{"schema_version": 4, "study_role": "supplement_to_completed_fixed_120", "formal_base": {"status": "selected", "method": "hnm", "version": "hnm-v1", "reason": "ユーザーの方針変更に従い、自作の調波・雑音方式を改善の出発点とする。WORLD（Harvest）は既存比較対象であり、初代採用はWORLDへの品質優越を意味しない。", "comparison_reference": "hnm", "comparison_reference_meaning": "この実験時点の自作ベース。初代の自己比較差は0。既存比較対象はWORLD（Harvest）の1方式。"}, "comparison_reference": "hnm", "method_labels": {"identity": "原音", "hnm": "自作HNM v1（当時のベース）", "candidate": "雑音包絡を分離した候補", "world_harvest": "WORLD（Harvest）"}, "contract": {"schema_version": 1, "study_role": "supplement_to_completed_fixed_120", "parent": {"result_path": "experiments/2026-10-12/noise-envelope/results/run-001/results.json", "result_sha256": "c50df39a5300056809a18c03e2793a1dbf00ab9a19810a3683b367351e8a0b21", "contract_path": "experiments/2026-10-12/noise-envelope/results/run-001/contract.json", "contract_sha256": "65fb527ea770a935c1228420a034fe4c8ab4b27efca8235595acdcb7cb825e50", "planned_recordings": 120, "planned_rows": 360, "completed_rows": 360, "failed_rows": 0, "planned_mos": 480, "completed_mos": 480, "failed_mos": 0, "public_report": "../../../noise-envelope/results/run-001/index.html"}, "shared_conditions": {"schema_version": 1, "manifest_sha256": "644f4d57483366bb20d8dbcfdaa254e354aed4af8318a6a2984bb2e8b3ddc9c1", "formal_base": {"status": "selected", "method": "hnm", "version": "hnm-v1", "reason": "ユーザーの方針変更に従い、自作の調波・雑音方式を改善の出発点とする。WORLD（Harvest）は既存比較対象であり、初代採用はWORLDへの品質優越を意味しない。", "comparison_reference": "hnm", "comparison_reference_meaning": "この実験時点の自作ベース。初代の自己比較差は0。既存比較対象はWORLD（Harvest）の1方式。"}, "baseline_sha256": "01014c4dc122d7fc8b470aa50454e706cc3f602670b78ef2a790250893e03b1a", "method_sources": {"hnm": {"repository_commit": "1b34ffb294f7dd432d5793940cff3d8d3a9c67d3", "path": "vocoderbench/hnm*.py"}, "candidate": {"path": "Git外の候補。棄却時はコードを公開せず完全再実行はできない"}, "world_harvest": {"schema_version": 1, "repository": "https://github.com/mmorise/World.git", "revision": "c794856b537758a3d300757db2e5e31685a822c2", "license": "BSD-3-Clause", "rng_policy": "upstream-fixed-state-per-offline-call", "compiler": "g++", "flags": ["-std=c++11", "-O2", "-fPIC", "-shared"], "sources": {"src/world/cheaptrick.h": "90acc1f7cbb692cccee2467ebe1c9d5499d92deaad7fd3c04416edf29f6c261d", "src/world/codec.h": "529736e308dd168ed60bd1dd76059ea8e04697de9d36c019dd9abccac22283a0", "src/world/common.h": "7a761e7d92a3dff74141f73a0bb36ea7af543f314638e4d53be21dfd3d6924d1", "src/world/constantnumbers.h": "ed3d3aec8d0e019db68b3845198bb2c87eedd1cd26a694a830bd57f4d26ba323", "src/world/d4c.h": "c736bb57d4b07ed74d8a56fb8302b6de0d5b21d4b5845fe115293aff9b71b55f", "src/world/dio.h": "e5a433f4454250f9e3a9c60dc40de65caea0cb26ad4073b87c739773a22d1ddd", "src/world/fft.h": "ac321b81dea5e8118933ecc66d2d9cbfb7721da52892a64d8a4f2e18a65829d6", "src/world/harvest.h": "1ab55206a28236b96e8bdd0f18ddd0ec45ad874217b876ab4a9a2699619e3de2", "src/world/macrodefinitions.h": "6d5417f864a4a4d95b470e72e3cb0114e8c96ba33cc189341e83a9f345e664f0", "src/world/matlabfunctions.h": "192a6be8cf749c147a7b5119b14ad50c5ddbddba9d6c810fbdf64f0dd7dc2af4", "src/world/stonemask.h": "e98a951d7443b81ed0062434a6656efd812011beb57a94c0492c13471698a7fc", "src/world/synthesis.h": "3905ef8d0f77a4d3081a3ec11cc81f61e0c0b8db42ce37db1d6a76d5a5096e44", "src/world/synthesisrealtime.h": "a0f21ec940cc6e692ef6e4cdce6e920c79ae3faff605bb5816ef19686dc60739", "src/cheaptrick.cpp": "6481ea68ebc3a90151852cea8a2efbf1bf6683e823b737847ce57a69f7cbe00b", "src/codec.cpp": "acbd6c22763d036ac338fee82c061e8526fdd2d68006fb4e73d4c58c9842b9e2", "src/common.cpp": "ef4a982d103bfd4c0efe6f1e6fa1192809e07ac39289f29951f3d95f1af8ca51", "src/d4c.cpp": "a988f6154b5c3332a17f2153a1e32afb04e798d57fa99ed08670c6a64e0ad28a", "src/dio.cpp": "38449de8a16c6ac6405b7289ed2e8adac9400885d53d181639ebd063366756da", "src/fft.cpp": "7a580cc02a0b040bf39de9a841f18b527a711093309ef408c08271abed6eec62", "src/harvest.cpp": "e9e80047a9d9ed3ff8521b966985c0b912ac09415565da1cc821319dc454975e", "src/matlabfunctions.cpp": "250d4cdc31b64cb3bda3a0c988d3853a09e66dd85f15f167161948d938662a4c", "src/stonemask.cpp": "de68ab826ff94176bfa89b5caf7ba46a6a0497eaaf1957e2e942245b7b663e76", "src/synthesis.cpp": "9888973e28f2194a0eb9807e18e36680f3d912bef3ddf174dc640fedc4e08b4c", "src/synthesisrealtime.cpp": "01403f641a1dce3de564335859b82815162bdee2ae7e25b5fa2288930539f5f2", "LICENSE.txt": "6921ef0a65a931509b4055075fd847d7257c4094609075dd0615e8e997215f7e"}}}, "world_binary_sha256": "01aa04d0c3fec82c2bf4a00e3417e00d77caff8ac8078a4b8ec5b611b081b86d", "world_build": {"revision": "c794856b537758a3d300757db2e5e31685a822c2", "lock_sha256": "44b8bc3adb62802ed060834d9e06ed7f5f3cc4d28583b8a44066c5959a42462b", "compiler": "g++", "compiler_version": "g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0", "flags": ["-std=c++11", "-O2", "-fPIC", "-shared"], "library_sha256": "01aa04d0c3fec82c2bf4a00e3417e00d77caff8ac8078a4b8ec5b611b081b86d", "source_sha256": {"src/world/cheaptrick.h": "90acc1f7cbb692cccee2467ebe1c9d5499d92deaad7fd3c04416edf29f6c261d", "src/world/codec.h": "529736e308dd168ed60bd1dd76059ea8e04697de9d36c019dd9abccac22283a0", "src/world/common.h": "7a761e7d92a3dff74141f73a0bb36ea7af543f314638e4d53be21dfd3d6924d1", "src/world/constantnumbers.h": "ed3d3aec8d0e019db68b3845198bb2c87eedd1cd26a694a830bd57f4d26ba323", "src/world/d4c.h": "c736bb57d4b07ed74d8a56fb8302b6de0d5b21d4b5845fe115293aff9b71b55f", "src/world/dio.h": "e5a433f4454250f9e3a9c60dc40de65caea0cb26ad4073b87c739773a22d1ddd", "src/world/fft.h": "ac321b81dea5e8118933ecc66d2d9cbfb7721da52892a64d8a4f2e18a65829d6", "src/world/harvest.h": "1ab55206a28236b96e8bdd0f18ddd0ec45ad874217b876ab4a9a2699619e3de2", "src/world/macrodefinitions.h": "6d5417f864a4a4d95b470e72e3cb0114e8c96ba33cc189341e83a9f345e664f0", "src/world/matlabfunctions.h": "192a6be8cf749c147a7b5119b14ad50c5ddbddba9d6c810fbdf64f0dd7dc2af4", "src/world/stonemask.h": "e98a951d7443b81ed0062434a6656efd812011beb57a94c0492c13471698a7fc", "src/world/synthesis.h": "3905ef8d0f77a4d3081a3ec11cc81f61e0c0b8db42ce37db1d6a76d5a5096e44", "src/world/synthesisrealtime.h": "a0f21ec940cc6e692ef6e4cdce6e920c79ae3faff605bb5816ef19686dc60739", "src/cheaptrick.cpp": "6481ea68ebc3a90151852cea8a2efbf1bf6683e823b737847ce57a69f7cbe00b", "src/codec.cpp": "acbd6c22763d036ac338fee82c061e8526fdd2d68006fb4e73d4c58c9842b9e2", "src/common.cpp": "ef4a982d103bfd4c0efe6f1e6fa1192809e07ac39289f29951f3d95f1af8ca51", "src/d4c.cpp": "a988f6154b5c3332a17f2153a1e32afb04e798d57fa99ed08670c6a64e0ad28a", "src/dio.cpp": "38449de8a16c6ac6405b7289ed2e8adac9400885d53d181639ebd063366756da", "src/fft.cpp": "7a580cc02a0b040bf39de9a841f18b527a711093309ef408c08271abed6eec62", "src/harvest.cpp": "e9e80047a9d9ed3ff8521b966985c0b912ac09415565da1cc821319dc454975e", "src/matlabfunctions.cpp": "250d4cdc31b64cb3bda3a0c988d3853a09e66dd85f15f167161948d938662a4c", "src/stonemask.cpp": "de68ab826ff94176bfa89b5caf7ba46a6a0497eaaf1957e2e942245b7b663e76", "src/synthesis.cpp": "9888973e28f2194a0eb9807e18e36680f3d912bef3ddf174dc640fedc4e08b4c", "src/synthesisrealtime.cpp": "01403f641a1dce3de564335859b82815162bdee2ae7e25b5fa2288930539f5f2", "LICENSE.txt": "6921ef0a65a931509b4055075fd847d7257c4094609075dd0615e8e997215f7e"}, "command": ["g++", "-std=c++11", "-O2", "-fPIC", "-shared", "-I", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/cheaptrick.cpp", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/codec.cpp", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/common.cpp", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/d4c.cpp", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/dio.cpp", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/fft.cpp", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/harvest.cpp", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/matlabfunctions.cpp", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/stonemask.cpp", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/synthesis.cpp", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/source/src/synthesisrealtime.cpp", "-o", "/workspace/scratch/f70a310f59ab/checkout/vocoderbench/.cache/world/c794856b537758a3d300757db2e5e31685a822c2/world-build-6gmdt99k/libworld.so"]}, "environment": {"python": "3.12.14", "numpy": "2.3.5", "scipy": "1.17.0", "platform": "Linux-6.18.44-x86_64-with-glibc2.39"}, "source_sha256": {"benchmark.py": "7f5dc6267f5d0b07052471c59677a5dd6de86955f2af0b2da5b468ac85463694", "benchmark_io.py": "6c6b0015c69e92ce0fcb3cdc44c7aee3fe25a9b0d28a95fb1a2837bca6a107b9", "benchmark_pipeline.py": "a049034dcd272bbafda47cbf5719cc6b1cd8dae6f80682200cd3fc7b90e522cd", "control.py": "bc41e73ff34b5f9cb52280a6f2317c989abc53f8b15f8f82db5ee3102b4b58bd", "corpus.py": "bc14cee2c3dd1a651cf2e5f0e9fe871fbd3a712d1a90d7c18a18547a625802e8", "extended_metrics.py": "ab3537d2c8e5d568a0cd2fa8aa36309de09c3bce7cf2f849214331a22fe3624f", "hnm.py": "58f0378793b7433f80bf854972882298649799d8e3d0868674816e9bf6b63f74", "hnm_analysis.py": "3f45703667237333d76c4145c1513e4eb3342bd40f01a714c10303082440e26a", "hnm_control.py": "b2f5efbbb1e550569c231a08f12997d94b0bacb130bcc816fe6bd458b17a98bc", "hnm_diagnostics.py": "a3f47468d10db7e8040c78fc24546043b2eeae6b518f59da1f5904c674aae436", "hnm_parameters.py": "635bf222bac8ce41897c0977677e67be4366724f4239a9e85e153169fcea2cf0", "hnm_synthesis.py": "574124b6c412a5adc3cbe4152c3188ed56796cb5efe5d632d9e84b85040b9fbf", "metrics.py": "b8767feb49494058bd9ec08fd95ae2fb50ce7897fcdd6cebe319ff8a0ac51f22", "mos.py": "fb632aa5440245525289962372db4f3eb007cd2b3b493b2d05ecccb878e85f03", "mos_batch.py": "c7a732dfe52b08fa155201a7134d2f5561a10b16d1866e9f0526f61b2b244f64", "temporal_metrics.py": "ce21b6a4767071a7b98ea0cdbfe54bdba15b596bf8d6b6127281a97095e7be91", "world.py": "d14558eed772e07031a9183f57facc55acb1c27deccb3dd4fa098ffcbe0cde3a"}, "dependency_lock_sha256": "c8b2bc28ebb1523bf8cfe0f4627d06bd5d03e0ba6a2bb5dc0905be77a3dc8823", "decision_criteria_sha256": "71a7ad269d92d9572965f7e9e2eaab336bca56eb2185ac2ed69bbb12e5eadbee", "candidate_source_sha256": {"__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "hnm.py": "58f0378793b7433f80bf854972882298649799d8e3d0868674816e9bf6b63f74", "hnm_analysis.py": "3f45703667237333d76c4145c1513e4eb3342bd40f01a714c10303082440e26a", "hnm_control.py": "b2f5efbbb1e550569c231a08f12997d94b0bacb130bcc816fe6bd458b17a98bc", "hnm_diagnostics.py": "a3f47468d10db7e8040c78fc24546043b2eeae6b518f59da1f5904c674aae436", "hnm_parameters.py": "635bf222bac8ce41897c0977677e67be4366724f4239a9e85e153169fcea2cf0", "hnm_synthesis.py": "937721cd363f06afa3bf4c20c1ff182a8c337c4b19ac9f4b57314f6adea6b44c"}, "noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "mos_noise_seed": 0, "mos_extraction_seed": 20261012, "mos_repetitions": 1, "mos_domain": "bvcc", "alignment": "none", "normalization": "none", "interpretation": "固定した開発・比較集合。未使用の最終評価集合ではない"}, "manifest_sha256": "1ff7a449b5f44580d6b48c187209c9786522880a7630ebfacf081660b2df4520", "manifest_id": "jvs_available_v1", "inputs": [{"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}], "entry_source_sha256": {"supplement.py": "8b72b63b7059f3e94ecb13f575ab93060e00fee0cb89c5abcaa51719061b890d", "supplement_contract.py": "748bff65db3bd3709cdd472b02358af35518c5d1a96fbf212f6b02ba5fa45cd4", "supplement_report.py": "332dd5cb247f02d088f3b8ac51976bb26a0ac1f57b2549492b51c276b34c8200"}, "summary_source_sha256": "8221086fe08bfc70cbfb9308a3a01d6fea976afb7de86af8cbacd7999e8281da", "mos": {"configuration": {"name": "UTMOSv2", "quantity": "predicted_mos_not_human_rating", "source_repository": "https://github.com/sarulab-speech/UTMOSv2", "source_commit": "cc2700db57bb83ee13dc31ebe1b868c254e15d09", "checkpoint_revision": "506474f2b33dc77c234d668cc419be1861899cad", "checkpoint_sha256": "c8149d988e4bbf3f347e6966b5d769de347a5f8c59ffca1dc4bd4bf5b8585e57", "fold": 0, "device": "cpu", "configuration": "fusion_stage3", "predict_dataset": "bvcc", "repetitions": 1, "extraction_seed": 20261012, "cpu_threads": 4, "remove_silent_section": false, "nnpack_enabled": false, "internal_sample_rate": 16000, "ssl_crop_seconds": 3.0, "spectrogram_crop_seconds": 1.4, "spectrogram_frames_per_repetition": 2, "spectrogram_inner_mixup": true, "short_input_extension": "tile", "code_license": "MIT", "weights_license": "MIT", "independent_human_rating_calibration": "not_performed_for_this_project", "scope": "JVS/LibriSpeechの再合成への適用は未校正。言語・発声別に集計する。", "paper_protocol_difference": "論文の5fold×5抽出平均ではなく、fold0と上記反復数。", "initialization": "official_architecture_then_complete_strict_state_dict"}, "cache_sha256": {"weights/fold0_s42_best_model.pth": "c8149d988e4bbf3f347e6966b5d769de347a5f8c59ffca1dc4bd4bf5b8585e57", "wav2vec2_config/config.json": "4937977e24d12d1bba70cdce8709c3c04807a8e4ae8ddac4229c48c436ae99ae", "wav2vec2_config/preprocessor_config.json": "b225d617c025463b9e157e06afea8b90dc7078fc70b013c533328423e0486b4a"}}, "planned": {"recordings": 12, "speakers": 4, "resynthesis_rows": 36, "syntheses_including_seeds": 204, "predicted_mos": 48}, "network": "offline_existing_cache_only", "public_audio": false, "interpretation": "発声様式別の補助診断。正式120件の分母・採否閾値は変更しない。"}, "execution": {"started_at": "2026-10-11T16:46:32.484944+00:00", "status": "completed", "parent_commit": "9f1025c64fddec37dfa2bbe1cd4bd7bb787dd5db", "last_stage": "all", "completed_at": "2026-10-11T16:48:46.786769+00:00"}, "generated_at": "2026-10-11T16:48:46.787032+00:00", "planned_cases": 12, "cases": [{"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"}, {"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"}, {"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"}, {"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"}, {"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"}, {"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"}, {"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"}, {"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"}, {"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"}, {"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"}, {"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"}, {"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"}], "resynthesis": [{"case": "jvs_jvs004_falset10_BASIC5000_2951", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs004", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.087693214416504, "predicted_mos": 2.087693214416504, "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": "9c7014a18e0410ac1c4c09362b421b354b4fe44cf9d84584fb6ba3d3db2e4e7d", "internal_samples": 72292, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.6149161499997717}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.087965665973979, "全帯域_10ms_rms_envelope_nrmse": 0.08680984932235031, "全帯域_10ms_envelope_correlation": 0.9930385302322923, "全帯域_10ms_modulation_mae_db": 0.3413475144217446, "全帯域_40ms_log_rms_mae_db": 0.7944310040470646, "全帯域_40ms_rms_envelope_nrmse": 0.0548072912784614, "全帯域_40ms_envelope_correlation": 0.9969691332078334, "全帯域_40ms_modulation_mae_db": 0.33581157731696293, "300–1000 Hz_10ms_log_rms_mae_db": 0.7457199430371618, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09601893817512715, "300–1000 Hz_10ms_envelope_correlation": 0.9920735277248771, "300–1000 Hz_10ms_modulation_mae_db": 0.2716201895122238, "300–1000 Hz_40ms_log_rms_mae_db": 0.5311471009572944, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.06148837632060813, "300–1000 Hz_40ms_envelope_correlation": 0.9964584038464487, "300–1000 Hz_40ms_modulation_mae_db": 0.30928157919492866, "1000–3000 Hz_10ms_log_rms_mae_db": 1.166249010606097, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09437408730802194, "1000–3000 Hz_10ms_envelope_correlation": 0.9940349106517171, "1000–3000 Hz_10ms_modulation_mae_db": 0.5769906261940935, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7376759714405345, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06547072737983353, "1000–3000 Hz_40ms_envelope_correlation": 0.9972306459932061, "1000–3000 Hz_40ms_modulation_mae_db": 0.5594997764529457, "3000–6000 Hz_10ms_log_rms_mae_db": 1.336452916534764, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15572683279159064, "3000–6000 Hz_10ms_envelope_correlation": 0.9830472965914566, "3000–6000 Hz_10ms_modulation_mae_db": 1.3338294558010066, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9085103192517019, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10178386596546156, "3000–6000 Hz_40ms_envelope_correlation": 0.9938220702630287, "3000–6000 Hz_40ms_modulation_mae_db": 1.0346311544273241, "mr_stft_db": 5.563633194330973, "band_mae_db": 1.6011258674058944, "rms_gain_error_db": -0.038243705930849914, "output_peak": 0.35924285507429343}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0539890103698262, "全帯域_10ms_rms_envelope_nrmse": 0.07421152659112823, "全帯域_10ms_envelope_correlation": 0.9950309735957652, "全帯域_10ms_modulation_mae_db": 0.3052075352014047, "全帯域_40ms_log_rms_mae_db": 0.6533607616314195, "全帯域_40ms_rms_envelope_nrmse": 0.042522344665743464, "全帯域_40ms_envelope_correlation": 0.9982562198189157, "全帯域_40ms_modulation_mae_db": 0.1175872722348139, "300–1000 Hz_10ms_log_rms_mae_db": 0.7424925743205688, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08085875917539008, "300–1000 Hz_10ms_envelope_correlation": 0.9945162076555333, "300–1000 Hz_10ms_modulation_mae_db": 0.32639751106818315, "300–1000 Hz_40ms_log_rms_mae_db": 0.5179970064561721, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04720771528373038, "300–1000 Hz_40ms_envelope_correlation": 0.9980185290974073, "300–1000 Hz_40ms_modulation_mae_db": 0.3198148834587173, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1595191857572802, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09032740290216848, "1000–3000 Hz_10ms_envelope_correlation": 0.9942473898054748, "1000–3000 Hz_10ms_modulation_mae_db": 0.26476314764261705, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6982198037948244, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05292126061168337, "1000–3000 Hz_40ms_envelope_correlation": 0.9979101260018125, "1000–3000 Hz_40ms_modulation_mae_db": 0.5172683515901514, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3333914330001138, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11867982677037059, "3000–6000 Hz_10ms_envelope_correlation": 0.9900403969030979, "3000–6000 Hz_10ms_modulation_mae_db": 0.8840461965455845, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8325277883595149, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07202610446033075, "3000–6000 Hz_40ms_envelope_correlation": 0.9968400968225712, "3000–6000 Hz_40ms_modulation_mae_db": 1.1793112614480556, "mr_stft_db": 5.5649919959522505, "band_mae_db": 1.7801035701874726, "rms_gain_error_db": 0.07319779011760658, "output_peak": 0.36413675589423716}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0260110984854447, "全帯域_10ms_rms_envelope_nrmse": 0.07929942078682303, "全帯域_10ms_envelope_correlation": 0.9943042639537537, "全帯域_10ms_modulation_mae_db": 0.7679459344602483, "全帯域_40ms_log_rms_mae_db": 0.6825461343171375, "全帯域_40ms_rms_envelope_nrmse": 0.04396639558740341, "全帯域_40ms_envelope_correlation": 0.9981994991936735, "全帯域_40ms_modulation_mae_db": 0.8075669968573077, "300–1000 Hz_10ms_log_rms_mae_db": 0.7315265020840286, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09146572015672443, "300–1000 Hz_10ms_envelope_correlation": 0.9928469608790371, "300–1000 Hz_10ms_modulation_mae_db": 0.739049478282146, "300–1000 Hz_40ms_log_rms_mae_db": 0.5064982624388502, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05052902033308926, "300–1000 Hz_40ms_envelope_correlation": 0.9977095643790563, "300–1000 Hz_40ms_modulation_mae_db": 0.9325975127963932, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1591661519773406, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08874356644377884, "1000–3000 Hz_10ms_envelope_correlation": 0.9947730600345202, "1000–3000 Hz_10ms_modulation_mae_db": 0.9178072056683222, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7349180089902793, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06388453058510778, "1000–3000 Hz_40ms_envelope_correlation": 0.9973587539400581, "1000–3000 Hz_40ms_modulation_mae_db": 0.7886987769157967, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2957789023594106, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13919154216924146, "3000–6000 Hz_10ms_envelope_correlation": 0.9856173091906579, "3000–6000 Hz_10ms_modulation_mae_db": 1.0950856461855851, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8267267564685199, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08397291451374991, "3000–6000 Hz_40ms_envelope_correlation": 0.9949661220781459, "3000–6000 Hz_40ms_modulation_mae_db": 1.052027515382198, "mr_stft_db": 5.579468258107531, "band_mae_db": 1.71031754894547, "rms_gain_error_db": -0.11446233087961728, "output_peak": 0.35693607903420244}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0387045608628647, "全帯域_10ms_rms_envelope_nrmse": 0.07079408772974775, "全帯域_10ms_envelope_correlation": 0.9954259840450069, "全帯域_10ms_modulation_mae_db": 0.47134960471382, "全帯域_40ms_log_rms_mae_db": 0.7398428519872969, "全帯域_40ms_rms_envelope_nrmse": 0.03816358564921289, "全帯域_40ms_envelope_correlation": 0.9986100039292207, "全帯域_40ms_modulation_mae_db": 0.5743294699478229, "300–1000 Hz_10ms_log_rms_mae_db": 0.7372129006987918, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07866278133011505, "300–1000 Hz_10ms_envelope_correlation": 0.9946830972252009, "300–1000 Hz_10ms_modulation_mae_db": 0.4045557394460313, "300–1000 Hz_40ms_log_rms_mae_db": 0.5241353264346892, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04264817075608939, "300–1000 Hz_40ms_envelope_correlation": 0.9983201103375223, "300–1000 Hz_40ms_modulation_mae_db": 0.48782071293242996, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1918207340572398, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09771317697971195, "1000–3000 Hz_10ms_envelope_correlation": 0.9934468632190171, "1000–3000 Hz_10ms_modulation_mae_db": 0.47276154871421655, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7309216953748615, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05938811016636368, "1000–3000 Hz_40ms_envelope_correlation": 0.9976878291850602, "1000–3000 Hz_40ms_modulation_mae_db": 1.1741492842959778, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3564287224517138, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14425746107850707, "3000–6000 Hz_10ms_envelope_correlation": 0.9860172296466789, "3000–6000 Hz_10ms_modulation_mae_db": 1.169169966455043, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8753993534186437, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09600533026063013, "3000–6000 Hz_40ms_envelope_correlation": 0.9950260930407668, "3000–6000 Hz_40ms_modulation_mae_db": 1.1264025161630584, "mr_stft_db": 5.565536855881999, "band_mae_db": 1.672735466210497, "rms_gain_error_db": -0.08578173785103775, "output_peak": 0.4030891991630551}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0912284718474143, "全帯域_10ms_rms_envelope_nrmse": 0.0824466221226245, "全帯域_10ms_envelope_correlation": 0.9938058922143801, "全帯域_10ms_modulation_mae_db": 0.7812178488692086, "全帯域_40ms_log_rms_mae_db": 0.7269383016927472, "全帯域_40ms_rms_envelope_nrmse": 0.04607621154180484, "全帯域_40ms_envelope_correlation": 0.9979859357403603, "全帯域_40ms_modulation_mae_db": 1.0369036076952243, "300–1000 Hz_10ms_log_rms_mae_db": 0.7726889445802505, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09154365271945265, "300–1000 Hz_10ms_envelope_correlation": 0.9929003640420667, "300–1000 Hz_10ms_modulation_mae_db": 0.7467764456370652, "300–1000 Hz_40ms_log_rms_mae_db": 0.5338141450193212, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05323808949625992, "300–1000 Hz_40ms_envelope_correlation": 0.9975388599143449, "300–1000 Hz_40ms_modulation_mae_db": 1.1287116907996784, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1460504495374644, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08994006484783992, "1000–3000 Hz_10ms_envelope_correlation": 0.9942293829715039, "1000–3000 Hz_10ms_modulation_mae_db": 0.7988824141942015, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7193237974898887, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05086909449985516, "1000–3000 Hz_40ms_envelope_correlation": 0.9980341883703991, "1000–3000 Hz_40ms_modulation_mae_db": 0.20064197538036174, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3368405724123122, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13869283169289473, "3000–6000 Hz_10ms_envelope_correlation": 0.9857121948472677, "3000–6000 Hz_10ms_modulation_mae_db": 1.0680339849965703, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7908232417706046, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07918497277389577, "3000–6000 Hz_40ms_envelope_correlation": 0.9956381591342489, "3000–6000 Hz_40ms_modulation_mae_db": 1.2651478334928832, "mr_stft_db": 5.565616909027291, "band_mae_db": 1.6327145570151187, "rms_gain_error_db": -0.10796287051818705, "output_peak": 0.34912086526879255}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.048174321705329, "全帯域_10ms_rms_envelope_nrmse": 0.07342906086156391, "全帯域_10ms_envelope_correlation": 0.9950533293502155, "全帯域_10ms_modulation_mae_db": 0.5759025628400598, "全帯域_40ms_log_rms_mae_db": 0.7351881485753334, "全帯域_40ms_rms_envelope_nrmse": 0.03693875625337137, "全帯域_40ms_envelope_correlation": 0.9986791500556798, "全帯域_40ms_modulation_mae_db": 1.096805356250078, "300–1000 Hz_10ms_log_rms_mae_db": 0.7450788978286078, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08176886959258985, "300–1000 Hz_10ms_envelope_correlation": 0.9942686280078978, "300–1000 Hz_10ms_modulation_mae_db": 0.621232660516808, "300–1000 Hz_40ms_log_rms_mae_db": 0.5071033075977026, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043901806362044764, "300–1000 Hz_40ms_envelope_correlation": 0.9982518016713688, "300–1000 Hz_40ms_modulation_mae_db": 1.2401124235521208, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1698256170203765, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10411355689271574, "1000–3000 Hz_10ms_envelope_correlation": 0.992248039491968, "1000–3000 Hz_10ms_modulation_mae_db": 0.2806748901911551, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7547249935825774, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05940417653329588, "1000–3000 Hz_40ms_envelope_correlation": 0.9973363729992336, "1000–3000 Hz_40ms_modulation_mae_db": 0.2666241424613091, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3515002004040684, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14062688915347682, "3000–6000 Hz_10ms_envelope_correlation": 0.9856559773239361, "3000–6000 Hz_10ms_modulation_mae_db": 1.168073140111281, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8487858532681692, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08178069634680114, "3000–6000 Hz_40ms_envelope_correlation": 0.9957700497810988, "3000–6000 Hz_40ms_modulation_mae_db": 0.631832220627592, "mr_stft_db": 5.577067294471683, "band_mae_db": 1.7596483674237664, "rms_gain_error_db": -0.07126602136710845, "output_peak": 0.3729233504371028}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0364591494048696, "全帯域_10ms_rms_envelope_nrmse": 0.07144343318810459, "全帯域_10ms_envelope_correlation": 0.9954922413601264, "全帯域_10ms_modulation_mae_db": 0.44431957559277646, "全帯域_40ms_log_rms_mae_db": 0.6974656841031405, "全帯域_40ms_rms_envelope_nrmse": 0.03876051463343465, "全帯域_40ms_envelope_correlation": 0.998761609678246, "全帯域_40ms_modulation_mae_db": 0.387359107900713, "300–1000 Hz_10ms_log_rms_mae_db": 0.7167592064720777, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08064851652952704, "300–1000 Hz_10ms_envelope_correlation": 0.9945874785522301, "300–1000 Hz_10ms_modulation_mae_db": 0.49757386281483945, "300–1000 Hz_40ms_log_rms_mae_db": 0.4968433207191975, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04364808038982866, "300–1000 Hz_40ms_envelope_correlation": 0.9984885934466436, "300–1000 Hz_40ms_modulation_mae_db": 0.583069193896752, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1932754563648151, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09253119283248241, "1000–3000 Hz_10ms_envelope_correlation": 0.9939557039507235, "1000–3000 Hz_10ms_modulation_mae_db": 0.5564846851075932, "1000–3000 Hz_40ms_log_rms_mae_db": 0.687061260764929, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.049279304937615676, "1000–3000 Hz_40ms_envelope_correlation": 0.9982691511038212, "1000–3000 Hz_40ms_modulation_mae_db": 0.5955602325665896, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3513598919608318, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14527401045946098, "3000–6000 Hz_10ms_envelope_correlation": 0.9841653421518661, "3000–6000 Hz_10ms_modulation_mae_db": 0.8325007516667274, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8759231726351041, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09078470034634206, "3000–6000 Hz_40ms_envelope_correlation": 0.9938346545009504, "3000–6000 Hz_40ms_modulation_mae_db": 0.41547625488575574, "mr_stft_db": 5.5734055442583825, "band_mae_db": 1.655934298241247, "rms_gain_error_db": -0.15118128518751617, "output_peak": 0.36675996740326416}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0674520038203537, "全帯域_10ms_rms_envelope_nrmse": 0.07696823906752749, "全帯域_10ms_envelope_correlation": 0.994538257973965, "全帯域_10ms_modulation_mae_db": 0.16916824574024503, "全帯域_40ms_log_rms_mae_db": 0.6891317745465534, "全帯域_40ms_rms_envelope_nrmse": 0.04212888422427598, "全帯域_40ms_envelope_correlation": 0.9982030967116773, "全帯域_40ms_modulation_mae_db": 0.30941270551080097, "300–1000 Hz_10ms_log_rms_mae_db": 0.7826648066971913, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0870367608259579, "300–1000 Hz_10ms_envelope_correlation": 0.9934849524598427, "300–1000 Hz_10ms_modulation_mae_db": 0.07963462621343953, "300–1000 Hz_40ms_log_rms_mae_db": 0.5471741467431062, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.049114878624434095, "300–1000 Hz_40ms_envelope_correlation": 0.9977368048335444, "300–1000 Hz_40ms_modulation_mae_db": 0.12739999426407525, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1946889555168343, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07829388111662948, "1000–3000 Hz_10ms_envelope_correlation": 0.9956302351313739, "1000–3000 Hz_10ms_modulation_mae_db": 0.4796593398276849, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7284009474531199, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.041369540640981584, "1000–3000 Hz_40ms_envelope_correlation": 0.9987050064996106, "1000–3000 Hz_40ms_modulation_mae_db": 0.24105427460731188, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3330568586795568, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13988762103307956, "3000–6000 Hz_10ms_envelope_correlation": 0.9855106167461928, "3000–6000 Hz_10ms_modulation_mae_db": 1.2739560537724852, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8565176118940655, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08718390949046154, "3000–6000 Hz_40ms_envelope_correlation": 0.9945606626980843, "3000–6000 Hz_40ms_modulation_mae_db": 0.9382983662675421, "mr_stft_db": 5.567171519144435, "band_mae_db": 1.6964904573914656, "rms_gain_error_db": 6.156557446835919e-05, "output_peak": 0.3523145859394934}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.4349156436608554, "spectral_convergence": 0.1956944302110688, "spectral_convergence_status": "ok", "amplitude_floor": 1.3518293902907786e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.736631409446293, "spectral_convergence": 0.21467687600904803, "spectral_convergence_status": "ok", "amplitude_floor": 1.2606433835114825e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.519352529885772, "spectral_convergence": 0.21917093872320476, "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": 1.1393850362771758e-06, "delta_db": 10.057905870699045, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0005754412253654517, "output_power": 0.0005582643783700763, "delta_db": -0.1316105474342982, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0015091092814657461, "output_power": 0.0015294769175858006, "delta_db": 0.058222369732949225, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00043576714857085195, "output_power": 0.00041863685495182934, "delta_db": -0.17417027669587357, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 9.403622080703858e-05, "output_power": 8.607697837245935e-05, "delta_db": -0.384081538645138, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.140246786176929e-05, "output_power": 2.921484199032399e-05, "delta_db": -0.313602380600663, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2121205040710494e-05, "output_power": 1.1877279839293782e-05, "delta_db": -0.08828808803329263, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.6011258674058944, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.038243705930849914, "pitch": null, "output_rms_dbfs": -25.792710314136833, "output_peak": 0.35924285507429343, "reference_rms_dbfs": -25.754466608205988, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.563633194330973}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 108438, "output_samples": 108438, "intelligibility": {"estoi": {"value": 0.7858434207163125, "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"}}, "level": {"reference": {"rms": 0.05155569782788039, "rms_dbfs": -25.754466608205988, "peak": 0.359771728515625, "peak_dbfs": -8.879459345216006, "crest_factor_db": 16.875007262989982, "mean": -3.1914027918026893e-07, "zero_energy": false}, "output": {"rms": 0.05132919867040651, "rms_dbfs": -25.792710314136833, "peak": 0.35924285507429343, "peak_dbfs": -8.892237214475449, "crest_factor_db": 16.900473099661387, "mean": -3.232858940892773e-06, "zero_energy": false}, "rms_difference_db": -0.038243705930845806}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 451, "uncovered_tail_samples": 198, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 3.559632289689034e-06, "threshold_dbfs": -54.48594862366153, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 182, "quiet_samples": 43680, "reference_mean_power": 2.0628618059386482e-07, "output_mean_power": 4.3120991477622757e-07, "output_rms_dbfs": -63.65311262007075, "output_zero_energy": false, "output_peak": 0.014415982331928262, "output_energy_fraction": 6.592663361800288e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 444, "reference_estimated_voiced_frames": 263, "output_estimated_voiced_frames": 238, "both_estimated_voiced_frames": 237, "reference_voiced_output_unvoiced_frames": 26, "reference_unvoiced_output_voiced_frames": 1, "paired_voiced_fraction": 0.9011406844106464, "absolute_difference_cents_median": 2.430951681126506, "absolute_difference_cents_p95": 15.091677048103115, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 198, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.087965665973979, "rms_envelope_nrmse": 0.08680984932235031, "envelope_correlation": 0.9930385302322923, "rms_gain_error_db": -0.03824369384940213, "reference_mean_power": 0.002662852134818696, "output_mean_power": 0.0026395061719021056}, "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": 0.00042794134856343613, "reference_active": true, "delta_db": 0.28188167407697307}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0004799671480036486, "output_power": 0.0004634528704855012, "reference_active": true, "delta_db": -0.15205936133100914}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.6992126812237875e-05, "output_power": 