db": 0.9044238658118355, "rms_envelope_nrmse": 0.08990314673007356, "envelope_correlation": 0.9923413328309502, "rms_gain_error_db": -0.1673547519663654, "reference_mean_power": 6.411560082425094e-07, "output_mean_power": 6.169191352849341e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.631066262241422e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.1382633554527724e-08, "output_power": 5.123289923125221e-08, "reference_active": true, "delta_db": -0.012674267674270184}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.770301277631505e-09, "output_power": 8.384339212958036e-09, "reference_active": true, "delta_db": -0.6643911520930919}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.622703760150784e-10, "output_power": 5.897985381358543e-10, "reference_active": true, "delta_db": -2.125934242399585}], "active_band_count": 3, "active_band_mae_db": 0.9343332207223156}}]}, {"name": "300–1000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [300.0, 1000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.2104964131871903e-06, "log_rms_mae_db": 2.312424798065714, "rms_envelope_nrmse": 0.2736387454730204, "envelope_correlation": 0.9460884302465113, "rms_gain_error_db": 0.5233153403531936, "reference_mean_power": 5.88463135957351e-08, "output_mean_power": 6.638207075185055e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.019969626272171e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.669218221395915e-09, "output_power": 6.908462564389654e-09, "reference_active": true, "delta_db": 0.8585823425893896}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.997554044063276e-09, "output_power": 5.265529612424832e-09, "reference_active": true, "delta_db": 0.22684560186730646}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.156278331683346e-09, "output_power": 3.7369569309444406e-09, "reference_active": true, "delta_db": -1.3981825961299768}], "active_band_count": 3, "active_band_mae_db": 0.8278701801955576}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.1954716835574657e-06, "log_rms_mae_db": 1.6137000344427066, "rms_envelope_nrmse": 0.1658659499156304, "envelope_correlation": 0.9803097647280306, "rms_gain_error_db": 0.5229899523190309, "reference_mean_power": 5.913056575013843e-08, "output_mean_power": 6.669772634037264e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.690703802813698e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.971603141472601e-09, "output_power": 7.70285264200339e-09, "reference_active": true, "delta_db": 0.4331893282343041}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1694216774888265e-09, "output_power": 2.751342299743425e-09, "reference_active": true, "delta_db": -0.6143539883197728}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5180140726512066e-10, "output_power": 2.799110600050345e-10, "reference_active": true, "delta_db": -2.0792752042541442}], "active_band_count": 3, "active_band_mae_db": 1.042272840269407}}]}, {"name": "1000–3000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [1000.0, 3000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 4.597874045564372e-06, "log_rms_mae_db": 1.3595514364765475, "rms_envelope_nrmse": 0.16170564414374106, "envelope_correlation": 0.9835697565981524, "rms_gain_error_db": -0.26109936664278577, "reference_mean_power": 3.0019112356646434e-07, "output_mean_power": 2.82675331181996e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.1704248469151792e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.917571308133626e-08, "output_power": 4.72313432758256e-08, "reference_active": true, "delta_db": -0.17520368964428726}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.373644839895842e-09, "output_power": 5.477735940143458e-09, "reference_active": true, "delta_db": -0.6578676670541634}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.9583662339560916e-09, "output_power": 3.7174061492542742e-09, "reference_active": true, "delta_db": -0.27275960299223956}], "active_band_count": 3, "active_band_mae_db": 0.3686103198968967}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 3.6957143825373563e-06, "log_rms_mae_db": 0.7997825361424044, "rms_envelope_nrmse": 0.08388575559404265, "envelope_correlation": 0.9959922954465967, "rms_gain_error_db": -0.2611285106962028, "reference_mean_power": 3.016958800523271e-07, "output_mean_power": 2.840903804877031e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.1236901446499244e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.541853281346178e-08, "output_power": 4.4414860632727027e-08, "reference_active": true, "delta_db": -0.09704797097629644}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5898805602165613e-09, "output_power": 