4.102182243052146e-05, "reference_active": true, "delta_db": -0.5901015078572515}], "active_band_count": 3, "active_band_mae_db": 0.3413475144217446}}, {"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": 0.7944310040470646, "rms_envelope_nrmse": 0.0548072912784614, "envelope_correlation": 0.9969691332078334, "rms_gain_error_db": -0.03824368221556595, "reference_mean_power": 0.002680683564334513, "output_mean_power": 0.0026571812754497917}, "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": 0.0003898422445000547, "output_power": 0.0004210171498369304, "reference_active": true, "delta_db": 0.33410888063335864}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0002615577546182838, "output_power": 0.0002355787870353608, "reference_active": true, "delta_db": -0.4543141911451557}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.9711216791425515e-06, "output_power": 5.228240531390102e-06, "reference_active": true, "delta_db": 0.21901166017237428}], "active_band_count": 3, "active_band_mae_db": 0.33581157731696293}}]}, {"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": 0.00018970614972877836, "log_rms_mae_db": 0.7457199430371618, "rms_envelope_nrmse": 0.09601893817512715, "envelope_correlation": 0.9920735277248771, "rms_gain_error_db": -0.003246458515767538, "reference_mean_power": 0.0020637883836989693, "output_mean_power": 0.002062246227381781}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.5811898835528856e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00043243433753203383, "output_power": 0.000473353451279549, "reference_active": true, "delta_db": 0.3926537607297491}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00038978360738039326, "output_power": 0.0003797634494843839, "reference_active": true, "delta_db": -0.11310407079068219}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.805770696622082e-05, "output_power": 3.5443152563807236e-05, "reference_active": true, "delta_db": -0.30910273701624}], "active_band_count": 3, "active_band_mae_db": 0.2716201895122238}}, {"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": 0.00016763715453010973, "log_rms_mae_db": 0.5311471009572944, "rms_envelope_nrmse": 0.06148837632060813, "envelope_correlation": 0.9964584038464487, "rms_gain_error_db": -0.003246466956701634, "reference_mean_power": 0.00207760838531689, "output_mean_power": 0.0020760558980324447}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.3894681028634637e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0004594859732757339, "output_power": 0.0005022391902422096, "reference_active": true, "delta_db": 0.3863833992500784}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019541576327050035, "output_power": 0.00017905333835477511, "reference_active": true, "delta_db": -0.3797717067468704}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.9559112605266995e-06, "output_power": 4.7747931069438715e-06, "reference_active": true, "delta_db": -0.16168963158783722}], "active_band_count": 3, "active_band_mae_db": 0.30928157919492866}}]}, {"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": 1.166249010606097, "rms_envelope_nrmse": 0.09437408730802194, "envelope_correlation": 0.9940349106517171, "rms_gain_error_db": -0.23506124240184673, "reference_mean_power": 0.0003994594973118105, "output_mean_power": 0.00037841350464437427}, "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": 0.00010008146178870414, "reference_active": true, "delta_db": -0.3128475525971457}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.796860879459569e-05, "output_power": 7.630064474556928e-05, "reference_active": true, "delta_db": -0.6179951595952796}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.822952666689089e-06, "output_power": 4.011437989294479e-06, "reference_active": true, "delta_db": -0.8001291663898552}], "active_band_count": 3, "active_band_mae_db": 0.5769906261940935}}, {"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": 0.7376759714405345, "rms_envelope_nrmse": 0.06547072737983353, "envelope_correlation": 0.9972306459932061, "rms_gain_error_db": -0.23506127235460061, "reference_mean_power": 0.00040213443933265886, "output_mean_power": 0.0003809475115765477}, "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": 9.813840696985285e-05, "reference_active": true, "delta_db": -0.34672385335839095}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.178329128126849e-05, "output_power": 4.326367099757512e-05, "reference_active": true, "delta_db": -0.7806628288337847}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.031671442188497e-07, "output_power": 4.577163195008839e-07, "reference_active": true, "delta_db": 0.5511126471666613}], "active_band_count": 3, "active_band_mae_db": 0.5594997764529457}}]}, {"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": 2.8330015424642847e-05, "log_rms_mae_db": 1.336452916534764, "rms_envelope_nrmse": 0.15572683279159064, "envelope_correlation": 0.9830472965914566, "rms_gain_error_db": -0.5248419613693139, "reference_mean_power": 5.860864109462448e-05, "output_mean_power": 5.193707122687e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 4.400349500158723e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.626242950468033e-05, "output_power": 1.4145939473778641e-05, "reference_active": true, "delta_db": -0.6055363143398622}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.53282953817687e-06, "output_power": 7.653941770443412e-06, "reference_active": true, "delta_db": -0.9533667334932937}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.75992153022225e-06, "output_power": 1.0028472140709607e-06, "reference_active": true, "delta_db": -2.4425853195698646}], "active_band_count": 3, "active_band_mae_db": 1.3338294558010066}}, {"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": 2.5104708341377374e-05, "log_rms_mae_db": 0.9085103192517019, "rms_envelope_nrmse": 0.10178386596546156, "envelope_correlation": 0.9938220702630287, "rms_gain_error_db": -0.5248420184569238, "reference_mean_power": 5.9001105225872584e-05, "output_mean_power": 5.2284859486031096e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 3.767766826204734e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3755010045242993e-05, "output_power": 1.1832881744883374e-05, "reference_active": true, "delta_db": -0.6537038759218141}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.79209512684818e-06, "output_power": 4.721658245059086e-06, "reference_active": true, "delta_db": -0.8874113638660148}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0124260162334762e-07, "output_power": 7.064565796269511e-08, "reference_active": true, "delta_db": -1.5627782234941434}], "active_band_count": 3, "active_band_mae_db": 1.0346311544273241}}]}], "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"]}}, "output_samples": 108438, "representation_scalars": 1018638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9940706981570373, "standard_deviation": 0.0009788935183959813, "minimum": 0.992248039491968, "maximum": 0.9956302351313739, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1725744451046811, "standard_deviation": 0.018475136635512784, "minimum": 1.1460504495374644, "maximum": 1.1946889555168343, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5435029821924855, "standard_deviation": 0.22755442529634076, "minimum": 0.26476314764261705, "maximum": 0.9178072056683222, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09200461616541859, "standard_deviation": 0.007471851041724593, "minimum": 0.07829388111662948, "maximum": 0.10411355689271574, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978165092616502, "standard_deviation": 0.0005141324681897213, "minimum": 0.9972306459932061, "maximum": 0.9987050064996106, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7239058098613769, "standard_deviation": 0.021936347591099775, "minimum": 0.687061260764929, "maximum": 0.7547249935825774, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5429371017838055, "standard_deviation": 0.32671045886680805, "minimum": 0.20064197538036174, "maximum": 1.1741492842959778, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05532334316934208, "standard_deviation": 0.008161654269799153, "minimum": 0.041369540640981584, "maximum": 0.06547072737983353, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9857207954251442, "standard_deviation": 0.002013278098351564, "minimum": 0.9830472965914566, "maximum": 0.9900403969030979, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.3368511872253466, "standard_deviation": 0.01898056950255686, "minimum": 1.2957789023594106, "maximum": 1.3564287224517138, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.1030868994417853, "standard_deviation": 0.17464944406966032, "minimum": 0.8325007516667274, "maximum": 1.3338294558010066, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14029212689357773, "standard_deviation": 0.010350358340740263, "minimum": 0.11867982677037059, "maximum": 0.15572683279159064, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9950572385398619, "standard_deviation": 0.0010212292649746616, "minimum": 0.9938220702630287, "maximum": 0.9968400968225712, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8519017621332905, "standard_deviation": 0.036064280061562294, "minimum": 0.7908232417706046, "maximum": 0.9085103192517019, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.9553908903368012, "standard_deviation": 0.28969010783700994, "minimum": 0.41547625488575574, "maximum": 1.2651478334928832, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0865903117697091, "standard_deviation": 0.009519680855805766, "minimum": 0.07202610446033075, "maximum": 0.10178386596546156, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9936701520683358, "standard_deviation": 0.0009852668097213972, "minimum": 0.9920735277248771, "maximum": 0.9946830972252009, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.7467679719648348, "standard_deviation": 0.021403730394638908, "minimum": 0.7167592064720777, "maximum": 0.7826648066971913, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.46085506418634203, "standard_deviation": 0.23561461258958272, "minimum": 0.07963462621343953, "maximum": 0.7467764456370652, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08600049981311052, "standard_deviation": 0.006423930153950867, "minimum": 0.07866278133011505, "maximum": 0.09601893817512715, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9978153334407921, "standard_deviation": 0.0006408611520591174, "minimum": 0.9964584038464487, "maximum": 0.9984885934466436, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5205890770457917, "standard_deviation": 0.016719163148561127, "minimum": 0.4968433207191975, "maximum": 0.5471741467431062, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.641100998861887, "standard_deviation": 0.4115526776252082, "minimum": 0.12739999426407525, "maximum": 1.2401124235521208, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04897201719576058, "standard_deviation": 0.006261656818787972, "minimum": 0.04264817075608939, "maximum": 0.06148837632060813, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.6886337666026165, "standard_deviation": 0.06100153875538329, "minimum": 1.6011258674058944, "maximum": 1.7801035701874726, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.569611446396818, "standard_deviation": 0.0061264329872233415, "minimum": 5.563633194330973, "maximum": 5.579468258107531, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3655654572768051, "standard_deviation": 0.017012976156704288, "minimum": 0.34912086526879255, "maximum": 0.4030891991630551, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06195482450528021, "standard_deviation": 0.07187691763207647, "minimum": -0.15118128518751617, "maximum": 0.07319779011760658, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9945861840906881, "standard_deviation": 0.0008475283299112052, "minimum": 0.9930385302322923, "maximum": 0.9954922413601264, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.0562480353087602, "standard_deviation": 0.024021127130364486, "minimum": 1.0260110984854447, "maximum": 1.0912284718474143, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.48205735272993844, "standard_deviation": 0.21730482625463754, "minimum": 0.16916824574024503, "maximum": 0.7812178488692086, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07692527995873372, "standard_deviation": 0.005619589314335737, "minimum": 0.07079408772974775, "maximum": 0.08680984932235031, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9982080810419509, "standard_deviation": 0.0005702879070389998, "minimum": 0.9969691332078334, "maximum": 0.998761609678246, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.7148630826125866, "standard_deviation": 0.04359825118466447, "minimum": 0.6533607616314195, "maximum": 0.7944310040470646, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5832220117142154, "standard_deviation": 0.36082564821867297, "minimum": 0.1175872722348139, "maximum": 1.096805356250078, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0429204979792135, "standard_deviation": 0.005717746479916324, "minimum": 0.03693875625337137, "maximum": 0.0548072912784614, "valid_count": 8, "planned_count": 8}}, "seconds": 3.897481070998765, "rtf_including_measurement": 0.8626085477781807}, {"case": "jvs_jvs004_falset10_BASIC5000_2951", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs004", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.472012758255005, "predicted_mos": 2.472012758255005, "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": 5.725749936005741}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.994361485669855, "全帯域_10ms_rms_envelope_nrmse": 0.08413795354842854, "全帯域_10ms_envelope_correlation": 0.9934640643529912, "全帯域_10ms_modulation_mae_db": 0.34182475265679096, "全帯域_40ms_log_rms_mae_db": 0.7176830550678875, "全帯域_40ms_rms_envelope_nrmse": 0.05213921785713584, "全帯域_40ms_envelope_correlation": 0.9972528134328876, "全帯域_40ms_modulation_mae_db": 0.29984734454171147, "300–1000 Hz_10ms_log_rms_mae_db": 0.7174736221729242, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0931000191788839, "300–1000 Hz_10ms_envelope_correlation": 0.9925578608936337, "300–1000 Hz_10ms_modulation_mae_db": 0.27826457505677615, "300–1000 Hz_40ms_log_rms_mae_db": 0.5255454632511392, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05878301130637659, "300–1000 Hz_40ms_envelope_correlation": 0.9967674393209743, "300–1000 Hz_40ms_modulation_mae_db": 0.3204822903032369, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1175148057526147, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0933719627669278, "1000–3000 Hz_10ms_envelope_correlation": 0.9940942929305878, "1000–3000 Hz_10ms_modulation_mae_db": 0.4839524172439358, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7309073544641382, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06307455182749092, "1000–3000 Hz_40ms_envelope_correlation": 0.9973859110029365, "1000–3000 Hz_40ms_modulation_mae_db": 0.6780075085912616, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3188478970985564, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15788212080159153, "3000–6000 Hz_10ms_envelope_correlation": 0.9819085335960327, "3000–6000 Hz_10ms_modulation_mae_db": 1.2109867524562132, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8891431545831362, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09707909263027742, "3000–6000 Hz_40ms_envelope_correlation": 0.9939041746471043, "3000–6000 Hz_40ms_modulation_mae_db": 0.7722544162984114, "mr_stft_db": 5.589305483408431, "band_mae_db": 1.598776173297294, "rms_gain_error_db": -0.024418067894821295, "output_peak": 0.3654046932475506}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9711412749792939, "全帯域_10ms_rms_envelope_nrmse": 0.07360551681326404, "全帯域_10ms_envelope_correlation": 0.995085158556724, "全帯域_10ms_modulation_mae_db": 0.35643207521990733, "全帯域_40ms_log_rms_mae_db": 0.6198486031241117, "全帯域_40ms_rms_envelope_nrmse": 0.0422537117636989, "全帯域_40ms_envelope_correlation": 0.9982559470437015, "全帯域_40ms_modulation_mae_db": 0.09854037238051117, "300–1000 Hz_10ms_log_rms_mae_db": 0.7139408467492915, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07982712534954216, "300–1000 Hz_10ms_envelope_correlation": 0.9946130733239086, "300–1000 Hz_10ms_modulation_mae_db": 0.3893119593474077, "300–1000 Hz_40ms_log_rms_mae_db": 0.49647766540201027, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04658871808374173, "300–1000 Hz_40ms_envelope_correlation": 0.9980332253668679, "300–1000 Hz_40ms_modulation_mae_db": 0.3405318500831232, "1000–3000 Hz_10ms_log_rms_mae_db": 1.104111901340075, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09429734573618205, "1000–3000 Hz_10ms_envelope_correlation": 0.9937439266872974, "1000–3000 Hz_10ms_modulation_mae_db": 0.14731447842074694, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6936735106542019, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.055423169390265696, "1000–3000 Hz_40ms_envelope_correlation": 0.9977191306444088, "1000–3000 Hz_40ms_modulation_mae_db": 0.7943070593177163, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2812472249981839, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11638954425524749, "3000–6000 Hz_10ms_envelope_correlation": 0.9903662905169366, "3000–6000 Hz_10ms_modulation_mae_db": 0.9428113271450248, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7946551329429022, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06976336052706232, "3000–6000 Hz_40ms_envelope_correlation": 0.9969715763575714, "3000–6000 Hz_40ms_modulation_mae_db": 1.1122275402471704, "mr_stft_db": 5.594092706908978, "band_mae_db": 1.781354014918395, "rms_gain_error_db": 0.06146856453529223, "output_peak": 0.3667089645921233}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9416610993820921, "全帯域_10ms_rms_envelope_nrmse": 0.07935179113956904, "全帯域_10ms_envelope_correlation": 0.9943131746473498, "全帯域_10ms_modulation_mae_db": 0.670591227621734, "全帯域_40ms_log_rms_mae_db": 0.6621059595761543, "全帯域_40ms_rms_envelope_nrmse": 0.044725263607877645, "全帯域_40ms_envelope_correlation": 0.9981596390154377, "全帯域_40ms_modulation_mae_db": 0.6801005646945385, "300–1000 Hz_10ms_log_rms_mae_db": 0.6938887461690891, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09101658148457598, "300–1000 Hz_10ms_envelope_correlation": 0.9929548060682769, "300–1000 Hz_10ms_modulation_mae_db": 0.6575738373256144, "300–1000 Hz_40ms_log_rms_mae_db": 0.48816690110828764, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05113781837069228, "300–1000 Hz_40ms_envelope_correlation": 0.997706485397096, "300–1000 Hz_40ms_modulation_mae_db": 0.8215369670201608, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0773311236901244, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08892755303527619, "1000–3000 Hz_10ms_envelope_correlation": 0.9946639318099083, "1000–3000 Hz_10ms_modulation_mae_db": 0.7572073642834868, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7010105178291491, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06374911431684926, "1000–3000 Hz_40ms_envelope_correlation": 0.9972817374707842, "1000–3000 Hz_40ms_modulation_mae_db": 0.5184999860263882, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2751916429287722, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1447492099593826, "3000–6000 Hz_10ms_envelope_correlation": 0.984082378387724, "3000–6000 Hz_10ms_modulation_mae_db": 1.0471268586119382, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8074926511498445, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08488551690535116, "3000–6000 Hz_40ms_envelope_correlation": 0.994428636692795, "3000–6000 Hz_40ms_modulation_mae_db": 0.8397782922218725, "mr_stft_db": 5.608019130165373, "band_mae_db": 1.7447996693622472, "rms_gain_error_db": -0.1251201230068453, "output_peak": 0.3527754672305711}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9692448582622096, "全帯域_10ms_rms_envelope_nrmse": 0.06737317814847596, "全帯域_10ms_envelope_correlation": 0.9958699307154668, "全帯域_10ms_modulation_mae_db": 0.4146123401856469, "全帯域_40ms_log_rms_mae_db": 0.6994405499790243, "全帯域_40ms_rms_envelope_nrmse": 0.037174880601906025, "全帯域_40ms_envelope_correlation": 0.99869324707427, "全帯域_40ms_modulation_mae_db": 0.43412633875293966, "300–1000 Hz_10ms_log_rms_mae_db": 0.7068607413590917, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.075038778795842, "300–1000 Hz_10ms_envelope_correlation": 0.9951682471559211, "300–1000 Hz_10ms_modulation_mae_db": 0.3507413815718859, "300–1000 Hz_40ms_log_rms_mae_db": 0.4931393522429403, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04158833924927736, "300–1000 Hz_40ms_envelope_correlation": 0.998411665518836, "300–1000 Hz_40ms_modulation_mae_db": 0.34370523206757103, "1000–3000 Hz_10ms_log_rms_mae_db": 1.104435341398842, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09645525750171381, "1000–3000 Hz_10ms_envelope_correlation": 0.9936274679300727, "1000–3000 Hz_10ms_modulation_mae_db": 0.46930053211201045, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7147019654437502, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05994300312038492, "1000–3000 Hz_40ms_envelope_correlation": 0.9976426070121661, "1000–3000 Hz_40ms_modulation_mae_db": 1.2038928722897653, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3163850895315297, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1462581666033441, "3000–6000 Hz_10ms_envelope_correlation": 0.9850678310574946, "3000–6000 Hz_10ms_modulation_mae_db": 1.121326476755281, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8596717055698574, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09445850254037633, "3000–6000 Hz_40ms_envelope_correlation": 0.9947010293858238, "3000–6000 Hz_40ms_modulation_mae_db": 0.928163064952671, "mr_stft_db": 5.59119230144375, "band_mae_db": 1.6948959043375165, "rms_gain_error_db": -0.08928271317351467, "output_peak": 0.4022433256117107}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0092555388688313, "全帯域_10ms_rms_envelope_nrmse": 0.08301655584355656, "全帯域_10ms_envelope_correlation": 0.993709238902528, "全帯域_10ms_modulation_mae_db": 0.7780535958850093, "全帯域_40ms_log_rms_mae_db": 0.6670113889557197, "全帯域_40ms_rms_envelope_nrmse": 0.046618972890827115, "全帯域_40ms_envelope_correlation": 0.997929383963972, "全帯域_40ms_modulation_mae_db": 0.9748772726516983, "300–1000 Hz_10ms_log_rms_mae_db": 0.7703224817697348, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09285676930231723, "300–1000 Hz_10ms_envelope_correlation": 0.9926839062310207, "300–1000 Hz_10ms_modulation_mae_db": 0.7331194985263584, "300–1000 Hz_40ms_log_rms_mae_db": 0.5378486978320286, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05412304564438133, "300–1000 Hz_40ms_envelope_correlation": 0.9974461314070548, "300–1000 Hz_40ms_modulation_mae_db": 1.0236018856998041, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0772516691940368, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08622210865752314, "1000–3000 Hz_10ms_envelope_correlation": 0.9946987533007581, "1000–3000 Hz_10ms_modulation_mae_db": 0.8639964002977085, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6956063650558939, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05049823858541646, "1000–3000 Hz_40ms_envelope_correlation": 0.9980668065453742, "1000–3000 Hz_40ms_modulation_mae_db": 0.29514396859412345, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2928447101534069, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14023370579959543, "3000–6000 Hz_10ms_envelope_correlation": 0.9852299735711574, "3000–6000 Hz_10ms_modulation_mae_db": 1.1438733548197615, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7702570406157737, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08019608431992126, "3000–6000 Hz_40ms_envelope_correlation": 0.9952958733741408, "3000–6000 Hz_40ms_modulation_mae_db": 1.270619490658922, "mr_stft_db": 5.596525438778536, "band_mae_db": 1.678271455085788, "rms_gain_error_db": -0.1079551730116105, "output_peak": 0.3522334223056132}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9164345358803155, "全帯域_10ms_rms_envelope_nrmse": 0.07223477857595442, "全帯域_10ms_envelope_correlation": 0.9952094434746734, "全帯域_10ms_modulation_mae_db": 0.5417720412973113, "全帯域_40ms_log_rms_mae_db": 0.6367658759935183, "全帯域_40ms_rms_envelope_nrmse": 0.036846227945087184, "全帯域_40ms_envelope_correlation": 0.9986796429545522, "全帯域_40ms_modulation_mae_db": 1.0480646288616748, "300–1000 Hz_10ms_log_rms_mae_db": 0.7063299003353894, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08038716217951562, "300–1000 Hz_10ms_envelope_correlation": 0.9944635278475157, "300–1000 Hz_10ms_modulation_mae_db": 0.5863674465263009, "300–1000 Hz_40ms_log_rms_mae_db": 0.4938103853894277, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04363386211201407, "300–1000 Hz_40ms_envelope_correlation": 0.9982753834532659, "300–1000 Hz_40ms_modulation_mae_db": 1.18985434300225, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1004374314659393, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1006680171447439, "1000–3000 Hz_10ms_envelope_correlation": 0.992755357920447, "1000–3000 Hz_10ms_modulation_mae_db": 0.2533838764069572, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7196149487822814, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05756410342825721, "1000–3000 Hz_40ms_envelope_correlation": 0.9974981147959046, "1000–3000 Hz_40ms_modulation_mae_db": 0.2870103924300845, "3000–6000 Hz_10ms_log_rms_mae_db": 1.30856699865719, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14301252715829466, "3000–6000 Hz_10ms_envelope_correlation": 0.9847864540966844, "3000–6000 Hz_10ms_modulation_mae_db": 1.0426186120094958, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8262593123886862, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0806251371335572, "3000–6000 Hz_40ms_envelope_correlation": 0.9954915581372978, "3000–6000 Hz_40ms_modulation_mae_db": 0.4233375000618138, "mr_stft_db": 5.602055462076906, "band_mae_db": 1.7457966522142419, "rms_gain_error_db": -0.06795312045195859, "output_peak": 0.37367641464609036}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9673659749827155, "全帯域_10ms_rms_envelope_nrmse": 0.0712011202510326, "全帯域_10ms_envelope_correlation": 0.9954675377261972, "全帯域_10ms_modulation_mae_db": 0.48158114562910015, "全帯域_40ms_log_rms_mae_db": 0.665714159934587, "全帯域_40ms_rms_envelope_nrmse": 0.03837639831146089, "全帯域_40ms_envelope_correlation": 0.9987211035116422, "全帯域_40ms_modulation_mae_db": 0.42121427190358557, "300–1000 Hz_10ms_log_rms_mae_db": 0.6877747464038957, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0806135506756732, "300–1000 Hz_10ms_envelope_correlation": 0.9945367788385985, "300–1000 Hz_10ms_modulation_mae_db": 0.5368392158992693, "300–1000 Hz_40ms_log_rms_mae_db": 0.4798966223193369, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04319813802792285, "300–1000 Hz_40ms_envelope_correlation": 0.9984547457311788, "300–1000 Hz_40ms_modulation_mae_db": 0.61446165269727, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1251955685740012, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09133045339034816, "1000–3000 Hz_10ms_envelope_correlation": 0.9941056355895763, "1000–3000 Hz_10ms_modulation_mae_db": 0.5026761994112937, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6757632355678646, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04867881969107097, "1000–3000 Hz_40ms_envelope_correlation": 0.9983031657148277, "1000–3000 Hz_40ms_modulation_mae_db": 0.6876242796412441, "3000–6000 Hz_10ms_log_rms_mae_db": 1.308453128713128, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14953157704541228, "3000–6000 Hz_10ms_envelope_correlation": 0.9829918201803785, "3000–6000 Hz_10ms_modulation_mae_db": 0.7482039295182559, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8300028102821349, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09092805092130499, "3000–6000 Hz_40ms_envelope_correlation": 0.9935530117284795, "3000–6000 Hz_40ms_modulation_mae_db": 0.5290051126023027, "mr_stft_db": 5.605235987655507, "band_mae_db": 1.6474019362797823, "rms_gain_error_db": -0.13126584276164852, "output_peak": 0.34830629930569773}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9833160969635085, "全帯域_10ms_rms_envelope_nrmse": 0.07512048988070776, "全帯域_10ms_envelope_correlation": 0.9947983051247945, "全帯域_10ms_modulation_mae_db": 0.19325306948667142, "全帯域_40ms_log_rms_mae_db": 0.635912933663267, "全帯域_40ms_rms_envelope_nrmse": 0.041520283625168235, "全帯域_40ms_envelope_correlation": 0.998255140773983, "全帯域_40ms_modulation_mae_db": 0.2453630459657216, "300–1000 Hz_10ms_log_rms_mae_db": 0.7584322804189074, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08455652147620552, "300–1000 Hz_10ms_envelope_correlation": 0.9938511180602471, "300–1000 Hz_10ms_modulation_mae_db": 0.10937475151809917, "300–1000 Hz_40ms_log_rms_mae_db": 0.5455074484734824, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0482591620935316, "300–1000 Hz_40ms_envelope_correlation": 0.9978149114032885, "300–1000 Hz_40ms_modulation_mae_db": 0.11035320244005926, "1000–3000 Hz_10ms_log_rms_mae_db": 1.104806459394018, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07954639719858271, "1000–3000 Hz_10ms_envelope_correlation": 0.9954868206601584, "1000–3000 Hz_10ms_modulation_mae_db": 0.3848032658105977, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6766468325615967, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0417499921792049, "1000–3000 Hz_40ms_envelope_correlation": 0.9986762881307805, "1000–3000 Hz_40ms_modulation_mae_db": 0.13998958740737186, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2928527511841443, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14416815827560386, "3000–6000 Hz_10ms_envelope_correlation": 0.9842272478701617, "3000–6000 Hz_10ms_modulation_mae_db": 1.1170714305775582, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8217727391284814, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08388616875423704, "3000–6000 Hz_40ms_envelope_correlation": 0.9946075188714081, "3000–6000 Hz_40ms_modulation_mae_db": 0.6244968241819593, "mr_stft_db": 5.593220738127438, "band_mae_db": 1.7100174889481352, "rms_gain_error_db": 0.0036585341170696384, "output_peak": 0.3531491668485316}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.4247663341555485, "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": 0.2125671444245829, "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": 1.1908140488952846e-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": 0.0015333470942817382, "delta_db": 0.06919784381235064, "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": 2.9741357908760126e-05, "delta_db": -0.23602986480626675, "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": 1.598776173297294, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.024418067894821295, "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}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 108438, "output_samples": 108438, "intelligibility": {"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"}}, "level": {"reference": {"rms": 0.05155569782788039, "rms_dbfs": -25.754466608205988, "peak": 0.359771728515625, "peak_dbfs": -8.879459345216006, "crest_factor_db": 16.875007262989982, "mean": -3.1914027918026893e-07, "zero_energy": false}, "output": {"rms": 0.05141096623199116, "rms_dbfs": -25.778884676100805, "peak": 0.3654046932475506, "peak_dbfs": -8.744517577632196, "crest_factor_db": 17.034367098468614, "mean": 4.349389705317901e-06, "zero_energy": false}, "rms_difference_db": -0.024418067894817597}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 451, "uncovered_tail_samples": 198, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 3.559632289689034e-06, "threshold_dbfs": -54.48594862366153, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 182, "quiet_samples": 43680, "reference_mean_power": 2.0628618059386482e-07, "output_mean_power": 3.3927987663624676e-07, "output_rms_dbfs": -64.69441898459827, "output_zero_energy": false, "output_peak": 0.013707460686728616, "output_energy_fraction": 5.170680459896621e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 444, "reference_estimated_voiced_frames": 263, "output_estimated_voiced_frames": 241, "both_estimated_voiced_frames": 240, "reference_voiced_output_unvoiced_frames": 23, "reference_unvoiced_output_voiced_frames": 1, "paired_voiced_fraction": 0.9125475285171103, "absolute_difference_cents_median": 2.469888984973377, "absolute_difference_cents_p95": 17.05467101858538, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 198, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.994361485669855, "rms_envelope_nrmse": 0.08413795354842854, "envelope_correlation": 0.9934640643529912, "rms_gain_error_db": -0.024418052707162675, "reference_mean_power": 0.002662852134818696, "output_mean_power": 0.0026479223538559225}, "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": 0.00042863340872873677, "reference_active": true, "delta_db": 0.28889934471866247}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0004799671480036486, "output_power": 0.00046654894494076724, "reference_active": true, "delta_db": -0.12314300876870143}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.6992126812237875e-05, "output_power": 4.0802043141821204e-05, "reference_active": true, "delta_db": -0.613431904483009}], "active_band_count": 3, "active_band_mae_db": 0.34182475265679096}}, {"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": 0.7176830550678875, "rms_envelope_nrmse": 0.05213921785713584, "envelope_correlation": 0.9972528134328876, "rms_gain_error_db": -0.024418029523618823, "reference_mean_power": 0.002680683564334513, "output_mean_power": 0.0026656538223406518}, "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": 0.0003898422445000547, "output_power": 0.0004192823973100845, "reference_active": true, "delta_db": 0.3161773103322164}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0002615577546182838, "output_power": 0.00023855850332896197, "reference_active": true, "delta_db": -0.3997269900487754}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.9711216791425515e-06, "output_power": 5.1858286999359295e-06, "reference_active": true, "delta_db": 0.18363773324414268}], "active_band_count": 3, "active_band_mae_db": 0.29984734454171147}}]}, {"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": 0.00018970614972877836, "log_rms_mae_db": 0.7174736221729242, "rms_envelope_nrmse": 0.0931000191788839, "envelope_correlation": 0.9925578608936337, "rms_gain_error_db": 0.005953683279080819, "reference_mean_power": 0.0020637883836989693, "output_mean_power": 0.0020666195429448384}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.5811898835528856e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00043243433753203383, "output_power": 0.00047130411301878755, "reference_active": true, "delta_db": 0.3738105792835458}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00038978360738039326, "output_power": 0.00038058917437020943, "reference_active": true, "delta_db": -0.10367139728610789}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.805770696622082e-05, "output_power": 3.505189023152108e-05, "reference_active": true, "delta_db": -0.35731174860067483}], "active_band_count": 3, "active_band_mae_db": 0.27826457505677615}}, {"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": 0.00016763715453010973, "log_rms_mae_db": 0.5255454632511392, "rms_envelope_nrmse": 0.05878301130637659, "envelope_correlation": 0.9967674393209743, "rms_gain_error_db": 0.0059536708990125305, "reference_mean_power": 0.00207760838531689, "output_mean_power": 0.002080458497274281}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.3894681028634637e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0004594859732757339, "output_power": 0.0004988340371432391, "reference_active": true, "delta_db": 0.35683820986730863}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019541576327050035, "output_power": 0.00018048793649026062, "reference_active": true, "delta_db": -0.34511413589093215}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.9559112605266995e-06, "output_power": 4.668464588017846e-06, "reference_active": true, "delta_db": -0.2594945251514697}], "active_band_count": 3, "active_band_mae_db": 0.3204822903032369}}]}, {"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": 1.1175148057526147, "rms_envelope_nrmse": 0.0933719627669278, "envelope_correlation": 0.9940942929305878, "rms_gain_error_db": -0.21347858570033906, "reference_mean_power": 0.0003994594973118105, "output_mean_power": 0.00038029874530565177}, "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": 9.988347573985858e-05, "reference_active": true, "delta_db": -0.3214474879325223}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.796860879459569e-05, "output_power": 7.8700153072011e-05, "reference_active": true, "delta_db": -0.4835214668360461}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.822952666689089e-06, "output_power": 4.155508452316829e-06, "reference_active": true, "delta_db": -0.646888296963239}], "active_band_count": 3, "active_band_mae_db": 0.4839524172439358}}, {"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": 0.7309073544641382, "rms_envelope_nrmse": 0.06307455182749092, "envelope_correlation": 0.9973859110029365, "rms_gain_error_db": -0.21347860638058602, "reference_mean_power": 0.00040213443933265886, "output_mean_power": 0.00038284537737451357}, "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": 9.790689346252202e-05, "reference_active": true, "delta_db": -0.3569811852339436}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.178329128126849e-05, "output_power": 4.456378843723135e-05, "reference_active": true, "delta_db": -0.6520754640350008}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.031671442188497e-07, "output_power": 5.104835126918806e-07, "reference_active": true, "delta_db": 1.0249658765048402}], "active_band_count": 3, "active_band_mae_db": 0.6780075085912616}}]}, {"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": 2.8330015424642847e-05, "log_rms_mae_db": 1.3188478970985564, "rms_envelope_nrmse": 0.15788212080159153, "envelope_correlation": 0.9819085335960327, "rms_gain_error_db": -0.44590271274916665, "reference_mean_power": 5.860864109462448e-05, "output_mean_power": 5.288973373424401e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 4.400349500158723e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.626242950468033e-05, "output_power": 1.4130640738465666e-05, "reference_active": true, "delta_db": -0.6102357206506339}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.53282953817687e-06, "output_power": 7.969097465176596e-06, "reference_active": true, "delta_db": -0.7781268878159981}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.75992153022225e-06, "output_power": 1.0496234852037119e-06, "reference_active": true, "delta_db": -2.244597648902008}], "active_band_count": 3, "active_band_mae_db": 1.2109867524562132}}, {"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": 2.5104708341377374e-05, "log_rms_mae_db": 0.8891431545831362, "rms_envelope_nrmse": 0.09707909263027742, "envelope_correlation": 0.9939041746471043, "rms_gain_error_db": -0.4459027415964159, "reference_mean_power": 5.9001105225872584e-05, "output_mean_power": 5.324390169116211e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 3.767766826204734e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3755010045242993e-05, "output_power": 1.176706193654265e-05, "reference_active": true, "delta_db": -0.6779287249844643}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.79209512684818e-06, "output_power": 4.894059563117505e-06, "reference_active": true, "delta_db": -0.7316643528524573}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0124260162334762e-07, "output_power": 8.215732294555252e-08, "reference_active": true, "delta_db": -0.9071701710583124}], "active_band_count": 3, "active_band_mae_db": 0.7722544162984114}}]}], "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"]}}, "output_samples": 108438, "representation_scalars": 1018638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9941470233536007, "standard_deviation": 0.0008229136382661373, "minimum": 0.992755357920447, "maximum": 0.9954868206601584, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1013855376012063, "standard_deviation": 0.016976728914784956, "minimum": 1.0772516691940368, "maximum": 1.1251955685740012, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4828293167483422, "standard_deviation": 0.2378397930674337, "minimum": 0.14731447842074694, "maximum": 0.8639964002977085, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09135238692891223, "standard_deviation": 0.006515401231908306, "minimum": 0.07954639719858271, "maximum": 0.1006680171447439, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978217201646478, "standard_deviation": 0.0004856484709545794, "minimum": 0.9972817374707842, "maximum": 0.9986762881307805, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7009905912948595, "standard_deviation": 0.019789785301649, "minimum": 0.6757632355678646, "maximum": 0.7309073544641382, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5755594567872444, "standard_deviation": 0.3423819557504907, "minimum": 0.13998958740737186, "maximum": 1.2038928722897653, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05508512406736754, "standard_deviation": 0.007640683232764331, "minimum": 0.0417499921792049, "maximum": 0.06374911431684926, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9848325661595713, "standard_deviation": 0.0024987144673580697, "minimum": 0.9819085335960327, "maximum": 0.9903662905169366, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.299298680408114, "standard_deviation": 0.016186550549912464, "minimum": 1.2751916429287722, "maximum": 1.3188478970985564, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.0467523427366912, "standard_deviation": 0.1448465324071813, "minimum": 0.7482039295182559, "maximum": 1.2109867524562132, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14277812623730898, "standard_deviation": 0.011919695998347113, "minimum": 0.11638954425524749, "maximum": 0.15788212080159153, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9948691723993276, "standard_deviation": 0.0010652864172908505, "minimum": 0.9935530117284795, "maximum": 0.9969715763575714, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.824906818332602, "standard_deviation": 0.03698945988516781, "minimum": 0.7702570406157737, "maximum": 0.8891431545831362, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.8124852801531404, "standard_deviation": 0.2884970457525218, "minimum": 0.4233375000618138, "maximum": 1.270619490658922, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08522773921651097, "standard_deviation": 0.008829500514990995, "minimum": 0.06976336052706232, "maximum": 0.09707909263027742, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9938536648023903, "standard_deviation": 0.0009999144379161688, "minimum": 0.9925578608936337, "maximum": 0.9951682471559211, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.7193779206722906, "standard_deviation": 0.029590463472478023, "minimum": 0.6877747464038957, "maximum": 0.7703224817697348, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.45519908322146396, "standard_deviation": 0.20983611368383456, "minimum": 0.10937475151809917, "maximum": 0.7331194985263584, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08467456355531947, "standard_deviation": 0.006859733022231098, "minimum": 0.075038778795842, "maximum": 0.0931000191788839, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9978637484498203, "standard_deviation": 0.0005670816428787873, "minimum": 0.9967674393209743, "maximum": 0.9984547457311788, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5075490670023316, "standard_deviation": 0.024905736193160433, "minimum": 0.4798966223193369, "maximum": 0.5455074484734824, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5955659279141844, "standard_deviation": 0.3831061113742007, "minimum": 0.11035320244005926, "maximum": 1.18985434300225, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04841401186099223, "standard_deviation": 0.005946535510359479, "minimum": 0.04158833924927736, "maximum": 0.05878301130637659, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.700164161805425, "standard_deviation": 0.058959980156587946, "minimum": 1.598776173297294, "maximum": 1.781354014918395, "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": 0.3643122192234861, "standard_deviation": 0.017700654014845055, "minimum": 0.34830629930569773, "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": 0.9947396066875906, "standard_deviation": 0.000846979888194628, "minimum": 0.9934640643529912, "maximum": 0.9958699307154668, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9690976081236027, "standard_deviation": 0.02924391593741167, "minimum": 0.9164345358803155, "maximum": 1.0092555388688313, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4722650309977714, "standard_deviation": 0.18874070968159565, "minimum": 0.19325306948667142, "maximum": 0.7780535958850093, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07575517302512362, "standard_deviation": 0.005908209880943847, "minimum": 0.06737317814847596, "maximum": 0.08413795354842854, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9982433647213058, "standard_deviation": 0.0004939707821239139, "minimum": 0.9972528134328876, "maximum": 0.9987211035116422, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6630603157867837, "standard_deviation": 0.03300727145346877, "minimum": 0.6198486031241117, "maximum": 0.7176830550678875, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5252667299690477, "standard_deviation": 0.34430668231349365, "minimum": 0.09854037238051117, "maximum": 1.0480646288616748, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.04245686957539523, "standard_deviation": 0.005253080767349403, "minimum": 0.036846227945087184, "maximum": 0.05213921785713584, "valid_count": 8, "planned_count": 8}}, "seconds": 4.4131754909976735, "rtf_including_measurement": 0.9767444233934982}, {"case": "jvs_jvs004_falset10_BASIC5000_2951", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs004", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.172290802001953, "predicted_mos": 2.172290802001953, "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": "12b28b335f1719827569e913be35ac19515ac0eb7dbc7e9390f324c8822ae64e", "internal_samples": 72292, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.567688160001126}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.834014491638036, "全帯域_10ms_rms_envelope_nrmse": 0.25334374761236084, "全帯域_10ms_envelope_correlation": 0.9883399114140473, "全帯域_10ms_modulation_mae_db": 1.764373584620565, "全帯域_40ms_log_rms_mae_db": 1.8437378792629013, "全帯域_40ms_rms_envelope_nrmse": 0.24738499874113068, "全帯域_40ms_envelope_correlation": 0.9897244825980688, "全帯域_40ms_modulation_mae_db": 1.7611897554795632, "300–1000 Hz_10ms_log_rms_mae_db": 1.1632265188609654, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2667669939250362, "300–1000 Hz_10ms_envelope_correlation": 0.989951508827169, "300–1000 Hz_10ms_modulation_mae_db": 1.9752990675221904, "300–1000 Hz_40ms_log_rms_mae_db": 1.0888944969433758, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.26211912365673684, "300–1000 Hz_40ms_envelope_correlation": 0.9909592645079284, "300–1000 Hz_40ms_modulation_mae_db": 1.9005309095649243, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0200974042997013, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.233988894449863, "1000–3000 Hz_10ms_envelope_correlation": 0.9829896385416298, "1000–3000 Hz_10ms_modulation_mae_db": 1.638978454407762, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8419471486639607, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.2263672665287744, "1000–3000 Hz_40ms_envelope_correlation": 0.9841558207070168, "1000–3000 Hz_40ms_modulation_mae_db": 1.630953624899732, "3000–6000 Hz_10ms_log_rms_mae_db": 1.35276139500429, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2656746583347149, "3000–6000 Hz_10ms_envelope_correlation": 0.9814936461616625, "3000–6000 Hz_10ms_modulation_mae_db": 1.6539208207565539, "3000–6000 Hz_40ms_log_rms_mae_db": 1.090423876476192, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.25149829789636613, "3000–6000 Hz_40ms_envelope_correlation": 0.9848965538941962, "3000–6000 Hz_40ms_modulation_mae_db": 1.5792467077021481, "mr_stft_db": 5.370968861541397, "band_mae_db": 3.8562529999439876, "rms_gain_error_db": 1.729073265652442, "output_peak": 0.38430579833817824}}], "planned_noise_seeds": [0], "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": 5.212308062273499, "spectral_convergence": 0.30385412956798324, "spectral_convergence_status": "ok", "amplitude_floor": 1.3518293902907786e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.509878787801963, "spectral_convergence": 0.2990872386286399, "spectral_convergence_status": "ok", "amplitude_floor": 1.2606433835114825e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.39071973454873, "spectral_convergence": 0.3237073370988172, "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": 9.99552777435808e-06, "delta_db": 19.489258058335494, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0005754412253654517, "output_power": 0.0009209086829326278, "delta_db": 2.0421559570691694, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0015091092814657461, "output_power": 0.0022775996761006407, "delta_db": 1.7875670222479578, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00043576714857085195, "output_power": 0.0005677487315175977, "delta_db": 1.1490168584230624, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 9.403622080703858e-05, "output_power": 0.00013123148727420568, "delta_db": 1.447428837323865, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.140246786176929e-05, "output_power": 3.729574132115705e-05, "delta_db": 0.746954641587625, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2121205040710494e-05, "output_power": 1.3082319766231727e-05, "delta_db": 0.3313896246207357, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 3.8562529999439876, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 1.729073265652442, "pitch": null, "output_rms_dbfs": -24.025393342553546, "output_peak": 0.38430579833817824, "reference_rms_dbfs": -25.754466608205988, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.370968861541397}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 108438, "output_samples": 108438, "intelligibility": {"estoi": {"value": 0.8572341459775907, "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"}}, "level": {"reference": {"rms": 0.05155569782788039, "rms_dbfs": -25.754466608205988, "peak": 0.359771728515625, "peak_dbfs": -8.879459345216006, "crest_factor_db": 16.875007262989982, "mean": -3.1914027918026893e-07, "zero_energy": false}, "output": {"rms": 0.06291154239634265, "rms_dbfs": -24.025393342553546, "peak": 0.38430579833817824, "peak_dbfs": -8.3064612585518, "crest_factor_db": 15.718932084001745, "mean": 9.424937499347548e-11, "zero_energy": false}, "rms_difference_db": 1.729073265652442}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 451, "uncovered_tail_samples": 198, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 3.559632289689034e-06, "threshold_dbfs": -54.48594862366153, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 182, "quiet_samples": 43680, "reference_mean_power": 2.0628618059386482e-07, "output_mean_power": 5.098757338255839e-07, "output_rms_dbfs": -62.92535656627195, "output_zero_energy": false, "output_peak": 0.02207622853421594, "output_energy_fraction": 5.189252561234716e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 444, "reference_estimated_voiced_frames": 263, "output_estimated_voiced_frames": 267, "both_estimated_voiced_frames": 256, "reference_voiced_output_unvoiced_frames": 7, "reference_unvoiced_output_voiced_frames": 11, "paired_voiced_fraction": 0.973384030418251, "absolute_difference_cents_median": 3.995341950698042, "absolute_difference_cents_p95": 13.99555122392462, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 198, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.834014491638036, "rms_envelope_nrmse": 0.25334374761236084, "envelope_correlation": 0.9883399114140473, "rms_gain_error_db": 1.7290732907222672, "reference_mean_power": 0.002662852134818696, "output_mean_power": 0.003965102150831891}, "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": 0.0007026999307496674, "reference_active": true, "delta_db": 2.435738272182472}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0004799671480036486, "output_power": 0.0007087452319579314, "reference_active": true, "delta_db": 1.692786376965787}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.6992126812237875e-05, "output_power": 6.14447401075749e-05, "reference_active": true, "delta_db": 1.1645961047134357}], "active_band_count": 3, "active_band_mae_db": 1.764373584620565}}, {"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": 1.8437378792629013, "rms_envelope_nrmse": 0.24738499874113068, "envelope_correlation": 0.9897244825980688, "rms_gain_error_db": 1.729073485602492, "reference_mean_power": 0.002680683564334513, "output_mean_power": 0.003991654100736527}, "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": 0.0003898422445000547, "output_power": 0.0007111655962122856, "reference_active": true, "delta_db": 2.61081839958919}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0002615577546182838, "output_power": 0.0003794907117442005, "reference_active": true, "delta_db": 1.6163355031093558}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.9711216791425515e-06, "output_power": 6.340097402290982e-06, "reference_active": true, "delta_db": 1.0564153637401439}], "active_band_count": 3, "active_band_mae_db": 1.7611897554795632}}]}, {"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": 0.00018970614972877836, "log_rms_mae_db": 1.1632265188609654, "rms_envelope_nrmse": 0.2667669939250362, "envelope_correlation": 0.989951508827169, "rms_gain_error_db": 1.8471164179532584, "reference_mean_power": 0.0020637883836989693, "output_mean_power": 0.003157743177100618}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.5811898835528856e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00043243433753203383, "output_power": 0.0007824128898876947, "reference_active": true, "delta_db": 2.575158247500002}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00038978360738039326, "output_power": 0.0006049179297134729, "reference_active": true, "delta_db": 1.9087288653743535}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.805770696622082e-05, "output_power": 5.304489899833402e-05, "reference_active": true, "delta_db": 1.4420100896922163}], "active_band_count": 3, "active_band_mae_db": 1.9752990675221904}}, {"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": 0.00016763715453010973, "log_rms_mae_db": 1.0888944969433758, "rms_envelope_nrmse": 0.26211912365673684, "envelope_correlation": 0.9909592645079284, "rms_gain_error_db": 1.8471163955315681, "reference_mean_power": 0.00207760838531689, "output_mean_power": 0.0031788887472038686}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.3894681028634637e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0004594859732757339, "output_power": 0.000848273442071292, "reference_active": true, "delta_db": 2.6626361200812165}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019541576327050035, "output_power": 0.00029922441848563266, "reference_active": true, "delta_db": 1.8503743835281041}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.9559112605266995e-06, "output_power": 6.516010026385465e-06, "reference_active": true, "delta_db": 1.1885822250854519}], "active_band_count": 3, "active_band_mae_db": 1.9005309095649243}}]}, {"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": 1.0200974042997013, "rms_envelope_nrmse": 0.233988894449863, "envelope_correlation": 0.9829896385416298, "rms_gain_error_db": 1.3069021630828492, "reference_mean_power": 0.0003994594973118105, "output_mean_power": 0.0005397131099384835}, "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": 0.00014315082718409632, "reference_active": true, "delta_db": 1.2415546660450079}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.796860879459569e-05, "output_power": 0.00011435004077101867, "reference_active": true, "delta_db": 1.1390860004120273}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.822952666689089e-06, "output_power": 8.648533447944537e-06, "reference_active": true, "delta_db": 2.5362946967662507}], "active_band_count": 3, "active_band_mae_db": 1.638978454407762}}, {"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": 0.8419471486639607, "rms_envelope_nrmse": 0.2263672665287744, "envelope_correlation": 0.9841558207070168, "rms_gain_error_db": 1.306902185494041, "reference_mean_power": 0.00040213443933265886, "output_mean_power": 0.0005433272495613603}, "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": 0.0001449232164709134, "reference_active": true, "delta_db": 1.3462657497658235}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.178329128126849e-05, "output_power": 6.716843325809304e-05, "reference_active": true, "delta_db": 1.1297556806051021}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.031671442188497e-07, "output_power": 7.033460889261039e-07, "reference_active": true, "delta_db": 2.4168394443282706}], "active_band_count": 3, "active_band_mae_db": 1.630953624899732}}]}, {"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": 2.8330015424642847e-05, "log_rms_mae_db": 1.35276139500429, "rms_envelope_nrmse": 0.2656746583347149, "envelope_correlation": 0.9814936461616625, "rms_gain_error_db": 1.5918684647214787, "reference_mean_power": 5.860864109462448e-05, "output_mean_power": 8.45567920903823e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 4.400349500158723e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.626242950468033e-05, "output_power": 2.419543656440808e-05, "reference_active": true, "delta_db": 1.725480356321016}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.53282953817687e-06, "output_power": 1.2930259399885555e-05, "reference_active": true, "delta_db": 1.3238541031870967}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.75992153022225e-06, "output_power": 2.7336071680402503e-06, "reference_active": true, "delta_db": 1.9124280027615495}], "active_band_count": 3, "active_band_mae_db": 1.6539208207565539}}, {"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": 2.5104708341377374e-05, "log_rms_mae_db": 1.090423876476192, "rms_envelope_nrmse": 0.25149829789636613, "envelope_correlation": 0.9848965538941962, "rms_gain_error_db": 1.5918685339929222, "reference_mean_power": 5.9001105225872584e-05, "output_mean_power": 8.512301555000243e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 3.767766826204734e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3755010045242993e-05, "output_power": 2.1480444803083158e-05, "reference_active": true, "delta_db": 1.9358235831856998}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.79209512684818e-06, "output_power": 7.657896084627372e-06, "reference_active": true, "delta_db": 1.2127378289356157}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0124260162334762e-07, "output_power": 1.4597590209359952e-07, "reference_active": true, "delta_db": 1.5891787109851288}], "active_band_count": 3, "active_band_mae_db": 1.5792467077021481}}]}], "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"]}}, "output_samples": 108438, "representation_scalars": 929312, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9829896385416298, "standard_deviation": null, "minimum": 0.9829896385416298, "maximum": 0.9829896385416298, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.0200974042997013, "standard_deviation": null, "minimum": 1.0200974042997013, "maximum": 1.0200974042997013, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 1.638978454407762, "standard_deviation": null, "minimum": 1.638978454407762, "maximum": 1.638978454407762, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.233988894449863, "standard_deviation": null, "minimum": 0.233988894449863, "maximum": 0.233988894449863, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9841558207070168, "standard_deviation": null, "minimum": 0.9841558207070168, "maximum": 0.9841558207070168, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8419471486639607, "standard_deviation": null, "minimum": 0.8419471486639607, "maximum": 0.8419471486639607, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.630953624899732, "standard_deviation": null, "minimum": 1.630953624899732, "maximum": 1.630953624899732, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.2263672665287744, "standard_deviation": null, "minimum": 0.2263672665287744, "maximum": 0.2263672665287744, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9814936461616625, "standard_deviation": null, "minimum": 0.9814936461616625, "maximum": 0.9814936461616625, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.35276139500429, "standard_deviation": null, "minimum": 1.35276139500429, "maximum": 1.35276139500429, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.6539208207565539, "standard_deviation": null, "minimum": 1.6539208207565539, "maximum": 1.6539208207565539, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2656746583347149, "standard_deviation": null, "minimum": 0.2656746583347149, "maximum": 0.2656746583347149, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9848965538941962, "standard_deviation": null, "minimum": 0.9848965538941962, "maximum": 0.9848965538941962, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.090423876476192, "standard_deviation": null, "minimum": 1.090423876476192, "maximum": 1.090423876476192, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.5792467077021481, "standard_deviation": null, "minimum": 1.5792467077021481, "maximum": 1.5792467077021481, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.25149829789636613, "standard_deviation": null, "minimum": 0.25149829789636613, "maximum": 0.25149829789636613, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.989951508827169, "standard_deviation": null, "minimum": 0.989951508827169, "maximum": 0.989951508827169, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.1632265188609654, "standard_deviation": null, "minimum": 1.1632265188609654, "maximum": 1.1632265188609654, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 1.9752990675221904, "standard_deviation": null, "minimum": 1.9752990675221904, "maximum": 1.9752990675221904, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2667669939250362, "standard_deviation": null, "minimum": 0.2667669939250362, "maximum": 0.2667669939250362, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9909592645079284, "standard_deviation": null, "minimum": 0.9909592645079284, "maximum": 0.9909592645079284, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.0888944969433758, "standard_deviation": null, "minimum": 1.0888944969433758, "maximum": 1.0888944969433758, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.9005309095649243, "standard_deviation": null, "minimum": 1.9005309095649243, "maximum": 1.9005309095649243, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.26211912365673684, "standard_deviation": null, "minimum": 0.26211912365673684, "maximum": 0.26211912365673684, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 3.8562529999439876, "standard_deviation": null, "minimum": 3.8562529999439876, "maximum": 3.8562529999439876, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 5.370968861541397, "standard_deviation": null, "minimum": 5.370968861541397, "maximum": 5.370968861541397, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.38430579833817824, "standard_deviation": null, "minimum": 0.38430579833817824, "maximum": 0.38430579833817824, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 1.729073265652442, "standard_deviation": null, "minimum": 1.729073265652442, "maximum": 1.729073265652442, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9883399114140473, "standard_deviation": null, "minimum": 0.9883399114140473, "maximum": 0.9883399114140473, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.834014491638036, "standard_deviation": null, "minimum": 1.834014491638036, "maximum": 1.834014491638036, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 1.764373584620565, "standard_deviation": null, "minimum": 1.764373584620565, "maximum": 1.764373584620565, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.25334374761236084, "standard_deviation": null, "minimum": 0.25334374761236084, "maximum": 0.25334374761236084, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9897244825980688, "standard_deviation": null, "minimum": 0.9897244825980688, "maximum": 0.9897244825980688, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 1.8437378792629013, "standard_deviation": null, "minimum": 1.8437378792629013, "maximum": 1.8437378792629013, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 1.7611897554795632, "standard_deviation": null, "minimum": 1.7611897554795632, "maximum": 1.7611897554795632, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.24738499874113068, "standard_deviation": null, "minimum": 0.24738499874113068, "maximum": 0.24738499874113068, "valid_count": 1, "planned_count": 1}}, "seconds": 1.3273232970022946, "rtf_including_measurement": 0.2937693348093387}, {"case": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "normal", "speaker": "jvs_jvs004", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.676879644393921, "predicted_mos": 1.676879644393921, "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": "ce18d8b3a945bd3e69227ada767924c0325cd0747959ab856f81471ef755b0a3", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.3861612230030005}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9946670911711095, "全帯域_10ms_rms_envelope_nrmse": 0.05234441454060623, "全帯域_10ms_envelope_correlation": 0.9971207965323974, "全帯域_10ms_modulation_mae_db": 0.4178186807899504, "全帯域_40ms_log_rms_mae_db": 0.5425257615343685, "全帯域_40ms_rms_envelope_nrmse": 0.027088398360148255, "全帯域_40ms_envelope_correlation": 0.9992028487411522, "全帯域_40ms_modulation_mae_db": 0.3447918393668104, "300–1000 Hz_10ms_log_rms_mae_db": 1.1510923469396819, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06517222375904663, "300–1000 Hz_10ms_envelope_correlation": 0.9964759033934395, "300–1000 Hz_10ms_modulation_mae_db": 0.8104200686739427, "300–1000 Hz_40ms_log_rms_mae_db": 0.7402757718647551, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.036035963312440786, "300–1000 Hz_40ms_envelope_correlation": 0.9988714072912467, "300–1000 Hz_40ms_modulation_mae_db": 0.9584176524424602, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4855231872038004, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1564329008649297, "1000–3000 Hz_10ms_envelope_correlation": 0.9838765851169813, "1000–3000 Hz_10ms_modulation_mae_db": 0.5862566233534673, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0581790366801127, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0898486424107162, "1000–3000 Hz_40ms_envelope_correlation": 0.995968713002013, "1000–3000 Hz_40ms_modulation_mae_db": 1.2693949712690296, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2815444021826161, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1518322234301353, "3000–6000 Hz_10ms_envelope_correlation": 0.9849146470024153, "3000–6000 Hz_10ms_modulation_mae_db": 0.6574002512657359, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8538357598137676, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10812109966279168, "3000–6000 Hz_40ms_envelope_correlation": 0.9920903008469805, "3000–6000 Hz_40ms_modulation_mae_db": 0.554318696216374, "mr_stft_db": 5.562378303462357, "band_mae_db": 0.23795956863005546, "rms_gain_error_db": -0.04907575916880806, "output_peak": 0.28232399798646884}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9394368234642235, "全帯域_10ms_rms_envelope_nrmse": 0.05371447196464645, "全帯域_10ms_envelope_correlation": 0.9971824973318192, "全帯域_10ms_modulation_mae_db": 0.6757282960084551, "全帯域_40ms_log_rms_mae_db": 0.5286935529119868, "全帯域_40ms_rms_envelope_nrmse": 0.032164200161988066, "全帯域_40ms_envelope_correlation": 0.9991151843648453, "全帯域_40ms_modulation_mae_db": 0.727493577211015, "300–1000 Hz_10ms_log_rms_mae_db": 1.1214894288819615, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06427496668321198, "300–1000 Hz_10ms_envelope_correlation": 0.9967605243188663, "300–1000 Hz_10ms_modulation_mae_db": 1.2573804019728658, "300–1000 Hz_40ms_log_rms_mae_db": 0.7206147006123772, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03656918736942718, "300–1000 Hz_40ms_envelope_correlation": 0.9990494835626749, "300–1000 Hz_40ms_modulation_mae_db": 1.5544581881405735, "1000–3000 Hz_10ms_log_rms_mae_db": 1.485355264088604, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.138328071801734, "1000–3000 Hz_10ms_envelope_correlation": 0.9896935489411081, "1000–3000 Hz_10ms_modulation_mae_db": 1.578289398226483, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0784904624727503, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10247109507196846, "1000–3000 Hz_40ms_envelope_correlation": 0.9960980330901362, "1000–3000 Hz_40ms_modulation_mae_db": 1.8185380079928322, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2673048276940542, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19838934388879345, "3000–6000 Hz_10ms_envelope_correlation": 0.9758151497475862, "3000–6000 Hz_10ms_modulation_mae_db": 2.0252280176940096, "3000–6000 Hz_40ms_log_rms_mae_db": 0.849894813218459, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11896215396168865, "3000–6000 Hz_40ms_envelope_correlation": 0.9937576231876772, "3000–6000 Hz_40ms_modulation_mae_db": 2.20933699588114, "mr_stft_db": 5.560190113913485, "band_mae_db": 0.3884941291315471, "rms_gain_error_db": -0.14301979255953726, "output_peak": 0.2829896467214802}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.003579652305038, "全帯域_10ms_rms_envelope_nrmse": 0.056786811748091075, "全帯域_10ms_envelope_correlation": 0.996687012586258, "全帯域_10ms_modulation_mae_db": 0.4737813206936201, "全帯域_40ms_log_rms_mae_db": 0.5773859397572461, "全帯域_40ms_rms_envelope_nrmse": 0.03264371891962084, "全帯域_40ms_envelope_correlation": 0.9989287091769967, "全帯域_40ms_modulation_mae_db": 0.5307564888718267, "300–1000 Hz_10ms_log_rms_mae_db": 1.0658104229625909, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06690109703573248, "300–1000 Hz_10ms_envelope_correlation": 0.9963490991620791, "300–1000 Hz_10ms_modulation_mae_db": 1.0810377234487654, "300–1000 Hz_40ms_log_rms_mae_db": 