2.6800545331982882e-09, "reference_active": true, "delta_db": -1.269363682485882}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.01076242530766e-10, "output_power": 2.0781927655450648e-10, "reference_active": true, "delta_db": -1.6099065869234956}], "active_band_count": 3, "active_band_mae_db": 0.992106080128558}}]}, {"name": "3000–6000 Hz", "status": "measured", "filter": {"kind": "butterworth-forward-backward", "prototype_order": 4, "edges_hz": [3000.0, 6000.0], "pad_type": "even", "pad_samples": 27}, "windows": [{"window_ms": 10.0, "window_samples": 240, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1199, "rms_floor": 2.0353597876360997e-06, "log_rms_mae_db": 1.2482409126377625, "rms_envelope_nrmse": 0.24323833758720287, "envelope_correlation": 0.9649002432016226, "rms_gain_error_db": 0.2603189361401664, "reference_mean_power": 5.358047115055493e-08, "output_mean_power": 5.6890325917866874e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.7539255872910824e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.2466604070258255e-09, "output_power": 5.822107979655689e-09, "reference_active": true, "delta_db": 0.4519730065553911}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.042126892400446e-09, "output_power": 3.200203135867863e-09, "reference_active": true, "delta_db": 0.22000221168161582}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.488177427019359e-09, "output_power": 1.565124882231575e-09, "reference_active": true, "delta_db": -2.01332349928731}], "active_band_count": 3, "active_band_mae_db": 0.8950995725081056}}, {"window_ms": 40.0, "window_samples": 960, "hop_samples": 120, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 144000, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1193, "rms_floor": 1.4732086031870805e-06, "log_rms_mae_db": 0.7129170756187816, "rms_envelope_nrmse": 0.12909144362817448, "envelope_correlation": 0.9898272114791996, "rms_gain_error_db": 0.260298173373428, "reference_mean_power": 5.3847422411461674e-08, "output_mean_power": 5.7173494364217686e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.6457241300858348e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.316794721929917e-09, "output_power": 6.522538828453659e-09, "reference_active": true, "delta_db": 0.1391990934640331}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0867827772247918e-09, "output_power": 1.8429897222756674e-09, "reference_active": true, "delta_db": -0.5395433040305397}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.2900642849732037e-10, "output_power": 1.2143721504109854e-10, "reference_active": true, "delta_db": -2.7549587485125224}], "active_band_count": 3, "active_band_mae_db": 1.1445670486690318}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.45860023774092995, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "6bbc16d247f4eadfd261100f82f828c00f468ad919fefd22f7746fc2837e9cb7", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9809292712160811, "standard_deviation": 0.0018152735984480917, "minimum": 0.9774363760297036, "maximum": 0.9835697565981524, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.365454325969003, "standard_deviation": 0.021326284087083175, "minimum": 1.335700227968051, "maximum": 1.4006301195329516, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.45391209675561095, "standard_deviation": 0.2562420494706741, "minimum": 0.17754604858246106, "maximum": 0.8360708402805418, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17581385593648546, "standard_deviation": 0.0121212820769985, "minimum": 0.16170564414374106, "maximum": 0.19773343380464325, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9952761047347035, "standard_deviation": 0.0010692590812193294, "minimum": 0.9929872321141416, "maximum": 0.9961091233661618, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.798139217200889, "standard_deviation": 0.02238612950872441, "minimum": 0.7612916091571071, "maximum": 0.835476328577318, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7194106200064012, "standard_deviation": 0.24973900614627098, "minimum": 0.27373954963072433, "maximum": 0.992106080128558, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09122369356373178, "standard_deviation": 0.01778801601314383, "minimum": 0.077415404702572, "maximum": 0.13147697554179394, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9669093203074267, "standard_deviation": 0.0033255668962822857, "minimum": 0.9640345296484006, "maximum": 0.9729156860906619, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2607756415814042, "standard_deviation": 0.03172038805707216, "minimum": 1.2339956611693952, "maximum": 1.3320361066754862, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.9136891061792003, "standard_deviation": 0.16955775332918352, "minimum": 0.6543290954352767, "maximum": 1.1583813192784995, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.23326957967281037, "standard_deviation": 0.011356494119183986, "minimum": 0.21474655598216477, "maximum": 0.24365002861334992, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9900038101589971, "standard_deviation": 0.0016035795454742126, "minimum": 0.9875002624504573, "maximum": 0.9923896139851224, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7348940777363026, "standard_deviation": 0.02924369873989674, "minimum": 0.7065213700834605, "maximum": 0.7887819968233718, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.3101672918617255, "standard_deviation": 0.2905328787010951, "minimum": 0.9869701945091004, "maximum": 1.7230019983026985, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.12665649586943123, "standard_deviation": 0.010318054816630824, "minimum": 0.11099080952183171, "maximum": 0.14272044024669253, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9366047591431097, "standard_deviation": 0.009726838090935115, "minimum": 0.9221255943686906, "maximum": 0.9473780917046973, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.293106562147204, "standard_deviation": 0.04645361309549847, "minimum": 2.2309863973924142, "maximum": 2.3566919878387846, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8496183968804569, "standard_deviation": 0.17595963806698323, "minimum": 0.5705944507365285, "maximum": 1.1305006141464453, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.30276776735315475, "standard_deviation": 0.01793819902263036, "minimum": 0.2736387454730204, "maximum": 0.3353717402090139, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9714510672563228, "standard_deviation": 0.005820671728816017, "minimum": 0.9654489845701785, "maximum": 0.9803097647280306, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.7212645957263266, "standard_deviation": 0.06843986807533987, "minimum": 1.6137000344427066, "maximum": 1.8201354224147661, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.0276916112836272, "standard_deviation": 0.5918368213859623, "minimum": 0.6077982080568486, "maximum": 2.3371155122434737, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.20386570075268073, "standard_deviation": 0.01876986060884806, "minimum": 0.1658659499156304, "maximum": 0.22289550911717235, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.506905235897868, "standard_deviation": 0.09385558662786006, "minimum": 0.36481344946871996, "maximum": 0.6287400471425044, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.911535219635003, "standard_deviation": 0.00587818141787261, "minimum": 5.9017686784017735, "maximum": 5.919324995533674, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.01579509979464316, "standard_deviation": 0.0018251397028074586, "minimum": 0.011977878914050338, "maximum": 0.01782986205192422, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.04053240562145815, "standard_deviation": 0.20327634545197482, "minimum": -0.25733847227763945, "maximum": 0.35054666373785565, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.970251535763412, "standard_deviation": 0.003301399531299789, "minimum": 0.9656708625618411, "maximum": 0.9758546344836542, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.7052190289646147, "standard_deviation": 0.03889978573722477, "minimum": 1.647349199875526, "maximum": 1.7548187977831595, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.5535694676016045, "standard_deviation": 0.13442565609727766, "minimum": 0.40229511805598656, "maximum": 0.8192874856537861, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.18463821405124614, "standard_deviation": 0.010904748415952596, "minimum": 0.16873278769147776, "maximum": 0.20029665761164783, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9921235865287685, "standard_deviation": 0.002142243012993089, "minimum": 0.9881359015615894, "maximum": 0.9940934652423401, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8602271371857451, "standard_deviation": 0.03719744727232971, "minimum": 0.8088548787819171, "maximum": 0.906785811089593, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.688634738110317, "standard_deviation": 0.190706056056825, "minimum": 0.46982355299725426, "maximum": 0.9343332207223156, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.09199991954869549, "standard_deviation": 0.014905861221186457, "minimum": 0.07948278006625377, "maximum": 0.12286075261352693, "valid_count": 8, "planned_count": 8}}}]}], "planned_recordings": 12, "failures": 0}