0.6904438796535611, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03595522589156346, "300–1000 Hz_40ms_envelope_correlation": 0.9989779443475165, "300–1000 Hz_40ms_modulation_mae_db": 0.947205765183328, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4838427243108636, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15303844361458102, "1000–3000 Hz_10ms_envelope_correlation": 0.9861108347310199, "1000–3000 Hz_10ms_modulation_mae_db": 0.7195674609638257, "1000–3000 Hz_40ms_log_rms_mae_db": 1.113698705918189, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11342792694136958, "1000–3000 Hz_40ms_envelope_correlation": 0.9939304591656158, "1000–3000 Hz_40ms_modulation_mae_db": 0.3309331479915669, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2604374934902411, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17511385419914216, "3000–6000 Hz_10ms_envelope_correlation": 0.9795372965360526, "3000–6000 Hz_10ms_modulation_mae_db": 0.5043300714603238, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7799862335324538, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09209661753353567, "3000–6000 Hz_40ms_envelope_correlation": 0.9941062178988466, "3000–6000 Hz_40ms_modulation_mae_db": 0.5991962684890716, "mr_stft_db": 5.563033124551535, "band_mae_db": 0.2725722868665189, "rms_gain_error_db": -0.09889027193838099, "output_peak": 0.2732575200948894}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9909961904697328, "全帯域_10ms_rms_envelope_nrmse": 0.055697772534592516, "全帯域_10ms_envelope_correlation": 0.9967778900275306, "全帯域_10ms_modulation_mae_db": 0.5246161373035328, "全帯域_40ms_log_rms_mae_db": 0.5309129606078601, "全帯域_40ms_rms_envelope_nrmse": 0.027265086332834948, "全帯域_40ms_envelope_correlation": 0.9992479963192532, "全帯域_40ms_modulation_mae_db": 0.5049302411807822, "300–1000 Hz_10ms_log_rms_mae_db": 1.1445101383690075, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07219409548696885, "300–1000 Hz_10ms_envelope_correlation": 0.9956990058611325, "300–1000 Hz_10ms_modulation_mae_db": 0.7134043255254584, "300–1000 Hz_40ms_log_rms_mae_db": 0.7547020179868971, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03838013987214523, "300–1000 Hz_40ms_envelope_correlation": 0.9987658489294156, "300–1000 Hz_40ms_modulation_mae_db": 0.7917496882351666, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3942516477998768, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11243302451799643, "1000–3000 Hz_10ms_envelope_correlation": 0.9920301810066737, "1000–3000 Hz_10ms_modulation_mae_db": 0.5910877352730356, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0220579913008725, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07148655929966388, "1000–3000 Hz_40ms_envelope_correlation": 0.9974525256807567, "1000–3000 Hz_40ms_modulation_mae_db": 0.9719732288108126, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2910815755273022, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1777225089646317, "3000–6000 Hz_10ms_envelope_correlation": 0.9818079639837337, "3000–6000 Hz_10ms_modulation_mae_db": 1.7808734272172027, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8457798281463693, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11777328359340306, "3000–6000 Hz_40ms_envelope_correlation": 0.9943364030791721, "3000–6000 Hz_40ms_modulation_mae_db": 1.8925664887768885, "mr_stft_db": 5.556481067296893, "band_mae_db": 0.2810747637533696, "rms_gain_error_db": -0.0813365623028465, "output_peak": 0.2781031840133591}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.984733115759093, "全帯域_10ms_rms_envelope_nrmse": 0.05440514432900865, "全帯域_10ms_envelope_correlation": 0.9969935802827558, "全帯域_10ms_modulation_mae_db": 0.4039536353672017, "全帯域_40ms_log_rms_mae_db": 0.5083367756480789, "全帯域_40ms_rms_envelope_nrmse": 0.029740036733902485, "全帯域_40ms_envelope_correlation": 0.9991584869436793, "全帯域_40ms_modulation_mae_db": 0.39267993890925007, "300–1000 Hz_10ms_log_rms_mae_db": 1.0928635006601877, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06465792870546425, "300–1000 Hz_10ms_envelope_correlation": 0.9966447746799413, "300–1000 Hz_10ms_modulation_mae_db": 0.7423741690497941, "300–1000 Hz_40ms_log_rms_mae_db": 0.6996892646339938, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.034761851484087766, "300–1000 Hz_40ms_envelope_correlation": 0.9990814339138158, "300–1000 Hz_40ms_modulation_mae_db": 0.9663811631648652, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4202073940539564, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.135201664983544, "1000–3000 Hz_10ms_envelope_correlation": 0.9885742586241173, "1000–3000 Hz_10ms_modulation_mae_db": 0.7635229982745265, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0315762759294902, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08721541068393357, "1000–3000 Hz_40ms_envelope_correlation": 0.9964003850717541, "1000–3000 Hz_40ms_modulation_mae_db": 0.7304602205371477, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2560720344384435, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17224866687675167, "3000–6000 Hz_10ms_envelope_correlation": 0.9827053061556997, "3000–6000 Hz_10ms_modulation_mae_db": 2.2923116866150064, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8497508417182583, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12379280187009124, "3000–6000 Hz_40ms_envelope_correlation": 0.9926160371536281, "3000–6000 Hz_40ms_modulation_mae_db": 2.6735787386973264, "mr_stft_db": 5.568944331584724, "band_mae_db": 0.3797712776354198, "rms_gain_error_db": -0.10698131250327146, "output_peak": 0.27310167197732693}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0219079033472285, "全帯域_10ms_rms_envelope_nrmse": 0.05621323805208055, "全帯域_10ms_envelope_correlation": 0.9967727557861569, "全帯域_10ms_modulation_mae_db": 0.49689536379798693, "全帯域_40ms_log_rms_mae_db": 0.5929603065308735, "全帯域_40ms_rms_envelope_nrmse": 0.030649805667937305, "全帯域_40ms_envelope_correlation": 0.9990926520252892, "全帯域_40ms_modulation_mae_db": 0.9135208650677812, "300–1000 Hz_10ms_log_rms_mae_db": 1.0984654240118072, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06901150927094354, "300–1000 Hz_10ms_envelope_correlation": 0.996134504921524, "300–1000 Hz_10ms_modulation_mae_db": 0.9245811089642156, "300–1000 Hz_40ms_log_rms_mae_db": 0.7506181071857715, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04004792193347995, "300–1000 Hz_40ms_envelope_correlation": 0.9987079716167496, "300–1000 Hz_40ms_modulation_mae_db": 1.1121308254802615, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4502479455268673, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13009716763861087, "1000–3000 Hz_10ms_envelope_correlation": 0.9891263766898472, "1000–3000 Hz_10ms_modulation_mae_db": 1.4687019138702107, "1000–3000 Hz_40ms_log_rms_mae_db": 1.071239620680607, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0849251527051782, "1000–3000 Hz_40ms_envelope_correlation": 0.9961277570766719, "1000–3000 Hz_40ms_modulation_mae_db": 1.6276107123056682, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2758702305414054, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19585591165274976, "3000–6000 Hz_10ms_envelope_correlation": 0.9759727086342055, "3000–6000 Hz_10ms_modulation_mae_db": 1.8981972051123428, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8676651477345134, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11683466691185666, "3000–6000 Hz_40ms_envelope_correlation": 0.9933771784586123, "3000–6000 Hz_40ms_modulation_mae_db": 2.331042482142219, "mr_stft_db": 5.549582216527561, "band_mae_db": 0.30656779476983603, "rms_gain_error_db": -0.10393527976433856, "output_peak": 0.2710550521827845}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.987673400990979, "全帯域_10ms_rms_envelope_nrmse": 0.049112979462188025, "全帯域_10ms_envelope_correlation": 0.9975591579393137, "全帯域_10ms_modulation_mae_db": 0.5112193109871512, "全帯域_40ms_log_rms_mae_db": 0.5303413117147444, "全帯域_40ms_rms_envelope_nrmse": 0.02616010407328836, "全帯域_40ms_envelope_correlation": 0.9993608989925982, "全帯域_40ms_modulation_mae_db": 0.6150845209920727, "300–1000 Hz_10ms_log_rms_mae_db": 1.0694176146590026, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06072326054637829, "300–1000 Hz_10ms_envelope_correlation": 0.997027708709207, "300–1000 Hz_10ms_modulation_mae_db": 0.6320567562225242, "300–1000 Hz_40ms_log_rms_mae_db": 0.7096792564949496, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03389934463620697, "300–1000 Hz_40ms_envelope_correlation": 0.9990951551667896, "300–1000 Hz_40ms_modulation_mae_db": 0.7594370119996895, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5208717908214313, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16019686257118476, "1000–3000 Hz_10ms_envelope_correlation": 0.9831765289391171, "1000–3000 Hz_10ms_modulation_mae_db": 0.42155560196125136, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1162057579646074, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10151527265102714, "1000–3000 Hz_40ms_envelope_correlation": 0.9944406197163634, "1000–3000 Hz_40ms_modulation_mae_db": 0.883568340287967, "3000–6000 Hz_10ms_log_rms_mae_db": 1.293499851935779, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1515706061175565, "3000–6000 Hz_10ms_envelope_correlation": 0.9857296980911238, "3000–6000 Hz_10ms_modulation_mae_db": 1.306335986844777, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8748095632463595, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08321004139502093, "3000–6000 Hz_40ms_envelope_correlation": 0.9968365352271119, "3000–6000 Hz_40ms_modulation_mae_db": 1.5336757871328086, "mr_stft_db": 5.56236304523878, "band_mae_db": 0.3144565252714884, "rms_gain_error_db": -0.09749424807656844, "output_peak": 0.2795747531093135}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9491667747317074, "全帯域_10ms_rms_envelope_nrmse": 0.05232117242132195, "全帯域_10ms_envelope_correlation": 0.9971770087793757, "全帯域_10ms_modulation_mae_db": 0.41995691575503397, "全帯域_40ms_log_rms_mae_db": 0.531082523269281, "全帯域_40ms_rms_envelope_nrmse": 0.025075305760106574, "全帯域_40ms_envelope_correlation": 0.9993900433946211, "全帯域_40ms_modulation_mae_db": 0.7090351049628438, "300–1000 Hz_10ms_log_rms_mae_db": 1.0819331759197233, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06465028422077569, "300–1000 Hz_10ms_envelope_correlation": 0.9966142020316984, "300–1000 Hz_10ms_modulation_mae_db": 0.677742443761368, "300–1000 Hz_40ms_log_rms_mae_db": 0.7097336865468458, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035056771685439095, "300–1000 Hz_40ms_envelope_correlation": 0.9990219845224845, "300–1000 Hz_40ms_modulation_mae_db": 0.9325795329086377, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4552893745321418, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13065031388956025, "1000–3000 Hz_10ms_envelope_correlation": 0.9896487709913184, "1000–3000 Hz_10ms_modulation_mae_db": 1.184736938315356, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0732075127770588, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08357913769028785, "1000–3000 Hz_40ms_envelope_correlation": 0.9970779954122077, "1000–3000 Hz_40ms_modulation_mae_db": 1.3619618285860018, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2964586695223879, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16018143513746144, "3000–6000 Hz_10ms_envelope_correlation": 0.9828380665128191, "3000–6000 Hz_10ms_modulation_mae_db": 1.2297367228733884, "3000–6000 Hz_40ms_log_rms_mae_db": 0.83162453557315, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08737662794605448, "3000–6000 Hz_40ms_envelope_correlation": 0.9948532108354068, "3000–6000 Hz_40ms_modulation_mae_db": 1.3955717366362081, "mr_stft_db": 5.55308880316436, "band_mae_db": 0.2537802806443176, "rms_gain_error_db": -0.08362090622154969, "output_peak": 0.27900857033188686}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.641757039808651, "spectral_convergence": 0.1522947611688196, "spectral_convergence_status": "ok", "amplitude_floor": 9.829298518478812e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.567876533352033, "spectral_convergence": 0.15502799924483684, "spectral_convergence_status": "ok", "amplitude_floor": 9.065329093063253e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.47750133722639, "spectral_convergence": 0.1590354780275675, "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": 0.00012054923477286424, "delta_db": 0.20650281340458243, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0017363654374162414, "output_power": 0.0017147160868464877, "delta_db": -0.05448910297423153, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0004421876194377549, "output_power": 0.00043513125384290975, "delta_db": -0.0698630069242521, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.7408011480563064e-05, "output_power": 2.531509177374221e-05, "delta_db": -0.34498021381771554, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7412343207141002e-05, "output_power": 2.357907557623004e-05, "delta_db": -0.65419386154161, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.428426915438781e-05, "output_power": 3.6567618754496645e-05, "delta_db": 0.2800178450623599, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.433275239990599e-05, "output_power": 1.4150200212454749e-05, "delta_db": -0.055670136685636806, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.23795956863005546, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.04907575916880806, "pitch": null, "output_rms_dbfs": -26.2525008507566, "output_peak": 0.28232399798646884, "reference_rms_dbfs": -26.20342509158779, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.562378303462357}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.9015413307358479, "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"}}, "level": {"reference": {"rms": 0.04895857238218429, "rms_dbfs": -26.20342509158779, "peak": 0.274444580078125, "peak_dbfs": -11.230906830925164, "crest_factor_db": 14.972518260662627, "mean": 2.86102294921875e-08, "zero_energy": false}, "output": {"rms": 0.04868273371308545, "rms_dbfs": -26.2525008507566, "peak": 0.28232399798646884, "peak_dbfs": -10.985044091320473, "crest_factor_db": 15.26745675943613, "mean": -5.0450103749001774e-05, "zero_energy": false}, "rms_difference_db": -0.04907575916881157}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.9656674889847638e-06, "threshold_dbfs": -57.06489945258896, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 169, "quiet_samples": 40560, "reference_mean_power": 1.257790860589557e-07, "output_mean_power": 1.8927020357721793e-07, "output_rms_dbfs": -67.22917750751118, "output_zero_energy": false, "output_peak": 0.008258640364559047, "output_energy_fraction": 2.2494056857286317e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 349, "output_estimated_voiced_frames": 337, "both_estimated_voiced_frames": 332, "reference_voiced_output_unvoiced_frames": 17, "reference_unvoiced_output_voiced_frames": 5, "paired_voiced_fraction": 0.9512893982808023, "absolute_difference_cents_median": 1.8278194096147502, "absolute_difference_cents_p95": 11.263739685916198, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.9946670911711095, "rms_envelope_nrmse": 0.05234441454060623, "envelope_correlation": 0.9971207965323974, "rms_gain_error_db": -0.049075792770425175, "reference_mean_power": 0.002398940884341968, "output_mean_power": 0.0023719851554557868}, "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": 0.00038418808294317104, "reference_active": true, "delta_db": -0.14451829862389878}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.277425400163653e-05, "output_power": 4.933733376026673e-05, "reference_active": true, "delta_db": -0.2924642691643619}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.46569016072901e-05, "output_power": 1.214492465763906e-05, "reference_active": true, "delta_db": -0.8164734745815903}], "active_band_count": 3, "active_band_mae_db": 0.4178186807899504}}, {"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": 0.5425257615343685, "rms_envelope_nrmse": 0.027088398360148255, "envelope_correlation": 0.9992028487411522, "rms_gain_error_db": -0.049075804861607106, "reference_mean_power": 0.0024110057038516162, "output_mean_power": 0.0023839144018349017}, "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": 0.0003415009566537694, "reference_active": true, "delta_db": -0.15214585513255763}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.2909806376051565e-05, "output_power": 2.187124630780674e-05, "reference_active": true, "delta_db": -0.2014788721834534}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.181144761591818e-07, "output_power": 6.994215322671101e-07, "reference_active": true, "delta_db": -0.6807507907844204}], "active_band_count": 3, "active_band_mae_db": 0.3447918393668104}}]}, {"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": 0.0001330045450117286, "log_rms_mae_db": 1.1510923469396819, "rms_envelope_nrmse": 0.06517222375904663, "envelope_correlation": 0.9964759033934395, "rms_gain_error_db": -0.056016842826398995, "reference_mean_power": 0.0013111812883454673, "output_mean_power": 0.001294377808563376}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.210472671322612e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00029715337433814054, "output_power": 0.00028437292821479004, "reference_active": true, "delta_db": -0.1909241629093828}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.93632000258319e-05, "output_power": 4.148712441361359e-05, "reference_active": true, "delta_db": -0.7548997184327078}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.447186660847196e-06, "output_power": 6.710561546970728e-06, "reference_active": true, "delta_db": -1.4854363246797373}], "active_band_count": 3, "active_band_mae_db": 0.8104200686739427}}, {"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": 0.00012063998479701062, "log_rms_mae_db": 0.7402757718647551, "rms_envelope_nrmse": 0.036035963312440786, "envelope_correlation": 0.9988714072912467, "rms_gain_error_db": -0.05601682204988901, "reference_mean_power": 0.001317775623677917, "output_mean_power": 0.0013008876402338166}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.775720236374232e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00027184637186405784, "output_power": 0.00025732976193723996, "reference_active": true, "delta_db": -0.23833522937612442}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0948015125222872e-05, "output_power": 1.82052316151132e-05, "reference_active": true, "delta_db": -0.6094667021176118}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.002499595181279e-07, "output_power": 4.3904394274887623e-07, "reference_active": true, "delta_db": -2.0274510258336447}], "active_band_count": 3, "active_band_mae_db": 0.9584176524424602}}]}, {"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": 1.4855231872038004, "rms_envelope_nrmse": 0.1564329008649297, "envelope_correlation": 0.9838765851169813, "rms_gain_error_db": -0.4680743274695739, "reference_mean_power": 3.621970358575803e-05, "output_mean_power": 3.251902074454892e-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": 1.3706110734389185e-05, "reference_active": true, "delta_db": -0.6764794457436603}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.217328435986185e-06, "output_power": 4.24875077499401e-06, "reference_active": true, "delta_db": -0.8918692004150887}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.162268250073546e-07, "output_power": 5.897914565936487e-07, "reference_active": true, "delta_db": -0.19042122390165306}], "active_band_count": 3, "active_band_mae_db": 0.5862566233534673}}, {"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": 1.0581790366801127, "rms_envelope_nrmse": 0.0898486424107162, "envelope_correlation": 0.995968713002013, "rms_gain_error_db": -0.46807436947774117, "reference_mean_power": 3.640185858193717e-05, "output_mean_power": 3.268256406663373e-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": 1.5750584190620256e-05, "output_power": 1.3380994237253645e-05, "reference_active": true, "delta_db": -0.7080828278242064}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.575523670498514e-06, "output_power": 2.0743935122222942e-06, "reference_active": true, "delta_db": -0.9397440015938942}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.671987913674405e-08, "output_power": 4.057134845831251e-08, "reference_active": true, "delta_db": -2.160358084388988}], "active_band_count": 3, "active_band_mae_db": 1.2693949712690296}}]}, {"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": 5.2682733202745264e-05, "log_rms_mae_db": 1.2815444021826161, "rms_envelope_nrmse": 0.1518322234301353, "envelope_correlation": 0.9849146470024153, "rms_gain_error_db": 0.05702055866714327, "reference_mean_power": 3.423479078027134e-05, "output_mean_power": 3.4687239102561726e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.0114400042064674e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3904345626991899e-05, "output_power": 1.5772746760318798e-05, "reference_active": true, "delta_db": 0.5475677584470302}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.3366002483256705e-06, "output_power": 4.804384281436528e-06, "reference_active": true, "delta_db": -0.45626934670577135}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0373079000270227e-06, "output_power": 1.630122734618796e-06, "reference_active": true, "delta_db": -0.9683636486444064}], "active_band_count": 3, "active_band_mae_db": 0.6574002512657359}}, {"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": 3.282155756745638e-05, "log_rms_mae_db": 0.8538357598137676, "rms_envelope_nrmse": 0.10812109966279168, "envelope_correlation": 0.9920903008469805, "rms_gain_error_db": 0.05702059908256768, "reference_mean_power": 3.440696652445241e-05, "output_mean_power": 3.486169065247616e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.861052719142989e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.506769965034781e-05, "output_power": 1.664583309702908e-05, "reference_active": true, "delta_db": 0.432585810972942}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.789058518393087e-06, "output_power": 2.5443417156957357e-06, "reference_active": true, "delta_db": -0.3988218802187485}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4153621023540904e-07, "output_power": 1.1687260467747593e-07, "reference_active": true, "delta_db": -0.8315483974574314}], "active_band_count": 3, "active_band_mae_db": 0.554318696216374}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9877796356300229, "standard_deviation": 0.003090915151140549, "minimum": 0.9831765289391171, "maximum": 0.9920301810066737, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4619486660421925, "standard_deviation": 0.04064020597426891, "minimum": 1.3942516477998768, "maximum": 1.5208717908214313, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.9142148337797695, "standard_deviation": 0.4370206950768517, "minimum": 0.42155560196125136, "maximum": 1.578289398226483, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.13954730623526762, "standard_deviation": 0.016113682147642357, "minimum": 0.11243302451799643, "maximum": 0.16019686257118476, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9959370610269398, "standard_deviation": 0.001203690754119266, "minimum": 0.9939304591656158, "maximum": 0.9974525256807567, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.070581920465461, "standard_deviation": 0.03389122644704727, "minimum": 1.0220579913008725, "maximum": 1.1162057579646074, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.124305057222628, "standard_deviation": 0.4896820675667377, "minimum": 0.3309331479915669, "maximum": 1.8185380079928322, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0918086496817681, "standard_deviation": 0.013246744339274624, "minimum": 0.07148655929966388, "maximum": 0.11342792694136958, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9811651045829545, "standard_deviation": 0.003755217787662055, "minimum": 0.9758151497475862, "maximum": 0.9857296980911238, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2777836356665286, "standard_deviation": 0.015457239287109929, "minimum": 1.2560720344384435, "maximum": 1.2964586695223879, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.4618016711353483, "standard_deviation": 0.6482152650700612, "minimum": 0.5043300714603238, "maximum": 2.2923116866150064, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17286431878340275, "standard_deviation": 0.017991301349007102, "minimum": 0.1515706061175565, "maximum": 0.19838934388879345, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9939966883359295, "standard_deviation": 0.0014593158655348698, "minimum": 0.9920903008469805, "maximum": 0.9968365352271119, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8441683403729163, "standard_deviation": 0.02910004191630273, "minimum": 0.7799862335324538, "maximum": 0.8748095632463595, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.6486608992465048, "standard_deviation": 0.7806760250873848, "minimum": 0.554318696216374, "maximum": 2.6735787386973264, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1060209116093053, "standard_deviation": 0.0160562104436606, "minimum": 0.08321004139502093, "maximum": 0.12379280187009124, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9964632153847359, "standard_deviation": 0.00040849135737527995, "minimum": 0.9956990058611325, "maximum": 0.997027708709207, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.1031977565504953, "standard_deviation": 0.0326353770825389, "minimum": 1.0658104229625909, "maximum": 1.1510923469396819, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8548746247023669, "standard_deviation": 0.21833449422538706, "minimum": 0.6320567562225242, "maximum": 1.2573804019728658, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06594817071356521, "standard_deviation": 0.0034507620983081706, "minimum": 0.06072326054637829, "maximum": 0.07219409548696885, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9989464036688367, "standard_deviation": 0.00014772911194250584, "minimum": 0.9987079716167496, "maximum": 0.9990951551667896, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7219695856223938, "standard_deviation": 0.023964719129890608, "minimum": 0.6904438796535611, "maximum": 0.7547020179868971, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.0027949784443728, "standard_deviation": 0.24824110433205945, "minimum": 0.7594370119996895, "maximum": 1.5544581881405735, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.036338300773098804, "standard_deviation": 0.0020106102551325964, "minimum": 0.03389934463620697, "maximum": 0.04004792193347995, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.3043345783378191, "standard_deviation": 0.05528136823699366, "minimum": 0.23795956863005546, "maximum": 0.3884941291315471, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.559507625717462, "standard_deviation": 0.006178483951562919, "minimum": 5.549582216527561, "maximum": 5.568944331584724, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.27742679955218863, "standard_deviation": 0.00445917680787757, "minimum": 0.2710550521827845, "maximum": 0.2829896467214802, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.09554426656691262, "standard_deviation": 0.026655169513431203, "minimum": -0.14301979255953726, "maximum": -0.04907575916880806, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9970338374082008, "standard_deviation": 0.00028827123448235464, "minimum": 0.996687012586258, "maximum": 0.9975591579393137, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.984020119029889, "standard_deviation": 0.02724587469852685, "minimum": 0.9394368234642235, "maximum": 1.0219079033472285, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.49049620758786655, "standard_deviation": 0.08780848579506058, "minimum": 0.4039536353672017, "maximum": 0.6757282960084551, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.053824500631566935, "standard_deviation": 0.0025351482606042145, "minimum": 0.049112979462188025, "maximum": 0.056786811748091075, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9991871024948044, "standard_deviation": 0.0001497737811578165, "minimum": 0.9989287091769967, "maximum": 0.9993900433946211, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.542779891496805, "standard_deviation": 0.02811415788351898, "minimum": 0.5083367756480789, "maximum": 0.5929603065308735, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5922865720702977, "standard_deviation": 0.18827635541066667, "minimum": 0.3447918393668104, "maximum": 0.9135208650677812, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.028848332001228355, "standard_deviation": 0.0028411948668073256, "minimum": 0.025075305760106574, "maximum": 0.03264371891962084, "valid_count": 8, "planned_count": 8}}, "seconds": 5.873392200002854, "rtf_including_measurement": 0.9788987000004757}, {"case": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "normal", "speaker": "jvs_jvs004", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.7263503074645996, "predicted_mos": 1.7263503074645996, "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": 6.71844756599603}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9315370829212664, "全帯域_10ms_rms_envelope_nrmse": 0.05169323246744281, "全帯域_10ms_envelope_correlation": 0.997195481477915, "全帯域_10ms_modulation_mae_db": 0.41678015462286316, "全帯域_40ms_log_rms_mae_db": 0.5116617492719026, "全帯域_40ms_rms_envelope_nrmse": 0.026753457254298025, "全帯域_40ms_envelope_correlation": 0.9992275494247639, "全帯域_40ms_modulation_mae_db": 0.34589150528068346, "300–1000 Hz_10ms_log_rms_mae_db": 1.1365509885149776, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0638396102307032, "300–1000 Hz_10ms_envelope_correlation": 0.9966277164996012, "300–1000 Hz_10ms_modulation_mae_db": 0.8372726632456232, "300–1000 Hz_40ms_log_rms_mae_db": 0.735139884343993, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035079922628879975, "300–1000 Hz_40ms_envelope_correlation": 0.9989410559869293, "300–1000 Hz_40ms_modulation_mae_db": 0.9530806987724061, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4672327648169978, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1577161025956383, "1000–3000 Hz_10ms_envelope_correlation": 0.9835703868414086, "1000–3000 Hz_10ms_modulation_mae_db": 0.5828082133275404, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0679743349209339, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09223510795440693, "1000–3000 Hz_40ms_envelope_correlation": 0.9956445072559342, "1000–3000 Hz_40ms_modulation_mae_db": 1.2171591822343724, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2545480398102464, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14464679117014598, "3000–6000 Hz_10ms_envelope_correlation": 0.9861605561836947, "3000–6000 Hz_10ms_modulation_mae_db": 0.5091776406922311, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8150399522904993, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.099784325005785, "3000–6000 Hz_40ms_envelope_correlation": 0.9931150303518008, "3000–6000 Hz_40ms_modulation_mae_db": 0.3302134953411164, "mr_stft_db": 5.568922089614407, "band_mae_db": 0.22192980125645798, "rms_gain_error_db": -0.05339151548452438, "output_peak": 0.2824466410723741}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8858283549790752, "全帯域_10ms_rms_envelope_nrmse": 0.053342519702947185, "全帯域_10ms_envelope_correlation": 0.9972045904407417, "全帯域_10ms_modulation_mae_db": 0.642562203477124, "全帯域_40ms_log_rms_mae_db": 0.5258574056870045, "全帯域_40ms_rms_envelope_nrmse": 0.03179684758841039, "全帯域_40ms_envelope_correlation": 0.9991177277020348, "全帯域_40ms_modulation_mae_db": 0.7022868667613852, "300–1000 Hz_10ms_log_rms_mae_db": 1.098008219026813, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06272049470343767, "300–1000 Hz_10ms_envelope_correlation": 0.9968960999262029, "300–1000 Hz_10ms_modulation_mae_db": 1.2434102930483597, "300–1000 Hz_40ms_log_rms_mae_db": 0.7083533539901655, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035382875441552136, "300–1000 Hz_40ms_envelope_correlation": 0.9990931165882462, "300–1000 Hz_40ms_modulation_mae_db": 1.5158890482879908, "1000–3000 Hz_10ms_log_rms_mae_db": 1.474477343076691, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.14007258864132047, "1000–3000 Hz_10ms_envelope_correlation": 0.9892501846698829, "1000–3000 Hz_10ms_modulation_mae_db": 1.505281119322614, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0775886831666215, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10326477760201437, "1000–3000 Hz_40ms_envelope_correlation": 0.9958919595817809, "1000–3000 Hz_40ms_modulation_mae_db": 1.743843739202268, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2553083499172126, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.20454524101720237, "3000–6000 Hz_10ms_envelope_correlation": 0.9744939832414824, "3000–6000 Hz_10ms_modulation_mae_db": 2.1704182632554234, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8338308016809768, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13246381496099482, "3000–6000 Hz_40ms_envelope_correlation": 0.9917925902473189, "3000–6000 Hz_40ms_modulation_mae_db": 2.368605627676801, "mr_stft_db": 5.568124854196441, "band_mae_db": 0.3729806875917494, "rms_gain_error_db": -0.13672727294078982, "output_peak": 0.28392376384758033}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9327525601580098, "全帯域_10ms_rms_envelope_nrmse": 0.0556550653032422, "全帯域_10ms_envelope_correlation": 0.996838802756841, "全帯域_10ms_modulation_mae_db": 0.46421286054460875, "全帯域_40ms_log_rms_mae_db": 0.5565273508136046, "全帯域_40ms_rms_envelope_nrmse": 0.03187922934733684, "全帯域_40ms_envelope_correlation": 0.9990035850281109, "全帯域_40ms_modulation_mae_db": 0.5151746271668013, "300–1000 Hz_10ms_log_rms_mae_db": 1.022464415311587, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06557506751521691, "300–1000 Hz_10ms_envelope_correlation": 0.9965099858606917, "300–1000 Hz_10ms_modulation_mae_db": 1.071013007855422, "300–1000 Hz_40ms_log_rms_mae_db": 0.6756640224286435, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03616020766626813, "300–1000 Hz_40ms_envelope_correlation": 0.9989812864989996, "300–1000 Hz_40ms_modulation_mae_db": 0.9333610270897852, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4917416667702292, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15296835339467454, "1000–3000 Hz_10ms_envelope_correlation": 0.9859686725298618, "1000–3000 Hz_10ms_modulation_mae_db": 0.8116596794350083, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1373771064871412, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11243477479215683, "1000–3000 Hz_40ms_envelope_correlation": 0.993941582247475, "1000–3000 Hz_40ms_modulation_mae_db": 0.37196223757638186, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2473902946555318, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16975996646779393, "3000–6000 Hz_10ms_envelope_correlation": 0.9806664356972182, "3000–6000 Hz_10ms_modulation_mae_db": 0.3563093006605897, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7741860740415601, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08332780110882979, "3000–6000 Hz_40ms_envelope_correlation": 0.9953232371978954, "3000–6000 Hz_40ms_modulation_mae_db": 0.4434748223129428, "mr_stft_db": 5.563514129583034, "band_mae_db": 0.23774376790640245, "rms_gain_error_db": -0.1059088129585081, "output_peak": 0.2731227831998249}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9446679040530642, "全帯域_10ms_rms_envelope_nrmse": 0.05492051304415142, "全帯域_10ms_envelope_correlation": 0.9968674922094137, "全帯域_10ms_modulation_mae_db": 0.4586553511513329, "全帯域_40ms_log_rms_mae_db": 0.5332169287662863, "全帯域_40ms_rms_envelope_nrmse": 0.027027125635420042, "全帯域_40ms_envelope_correlation": 0.9992602165313816, "全帯域_40ms_modulation_mae_db": 0.43703352870139706, "300–1000 Hz_10ms_log_rms_mae_db": 1.0990739942060574, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07229047378358952, "300–1000 Hz_10ms_envelope_correlation": 0.9956833916014545, "300–1000 Hz_10ms_modulation_mae_db": 0.682209628041378, "300–1000 Hz_40ms_log_rms_mae_db": 0.7291289446623432, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03859136837015616, "300–1000 Hz_40ms_envelope_correlation": 0.9987505629163658, "300–1000 Hz_40ms_modulation_mae_db": 0.7225095697077265, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3876034846077245, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1139534940682348, "1000–3000 Hz_10ms_envelope_correlation": 0.9916985206739511, "1000–3000 Hz_10ms_modulation_mae_db": 0.5120049681761096, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0182465312882703, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07239252895249168, "1000–3000 Hz_40ms_envelope_correlation": 0.9972640242774021, "1000–3000 Hz_40ms_modulation_mae_db": 0.8694938026768674, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2722286503492162, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17047456732306374, "3000–6000 Hz_10ms_envelope_correlation": 0.9829142493107461, "3000–6000 Hz_10ms_modulation_mae_db": 1.4420079239861512, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8302832993192211, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11319294277732861, "3000–6000 Hz_40ms_envelope_correlation": 0.9942681973533756, "3000–6000 Hz_40ms_modulation_mae_db": 1.4958425837213547, "mr_stft_db": 5.555275517184, "band_mae_db": 0.24645425085711445, "rms_gain_error_db": -0.08023086588573639, "output_peak": 0.27835030163170005}}, {"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": 0.3187976576558817, "全帯域_40ms_log_rms_mae_db": 0.49969557159076605, "全帯域_40ms_rms_envelope_nrmse": 0.029773761737596938, "全帯域_40ms_envelope_correlation": 0.9991553812223614, "全帯域_40ms_modulation_mae_db": 0.302798205567626, "300–1000 Hz_10ms_log_rms_mae_db": 1.0547230000723622, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.062573511116533, "300–1000 Hz_10ms_envelope_correlation": 0.9968691779106537, "300–1000 Hz_10ms_modulation_mae_db": 0.6814754558830071, "300–1000 Hz_40ms_log_rms_mae_db": 0.6954223374181839, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.034557574277962036, "300–1000 Hz_40ms_envelope_correlation": 0.9990950208882381, "300–1000 Hz_40ms_modulation_mae_db": 0.8464260229974393, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4199995296811851, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1364525826181342, "1000–3000 Hz_10ms_envelope_correlation": 0.9881872786177704, "1000–3000 Hz_10ms_modulation_mae_db": 0.6261466349785533, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0524056626282663, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08782690312088873, "1000–3000 Hz_40ms_envelope_correlation": 0.996172576932903, "1000–3000 Hz_40ms_modulation_mae_db": 0.6094916712189989, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2292857213496635, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16762098469479342, "3000–6000 Hz_10ms_envelope_correlation": 0.9837355494225892, "3000–6000 Hz_10ms_modulation_mae_db": 2.1777004064073284, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7994800294864488, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1210479539097843, "3000–6000 Hz_40ms_envelope_correlation": 0.9929917810741393, "3000–6000 Hz_40ms_modulation_mae_db": 2.5119481399732226, "mr_stft_db": 5.573383731452393, "band_mae_db": 0.36227307159227407, "rms_gain_error_db": -0.10697375025968767, "output_peak": 0.2727423009064838}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9516114090001102, "全帯域_10ms_rms_envelope_nrmse": 0.055245734885806475, "全帯域_10ms_envelope_correlation": 0.9968892484430428, "全帯域_10ms_modulation_mae_db": 0.4785741883439843, "全帯域_40ms_log_rms_mae_db": 0.549306567862663, "全帯域_40ms_rms_envelope_nrmse": 0.030542290580230638, "全帯域_40ms_envelope_correlation": 0.9991016937419336, "全帯域_40ms_modulation_mae_db": 0.8679374182229713, "300–1000 Hz_10ms_log_rms_mae_db": 1.0681696644501042, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06840180772760344, "300–1000 Hz_10ms_envelope_correlation": 0.9961983418771558, "300–1000 Hz_10ms_modulation_mae_db": 0.8591902744843155, "300–1000 Hz_40ms_log_rms_mae_db": 0.7364061210684311, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03984152036877206, "300–1000 Hz_40ms_envelope_correlation": 0.9987198749923973, "300–1000 Hz_40ms_modulation_mae_db": 1.0688729648075552, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4368015149314681, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12876476547750823, "1000–3000 Hz_10ms_envelope_correlation": 0.989207790625399, "1000–3000 Hz_10ms_modulation_mae_db": 1.402153375218255, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0672919590893024, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.084125245772578, "1000–3000 Hz_40ms_envelope_correlation": 0.996023178404845, "1000–3000 Hz_40ms_modulation_mae_db": 1.5482403681797583, "3000–6000 Hz_10ms_log_rms_mae_db": 1.266825415741867, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19772533358042785, "3000–6000 Hz_10ms_envelope_correlation": 0.9761791797288096, "3000–6000 Hz_10ms_modulation_mae_db": 2.2119020651380876, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8501526028088341, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12597568677803744, "3000–6000 Hz_40ms_envelope_correlation": 0.9926414918950908, "3000–6000 Hz_40ms_modulation_mae_db": 2.6606924354138015, "mr_stft_db": 5.5572456557634995, "band_mae_db": 0.2976222013564837, "rms_gain_error_db": -0.10570937460654552, "output_peak": 0.2718293109304641}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9128546413992539, "全帯域_10ms_rms_envelope_nrmse": 0.048238932435754125, "全帯域_10ms_envelope_correlation": 0.9976454267121504, "全帯域_10ms_modulation_mae_db": 0.46859010455024813, "全帯域_40ms_log_rms_mae_db": 0.5051910312616704, "全帯域_40ms_rms_envelope_nrmse": 0.02535228853366984, "全帯域_40ms_envelope_correlation": 0.9994051771591547, "全帯域_40ms_modulation_mae_db": 0.573636660127394, "300–1000 Hz_10ms_log_rms_mae_db": 1.040700299822052, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05834461067554268, "300–1000 Hz_10ms_envelope_correlation": 0.9972560410340112, "300–1000 Hz_10ms_modulation_mae_db": 0.5996303046313275, "300–1000 Hz_40ms_log_rms_mae_db": 0.6828874192648101, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.032157105060893955, "300–1000 Hz_40ms_envelope_correlation": 0.9991926711006439, "300–1000 Hz_40ms_modulation_mae_db": 0.7179733812173752, "1000–3000 Hz_10ms_log_rms_mae_db": 1.521752737232611, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1637333955900092, "1000–3000 Hz_10ms_envelope_correlation": 0.9823942503841385, "1000–3000 Hz_10ms_modulation_mae_db": 0.41330553074882337, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1184674405498556, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10525917034092853, "1000–3000 Hz_40ms_envelope_correlation": 0.9939460004048656, "1000–3000 Hz_40ms_modulation_mae_db": 0.7238854456122917, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2874962317515568, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1458066934994391, "3000–6000 Hz_10ms_envelope_correlation": 0.9867401511370677, "3000–6000 Hz_10ms_modulation_mae_db": 1.0578650538715715, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8402757897853902, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08165079512143852, "3000–6000 Hz_40ms_envelope_correlation": 0.9967684194825882, "3000–6000 Hz_40ms_modulation_mae_db": 1.2283398865072406, "mr_stft_db": 5.5620722755465435, "band_mae_db": 0.2922417615507095, "rms_gain_error_db": -0.09683588334369532, "output_peak": 0.2795111188134531}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8888530202150069, "全帯域_10ms_rms_envelope_nrmse": 0.04991690908535333, "全帯域_10ms_envelope_correlation": 0.9974507120823614, "全帯域_10ms_modulation_mae_db": 0.4387704234772423, "全帯域_40ms_log_rms_mae_db": 0.5099004065988975, "全帯域_40ms_rms_envelope_nrmse": 0.024354026357884175, "全帯域_40ms_envelope_correlation": 0.9994442313768965, "全帯域_40ms_modulation_mae_db": 0.7064016467078762, "300–1000 Hz_10ms_log_rms_mae_db": 1.0386436390387024, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06241574019949519, "300–1000 Hz_10ms_envelope_correlation": 0.9968497632511799, "300–1000 Hz_10ms_modulation_mae_db": 0.6966770102245324, "300–1000 Hz_40ms_log_rms_mae_db": 0.6903431411687245, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03321811720399553, "300–1000 Hz_40ms_envelope_correlation": 0.999137392717255, "300–1000 Hz_40ms_modulation_mae_db": 0.8903765931218821, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4558690233564857, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13247752504463206, "1000–3000 Hz_10ms_envelope_correlation": 0.9892010222563747, "1000–3000 Hz_10ms_modulation_mae_db": 1.2362730193084135, "1000–3000 Hz_40ms_log_rms_mae_db": 1.08442784573557, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08530364418268667, "1000–3000 Hz_40ms_envelope_correlation": 0.9967531583831206, "1000–3000 Hz_40ms_modulation_mae_db": 1.4220777722357365, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2784370820817061, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15435269257145745, "3000–6000 Hz_10ms_envelope_correlation": 0.9841443334437864, "3000–6000 Hz_10ms_modulation_mae_db": 1.256266913178643, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8143271630598738, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08395108290372773, "3000–6000 Hz_40ms_envelope_correlation": 0.9953703859939494, "3000–6000 Hz_40ms_modulation_mae_db": 1.5668489413338191, "mr_stft_db": 5.55543236414091, "band_mae_db": 0.2371005811322278, "rms_gain_error_db": -0.09019341346300494, "output_peak": 0.2779013481938124}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.631064715334124, "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": 5.569330114313072, "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": 5.506371439196027, "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": 2.528759096307183e-05, "delta_db": -0.34970069536213555, "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": 3.6398547102869416e-05, "delta_db": 0.2598915259946608, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.433275239990599e-05, "output_power": 1.4350469462922995e-05, "delta_db": 0.005365104184712935, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.22192980125645798, "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": 0.2824466410723741, "reference_rms_dbfs": -26.20342509158779, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.568922089614407}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.9013501246093948, "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"}}, "level": {"reference": {"rms": 0.04895857238218429, "rms_dbfs": -26.20342509158779, "peak": 0.274444580078125, "peak_dbfs": -11.230906830925164, "crest_factor_db": 14.972518260662627, "mean": 2.86102294921875e-08, "zero_energy": false}, "output": {"rms": 0.04865855074093033, "rms_dbfs": -26.256816607072317, "peak": 0.2824466410723741, "peak_dbfs": -10.98127171275786, "crest_factor_db": 15.275544894314457, "mean": -5.6739620089185837e-05, "zero_energy": false}, "rms_difference_db": -0.053391515484527474}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.9656674889847638e-06, "threshold_dbfs": -57.06489945258896, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 169, "quiet_samples": 40560, "reference_mean_power": 1.257790860589557e-07, "output_mean_power": 1.442763430172665e-07, "output_rms_dbfs": -68.40804874307304, "output_zero_energy": false, "output_peak": 0.00677929561074807, "output_energy_fraction": 1.7163752390029943e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 349, "output_estimated_voiced_frames": 336, "both_estimated_voiced_frames": 331, "reference_voiced_output_unvoiced_frames": 18, "reference_unvoiced_output_voiced_frames": 5, "paired_voiced_fraction": 0.9484240687679083, "absolute_difference_cents_median": 1.7313667749632111, "absolute_difference_cents_p95": 11.092287435892121, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.9315370829212664, "rms_envelope_nrmse": 0.05169323246744281, "envelope_correlation": 0.997195481477915, "rms_gain_error_db": -0.05339153292308116, "reference_mean_power": 0.002398940884341968, "output_mean_power": 0.002369629199459496}, "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": 0.0003838095519743816, "reference_active": true, "delta_db": -0.14879940358601318}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.277425400163653e-05, "output_power": 4.9013662656672806e-05, "reference_active": true, "delta_db": -0.32104945626869386}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.46569016072901e-05, "output_power": 1.2245964948172324e-05, "reference_active": true, "delta_db": -0.7804916040138825}], "active_band_count": 3, "active_band_mae_db": 0.41678015462286316}}, {"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": 0.5116617492719026, "rms_envelope_nrmse": 0.026753457254298025, "envelope_correlation": 0.9992275494247639, "rms_gain_error_db": -0.053391539555837746, "reference_mean_power": 0.0024110057038516162, "output_mean_power": 0.00238154660019972}, "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": 0.0003407416994912562, "reference_active": true, "delta_db": -0.16181224960920074}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.2909806376051565e-05, "output_power": 2.1838254644364392e-05, "reference_active": true, "delta_db": -0.20803492969528434}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.181144761591818e-07, "output_power": 7.015059253801525e-07, "reference_active": true, "delta_db": -0.6678273365375652}], "active_band_count": 3, "active_band_mae_db": 0.34589150528068346}}]}, {"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": 0.0001330045450117286, "log_rms_mae_db": 1.1365509885149776, "rms_envelope_nrmse": 0.0638396102307032, "envelope_correlation": 0.9966277164996012, "rms_gain_error_db": -0.061063616200730905, "reference_mean_power": 0.0013111812883454673, "output_mean_power": 0.0012928745342516913}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.210472671322612e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00029715337433814054, "output_power": 0.00028310978267440974, "reference_active": true, "delta_db": -0.21025789884469015}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.93632000258319e-05, "output_power": 4.158859865369663e-05, "reference_active": true, "delta_db": -0.7442901870766558}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.447186660847196e-06, "output_power": 6.6004797956822675e-06, "reference_active": true, "delta_db": -1.5572699038155235}], "active_band_count": 3, "active_band_mae_db": 0.8372726632456232}}, {"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": 0.00012063998479701062, "log_rms_mae_db": 0.735139884343993, "rms_envelope_nrmse": 0.035079922628879975, "envelope_correlation": 0.9989410559869293, "rms_gain_error_db": -0.0610636014334049, "reference_mean_power": 0.001317775623677917, "output_mean_power": 0.001299376803686574}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.775720236374232e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00027184637186405784, "output_power": 0.0002560659587153673, "reference_active": true, "delta_db": -0.25971693756151937}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0948015125222872e-05, "output_power": 1.832341824182064e-05, "reference_active": true, "delta_db": -0.5813638408741135}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.002499595181279e-07, "output_power": 4.399840779360057e-07, "reference_active": true, "delta_db": -2.018161317881585}], "active_band_count": 3, "active_band_mae_db": 0.9530806987724061}}]}, {"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": 1.4672327648169978, "rms_envelope_nrmse": 0.1577161025956383, "envelope_correlation": 0.9835703868414086, "rms_gain_error_db": -0.4595407860100338, "reference_mean_power": 3.621970358575803e-05, "output_mean_power": 3.258298085389228e-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": 1.3680481743581312e-05, "reference_active": true, "delta_db": -0.6846078995064286}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.217328435986185e-06, "output_power": 4.191404170761103e-06, "reference_active": true, "delta_db": -0.9508863563742537}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.162268250073546e-07, "output_power": 6.004095083180499e-07, "reference_active": true, "delta_db": -0.11293038410193865}], "active_band_count": 3, "active_band_mae_db": 0.5828082133275404}}, {"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": 1.0679743349209339, "rms_envelope_nrmse": 0.09223510795440693, "envelope_correlation": 0.9956445072559342, "rms_gain_error_db": -0.45954088342585875, "reference_mean_power": 3.640185858193717e-05, "output_mean_power": 3.274684542374221e-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": 1.5750584190620256e-05, "output_power": 1.3329881717411537e-05, "reference_active": true, "delta_db": -0.7247037072405572}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.575523670498514e-06, "output_power": 2.0379012754802783e-06, "reference_active": true, "delta_db": -1.016824045169564}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.671987913674405e-08, "output_power": 4.2979392390199845e-08, "reference_active": true, "delta_db": -1.9099497942929957}], "active_band_count": 3, "active_band_mae_db": 1.2171591822343724}}]}, {"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": 5.2682733202745264e-05, "log_rms_mae_db": 1.2545480398102464, "rms_envelope_nrmse": 0.14464679117014598, "envelope_correlation": 0.9861605561836947, "rms_gain_error_db": 0.029331099913000865, "reference_mean_power": 3.423479078027134e-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": 3.0114400042064674e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3904345626991899e-05, "output_power": 1.5273510184477063e-05, "reference_active": true, "delta_db": 0.4078830412989473}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.3366002483256705e-06, "output_power": 4.693191104252162e-06, "reference_active": true, "delta_db": -0.5579643327089393}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0373079000270227e-06, "output_power": 1.7901446067783784e-06, "reference_active": true, "delta_db": -0.561685548068807}], "active_band_count": 3, "active_band_mae_db": 0.5091776406922311}}, {"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": 3.282155756745638e-05, "log_rms_mae_db": 0.8150399522904993, "rms_envelope_nrmse": 0.099784325005785, "envelope_correlation": 0.9931150303518008, "rms_gain_error_db": 0.029331125705465685, "reference_mean_power": 3.440696652445241e-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": 2.861052719142989e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.506769965034781e-05, "output_power": 1.6219514283474224e-05, "reference_active": true, "delta_db": 0.3199088982532656}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.789058518393087e-06, "output_power": 2.524901636285786e-06, "reference_active": true, "delta_db": -0.43213162692967644}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4153621023540904e-07, "output_power": 1.3397000287748956e-07, "reference_active": true, "delta_db": -0.23859996084040708}], "active_band_count": 3, "active_band_mae_db": 0.3302134953411164}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9874347633248484, "standard_deviation": 0.0031801742003090923, "minimum": 0.9823942503841385, "maximum": 0.9916985206739511, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.456934758059174, "standard_deviation": 0.04209547378699066, "minimum": 1.3876034846077245, "maximum": 1.521752737232611, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8862040675644147, "standard_deviation": 0.43109530361219756, "minimum": 0.41330553074882337, "maximum": 1.505281119322614, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14076735092876896, "standard_deviation": 0.016537532905796775, "minimum": 0.1139534940682348, "maximum": 0.1637333955900092, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9957046234360408, "standard_deviation": 0.0012006779184891656, "minimum": 0.993941582247475, "maximum": 0.9972640242774021, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.0779724454832451, "standard_deviation": 0.03712037957159022, "minimum": 1.0182465312882703, "maximum": 1.1373771064871412, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.0632692773670844, "standard_deviation": 0.4909690206680066, "minimum": 0.37196223757638186, "maximum": 1.743843739202268, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09285526908976896, "standard_deviation": 0.013219059947111946, "minimum": 0.07239252895249168, "maximum": 0.11243477479215683, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9818793047706743, "standard_deviation": 0.0044738845589832365, "minimum": 0.9744939832414824, "maximum": 0.9867401511370677, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2614399732071249, "standard_deviation": 0.01863028945113882, "minimum": 1.2292857213496635, "maximum": 1.2874962317515568, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.3977059458987533, "standard_deviation": 0.7444883212556829, "minimum": 0.3563093006605897, "maximum": 2.2119020651380876, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16936653379054045, "standard_deviation": 0.022160903845676025, "minimum": 0.14464679117014598, "maximum": 0.20454524101720237, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9940338916995198, "standard_deviation": 0.0016849620723116267, "minimum": 0.9917925902473189, "maximum": 0.9967684194825882, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8196969640591005, "standard_deviation": 0.02447552110980693, "minimum": 0.7741860740415601, "maximum": 0.8501526028088341, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.5757457415350373, "standard_deviation": 0.8978349804682958, "minimum": 0.3302134953411164, "maximum": 2.6606924354138015, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10517430032074077, "standard_deviation": 0.020715033909359023, "minimum": 0.08165079512143852, "maximum": 0.13246381496099482, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9966113147451189, "standard_deviation": 0.00048730310305471794, "minimum": 0.9956833916014545, "maximum": 0.9972560410340112, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.069791777555332, "standard_deviation": 0.03853849126284219, "minimum": 1.022464415311587, "maximum": 1.1365509885149776, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8338598296767457, "standard_deviation": 0.2218519030549393, "minimum": 0.5996303046313275, "maximum": 1.2434102930483597, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.0645201644940152, "standard_deviation": 0.00425298504315928, "minimum": 0.05834461067554268, "maximum": 0.07229047378358952, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9989888727111345, "standard_deviation": 0.0001761580126311669, "minimum": 0.9987198749923973, "maximum": 0.9991926711006439, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7066681530431619, "standard_deviation": 0.02426657631953054, "minimum": 0.6756640224286435, "maximum": 0.7364061210684311, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.95606116325027, "standard_deviation": 0.2547335886533306, "minimum": 0.7179733812173752, "maximum": 1.5158890482879908, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.035623586377309994, "standard_deviation": 0.0025684716968848685, "minimum": 0.032157105060893955, "maximum": 0.03984152036877206, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.2835432654054274, "standard_deviation": 0.0584290118746316, "minimum": 0.22192980125645798, "maximum": 0.3729806875917494, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.562996327185154, "standard_deviation": 0.0067647328491967475, "minimum": 5.555275517184, "maximum": 5.573383731452393, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.2774784460744616, "standard_deviation": 0.0045451923975879105, "minimum": 0.2718293109304641, "maximum": 0.28392376384758033, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.09699636111781151, "standard_deviation": 0.024089749726597883, "minimum": -0.13672727294078982, "maximum": -0.05339151548452438, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9971426504314032, "standard_deviation": 0.00029160837809095433, "minimum": 0.996838802756841, "maximum": 0.9976454267121504, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9207755287361463, "standard_deviation": 0.024175583401799722, "minimum": 0.8858283549790752, "maximum": 0.9516114090001102, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4608678679779107, "standard_deviation": 0.0894571171490624, "minimum": 0.3187976576558817, "maximum": 0.642562203477124, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.052864877539846186, "standard_deviation": 0.0026847244927531485, "minimum": 0.048238932435754125, "maximum": 0.0556550653032422, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9992144452733297, "standard_deviation": 0.00015187628145073057, "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": 0.02098405684218702, "minimum": 0.49969557159076605, "maximum": 0.5565273508136046, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5563950573170169, "standard_deviation": 0.19483022625656812, "minimum": 0.302798205567626, "maximum": 0.8679374182229713, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.028434878379355863, "standard_deviation": 0.002936587999468546, "minimum": 0.024354026357884175, "maximum": 0.03187922934733684, "valid_count": 8, "planned_count": 8}}, "seconds": 5.893090934994689, "rtf_including_measurement": 0.9821818224991148}, {"case": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "normal", "speaker": "jvs_jvs004", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.2868306636810303, "predicted_mos": 2.2868306636810303, "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": "0a0edada4e6967061655a6c71960906d0d860605b03691ef89b118097f38858e", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.855361997993896}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.9674909756384353, "全帯域_10ms_rms_envelope_nrmse": 0.2810289946040782, "全帯域_10ms_envelope_correlation": 0.9882105992630176, "全帯域_10ms_modulation_mae_db": 1.8190343874088535, "全帯域_40ms_log_rms_mae_db": 1.9199790180906258, "全帯域_40ms_rms_envelope_nrmse": 0.27331998969581034, "全帯域_40ms_envelope_correlation": 0.9912467427653892, "全帯域_40ms_modulation_mae_db": 1.708508754596749, "300–1000 Hz_10ms_log_rms_mae_db": 1.5690621258658817, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3391131975259601, "300–1000 Hz_10ms_envelope_correlation": 0.9893123326212147, "300–1000 Hz_10ms_modulation_mae_db": 2.417005066103638, "300–1000 Hz_40ms_log_rms_mae_db": 1.4752963245685762, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.3313196272989434, "300–1000 Hz_40ms_envelope_correlation": 0.9921416354973294, "300–1000 Hz_40ms_modulation_mae_db": 2.2318268240506502, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2239423764683939, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18968092437798553, "1000–3000 Hz_10ms_envelope_correlation": 0.9925498652950185, "1000–3000 Hz_10ms_modulation_mae_db": 1.3034238777295333, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9851130112626761, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.17614882768099324, "1000–3000 Hz_40ms_envelope_correlation": 0.9953319065140567, "1000–3000 Hz_40ms_modulation_mae_db": 1.2154194216825618, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2500769976528352, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.20364653335664548, "3000–6000 Hz_10ms_envelope_correlation": 0.9853255240559912, "3000–6000 Hz_10ms_modulation_mae_db": 1.1178139385280483, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9730190199917756, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1552736841376362, "3000–6000 Hz_40ms_envelope_correlation": 0.9952934622308512, "3000–6000 Hz_40ms_modulation_mae_db": 0.9672686821766495, "mr_stft_db": 5.476427289936983, "band_mae_db": 1.3078625877689993, "rms_gain_error_db": 1.9509731432273025, "output_peak": 0.3533932070713408}}], "planned_noise_seeds": [0], "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": 5.667350046184027, "spectral_convergence": 0.4212121671860118, "spectral_convergence_status": "ok", "amplitude_floor": 9.829298518478812e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.362227541832374, "spectral_convergence": 0.3202254575397849, "spectral_convergence_status": "ok", "amplitude_floor": 9.065329093063253e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.39970428179455, "spectral_convergence": 0.33671262700627813, "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": 0.00014031471447208233, "delta_db": 0.8658904030088859, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0017363654374162414, "output_power": 0.0026371534103383056, "delta_db": 1.8149426204801031, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0004421876194377549, "output_power": 0.0008498794273857322, "delta_db": 2.8375073776773245, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.7408011480563064e-05, "output_power": 3.380566053184498e-05, "delta_db": 0.9111189853693934, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7412343207141002e-05, "output_power": 3.7103971069757686e-05, "delta_db": 1.3147423205215358, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.428426915438781e-05, "output_power": 4.168131070384219e-05, "delta_db": 0.8484647131594001, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.433275239990599e-05, "output_power": 1.6314237028765945e-05, "delta_db": 0.5623716941663514, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.3078625877689993, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 1.9509731432273025, "pitch": null, "output_rms_dbfs": -24.252451948360488, "output_peak": 0.3533932070713408, "reference_rms_dbfs": -26.20342509158779, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.476427289936983}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.9431824926762279, "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"}}, "level": {"reference": {"rms": 0.04895857238218429, "rms_dbfs": -26.20342509158779, "peak": 0.274444580078125, "peak_dbfs": -11.230906830925164, "crest_factor_db": 14.972518260662627, "mean": 2.86102294921875e-08, "zero_energy": false}, "output": {"rms": 0.06128827564494151, "rms_dbfs": -24.252451948360488, "peak": 0.3533932070713408, "peak_dbfs": -9.034836055260035, "crest_factor_db": 15.217615893100454, "mean": 3.761561179450906e-08, "zero_energy": false}, "rms_difference_db": 1.9509731432273014}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.9656674889847638e-06, "threshold_dbfs": -57.06489945258896, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 169, "quiet_samples": 40560, "reference_mean_power": 1.257790860589557e-07, "output_mean_power": 1.5775591619323692e-07, "output_rms_dbfs": -68.02014344781783, "output_zero_energy": false, "output_peak": 0.00529635268503912, "output_energy_fraction": 1.1829497703417846e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 349, "output_estimated_voiced_frames": 364, "both_estimated_voiced_frames": 339, "reference_voiced_output_unvoiced_frames": 10, "reference_unvoiced_output_voiced_frames": 25, "paired_voiced_fraction": 0.9713467048710601, "absolute_difference_cents_median": 5.59507385275525, "absolute_difference_cents_p95": 19.91040777733604, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.9674909756384353, "rms_envelope_nrmse": 0.2810289946040782, "envelope_correlation": 0.9882105992630176, "rms_gain_error_db": 1.9509732086307288, "reference_mean_power": 0.002398940884341968, "output_mean_power": 0.003759385542369312}, "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": 0.0006214482311214458, "reference_active": true, "delta_db": 1.9440923688875515}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.277425400163653e-05, "output_power": 8.278558886371563e-05, "reference_active": true, "delta_db": 1.955326393316525}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.46569016072901e-05, "output_power": 2.0980247753113177e-05, "reference_active": true, "delta_db": 1.5576844000224834}], "active_band_count": 3, "active_band_mae_db": 1.8190343874088535}}, {"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": 1.9199790180906258, "rms_envelope_nrmse": 0.27331998969581034, "envelope_correlation": 0.9912467427653892, "rms_gain_error_db": 1.9509734176070535, "reference_mean_power": 0.0024110057038516162, "output_mean_power": 0.0037782925293959164}, "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": 0.0005565048170587349, "reference_active": true, "delta_db": 1.968624177726608}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.2909806376051565e-05, "output_power": 3.7238317128390265e-05, "reference_active": true, "delta_db": 2.1096862741225535}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.181144761591818e-07, "output_power": 1.0412035940911022e-06, "reference_active": true, "delta_db": 1.047215811941086}], "active_band_count": 3, "active_band_mae_db": 1.708508754596749}}]}, {"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": 0.0001330045450117286, "log_rms_mae_db": 1.5690621258658817, "rms_envelope_nrmse": 0.3391131975259601, "envelope_correlation": 0.9893123326212147, "rms_gain_error_db": 2.353707012609487, "reference_mean_power": 0.0013111812883454673, "output_mean_power": 0.002254412813146459}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.210472671322612e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00029715337433814054, "output_power": 0.0005090406671444518, "reference_active": true, "delta_db": 2.337718131390501}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.93632000258319e-05, "output_power": 9.119350287740053e-05, "reference_active": true, "delta_db": 2.6656059234896876}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.447186660847196e-06, "output_power": 1.5851545467198537e-05, "reference_active": true, "delta_db": 2.2476911434307265}], "active_band_count": 3, "active_band_mae_db": 2.417005066103638}}, {"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": 0.00012063998479701062, "log_rms_mae_db": 1.4752963245685762, "rms_envelope_nrmse": 0.3313196272989434, "envelope_correlation": 0.9921416354973294, "rms_gain_error_db": 2.3537069686344045, "reference_mean_power": 0.001317775623677917, "output_mean_power": 0.002265750927958235}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.775720236374232e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00027184637186405784, "output_power": 0.0004708375072784178, "reference_active": true, "delta_db": 2.3854751061871475}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0948015125222872e-05, "output_power": 3.906072748458126e-05, "reference_active": true, "delta_db": 2.705974487173417}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.002499595181279e-07, "output_power": 1.0131090159115295e-06, "reference_active": true, "delta_db": 1.6040308787913862}], "active_band_count": 3, "active_band_mae_db": 2.2318268240506502}}]}, {"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": 1.2239423764683939, "rms_envelope_nrmse": 0.18968092437798553, "envelope_correlation": 0.9925498652950185, "rms_gain_error_db": 1.234543322456994, "reference_mean_power": 3.621970358575803e-05, "output_mean_power": 4.812815619830821e-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": 2.2582336427877844e-05, "reference_active": true, "delta_db": 1.4920669234083874}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.217328435986185e-06, "output_power": 7.7136903054147e-06, "reference_active": true, "delta_db": 1.6981402167395565}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.162268250073546e-07, "output_power": 7.27356039007242e-07, "reference_active": true, "delta_db": 0.7200644930406558}], "active_band_count": 3, "active_band_mae_db": 1.3034238777295333}}, {"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": 0.9851130112626761, "rms_envelope_nrmse": 0.17614882768099324, "envelope_correlation": 0.9953319065140567, "rms_gain_error_db": 1.2345436151712086, "reference_mean_power": 3.640185858193717e-05, "output_mean_power": 4.837020407065684e-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": 1.5750584190620256e-05, "output_power": 2.2433731111869925e-05, "reference_active": true, "delta_db": 1.5360484371843306}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.575523670498514e-06, "output_power": 3.852964333900067e-06, "reference_active": true, "delta_db": 1.7492944321336843}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.671987913674405e-08, "output_power": 7.25014663775355e-08, "reference_active": true, "delta_db": 0.36091539572967074}], "active_band_count": 3, "active_band_mae_db": 1.2154194216825618}}]}, {"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": 5.2682733202745264e-05, "log_rms_mae_db": 1.2500769976528352, "rms_envelope_nrmse": 0.20364653335664548, "envelope_correlation": 0.9853255240559912, "rms_gain_error_db": 1.0501620891290593, "reference_mean_power": 3.423479078027134e-05, "output_mean_power": 4.359973875321366e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.0114400042064674e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3904345626991899e-05, "output_power": 1.8345985480787555e-05, "reference_active": true, "delta_db": 1.20390490761217}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.3366002483256705e-06, "output_power": 6.675790363111327e-06, "reference_active": true, "delta_db": 0.9723801817966505}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0373079000270227e-06, "output_power": 2.671605579920975e-06, "reference_active": true, "delta_db": 1.1771567261753244}], "active_band_count": 3, "active_band_mae_db": 1.1178139385280483}}, {"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": 3.282155756745638e-05, "log_rms_mae_db": 0.9730190199917756, "rms_envelope_nrmse": 0.1552736841376362, "envelope_correlation": 0.9952934622308512, "rms_gain_error_db": 1.0501622106928759, "reference_mean_power": 3.440696652445241e-05, "output_mean_power": 4.3819014504146184e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.861052719142989e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.506769965034781e-05, "output_power": 1.984178311518521e-05, "reference_active": true, "delta_db": 1.195337434995648}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.789058518393087e-06, "output_power": 3.4283808703400337e-06, "reference_active": true, "delta_db": 0.8963143668904083}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4153621023540904e-07, "output_power": 1.7056227780415364e-07, "reference_active": true, "delta_db": 0.8101542446438923}], "active_band_count": 3, "active_band_mae_db": 0.9672686821766495}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1234628, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9925498652950185, "standard_deviation": null, "minimum": 0.9925498652950185, "maximum": 0.9925498652950185, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.2239423764683939, "standard_deviation": null, "minimum": 1.2239423764683939, "maximum": 1.2239423764683939, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 1.3034238777295333, "standard_deviation": null, "minimum": 1.3034238777295333, "maximum": 1.3034238777295333, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.18968092437798553, "standard_deviation": null, "minimum": 0.18968092437798553, "maximum": 0.18968092437798553, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9953319065140567, "standard_deviation": null, "minimum": 0.9953319065140567, "maximum": 0.9953319065140567, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.9851130112626761, "standard_deviation": null, "minimum": 0.9851130112626761, "maximum": 0.9851130112626761, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.2154194216825618, "standard_deviation": null, "minimum": 1.2154194216825618, "maximum": 1.2154194216825618, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.17614882768099324, "standard_deviation": null, "minimum": 0.17614882768099324, "maximum": 0.17614882768099324, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9853255240559912, "standard_deviation": null, "minimum": 0.9853255240559912, "maximum": 0.9853255240559912, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2500769976528352, "standard_deviation": null, "minimum": 1.2500769976528352, "maximum": 1.2500769976528352, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.1178139385280483, "standard_deviation": null, "minimum": 1.1178139385280483, "maximum": 1.1178139385280483, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.20364653335664548, "standard_deviation": null, "minimum": 0.20364653335664548, "maximum": 0.20364653335664548, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9952934622308512, "standard_deviation": null, "minimum": 0.9952934622308512, "maximum": 0.9952934622308512, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9730190199917756, "standard_deviation": null, "minimum": 0.9730190199917756, "maximum": 0.9730190199917756, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.9672686821766495, "standard_deviation": null, "minimum": 0.9672686821766495, "maximum": 0.9672686821766495, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1552736841376362, "standard_deviation": null, "minimum": 0.1552736841376362, "maximum": 0.1552736841376362, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9893123326212147, "standard_deviation": null, "minimum": 0.9893123326212147, "maximum": 0.9893123326212147, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.5690621258658817, "standard_deviation": null, "minimum": 1.5690621258658817, "maximum": 1.5690621258658817, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 2.417005066103638, "standard_deviation": null, "minimum": 2.417005066103638, "maximum": 2.417005066103638, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.3391131975259601, "standard_deviation": null, "minimum": 0.3391131975259601, "maximum": 0.3391131975259601, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9921416354973294, "standard_deviation": null, "minimum": 0.9921416354973294, "maximum": 0.9921416354973294, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.4752963245685762, "standard_deviation": null, "minimum": 1.4752963245685762, "maximum": 1.4752963245685762, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 2.2318268240506502, "standard_deviation": null, "minimum": 2.2318268240506502, "maximum": 2.2318268240506502, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.3313196272989434, "standard_deviation": null, "minimum": 0.3313196272989434, "maximum": 0.3313196272989434, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 1.3078625877689993, "standard_deviation": null, "minimum": 1.3078625877689993, "maximum": 1.3078625877689993, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 5.476427289936983, "standard_deviation": null, "minimum": 5.476427289936983, "maximum": 5.476427289936983, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.3533932070713408, "standard_deviation": null, "minimum": 0.3533932070713408, "maximum": 0.3533932070713408, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 1.9509731432273025, "standard_deviation": null, "minimum": 1.9509731432273025, "maximum": 1.9509731432273025, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9882105992630176, "standard_deviation": null, "minimum": 0.9882105992630176, "maximum": 0.9882105992630176, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.9674909756384353, "standard_deviation": null, "minimum": 1.9674909756384353, "maximum": 1.9674909756384353, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 1.8190343874088535, "standard_deviation": null, "minimum": 1.8190343874088535, "maximum": 1.8190343874088535, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.2810289946040782, "standard_deviation": null, "minimum": 0.2810289946040782, "maximum": 0.2810289946040782, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9912467427653892, "standard_deviation": null, "minimum": 0.9912467427653892, "maximum": 0.9912467427653892, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 1.9199790180906258, "standard_deviation": null, "minimum": 1.9199790180906258, "maximum": 1.9199790180906258, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 1.708508754596749, "standard_deviation": null, "minimum": 1.708508754596749, "maximum": 1.708508754596749, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.27331998969581034, "standard_deviation": null, "minimum": 0.27331998969581034, "maximum": 0.27331998969581034, "valid_count": 1, "planned_count": 1}}, "seconds": 1.6014753359995666, "rtf_including_measurement": 0.26691255599992775}, {"case": "jvs_jvs004_whisper10_BASIC5000_0074", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "whisper", "speaker": "jvs_jvs004", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.7150726318359375, "predicted_mos": 1.7150726318359375, "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": "69c27ebfcdfea4159f8e0a969a82625d7603454ae9f46ca3f2fc9cac566b4e16", "internal_samples": 72707, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.085964639998565}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5504264271137347, "全帯域_10ms_rms_envelope_nrmse": 0.13712899786094193, "全帯域_10ms_envelope_correlation": 0.9837468100363665, "全帯域_10ms_modulation_mae_db": 0.567904053890875, "全帯域_40ms_log_rms_mae_db": 0.7723483212166591, "全帯域_40ms_rms_envelope_nrmse": 0.0692206201343557, "全帯域_40ms_envelope_correlation": 0.9957727485253733, "全帯域_40ms_modulation_mae_db": 0.9698092279860164, "300–1000 Hz_10ms_log_rms_mae_db": 2.1942003065857802, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.28654660114832176, "300–1000 Hz_10ms_envelope_correlation": 0.931464864495294, "300–1000 Hz_10ms_modulation_mae_db": 0.612704311480408, "300–1000 Hz_40ms_log_rms_mae_db": 1.5434604808275958, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17426379864140282, "300–1000 Hz_40ms_envelope_correlation": 0.9740038672054219, "300–1000 Hz_40ms_modulation_mae_db": 1.009743649963031, "1000–3000 Hz_10ms_log_rms_mae_db": 1.626069972069995, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19402403220513087, "1000–3000 Hz_10ms_envelope_correlation": 0.9712341811665633, "1000–3000 Hz_10ms_modulation_mae_db": 0.8846878228219652, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9305570624150561, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11398980335239381, "1000–3000 Hz_40ms_envelope_correlation": 0.9894798758693675, "1000–3000 Hz_40ms_modulation_mae_db": 1.2744690520421058, "3000–6000 Hz_10ms_log_rms_mae_db": 1.470082353180033, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17082515113514363, "3000–6000 Hz_10ms_envelope_correlation": 0.9774504694868248, "3000–6000 Hz_10ms_modulation_mae_db": 0.31737789040972225, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8104637834567735, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07905283861119954, "3000–6000 Hz_40ms_envelope_correlation": 0.9948606359689528, "3000–6000 Hz_40ms_modulation_mae_db": 0.6141578193882241, "mr_stft_db": 6.064989254223085, "band_mae_db": 0.43755401261328997, "rms_gain_error_db": 0.15779268536129545, "output_peak": 0.031622464196179166}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4521906028261313, "全帯域_10ms_rms_envelope_nrmse": 0.12975533139038645, "全帯域_10ms_envelope_correlation": 0.9850876548899277, "全帯域_10ms_modulation_mae_db": 0.3962152098159866, "全帯域_40ms_log_rms_mae_db": 0.737775146446323, "全帯域_40ms_rms_envelope_nrmse": 0.0589329363230216, "全帯域_40ms_envelope_correlation": 0.996732288456758, "全帯域_40ms_modulation_mae_db": 0.6886204851808705, "300–1000 Hz_10ms_log_rms_mae_db": 2.302216910144328, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2700248722734769, "300–1000 Hz_10ms_envelope_correlation": 0.9419851319901188, "300–1000 Hz_10ms_modulation_mae_db": 1.1987773470482634, "300–1000 Hz_40ms_log_rms_mae_db": 1.528606366684497, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1550600278066589, "300–1000 Hz_40ms_envelope_correlation": 0.9820573733777439, "300–1000 Hz_40ms_modulation_mae_db": 1.1262258522928936, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6420068093243976, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21145589292661227, "1000–3000 Hz_10ms_envelope_correlation": 0.9653981915755133, "1000–3000 Hz_10ms_modulation_mae_db": 0.645745696587327, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9137193630828723, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10433073958617953, "1000–3000 Hz_40ms_envelope_correlation": 0.9910579662645281, "1000–3000 Hz_40ms_modulation_mae_db": 0.7772231357088192, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4206875676254007, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16543084928777316, "3000–6000 Hz_10ms_envelope_correlation": 0.978457695511452, "3000–6000 Hz_10ms_modulation_mae_db": 0.4679356650578497, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8023244968373254, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08624486632822405, "3000–6000 Hz_40ms_envelope_correlation": 0.9937864661535573, "3000–6000 Hz_40ms_modulation_mae_db": 0.6405879598899152, "mr_stft_db": 6.057070548396109, "band_mae_db": 0.44848319641238377, "rms_gain_error_db": 0.0692313110179168, "output_peak": 0.038529194704682725}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.451559718772843, "全帯域_10ms_rms_envelope_nrmse": 0.12470966256623828, "全帯域_10ms_envelope_correlation": 0.9864075445952226, "全帯域_10ms_modulation_mae_db": 0.1811936219132756, "全帯域_40ms_log_rms_mae_db": 0.7740996827176783, "全帯域_40ms_rms_envelope_nrmse": 0.06877401040277416, "全帯域_40ms_envelope_correlation": 0.9956601528736508, "全帯域_40ms_modulation_mae_db": 0.17591132827514974, "300–1000 Hz_10ms_log_rms_mae_db": 2.208601669447956, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24762905249789072, "300–1000 Hz_10ms_envelope_correlation": 0.9475167996137923, "300–1000 Hz_10ms_modulation_mae_db": 0.3004425365900015, "300–1000 Hz_40ms_log_rms_mae_db": 1.508812476106883, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13237200685024908, "300–1000 Hz_40ms_envelope_correlation": 0.9848143448550065, "300–1000 Hz_40ms_modulation_mae_db": 1.131001088843659, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6059792264627981, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18673138788622046, "1000–3000 Hz_10ms_envelope_correlation": 0.9735505546649781, "1000–3000 Hz_10ms_modulation_mae_db": 0.7148663716553484, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9012902034916652, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1067171482628533, "1000–3000 Hz_40ms_envelope_correlation": 0.9907525469211167, "1000–3000 Hz_40ms_modulation_mae_db": 0.20503323053285172, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3960494115460467, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15403613763662236, "3000–6000 Hz_10ms_envelope_correlation": 0.9821191991984001, "3000–6000 Hz_10ms_modulation_mae_db": 0.41937923822089584, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8057891882270597, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08668006947286605, "3000–6000 Hz_40ms_envelope_correlation": 0.9941435003577243, "3000–6000 Hz_40ms_modulation_mae_db": 0.9482041932614851, "mr_stft_db": 6.059572169565033, "band_mae_db": 0.4476167104290906, "rms_gain_error_db": 0.1153820059428639, "output_peak": 0.037547155219532495}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.494959357051985, "全帯域_10ms_rms_envelope_nrmse": 0.1266034796760587, "全帯域_10ms_envelope_correlation": 0.9857489537806265, "全帯域_10ms_modulation_mae_db": 0.9131791213969773, "全帯域_40ms_log_rms_mae_db": 0.8014855329242985, "全帯域_40ms_rms_envelope_nrmse": 0.06767470339847764, "全帯域_40ms_envelope_correlation": 0.9959011253185552, "全帯域_40ms_modulation_mae_db": 1.0610910395149913, "300–1000 Hz_10ms_log_rms_mae_db": 2.264395275300637, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2827853043526808, "300–1000 Hz_10ms_envelope_correlation": 0.9401040885040836, "300–1000 Hz_10ms_modulation_mae_db": 0.7805082210463629, "300–1000 Hz_40ms_log_rms_mae_db": 1.523523878566932, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1853628216575478, "300–1000 Hz_40ms_envelope_correlation": 0.976152521898904, "300–1000 Hz_40ms_modulation_mae_db": 0.7281336340214501, "1000–3000 Hz_10ms_log_rms_mae_db": 1.584464828167966, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2017560724920589, "1000–3000 Hz_10ms_envelope_correlation": 0.9685062145576634, "1000–3000 Hz_10ms_modulation_mae_db": 0.7904518327434243, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8896080865237939, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10465339154338728, "1000–3000 Hz_40ms_envelope_correlation": 0.9910842133122915, "1000–3000 Hz_40ms_modulation_mae_db": 1.1400673026470962, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3743780853215153, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1489528285775885, "3000–6000 Hz_10ms_envelope_correlation": 0.9828937343167711, "3000–6000 Hz_10ms_modulation_mae_db": 1.2316345696890199, "3000–6000 Hz_40ms_log_rms_mae_db": 0.736868660279302, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08697505094815111, "3000–6000 Hz_40ms_envelope_correlation": 0.9942709015900122, "3000–6000 Hz_40ms_modulation_mae_db": 1.8184757275328174, "mr_stft_db": 6.05488055937136, "band_mae_db": 0.45911467582286153, "rms_gain_error_db": -0.13755619265578967, "output_peak": 0.03293599272260891}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5115669256128712, "全帯域_10ms_rms_envelope_nrmse": 0.13417402471613518, "全帯域_10ms_envelope_correlation": 0.9838671754660155, "全帯域_10ms_modulation_mae_db": 0.1470303989671586, "全帯域_40ms_log_rms_mae_db": 0.8173568093171547, "全帯域_40ms_rms_envelope_nrmse": 0.07971778872549065, "全帯域_40ms_envelope_correlation": 0.9938566804590031, "全帯域_40ms_modulation_mae_db": 0.356397738644698, "300–1000 Hz_10ms_log_rms_mae_db": 2.2979498977371975, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.269870879493648, "300–1000 Hz_10ms_envelope_correlation": 0.9351630263374574, "300–1000 Hz_10ms_modulation_mae_db": 0.46064376323914275, "300–1000 Hz_40ms_log_rms_mae_db": 1.5633253522445254, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16698734821203515, "300–1000 Hz_40ms_envelope_correlation": 0.9730033326952804, "300–1000 Hz_40ms_modulation_mae_db": 0.12822619299667495, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6578328125238655, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19488065632647666, "1000–3000 Hz_10ms_envelope_correlation": 0.9706250217344713, "1000–3000 Hz_10ms_modulation_mae_db": 0.39031498027933065, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9574450821541605, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11897509671987515, "1000–3000 Hz_40ms_envelope_correlation": 0.9883011403648376, "1000–3000 Hz_40ms_modulation_mae_db": 0.26593076409312094, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3916604698450814, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1641148594390006, "3000–6000 Hz_10ms_envelope_correlation": 0.9788489441194088, "3000–6000 Hz_10ms_modulation_mae_db": 0.27536105781112313, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7682996269207062, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08113393849611354, "3000–6000 Hz_40ms_envelope_correlation": 0.9944645795178846, "3000–6000 Hz_40ms_modulation_mae_db": 0.8647374432065821, "mr_stft_db": 6.072247312787659, "band_mae_db": 0.3687127163751834, "rms_gain_error_db": -0.0007692435869224752, "output_peak": 0.043993006764610564}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.494828834115026, "全帯域_10ms_rms_envelope_nrmse": 0.12901847368941705, "全帯域_10ms_envelope_correlation": 0.9851296072874314, "全帯域_10ms_modulation_mae_db": 0.5391268432325725, "全帯域_40ms_log_rms_mae_db": 0.8252948449985416, "全帯域_40ms_rms_envelope_nrmse": 0.06603273366310704, "全帯域_40ms_envelope_correlation": 0.9959445366428915, "全帯域_40ms_modulation_mae_db": 0.9625402887403771, "300–1000 Hz_10ms_log_rms_mae_db": 2.235996054235898, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.28019522331484825, "300–1000 Hz_10ms_envelope_correlation": 0.9357589971110825, "300–1000 Hz_10ms_modulation_mae_db": 0.5729275216798437, "300–1000 Hz_40ms_log_rms_mae_db": 1.5089123621172278, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1467024433051259, "300–1000 Hz_40ms_envelope_correlation": 0.9835735087003801, "300–1000 Hz_40ms_modulation_mae_db": 0.9362616647701625, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6179252200061345, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19810743269295408, "1000–3000 Hz_10ms_envelope_correlation": 0.9704494623196623, "1000–3000 Hz_10ms_modulation_mae_db": 0.33944194716599396, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9635472881022381, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10732231376869045, "1000–3000 Hz_40ms_envelope_correlation": 0.9908231374807996, "1000–3000 Hz_40ms_modulation_mae_db": 0.8061333525425539, "3000–6000 Hz_10ms_log_rms_mae_db": 1.443067897283665, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17242905359898766, "3000–6000 Hz_10ms_envelope_correlation": 0.976586618088436, "3000–6000 Hz_10ms_modulation_mae_db": 0.5225777638794137, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7901424083929893, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08954364108875722, "3000–6000 Hz_40ms_envelope_correlation": 0.9935352154032336, "3000–6000 Hz_40ms_modulation_mae_db": 0.8606843725476386, "mr_stft_db": 6.057506179611923, "band_mae_db": 0.4577408180426344, "rms_gain_error_db": -0.05631459967833107, "output_peak": 0.03926235328068393}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5402143883338857, "全帯域_10ms_rms_envelope_nrmse": 0.1372480919621347, "全帯域_10ms_envelope_correlation": 0.9832880103186308, "全帯域_10ms_modulation_mae_db": 1.2584296449370178, "全帯域_40ms_log_rms_mae_db": 0.8381939134277768, "全帯域_40ms_rms_envelope_nrmse": 0.07176758353858842, "全帯域_40ms_envelope_correlation": 0.995558821685357, "全帯域_40ms_modulation_mae_db": 1.8600755557559594, "300–1000 Hz_10ms_log_rms_mae_db": 2.160815556885382, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2546715318876007, "300–1000 Hz_10ms_envelope_correlation": 0.9449134053195319, "300–1000 Hz_10ms_modulation_mae_db": 0.7047476610335445, "300–1000 Hz_40ms_log_rms_mae_db": 1.4562574098554713, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14078171343022194, "300–1000 Hz_40ms_envelope_correlation": 0.9830102111787495, "300–1000 Hz_40ms_modulation_mae_db": 0.724782362891052, "1000–3000 Hz_10ms_log_rms_mae_db": 1.7150402660202435, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20956467844269697, "1000–3000 Hz_10ms_envelope_correlation": 0.9659798888896861, "1000–3000 Hz_10ms_modulation_mae_db": 1.2605909378460842, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9915037537575206, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10675504539717783, "1000–3000 Hz_40ms_envelope_correlation": 0.9907058557440961, "1000–3000 Hz_40ms_modulation_mae_db": 1.932368543648959, "3000–6000 Hz_10ms_log_rms_mae_db": 1.402403216597902, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15446482703039816, "3000–6000 Hz_10ms_envelope_correlation": 0.981275635791512, "3000–6000 Hz_10ms_modulation_mae_db": 0.7088860500196006, "3000–6000 Hz_40ms_log_rms_mae_db": 0.792618597027256, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07991099603454584, "3000–6000 Hz_40ms_envelope_correlation": 0.9948798592420129, "3000–6000 Hz_40ms_modulation_mae_db": 1.0802380424143698, "mr_stft_db": 6.060043357357568, "band_mae_db": 0.38989404144363593, "rms_gain_error_db": -0.2143939723328861, "output_peak": 0.032965907187971585}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4895798708542565, "全帯域_10ms_rms_envelope_nrmse": 0.13990355499111004, "全帯域_10ms_envelope_correlation": 0.9826697964260678, "全帯域_10ms_modulation_mae_db": 0.5753807904099357, "全帯域_40ms_log_rms_mae_db": 0.7594686021853458, "全帯域_40ms_rms_envelope_nrmse": 0.06531099266163998, "全帯域_40ms_envelope_correlation": 0.9959847355220954, "全帯域_40ms_modulation_mae_db": 0.863775592928017, "300–1000 Hz_10ms_log_rms_mae_db": 2.3116471973796235, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26622083417341863, "300–1000 Hz_10ms_envelope_correlation": 0.9396952912600506, "300–1000 Hz_10ms_modulation_mae_db": 0.7372816826785407, "300–1000 Hz_40ms_log_rms_mae_db": 1.6189763073163121, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14796098563525506, "300–1000 Hz_40ms_envelope_correlation": 0.9810151955537647, "300–1000 Hz_40ms_modulation_mae_db": 0.9399873412425851, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6683007565770542, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2025139700093837, "1000–3000 Hz_10ms_envelope_correlation": 0.9687663689837162, "1000–3000 Hz_10ms_modulation_mae_db": 0.4652575007907698, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9392217375260689, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09795047945242934, "1000–3000 Hz_40ms_envelope_correlation": 0.9921880112288206, "1000–3000 Hz_40ms_modulation_mae_db": 0.8496327941145192, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3769333214266941, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15777217100601598, "3000–6000 Hz_10ms_envelope_correlation": 0.9808136381848234, "3000–6000 Hz_10ms_modulation_mae_db": 0.7671067688394183, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7359252500774089, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07718580429672454, "3000–6000 Hz_40ms_envelope_correlation": 0.9951432155164217, "3000–6000 Hz_40ms_modulation_mae_db": 0.95246576634475, "mr_stft_db": 6.04990178842004, "band_mae_db": 0.33524067947101344, "rms_gain_error_db": 0.07478022655234698, "output_peak": 0.03730095721341435}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 6.1899405217300725, "spectral_convergence": 0.6304625343081103, "spectral_convergence_status": "ok", "amplitude_floor": 7.347807435362163e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.920537193563659, "spectral_convergence": 0.6171944294986428, "spectral_convergence_status": "ok", "amplitude_floor": 3.5954742817466214e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.084490047375524, "spectral_convergence": 0.6416756478855394, "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": 1.1505282756825447e-07, "delta_db": -0.3659645226479619, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 8.469209703610173e-08, "output_power": 1.1677491738146698e-07, "delta_db": 1.3950668225791563, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 4.7196494133004234e-07, "output_power": 5.023980444346985e-07, "delta_db": 0.2713820084474653, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.5661034348838578e-06, "output_power": 1.541823367339551e-06, "delta_db": -0.06785818685762274, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2294550474819316e-06, "output_power": 1.3210177608080067e-06, "delta_db": 0.3119600237999803, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.3429464378207576e-06, "output_power": 3.363093529343432e-06, "delta_db": 0.026095272448870874, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.563896615059082e-07, "output_power": 1.1043074395014017e-06, "delta_db": 0.6245512515119725, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.43755401261328997, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.15779268536129545, "pitch": null, "output_rms_dbfs": -50.93424283158369, "output_peak": 0.031622464196179166, "reference_rms_dbfs": -51.09203551694498, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.064989254223085}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 109060, "output_samples": 109060, "intelligibility": {"estoi": {"value": 0.5445331044767726, "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"}}, "level": {"reference": {"rms": 0.002788677060125476, "rms_dbfs": -51.09203551694498, "peak": 0.031829833984375, "peak_dbfs": -29.94331253066374, "crest_factor_db": 21.148722986281236, "mean": 3.343893807021364e-07, "zero_energy": false}, "output": {"rms": 0.002839800677226627, "rms_dbfs": -50.93424283158369, "peak": 0.031622464196179166, "peak_dbfs": -30.000085809452266, "crest_factor_db": 20.934157022131423, "mean": -9.843167078528449e-06, "zero_energy": false}, "rms_difference_db": 0.15779268536129365}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 454, "uncovered_tail_samples": 100, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 216, "quiet_samples": 51840, "reference_mean_power": 1.3537558706845214e-07, "output_mean_power": 1.906478672471115e-07, "output_rms_dbfs": -67.19768048759005, "output_zero_energy": false, "output_peak": 0.005423041324164932, "output_energy_fraction": 0.011237138506392377, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 447, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 0, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 100, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.5504264271137347, "rms_envelope_nrmse": 0.13712899786094193, "envelope_correlation": 0.9837468100363665, "rms_gain_error_db": 0.15773896757351957, "reference_mean_power": 7.792370026271951e-06, "output_mean_power": 8.080597297153427e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 4.121961515330989e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.794158794213974e-06, "output_power": 1.7187493325840309e-06, "reference_active": true, "delta_db": -0.18648335641017022}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.126361226638654e-07, "output_power": 2.8123939060523115e-07, "reference_active": true, "delta_db": -0.45963007693110935}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9590349245364566e-07, "output_power": 1.5356148581893583e-07, "reference_active": true, "delta_db": -1.0575987283313453}], "active_band_count": 3, "active_band_mae_db": 0.567904053890875}}, {"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": 0.7723483212166591, "rms_envelope_nrmse": 0.0692206201343557, "envelope_correlation": 0.9957727485253733, "rms_gain_error_db": 0.15774176449134816, "reference_mean_power": 7.844041250222317e-06, "output_mean_power": 8.134184995342508e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 3.76922807220892e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6572550629104971e-06, "output_power": 1.585670173146142e-06, "reference_active": true, "delta_db": -0.19176497379738794}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5392861690297655e-07, "output_power": 1.2589155189865647e-07, "reference_active": true, "delta_db": -0.8732277987878658}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6336932951152273e-08, "output_power": 1.0683831637358654e-08, "reference_active": true, "delta_db": -1.8444349113727956}], "active_band_count": 3, "active_band_mae_db": 0.9698092279860164}}]}, {"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": 2.930731002663351e-06, "log_rms_mae_db": 2.1942003065857802, "rms_envelope_nrmse": 0.28654660114832176, "envelope_correlation": 0.931464864495294, "rms_gain_error_db": 0.5159078160530808, "reference_mean_power": 4.2741366364654733e-07, "output_mean_power": 4.813258464797922e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 2.439886077983056e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.61585037342205e-08, "output_power": 1.0198248168297907e-07, "reference_active": true, "delta_db": 0.25537879146837117}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8718875021930907e-08, "output_power": 2.6602843061839195e-08, "reference_active": true, "delta_db": 1.5264830772522022}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0143942568188063e-08, "output_power": 1.988471487174488e-08, "reference_active": true, "delta_db": -0.05625106572065084}], "active_band_count": 3, "active_band_mae_db": 0.612704311480408}}, {"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": 1.7360896811833872e-06, "log_rms_mae_db": 1.5434604808275958, "rms_envelope_nrmse": 0.17426379864140282, "envelope_correlation": 0.9740038672054219, "rms_gain_error_db": 0.5158510860369039, "reference_mean_power": 4.3025101883138414e-07, "output_mean_power": 4.845147648042908e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 2.1733905138014219e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.047483464267475e-08, "output_power": 9.67319698107291e-08, "reference_active": true, "delta_db": 0.29042233622774555}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.338915747949231e-09, "output_power": 1.278523876925398e-08, "reference_active": true, "delta_db": 1.3641238567002305}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4382767429380366e-09, "output_power": 1.0480306459349445e-09, "reference_active": true, "delta_db": -1.3746847569611171}], "active_band_count": 3, "active_band_mae_db": 1.009743649963031}}]}, {"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": 1.626069972069995, "rms_envelope_nrmse": 0.19402403220513087, "envelope_correlation": 0.9712341811665633, "rms_gain_error_db": 0.002942138184843242, "reference_mean_power": 1.7870157226185334e-06, "output_mean_power": 1.7882267507845695e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.838724239404774e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.063249741710561e-07, "output_power": 6.187705896449914e-07, "reference_active": true, "delta_db": -0.5747489889692549}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.6547376644024293e-07, "output_power": 1.1801058067558494e-07, "reference_active": true, "delta_db": -1.4680820489904465}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2023841152792086e-07, "output_power": 1.0445277613253908e-07, "reference_active": true, "delta_db": -0.6112324305061946}], "active_band_count": 3, "active_band_mae_db": 0.8846878228219652}}, {"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": 0.9305570624150561, "rms_envelope_nrmse": 0.11398980335239381, "envelope_correlation": 0.9894798758693675, "rms_gain_error_db": 0.002942063211546551, "reference_mean_power": 1.7989086732437154e-06, "output_mean_power": 1.800127729970797e-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": 5.792190715505501e-07, "reference_active": true, "delta_db": -0.6092592457222294}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.184085944051964e-08, "output_power": 5.7915969454113726e-08, "reference_active": true, "delta_db": -1.501718510256034}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1933830695482323e-08, "output_power": 8.045201617140914e-09, "reference_active": true, "delta_db": -1.7124294001480542}], "active_band_count": 3, "active_band_mae_db": 1.2744690520421058}}]}, {"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": 1.470082353180033, "rms_envelope_nrmse": 0.17082515113514363, "envelope_correlation": 0.9774504694868248, "rms_gain_error_db": 0.07238523859673043, "reference_mean_power": 1.7907615060268865e-06, "output_mean_power": 1.8208588199499968e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.0367232303591375e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.7413558674441084e-07, "output_power": 4.777501797025337e-07, "reference_active": true, "delta_db": 0.03298306113302497}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0977135221440411e-07, "output_power": 1.2492734593783993e-07, "reference_active": true, "delta_db": 0.5616849947425161}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.057533835167398e-08, "output_power": 2.81594851495235e-08, "reference_active": true, "delta_db": -0.35746561535362564}], "active_band_count": 3, "active_band_mae_db": 0.31737789040972225}}, {"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": 0.8104637834567735, "rms_envelope_nrmse": 0.07905283861119954, "envelope_correlation": 0.9948606359689528, "rms_gain_error_db": 0.0723857976550839, "reference_mean_power": 1.8026836617488883e-06, "output_mean_power": 1.8329815872012282e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 9.630136220520236e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.5232190822756626e-07, "output_power": 4.621546388444431e-07, "reference_active": true, "delta_db": 0.09339693270702196}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.528340255264922e-08, "output_power": 6.226828558250878e-08, "reference_active": true, "delta_db": 0.5167214365396964}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.335569867441393e-09, "output_power": 1.7585606645298873e-09, "reference_active": true, "delta_db": -1.2323550889179542}], "active_band_count": 3, "active_band_mae_db": 0.6141578193882241}}]}], "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"]}}, "output_samples": 109060, "representation_scalars": 1024263, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9693137354865318, "standard_deviation": 0.0027267409331001896, "minimum": 0.9653981915755133, "maximum": 0.9735505546649781, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.6397024863940568, "standard_deviation": 0.0408415276246827, "minimum": 1.584464828167966, "maximum": 1.7150402660202435, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6864196362362804, "standard_deviation": 0.30219516295261456, "minimum": 0.33944194716599396, "maximum": 1.2605909378460842, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.19987926537269174, "standard_deviation": 0.008225096843827487, "minimum": 0.18673138788622046, "maximum": 0.21145589292661227, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9905490933982322, "standard_deviation": 0.0011691842983477347, "minimum": 0.9883011403648376, "maximum": 0.9921880112288206, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.9358615721316719, "standard_deviation": 0.0342108369770065, "minimum": 0.8896080865237939, "maximum": 0.9915037537575206, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.9063572719162533, "standard_deviation": 0.5573874568440604, "minimum": 0.20503323053285172, "maximum": 1.932368543648959, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10758675226037334, "standard_deviation": 0.006372657050797478, "minimum": 0.09795047945242934, "maximum": 0.11897509671987515, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9798057418372035, "standard_deviation": 0.0022899464162129237, "minimum": 0.976586618088436, "maximum": 0.9828937343167711, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.4094077903532924, "standard_deviation": 0.0333076306955119, "minimum": 1.3743780853215153, "maximum": 1.470082353180033, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5887823754908804, "standard_deviation": 0.3114622525443709, "minimum": 0.27536105781112313, "maximum": 1.2316345696890199, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16100323471394123, "standard_deviation": 0.008478954080374523, "minimum": 0.1489528285775885, "maximum": 0.17242905359898766, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9943855467187249, "standard_deviation": 0.0005611281586215055, "minimum": 0.9935352154032336, "maximum": 0.9951432155164217, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7803040014023526, "standard_deviation": 0.029982519602768824, "minimum": 0.7359252500774089, "maximum": 0.8104637834567735, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.9724439155732227, "standard_deviation": 0.3762530062342827, "minimum": 0.6141578193882241, "maximum": 1.8184757275328174, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08334090065957273, "standard_deviation": 0.004538277162324883, "minimum": 0.07718580429672454, "maximum": 0.08954364108875722, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9395752005789264, "standard_deviation": 0.005311383738637838, "minimum": 0.931464864495294, "maximum": 0.9475167996137923, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.2469778584646, "standard_deviation": 0.05598180256162026, "minimum": 2.160815556885382, "maximum": 2.3116471973796235, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6710041305995135, "standard_deviation": 0.2647511831400392, "minimum": 0.3004425365900015, "maximum": 1.1987773470482634, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.26974303739273575, "standard_deviation": 0.013577233933708978, "minimum": 0.24762905249789072, "maximum": 0.28654660114832176, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9797037944331564, "standard_deviation": 0.004617989777289453, "minimum": 0.9730033326952804, "maximum": 0.9848143448550065, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.5314843292149307, "standard_deviation": 0.04715683960131101, "minimum": 1.4562574098554713, "maximum": 1.6189763073163121, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8405452233776886, "standard_deviation": 0.32669171080717124, "minimum": 0.12822619299667495, "maximum": 1.131001088843659, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1561863931923121, "standard_deviation": 0.017960343953283966, "minimum": 0.13237200685024908, "maximum": 0.1853628216575478, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.4180446063262616, "standard_deviation": 0.04709679067965704, "minimum": 0.33524067947101344, "maximum": 0.45911467582286153, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.059526396216597, "standard_deviation": 0.006721641157006847, "minimum": 6.04990178842004, "maximum": 6.072247312787659, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.03676962891121047, "standard_deviation": 0.004106304579191601, "minimum": 0.031622464196179166, "maximum": 0.043993006764610564, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": 0.0010190275775617263, "standard_deviation": 0.12908839474397538, "minimum": -0.2143939723328861, "maximum": 0.15779268536129545, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9844931941000361, "standard_deviation": 0.0012942902685400856, "minimum": 0.9826697964260678, "maximum": 0.9864075445952226, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.4981657655850915, "standard_deviation": 0.035975840016791466, "minimum": 1.451559718772843, "maximum": 1.5504264271137347, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.5723074605704749, "standard_deviation": 0.3689610944335167, "minimum": 0.1470303989671586, "maximum": 1.2584296449370178, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.13231770210655278, "standard_deviation": 0.005560494120500879, "minimum": 0.12470966256623828, "maximum": 0.13990355499111004, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9956763861854606, "standard_deviation": 0.0008165363109108434, "minimum": 0.9938566804590031, "maximum": 0.996732288456758, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.7907528566542221, "standard_deviation": 0.03518961077842517, "minimum": 0.737775146446323, "maximum": 0.8381939134277768, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.8672776571282599, "standard_deviation": 0.5090208146234558, "minimum": 0.17591132827514974, "maximum": 1.8600755557559594, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0684289211059319, "standard_deviation": 0.005922557800935264, "minimum": 0.0589329363230216, "maximum": 0.07971778872549065, "valid_count": 8, "planned_count": 8}}, "seconds": 3.8734620929972152, "rtf_including_measurement": 0.8524031746922168}, {"case": "jvs_jvs004_whisper10_BASIC5000_0074", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "whisper", "speaker": "jvs_jvs004", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.7200062274932861, "predicted_mos": 1.7200062274932861, "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": 3.9024998050008435}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4433431828271832, "全帯域_10ms_rms_envelope_nrmse": 0.13108550889810375, "全帯域_10ms_envelope_correlation": 0.9852155529682795, "全帯域_10ms_modulation_mae_db": 0.4120894170300216, "全帯域_40ms_log_rms_mae_db": 0.7304176165376752, "全帯域_40ms_rms_envelope_nrmse": 0.06808680891881788, "全帯域_40ms_envelope_correlation": 0.9959346247008385, "全帯域_40ms_modulation_mae_db": 0.7486778042127537, "300–1000 Hz_10ms_log_rms_mae_db": 2.1061653263980804, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.281340561529201, "300–1000 Hz_10ms_envelope_correlation": 0.9343003809336886, "300–1000 Hz_10ms_modulation_mae_db": 0.6215222702004203, "300–1000 Hz_40ms_log_rms_mae_db": 1.4748331373942913, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1739676655398501, "300–1000 Hz_40ms_envelope_correlation": 0.9742684915877897, "300–1000 Hz_40ms_modulation_mae_db": 0.8678282373469778, "1000–3000 Hz_10ms_log_rms_mae_db": 1.491508055400152, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18269189303738878, "1000–3000 Hz_10ms_envelope_correlation": 0.9744391544981142, "1000–3000 Hz_10ms_modulation_mae_db": 0.9100684382184072, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8501143252249193, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11166648127850301, "1000–3000 Hz_40ms_envelope_correlation": 0.9898843550249055, "1000–3000 Hz_40ms_modulation_mae_db": 1.1308208496035423, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3630157745365261, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16807540043157845, "3000–6000 Hz_10ms_envelope_correlation": 0.9783623832918343, "3000–6000 Hz_10ms_modulation_mae_db": 0.36567147213879875, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7484888005849961, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08066518889654731, "3000–6000 Hz_40ms_envelope_correlation": 0.9947409176976364, "3000–6000 Hz_40ms_modulation_mae_db": 0.45662251700971807, "mr_stft_db": 6.030840474135386, "band_mae_db": 0.43567852412603264, "rms_gain_error_db": 0.15374172925389046, "output_peak": 0.03252869516708512}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.397025140323527, "全帯域_10ms_rms_envelope_nrmse": 0.12036627781851811, "全帯域_10ms_envelope_correlation": 0.9871831250484683, "全帯域_10ms_modulation_mae_db": 0.4176260861776901, "全帯域_40ms_log_rms_mae_db": 0.7204312639536327, "全帯域_40ms_rms_envelope_nrmse": 0.055306210504167765, "全帯域_40ms_envelope_correlation": 0.997124171398232, "全帯域_40ms_modulation_mae_db": 0.6378272872869085, "300–1000 Hz_10ms_log_rms_mae_db": 2.224524536977115, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2622392518165241, "300–1000 Hz_10ms_envelope_correlation": 0.9444840645317522, "300–1000 Hz_10ms_modulation_mae_db": 1.1165489064473033, "300–1000 Hz_40ms_log_rms_mae_db": 1.46324250513393, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15131808239693031, "300–1000 Hz_40ms_envelope_correlation": 0.982199217820344, "300–1000 Hz_40ms_modulation_mae_db": 0.9387409571276389, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5516622406962661, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19488348042546963, "1000–3000 Hz_10ms_envelope_correlation": 0.9706202864390255, "1000–3000 Hz_10ms_modulation_mae_db": 0.7869344119529503, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8700099641005794, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09944655093074338, "1000–3000 Hz_40ms_envelope_correlation": 0.9919564482887219, "1000–3000 Hz_40ms_modulation_mae_db": 0.9293368045170206, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2982366630028148, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1602060136223135, "3000–6000 Hz_10ms_envelope_correlation": 0.9798245396447235, "3000–6000 Hz_10ms_modulation_mae_db": 0.2297747982779708, "3000–6000 Hz_40ms_log_rms_mae_db": 0.742414852038778, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08451787220194258, "3000–6000 Hz_40ms_envelope_correlation": 0.9940306714622492, "3000–6000 Hz_40ms_modulation_mae_db": 0.3524901145927548, "mr_stft_db": 6.022319690496169, "band_mae_db": 0.42197975887055467, "rms_gain_error_db": 0.0617484162887187, "output_peak": 0.036884045363715166}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3977611107847805, "全帯域_10ms_rms_envelope_nrmse": 0.11759362966840217, "全帯域_10ms_envelope_correlation": 0.9878638431801119, "全帯域_10ms_modulation_mae_db": 0.24444868493349967, "全帯域_40ms_log_rms_mae_db": 0.7556345375610658, "全帯域_40ms_rms_envelope_nrmse": 0.06569309737976692, "全帯域_40ms_envelope_correlation": 0.9959891513315922, "全帯域_40ms_modulation_mae_db": 0.0634752617391839, "300–1000 Hz_10ms_log_rms_mae_db": 2.111312172485521, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24286414041156165, "300–1000 Hz_10ms_envelope_correlation": 0.9492308863159639, "300–1000 Hz_10ms_modulation_mae_db": 0.2174192337463375, "300–1000 Hz_40ms_log_rms_mae_db": 1.424449874322819, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13263346130703002, "300–1000 Hz_40ms_envelope_correlation": 0.9844342172192104, "300–1000 Hz_40ms_modulation_mae_db": 0.9702309240281703, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4958066896679187, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17358048051620936, "1000–3000 Hz_10ms_envelope_correlation": 0.9770184638723357, "1000–3000 Hz_10ms_modulation_mae_db": 0.8266204816247119, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8068760027000335, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0986885723653767, "1000–3000 Hz_40ms_envelope_correlation": 0.9920264168613229, "1000–3000 Hz_40ms_modulation_mae_db": 0.3907900354010776, "3000–6000 Hz_10ms_log_rms_mae_db": 1.30340921487688, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.149052317432758, "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": 0.7755317518390931, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08722542762360919, "3000–6000 Hz_40ms_envelope_correlation": 0.9939670309551899, "3000–6000 Hz_40ms_modulation_mae_db": 0.8079729357349733, "mr_stft_db": 6.025917436116001, "band_mae_db": 0.4204101741537497, "rms_gain_error_db": 0.09045333659756674, "output_peak": 0.03397905566477762}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.402903112476803, "全帯域_10ms_rms_envelope_nrmse": 0.11834249355802673, "全帯域_10ms_envelope_correlation": 0.9875476924345424, "全帯域_10ms_modulation_mae_db": 0.7670556945300229, "全帯域_40ms_log_rms_mae_db": 0.785505832057593, "全帯域_40ms_rms_envelope_nrmse": 0.06401245439946449, "全帯域_40ms_envelope_correlation": 0.9963358434481543, "全帯域_40ms_modulation_mae_db": 0.879946019666307, "300–1000 Hz_10ms_log_rms_mae_db": 2.1811409287370855, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2785163523697122, "300–1000 Hz_10ms_envelope_correlation": 0.9416813962693661, "300–1000 Hz_10ms_modulation_mae_db": 0.7841550548555568, "300–1000 Hz_40ms_log_rms_mae_db": 1.4792432394351085, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.18518300337165877, "300–1000 Hz_40ms_envelope_correlation": 0.9757302334776594, "300–1000 Hz_40ms_modulation_mae_db": 0.6269111425633279, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4682467850412322, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19130682693290108, "1000–3000 Hz_10ms_envelope_correlation": 0.9716917323352137, "1000–3000 Hz_10ms_modulation_mae_db": 0.647919142605216, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8246425475557516, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10062259845799702, "1000–3000 Hz_40ms_envelope_correlation": 0.9918418013619046, "1000–3000 Hz_40ms_modulation_mae_db": 0.9820469808902231, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2564447744977576, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14108397904265316, "3000–6000 Hz_10ms_envelope_correlation": 0.984753503561676, "3000–6000 Hz_10ms_modulation_mae_db": 1.0795795425277093, "3000–6000 Hz_40ms_log_rms_mae_db": 0.682856372090324, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08436517155579504, "3000–6000 Hz_40ms_envelope_correlation": 0.9946916762527479, "3000–6000 Hz_40ms_modulation_mae_db": 1.5707948440974129, "mr_stft_db": 6.021091542496752, "band_mae_db": 0.4521201739038084, "rms_gain_error_db": -0.14996843989418626, "output_peak": 0.03415179745739628}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4072905279926318, "全帯域_10ms_rms_envelope_nrmse": 0.13221736675978757, "全帯域_10ms_envelope_correlation": 0.9843726093400607, "全帯域_10ms_modulation_mae_db": 0.08276861680379054, "全帯域_40ms_log_rms_mae_db": 0.7690493606729815, "全帯域_40ms_rms_envelope_nrmse": 0.07873024427422291, "全帯域_40ms_envelope_correlation": 0.9940186724664865, "全帯域_40ms_modulation_mae_db": 0.16440027311353378, "300–1000 Hz_10ms_log_rms_mae_db": 2.228203547509592, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.271875884580171, "300–1000 Hz_10ms_envelope_correlation": 0.9357699945758772, "300–1000 Hz_10ms_modulation_mae_db": 0.6534742827620493, "300–1000 Hz_40ms_log_rms_mae_db": 1.5381761576674882, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17177571499116254, "300–1000 Hz_40ms_envelope_correlation": 0.9724952109791296, "300–1000 Hz_40ms_modulation_mae_db": 0.34589141278439145, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5586533885356924, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19261942306689525, "1000–3000 Hz_10ms_envelope_correlation": 0.9713149124014742, "1000–3000 Hz_10ms_modulation_mae_db": 0.4767436442163677, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9303298748970049, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11872714173092351, "1000–3000 Hz_40ms_envelope_correlation": 0.988355499049994, "1000–3000 Hz_40ms_modulation_mae_db": 0.16296771208971747, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2931375677976884, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16119205237181766, "3000–6000 Hz_10ms_envelope_correlation": 0.97966832140906, "3000–6000 Hz_10ms_modulation_mae_db": 0.28770972514467424, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7261779154487193, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08289154892747172, "3000–6000 Hz_40ms_envelope_correlation": 0.9942261642314678, "3000–6000 Hz_40ms_modulation_mae_db": 0.5867834666743511, "mr_stft_db": 6.039541613712944, "band_mae_db": 0.3779385813916164, "rms_gain_error_db": -0.002661515318318061, "output_peak": 0.044735342927324714}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3743995224342163, "全帯域_10ms_rms_envelope_nrmse": 0.12215842985943096, "全帯域_10ms_envelope_correlation": 0.9866074329488916, "全帯域_10ms_modulation_mae_db": 0.27792822197314776, "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": 0.5681569156878704, "300–1000 Hz_10ms_log_rms_mae_db": 2.160852093305784, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.28110492091763006, "300–1000 Hz_10ms_envelope_correlation": 0.9356464424175562, "300–1000 Hz_10ms_modulation_mae_db": 0.46390303491750823, "300–1000 Hz_40ms_log_rms_mae_db": 1.4754217688407443, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15281314957178893, "300–1000 Hz_40ms_envelope_correlation": 0.9819736773870896, "300–1000 Hz_40ms_modulation_mae_db": 0.8458153124157972, "1000–3000 Hz_10ms_log_rms_mae_db": 1.514248132593275, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18669372220138714, "1000–3000 Hz_10ms_envelope_correlation": 0.9736503457425733, "1000–3000 Hz_10ms_modulation_mae_db": 0.3916006283215057, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8877465264062339, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10137186393944385, "1000–3000 Hz_40ms_envelope_correlation": 0.991771452440128, "1000–3000 Hz_40ms_modulation_mae_db": 0.3890653961027173, "3000–6000 Hz_10ms_log_rms_mae_db": 1.325363368080773, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16775752557083112, "3000–6000 Hz_10ms_envelope_correlation": 0.9778282528893446, "3000–6000 Hz_10ms_modulation_mae_db": 0.40397408011659924, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7412424342616807, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09157327831495164, "3000–6000 Hz_40ms_envelope_correlation": 0.9930975512862692, "3000–6000 Hz_40ms_modulation_mae_db": 0.7120896179696966, "mr_stft_db": 6.025819316033329, "band_mae_db": 0.4680630987767448, "rms_gain_error_db": -0.04795822402297491, "output_peak": 0.03849887028936362}}, {"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": 1.0862512193146783, "全帯域_40ms_log_rms_mae_db": 0.8040455322066515, "全帯域_40ms_rms_envelope_nrmse": 0.06977573442078171, "全帯域_40ms_envelope_correlation": 0.9958666985490456, "全帯域_40ms_modulation_mae_db": 1.5840013688997103, "300–1000 Hz_10ms_log_rms_mae_db": 2.052107895112964, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24780254036000152, "300–1000 Hz_10ms_envelope_correlation": 0.9486208787555646, "300–1000 Hz_10ms_modulation_mae_db": 0.7060530951907974, "300–1000 Hz_40ms_log_rms_mae_db": 1.4030393682303606, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14023866959536035, "300–1000 Hz_40ms_envelope_correlation": 0.9836534383857906, "300–1000 Hz_40ms_modulation_mae_db": 0.6784689780500305, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6053206852762683, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20438242563883974, "1000–3000 Hz_10ms_envelope_correlation": 0.9676315001928434, "1000–3000 Hz_10ms_modulation_mae_db": 1.1412246693175379, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9416240107833534, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10690013212827006, "1000–3000 Hz_40ms_envelope_correlation": 0.9907545575437892, "1000–3000 Hz_40ms_modulation_mae_db": 1.713489971145691, "3000–6000 Hz_10ms_log_rms_mae_db": 1.295237399857097, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15045462780396077, "3000–6000 Hz_10ms_envelope_correlation": 0.9822246725851667, "3000–6000 Hz_10ms_modulation_mae_db": 0.5548147473189403, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7513738412098065, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08045249245775954, "3000–6000 Hz_40ms_envelope_correlation": 0.994729582120111, "3000–6000 Hz_40ms_modulation_mae_db": 0.8682607818393543, "mr_stft_db": 6.025832283901642, "band_mae_db": 0.3923350279479746, "rms_gain_error_db": -0.22789809010759632, "output_peak": 0.034292892043860136}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.4169030956098874, "全帯域_10ms_rms_envelope_nrmse": 0.13301891989762793, "全帯域_10ms_envelope_correlation": 0.984328715120554, "全帯域_10ms_modulation_mae_db": 0.5104461614432981, "全帯域_40ms_log_rms_mae_db": 0.7235654536728877, "全帯域_40ms_rms_envelope_nrmse": 0.06460718329033704, "全帯域_40ms_envelope_correlation": 0.9960542117628094, "全帯域_40ms_modulation_mae_db": 0.7652842184824968, "300–1000 Hz_10ms_log_rms_mae_db": 2.210860236535021, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25715385888162345, "300–1000 Hz_10ms_envelope_correlation": 0.9442733863206226, "300–1000 Hz_10ms_modulation_mae_db": 0.5663201570361102, "300–1000 Hz_40ms_log_rms_mae_db": 1.554637119440705, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14735886743163903, "300–1000 Hz_40ms_envelope_correlation": 0.9814517679033694, "300–1000 Hz_40ms_modulation_mae_db": 0.682869468989819, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5539890762946595, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1950551527298227, "1000–3000 Hz_10ms_envelope_correlation": 0.9707174639690875, "1000–3000 Hz_10ms_modulation_mae_db": 0.5170391313397391, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8832591231135505, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09865745601408027, "1000–3000 Hz_40ms_envelope_correlation": 0.9919787395737835, "1000–3000 Hz_40ms_modulation_mae_db": 0.8701436092800504, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2769462899926725, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15430062285826623, "3000–6000 Hz_10ms_envelope_correlation": 0.9816474694603042, "3000–6000 Hz_10ms_modulation_mae_db": 0.6703953278202691, "3000–6000 Hz_40ms_log_rms_mae_db": 0.6937105019973524, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07694947782314299, "3000–6000 Hz_40ms_envelope_correlation": 0.9951603091373145, "3000–6000 Hz_40ms_modulation_mae_db": 0.8275076361313864, "mr_stft_db": 6.009906532709134, "band_mae_db": 0.36584797496939664, "rms_gain_error_db": 0.05841759973500939, "output_peak": 0.035740351298729295}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.8799027127145065, "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": 8.469209703610173e-08, "output_power": 1.154010604871324e-07, "delta_db": 1.3436691338375975, "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": 0.43567852412603264, "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": 6.030840474135386}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 109060, "output_samples": 109060, "intelligibility": {"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"}}, "level": {"reference": {"rms": 0.002788677060125476, "rms_dbfs": -51.09203551694498, "peak": 0.031829833984375, "peak_dbfs": -29.94331253066374, "crest_factor_db": 21.148722986281236, "mean": 3.343893807021364e-07, "zero_energy": false}, "output": {"rms": 0.0028384765496845188, "rms_dbfs": -50.93829378769109, "peak": 0.03252869516708512, "peak_dbfs": -29.754667146966874, "crest_factor_db": 21.183626640724214, "mean": -1.0026677173430259e-05, "zero_energy": false}, "rms_difference_db": 0.15374172925389473}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 454, "uncovered_tail_samples": 100, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 216, "quiet_samples": 51840, "reference_mean_power": 1.3537558706845214e-07, "output_mean_power": 1.6417568080261926e-07, "output_rms_dbfs": -67.8469117410717, "output_zero_energy": false, "output_peak": 0.004614921149572963, "output_energy_fraction": 0.009685849222007272, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 447, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 0, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 100, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.13108550889810375, "envelope_correlation": 0.9852155529682795, "rms_gain_error_db": 0.15370763997548864, "reference_mean_power": 7.792370026271951e-06, "output_mean_power": 8.073099983269135e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 4.121961515330989e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.794158794213974e-06, "output_power": 1.75078199553777e-06, "reference_active": true, "delta_db": -0.10628806348955593}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.126361226638654e-07, "output_power": 2.885627855785954e-07, "reference_active": true, "delta_db": -0.3479883422141796}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9590349245364566e-07, "output_power": 1.6362248865293326e-07, "reference_active": true, "delta_db": -0.7819918453863294}], "active_band_count": 3, "active_band_mae_db": 0.4120894170300216}}, {"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": 0.7304176165376752, "rms_envelope_nrmse": 0.06808680891881788, "envelope_correlation": 0.9959346247008385, "rms_gain_error_db": 0.15371680811696067, "reference_mean_power": 7.844041250222317e-06, "output_mean_power": 8.126649883909748e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 3.76922807220892e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6572550629104971e-06, "output_power": 1.615963862715353e-06, "reference_active": true, "delta_db": -0.10957709902136516}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5392861690297655e-07, "output_power": 1.3019538185320005e-07, "reference_active": true, "delta_db": -0.7272378742895937}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6336932951152273e-08, "output_power": 1.180996696274959e-08, "reference_active": true, "delta_db": -1.409218439327302}], "active_band_count": 3, "active_band_mae_db": 0.7486778042127537}}]}, {"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": 2.930731002663351e-06, "log_rms_mae_db": 2.1061653263980804, "rms_envelope_nrmse": 0.281340561529201, "envelope_correlation": 0.9343003809336886, "rms_gain_error_db": 0.5242152023438241, "reference_mean_power": 4.2741366364654733e-07, "output_mean_power": 4.822474300273802e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 2.439886077983056e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.61585037342205e-08, "output_power": 1.0523712740421762e-07, "reference_active": true, "delta_db": 0.39181287984318697}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8718875021930907e-08, "output_power": 2.5525403232050898e-08, "reference_active": true, "delta_db": 1.3469286678788996}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0143942568188063e-08, "output_power": 2.073609628841775e-08, "reference_active": true, "delta_db": 0.1258252628791742}], "active_band_count": 3, "active_band_mae_db": 0.6215222702004203}}, {"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": 1.7360896811833872e-06, "log_rms_mae_db": 1.4748331373942913, "rms_envelope_nrmse": 0.1739676655398501, "envelope_correlation": 0.9742684915877897, "rms_gain_error_db": 0.5241593065627645, "reference_mean_power": 4.3025101883138414e-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": 2.1733905138014219e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.047483464267475e-08, "output_power": 9.936442931542552e-08, "reference_active": true, "delta_db": 0.40703144540727787}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.338915747949231e-09, "output_power": 1.2341783997124364e-08, "reference_active": true, "delta_db": 1.210814838447677}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4382767429380366e-09, "output_power": 1.1462480638699243e-09, "reference_active": true, "delta_db": -0.9856384281859785}], "active_band_count": 3, "active_band_mae_db": 0.8678282373469778}}]}, {"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": 1.491508055400152, "rms_envelope_nrmse": 0.18269189303738878, "envelope_correlation": 0.9744391544981142, "rms_gain_error_db": -0.027894061195853047, "reference_mean_power": 1.7870157226185334e-06, "output_mean_power": 1.7755747787455611e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.838724239404774e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.063249741710561e-07, "output_power": 6.22107143302449e-07, "reference_active": true, "delta_db": -0.5513937413771548}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.6547376644024293e-07, "output_power": 1.1620283182955382e-07, "reference_active": true, "delta_db": -1.5351244041599765}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2023841152792086e-07, "output_power": 1.0367511200670386e-07, "reference_active": true, "delta_db": -0.6436871691180899}], "active_band_count": 3, "active_band_mae_db": 0.9100684382184072}}, {"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": 0.8501143252249193, "rms_envelope_nrmse": 0.11166648127850301, "envelope_correlation": 0.9898843550249055, "rms_gain_error_db": -0.0278936460045971, "reference_mean_power": 1.7989086732437154e-06, "output_mean_power": 1.787391758455111e-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": 5.834370482259196e-07, "reference_active": true, "delta_db": -0.5777477437325013}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.184085944051964e-08, "output_power": 5.7586030458699377e-08, "reference_active": true, "delta_db": -1.5265303879606988}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1933830695482323e-08, "output_power": 8.870772276686332e-09, "reference_active": true, "delta_db": -1.288184417117427}], "active_band_count": 3, "active_band_mae_db": 1.1308208496035423}}]}, {"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": 1.3630157745365261, "rms_envelope_nrmse": 0.16807540043157845, "envelope_correlation": 0.9783623832918343, "rms_gain_error_db": 0.10366242570593473, "reference_mean_power": 1.7907615060268865e-06, "output_mean_power": 1.8340196853937105e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.0367232303591375e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.7413558674441084e-07, "output_power": 4.86662748771981e-07, "reference_active": true, "delta_db": 0.11325551805898547}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0977135221440411e-07, "output_power": 1.3092985046826253e-07, "reference_active": true, "delta_db": 0.7654965780101864}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.057533835167398e-08, "output_power": 3.215122344758195e-08, "reference_active": true, "delta_db": 0.2182623203472242}], "active_band_count": 3, "active_band_mae_db": 0.36567147213879875}}, {"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": 0.7484888005849961, "rms_envelope_nrmse": 0.08066518889654731, "envelope_correlation": 0.9947409176976364, "rms_gain_error_db": 0.10366266685889827, "reference_mean_power": 1.8026836617488883e-06, "output_mean_power": 1.8462299388504767e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 9.630136220520236e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.5232190822756626e-07, "output_power": 4.7200836767731916e-07, "reference_active": true, "delta_db": 0.1850207447094891}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.528340255264922e-08, "output_power": 6.544057112615604e-08, "reference_active": true, "delta_db": 0.7325231603404556}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.335569867441393e-09, "output_power": 2.104556060945086e-09, "reference_active": true, "delta_db": -0.45232364597920954}], "active_band_count": 3, "active_band_mae_db": 0.45662251700971807}}]}], "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"]}}, "output_samples": 109060, "representation_scalars": 1024263, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9721354824313335, "standard_deviation": 0.0028512634837634153, "minimum": 0.9676315001928434, "maximum": 0.9770184638723357, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.529929381688183, "standard_deviation": 0.04512095493232901, "minimum": 1.4682467850412322, "maximum": 1.6053206852762683, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7122688184495545, "standard_deviation": 0.2513775682305565, "minimum": 0.3916006283215057, "maximum": 1.1412246693175379, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.19015167556861423, "standard_deviation": 0.009247260349443304, "minimum": 0.17358048051620936, "maximum": 0.20438242563883974, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9910711587680686, "standard_deviation": 0.0013356543007585352, "minimum": 0.988355499049994, "maximum": 0.9920264168613229, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8743252968476782, "standard_deviation": 0.047129227231922616, "minimum": 0.8068760027000335, "maximum": 0.9416240107833534, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.821082669878755, "standard_deviation": 0.4981781018280025, "minimum": 0.16296771208971747, "maximum": 1.713489971145691, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10451009960566723, "standard_deviation": 0.007346473116600295, "minimum": 0.09865745601408027, "maximum": 0.11872714173092351, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9809351467743539, "standard_deviation": 0.002416135575965855, "minimum": 0.9778282528893446, "maximum": 0.984753503561676, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.3014738815802762, "standard_deviation": 0.03187015692839951, "minimum": 1.2564447744977576, "maximum": 1.3630157745365261, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.49593351193025115, "standard_deviation": 0.27481462092855663, "minimum": 0.2297747982779708, "maximum": 1.0795795425277093, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15651531739177238, "standard_deviation": 0.009494173063802368, "minimum": 0.14108397904265316, "maximum": 0.16807540043157845, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9943304878928733, "standard_deviation": 0.0006436276758391715, "minimum": 0.9930975512862692, "maximum": 0.9951603091373145, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7327245586838438, "standard_deviation": 0.03081514012822989, "minimum": 0.682856372090324, "maximum": 0.7755317518390931, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.772815239256206, "standard_deviation": 0.37130178191152885, "minimum": 0.3524901145927548, "maximum": 1.5707948440974129, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0835800572251525, "standard_deviation": 0.00449432905853743, "minimum": 0.07694947782314299, "maximum": 0.09157327831495164, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.941750928765049, "standard_deviation": 0.005922482903211775, "minimum": 0.9343003809336886, "maximum": 0.9492308863159639, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.1593958421326453, "standard_deviation": 0.06409371623902589, "minimum": 2.052107895112964, "maximum": 2.228203547509592, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6411745043945104, "standard_deviation": 0.2585033470213574, "minimum": 0.2174192337463375, "maximum": 1.1165489064473033, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2653621888583031, "standard_deviation": 0.015166858190582269, "minimum": 0.24286414041156165, "maximum": 0.281340561529201, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9795257818450478, "standard_deviation": 0.004620658210614218, "minimum": 0.9724952109791296, "maximum": 0.9844342172192104, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.4766303963081808, "standard_deviation": 0.050993177950787186, "minimum": 1.4030393682303606, "maximum": 1.554637119440705, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7445945541632691, "standard_deviation": 0.20529871547479897, "minimum": 0.34589141278439145, "maximum": 0.9702309240281703, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1569110767756775, "standard_deviation": 0.018196850566854834, "minimum": 0.13263346130703002, "maximum": 0.18518300337165877, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.41679666426748474, "standard_deviation": 0.03581008515729492, "minimum": 0.36584797496939664, "maximum": 0.4680630987767448, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.02515861120017, "standard_deviation": 0.008433326115849332, "minimum": 6.009906532709134, "maximum": 6.039541613712944, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.036351381276531494, "standard_deviation": 0.0038706960519065982, "minimum": 0.03252869516708512, "maximum": 0.044735342927324714, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.008015648433486285, "standard_deviation": 0.12832155518980637, "minimum": -0.22789809010759632, "maximum": 0.15374172925389046, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9860054397040598, "standard_deviation": 0.0014565780300935924, "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": 0.030808794757509632, "minimum": 1.3743995224342163, "maximum": 1.4730480830362849, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.47482676277576863, "standard_deviation": 0.31921039458271183, "minimum": 0.08276861680379054, "maximum": 1.0862512193146783, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.12567949237879117, "standard_deviation": 0.00665921227996766, "minimum": 0.11759362966840217, "maximum": 0.13301891989762793, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9959538328812761, "standard_deviation": 0.0008786910974366699, "minimum": 0.9940186724664865, "maximum": 0.997124171398232, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.7562245494190643, "standard_deviation": 0.030111853260366972, "minimum": 0.7204312639536327, "maximum": 0.8040455322066515, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6764711436360955, "standard_deviation": 0.46741241292700353, "minimum": 0.0634752617391839, "maximum": 1.5840013688997103, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.06607531976555497, "standard_deviation": 0.006697466686967697, "minimum": 0.055306210504167765, "maximum": 0.07873024427422291, "valid_count": 8, "planned_count": 8}}, "seconds": 4.226154121999571, "rtf_including_measurement": 0.9300174117732414}, {"case": "jvs_jvs004_whisper10_BASIC5000_0074", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "whisper", "speaker": "jvs_jvs004", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.8988327980041504, "predicted_mos": 1.8988327980041504, "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": "2271e913740a88809dc63e53028cf199928fcfa437e32a4365b2e6596c7b8bbd", "internal_samples": 72707, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.9613522039944655}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 2.5524841640807163, "全帯域_10ms_rms_envelope_nrmse": 0.19391603251268158, "全帯域_10ms_envelope_correlation": 0.9750158306138338, "全帯域_10ms_modulation_mae_db": 1.1089315910098179, "全帯域_40ms_log_rms_mae_db": 2.0139832398927218, "全帯域_40ms_rms_envelope_nrmse": 0.12605044407475774, "全帯域_40ms_envelope_correlation": 0.9920213160639263, "全帯域_40ms_modulation_mae_db": 0.8308245474619081, "300–1000 Hz_10ms_log_rms_mae_db": 2.6660342212593204, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.33264883515521043, "300–1000 Hz_10ms_envelope_correlation": 0.9205250057379113, "300–1000 Hz_10ms_modulation_mae_db": 0.5733120966265658, "300–1000 Hz_40ms_log_rms_mae_db": 2.190228324673947, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2274517694882282, "300–1000 Hz_40ms_envelope_correlation": 0.9653495695293247, "300–1000 Hz_40ms_modulation_mae_db": 0.6513779291503538, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8043193318495827, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2733448403183212, "1000–3000 Hz_10ms_envelope_correlation": 0.9514777238146841, "1000–3000 Hz_10ms_modulation_mae_db": 1.0531847753756625, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1888932046316008, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.15866358380078172, "1000–3000 Hz_40ms_envelope_correlation": 0.9855933884258581, "1000–3000 Hz_40ms_modulation_mae_db": 0.7488972432391484, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5736760918364514, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2278879141774654, "3000–6000 Hz_10ms_envelope_correlation": 0.9691155080052187, "3000–6000 Hz_10ms_modulation_mae_db": 1.4987518013247063, "3000–6000 Hz_40ms_log_rms_mae_db": 0.992956256623968, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14208866687279229, "3000–6000 Hz_40ms_envelope_correlation": 0.9910227129067047, "3000–6000 Hz_40ms_modulation_mae_db": 1.2439630974791012, "mr_stft_db": 6.2336384486631715, "band_mae_db": 1.346584272424875, "rms_gain_error_db": 0.6634792006992816, "output_peak": 0.03790565000302888}}], "planned_noise_seeds": [0], "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": 6.339236573558885, "spectral_convergence": 0.6749279991241011, "spectral_convergence_status": "ok", "amplitude_floor": 7.347807435362163e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.129431677965191, "spectral_convergence": 0.6701129442232489, "spectral_convergence_status": "ok", "amplitude_floor": 3.5954742817466214e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.232247094465437, "spectral_convergence": 0.6880683085240212, "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": 4.3291788654899445e-08, "delta_db": -4.610882191262962, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 8.469209703610173e-08, "output_power": 1.1909942648585325e-07, "delta_db": 1.4806678373843953, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 4.7196494133004234e-07, "output_power": 5.78074841930483e-07, "delta_db": 0.8807432968800302, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.5661034348838578e-06, "output_power": 1.7580348540174925e-06, "delta_db": 0.5020703886536199, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2294550474819316e-06, "output_power": 1.5455064421835429e-06, "delta_db": 0.9935816541414237, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.3429464378207576e-06, "output_power": 4.02622665859144e-06, "delta_db": 0.8076880189350545, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.563896615059082e-07, "output_power": 9.901033381675496e-07, "delta_db": 0.15045651971663948, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.346584272424875, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.6634792006992816, "pitch": null, "output_rms_dbfs": -50.4285563162457, "output_peak": 0.03790565000302888, "reference_rms_dbfs": -51.09203551694498, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.2336384486631715}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 109060, "output_samples": 109060, "intelligibility": {"estoi": {"value": 0.5141538114223927, "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"}}, "level": {"reference": {"rms": 0.002788677060125476, "rms_dbfs": -51.09203551694498, "peak": 0.031829833984375, "peak_dbfs": -29.94331253066374, "crest_factor_db": 21.148722986281236, "mean": 3.343893807021364e-07, "zero_energy": false}, "output": {"rms": 0.003010039426657276, "rms_dbfs": -50.4285563162457, "peak": 0.03790565000302888, "peak_dbfs": -28.425921034276087, "crest_factor_db": 22.002635281969614, "mean": -2.569090982056312e-09, "zero_energy": false}, "rms_difference_db": 0.6634792006992853}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 454, "uncovered_tail_samples": 100, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 216, "quiet_samples": 51840, "reference_mean_power": 1.3537558706845214e-07, "output_mean_power": 1.5695778846966057e-07, "output_rms_dbfs": -68.0421712911671, "output_zero_energy": false, "output_peak": 0.014244328548349842, "output_energy_fraction": 0.008234514564348702, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 447, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 3, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 3, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 100, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 2.5524841640807163, "rms_envelope_nrmse": 0.19391603251268158, "envelope_correlation": 0.9750158306138338, "rms_gain_error_db": 0.6635082336020557, "reference_mean_power": 7.792370026271951e-06, "output_mean_power": 9.078631541449928e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 4.121961515330989e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.794158794213974e-06, "output_power": 2.237830864191097e-06, "reference_active": true, "delta_db": 0.9596638117621916}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.126361226638654e-07, "output_power": 4.0133067980069403e-07, "reference_active": true, "delta_db": 1.0846320480769793}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9590349245364566e-07, "output_power": 2.632037482596147e-07, "reference_active": true, "delta_db": 1.2824989131902824}], "active_band_count": 3, "active_band_mae_db": 1.1089315910098179}}, {"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": 2.0139832398927218, "rms_envelope_nrmse": 0.12605044407475774, "envelope_correlation": 0.9920213160639263, "rms_gain_error_db": 0.6635686713708394, "reference_mean_power": 7.844041250222317e-06, "output_mean_power": 9.138959148237808e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 3.76922807220892e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6572550629104971e-06, "output_power": 2.112549096521009e-06, "reference_active": true, "delta_db": 1.0541745646342446}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5392861690297655e-07, "output_power": 2.0078455302455387e-07, "reference_active": true, "delta_db": 1.1541093102297042}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6336932951152273e-08, "output_power": 1.7441727756028737e-08, "reference_active": true, "delta_db": 0.2841897675217753}], "active_band_count": 3, "active_band_mae_db": 0.8308245474619081}}]}, {"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": 2.930731002663351e-06, "log_rms_mae_db": 2.6660342212593204, "rms_envelope_nrmse": 0.33264883515521043, "envelope_correlation": 0.9205250057379113, "rms_gain_error_db": 0.976003538181148, "reference_mean_power": 4.2741366364654733e-07, "output_mean_power": 5.351170089877165e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 2.439886077983056e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.61585037342205e-08, "output_power": 1.1784224376929966e-07, "reference_active": true, "delta_db": 0.8831330616460358}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8718875021930907e-08, "output_power": 2.1189055167178972e-08, "reference_active": true, "delta_db": 0.5383184698955866}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0143942568188063e-08, "output_power": 2.1577093842487975e-08, "reference_active": true, "delta_db": 0.29848475833807486}], "active_band_count": 3, "active_band_mae_db": 0.5733120966265658}}, {"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": 1.7360896811833872e-06, "log_rms_mae_db": 2.190228324673947, "rms_envelope_nrmse": 0.2274517694882282, "envelope_correlation": 0.9653495695293247, "rms_gain_error_db": 0.9757069334396593, "reference_mean_power": 4.3025101883138414e-07, "output_mean_power": 5.386325575856714e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 2.1733905138014219e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.047483464267475e-08, "output_power": 1.1306298467532212e-07, "reference_active": true, "delta_db": 0.9679264789174886}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.338915747949231e-09, "output_power": 8.07362579919991e-09, "reference_active": true, "delta_db": -0.6322784076076182}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4382767429380366e-09, "output_power": 1.3257131612467386e-09, "reference_active": true, "delta_db": -0.3539289009259545}], "active_band_count": 3, "active_band_mae_db": 0.6513779291503538}}]}, {"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": 1.8043193318495827, "rms_envelope_nrmse": 0.2733448403183212, "envelope_correlation": 0.9514777238146841, "rms_gain_error_db": 0.665061365557331, "reference_mean_power": 1.7870157226185334e-06, "output_mean_power": 2.0827373727897765e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.838724239404774e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.063249741710561e-07, "output_power": 7.983142109865272e-07, "reference_active": true, "delta_db": 0.5316929805664957}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.6547376644024293e-07, "output_power": 2.394279165620207e-07, "reference_active": true, "delta_db": 1.6044563419887523}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2023841152792086e-07, "output_power": 1.5218916368736734e-07, "reference_active": true, "delta_db": 1.0234050035717392}], "active_band_count": 3, "active_band_mae_db": 1.0531847753756625}}, {"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": 1.1888932046316008, "rms_envelope_nrmse": 0.15866358380078172, "envelope_correlation": 0.9855933884258581, "rms_gain_error_db": 0.6650698457282032, "reference_mean_power": 1.7989086732437154e-06, "output_mean_power": 2.096602504623039e-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": 7.790664825598344e-07, "reference_active": true, "delta_db": 0.6780574257295067}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.184085944051964e-08, "output_power": 1.1217758057392127e-07, "reference_active": true, "delta_db": 1.3693588757670052}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1933830695482323e-08, "output_power": 1.1398621410908003e-08, "reference_active": true, "delta_db": -0.19927542822093347}], "active_band_count": 3, "active_band_mae_db": 0.7488972432391484}}]}, {"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": 1.5736760918364514, "rms_envelope_nrmse": 0.2278879141774654, "envelope_correlation": 0.9691155080052187, "rms_gain_error_db": 0.7642630981744475, "reference_mean_power": 1.7907615060268865e-06, "output_mean_power": 2.1353253705342e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.0367232303591375e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.7413558674441084e-07, "output_power": 6.022745322664728e-07, "reference_active": true, "delta_db": 1.0389194604578562}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0977135221440411e-07, "output_power": 1.2701970153517499e-07, "reference_active": true, "delta_db": 0.6338207383985545}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.057533835167398e-08, "output_power": 5.85764155123249e-08, "reference_active": true, "delta_db": 2.823515205117708}], "active_band_count": 3, "active_band_mae_db": 1.4987518013247063}}, {"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": 0.992956256623968, "rms_envelope_nrmse": 0.14208866687279229, "envelope_correlation": 0.9910227129067047, "rms_gain_error_db": 0.7642634297080804, "reference_mean_power": 1.8026836617488883e-06, "output_mean_power": 2.149541655254288e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 9.630136220520236e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.5232190822756626e-07, "output_power": 5.885481762441876e-07, "reference_active": true, "delta_db": 1.1433439495269613}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.528340255264922e-08, "output_power": 6.52100808136845e-08, "reference_active": true, "delta_db": 0.7171997351297212}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.335569867441393e-09, "output_power": 3.593580883510084e-09, "reference_active": true, "delta_db": 1.8713456077806208}], "active_band_count": 3, "active_band_mae_db": 1.2439630974791012}}]}], "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"]}}, "output_samples": 109060, "representation_scalars": 934452, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9514777238146841, "standard_deviation": null, "minimum": 0.9514777238146841, "maximum": 0.9514777238146841, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.8043193318495827, "standard_deviation": null, "minimum": 1.8043193318495827, "maximum": 1.8043193318495827, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 1.0531847753756625, "standard_deviation": null, "minimum": 1.0531847753756625, "maximum": 1.0531847753756625, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2733448403183212, "standard_deviation": null, "minimum": 0.2733448403183212, "maximum": 0.2733448403183212, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9855933884258581, "standard_deviation": null, "minimum": 0.9855933884258581, "maximum": 0.9855933884258581, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.1888932046316008, "standard_deviation": null, "minimum": 1.1888932046316008, "maximum": 1.1888932046316008, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7488972432391484, "standard_deviation": null, "minimum": 0.7488972432391484, "maximum": 0.7488972432391484, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15866358380078172, "standard_deviation": null, "minimum": 0.15866358380078172, "maximum": 0.15866358380078172, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9691155080052187, "standard_deviation": null, "minimum": 0.9691155080052187, "maximum": 0.9691155080052187, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5736760918364514, "standard_deviation": null, "minimum": 1.5736760918364514, "maximum": 1.5736760918364514, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.4987518013247063, "standard_deviation": null, "minimum": 1.4987518013247063, "maximum": 1.4987518013247063, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2278879141774654, "standard_deviation": null, "minimum": 0.2278879141774654, "maximum": 0.2278879141774654, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9910227129067047, "standard_deviation": null, "minimum": 0.9910227129067047, "maximum": 0.9910227129067047, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.992956256623968, "standard_deviation": null, "minimum": 0.992956256623968, "maximum": 0.992956256623968, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.2439630974791012, "standard_deviation": null, "minimum": 1.2439630974791012, "maximum": 1.2439630974791012, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.14208866687279229, "standard_deviation": null, "minimum": 0.14208866687279229, "maximum": 0.14208866687279229, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9205250057379113, "standard_deviation": null, "minimum": 0.9205250057379113, "maximum": 0.9205250057379113, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.6660342212593204, "standard_deviation": null, "minimum": 2.6660342212593204, "maximum": 2.6660342212593204, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5733120966265658, "standard_deviation": null, "minimum": 0.5733120966265658, "maximum": 0.5733120966265658, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.33264883515521043, "standard_deviation": null, "minimum": 0.33264883515521043, "maximum": 0.33264883515521043, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9653495695293247, "standard_deviation": null, "minimum": 0.9653495695293247, "maximum": 0.9653495695293247, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 2.190228324673947, "standard_deviation": null, "minimum": 2.190228324673947, "maximum": 2.190228324673947, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6513779291503538, "standard_deviation": null, "minimum": 0.6513779291503538, "maximum": 0.6513779291503538, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.2274517694882282, "standard_deviation": null, "minimum": 0.2274517694882282, "maximum": 0.2274517694882282, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 1.346584272424875, "standard_deviation": null, "minimum": 1.346584272424875, "maximum": 1.346584272424875, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 6.2336384486631715, "standard_deviation": null, "minimum": 6.2336384486631715, "maximum": 6.2336384486631715, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.03790565000302888, "standard_deviation": null, "minimum": 0.03790565000302888, "maximum": 0.03790565000302888, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 0.6634792006992816, "standard_deviation": null, "minimum": 0.6634792006992816, "maximum": 0.6634792006992816, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9750158306138338, "standard_deviation": null, "minimum": 0.9750158306138338, "maximum": 0.9750158306138338, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 2.5524841640807163, "standard_deviation": null, "minimum": 2.5524841640807163, "maximum": 2.5524841640807163, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 1.1089315910098179, "standard_deviation": null, "minimum": 1.1089315910098179, "maximum": 1.1089315910098179, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.19391603251268158, "standard_deviation": null, "minimum": 0.19391603251268158, "maximum": 0.19391603251268158, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9920213160639263, "standard_deviation": null, "minimum": 0.9920213160639263, "maximum": 0.9920213160639263, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 2.0139832398927218, "standard_deviation": null, "minimum": 2.0139832398927218, "maximum": 2.0139832398927218, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 0.8308245474619081, "standard_deviation": null, "minimum": 0.8308245474619081, "maximum": 0.8308245474619081, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.12605044407475774, "standard_deviation": null, "minimum": 0.12605044407475774, "maximum": 0.12605044407475774, "valid_count": 1, "planned_count": 1}}, "seconds": 1.2851597010012483, "rtf_including_measurement": 0.2828152652120847}, {"case": "jvs_jvs018_falset10_VOICEACTRESS100_004", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs018", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.275520086288452, "predicted_mos": 2.275520086288452, "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": "d4d7ab176a6c6c8be62abb46c7297b9be4d23ac020cf14793f80898b4c21fbf1", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.865420849004295}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7231890315381387, "全帯域_10ms_rms_envelope_nrmse": 0.0603758037020363, "全帯域_10ms_envelope_correlation": 0.9969127219033088, "全帯域_10ms_modulation_mae_db": 0.4440139893902457, "全帯域_40ms_log_rms_mae_db": 0.4605754211924222, "全帯域_40ms_rms_envelope_nrmse": 0.03314413693469261, "全帯域_40ms_envelope_correlation": 0.9990918012492291, "全帯域_40ms_modulation_mae_db": 0.39448148555632595, "300–1000 Hz_10ms_log_rms_mae_db": 0.855780604541179, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05362709431328453, "300–1000 Hz_10ms_envelope_correlation": 0.9979269770558421, "300–1000 Hz_10ms_modulation_mae_db": 0.4121508313347626, "300–1000 Hz_40ms_log_rms_mae_db": 0.5862068535644422, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.028301894501476046, "300–1000 Hz_40ms_envelope_correlation": 0.9994228271668238, "300–1000 Hz_40ms_modulation_mae_db": 0.30919151019788504, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8458534931237796, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11572794413974491, "1000–3000 Hz_10ms_envelope_correlation": 0.9923662981404767, "1000–3000 Hz_10ms_modulation_mae_db": 1.4258860452218378, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5716463276983605, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07568032739720595, "1000–3000 Hz_40ms_envelope_correlation": 0.9968541624830833, "1000–3000 Hz_40ms_modulation_mae_db": 1.3797803062734417, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1505176864270241, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16701092252718674, "3000–6000 Hz_10ms_envelope_correlation": 0.9801157853488748, "3000–6000 Hz_10ms_modulation_mae_db": 1.8553397682971593, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7996534890637776, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10173122867465535, "3000–6000 Hz_40ms_envelope_correlation": 0.993126033719959, "3000–6000 Hz_40ms_modulation_mae_db": 2.1774611105309742, "mr_stft_db": 5.250902543650666, "band_mae_db": 0.1269682089665368, "rms_gain_error_db": -0.08528088234161214, "output_peak": 0.365251386156346}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6966918857432857, "全帯域_10ms_rms_envelope_nrmse": 0.0529589700251374, "全帯域_10ms_envelope_correlation": 0.9975817368765159, "全帯域_10ms_modulation_mae_db": 0.3747635296294756, "全帯域_40ms_log_rms_mae_db": 0.40903180926183264, "全帯域_40ms_rms_envelope_nrmse": 0.02547528329087968, "全帯域_40ms_envelope_correlation": 0.9994170831935416, "全帯域_40ms_modulation_mae_db": 0.5160004054069377, "300–1000 Hz_10ms_log_rms_mae_db": 0.8551493209059707, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.054388692299687756, "300–1000 Hz_10ms_envelope_correlation": 0.9978690190294844, "300–1000 Hz_10ms_modulation_mae_db": 0.5829089659918184, "300–1000 Hz_40ms_log_rms_mae_db": 0.5422347649734748, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029110349855462746, "300–1000 Hz_40ms_envelope_correlation": 0.9993759935957455, "300–1000 Hz_40ms_modulation_mae_db": 0.07675975469144573, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8172494571380785, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07556736406622372, "1000–3000 Hz_10ms_envelope_correlation": 0.9966927181521489, "1000–3000 Hz_10ms_modulation_mae_db": 0.23350032317454814, "1000–3000 Hz_40ms_log_rms_mae_db": 0.555793094683903, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03775154005491573, "1000–3000 Hz_40ms_envelope_correlation": 0.9991616993881763, "1000–3000 Hz_40ms_modulation_mae_db": 0.13326375564103168, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1596387200527736, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15209488704266205, "3000–6000 Hz_10ms_envelope_correlation": 0.9832365761126316, "3000–6000 Hz_10ms_modulation_mae_db": 0.6267959221594556, "3000–6000 Hz_40ms_log_rms_mae_db": 0.820570993027353, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07897200872344294, "3000–6000 Hz_40ms_envelope_correlation": 0.9955249028278892, "3000–6000 Hz_40ms_modulation_mae_db": 0.9009858594539705, "mr_stft_db": 5.23904654195821, "band_mae_db": 0.1082924173511074, "rms_gain_error_db": -0.0013343867028563572, "output_peak": 0.37690523847981633}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6991736257457634, "全帯域_10ms_rms_envelope_nrmse": 0.05371007466022706, "全帯域_10ms_envelope_correlation": 0.9975299143703427, "全帯域_10ms_modulation_mae_db": 0.10562117883053873, "全帯域_40ms_log_rms_mae_db": 0.4495366074651454, "全帯域_40ms_rms_envelope_nrmse": 0.0278572967809166, "全帯域_40ms_envelope_correlation": 0.9993304831522317, "全帯域_40ms_modulation_mae_db": 0.35016676079613723, "300–1000 Hz_10ms_log_rms_mae_db": 0.8993929514821319, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.057385039499239246, "300–1000 Hz_10ms_envelope_correlation": 0.9976276336535874, "300–1000 Hz_10ms_modulation_mae_db": 0.7150090051004637, "300–1000 Hz_40ms_log_rms_mae_db": 0.5922037482022742, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03153263404340907, "300–1000 Hz_40ms_envelope_correlation": 0.999283627506639, "300–1000 Hz_40ms_modulation_mae_db": 0.48511419778661447, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8105554724145251, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07739084424319764, "1000–3000 Hz_10ms_envelope_correlation": 0.9965701558950496, "1000–3000 Hz_10ms_modulation_mae_db": 0.7095292001544641, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5648676384577392, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04398579473476077, "1000–3000 Hz_40ms_envelope_correlation": 0.9989264675476666, "1000–3000 Hz_40ms_modulation_mae_db": 0.5705852839904283, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1481398429061764, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15627555208898847, "3000–6000 Hz_10ms_envelope_correlation": 0.9825594608985387, "3000–6000 Hz_10ms_modulation_mae_db": 0.8083256576073689, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7559379465235058, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09692213751273737, "3000–6000 Hz_40ms_envelope_correlation": 0.9935838978046571, "3000–6000 Hz_40ms_modulation_mae_db": 0.6761880716938871, "mr_stft_db": 5.249521151032055, "band_mae_db": 0.1077360012314017, "rms_gain_error_db": -0.05190764334012895, "output_peak": 0.38160986437601946}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7023879957749961, "全帯域_10ms_rms_envelope_nrmse": 0.0582834881154331, "全帯域_10ms_envelope_correlation": 0.9971469748331797, "全帯域_10ms_modulation_mae_db": 0.7242092419836501, "全帯域_40ms_log_rms_mae_db": 0.4203346808856968, "全帯域_40ms_rms_envelope_nrmse": 0.02960794356894052, "全帯域_40ms_envelope_correlation": 0.9993185683249471, "全帯域_40ms_modulation_mae_db": 0.7296970718536374, "300–1000 Hz_10ms_log_rms_mae_db": 0.8919992637593327, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07013681051628333, "300–1000 Hz_10ms_envelope_correlation": 0.9964518957039393, "300–1000 Hz_10ms_modulation_mae_db": 0.5322153378036613, "300–1000 Hz_40ms_log_rms_mae_db": 0.5912234107669131, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04151541700692019, "300–1000 Hz_40ms_envelope_correlation": 0.9987518735817904, "300–1000 Hz_40ms_modulation_mae_db": 0.9689500995767656, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8679625691321584, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09490194898618827, "1000–3000 Hz_10ms_envelope_correlation": 0.9949160020736235, "1000–3000 Hz_10ms_modulation_mae_db": 1.529517121741769, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5953391661467277, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06162905759813224, "1000–3000 Hz_40ms_envelope_correlation": 0.9979563872574919, "1000–3000 Hz_40ms_modulation_mae_db": 1.3184378581572196, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1398833288964367, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15679709959023758, "3000–6000 Hz_10ms_envelope_correlation": 0.9842309998815907, "3000–6000 Hz_10ms_modulation_mae_db": 1.9482448407801556, "3000–6000 Hz_40ms_log_rms_mae_db": 0.825024511602742, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10520261124623013, "3000–6000 Hz_40ms_envelope_correlation": 0.9944999637535514, "3000–6000 Hz_40ms_modulation_mae_db": 2.481446521397898, "mr_stft_db": 5.235524261208925, "band_mae_db": 0.2056681330494882, "rms_gain_error_db": -0.09748944325523902, "output_peak": 0.3756785116835729}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7196522679834512, "全帯域_10ms_rms_envelope_nrmse": 0.05290564995763889, "全帯域_10ms_envelope_correlation": 0.9977204956432268, "全帯域_10ms_modulation_mae_db": 0.6900473511280989, "全帯域_40ms_log_rms_mae_db": 0.4355307877732851, "全帯域_40ms_rms_envelope_nrmse": 0.02691405227250175, "全帯域_40ms_envelope_correlation": 0.9995093655925226, "全帯域_40ms_modulation_mae_db": 0.5547471082683578, "300–1000 Hz_10ms_log_rms_mae_db": 0.8493012660471398, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05228927681351531, "300–1000 Hz_10ms_envelope_correlation": 0.9981077456094052, "300–1000 Hz_10ms_modulation_mae_db": 0.4476942272540249, "300–1000 Hz_40ms_log_rms_mae_db": 0.560830021656994, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02842079493975115, "300–1000 Hz_40ms_envelope_correlation": 0.9995039973116465, "300–1000 Hz_40ms_modulation_mae_db": 0.7118129308412922, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8519302239955209, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08182106339147581, "1000–3000 Hz_10ms_envelope_correlation": 0.996283986878494, "1000–3000 Hz_10ms_modulation_mae_db": 0.33066696065698636, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5695570466087576, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04414571842116257, "1000–3000 Hz_40ms_envelope_correlation": 0.9990717134451542, "1000–3000 Hz_40ms_modulation_mae_db": 0.32567995562909124, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1379623412499524, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14722069766144505, "3000–6000 Hz_10ms_envelope_correlation": 0.9851190173823391, "3000–6000 Hz_10ms_modulation_mae_db": 1.481785215851854, "3000–6000 Hz_40ms_log_rms_mae_db": 0.772216977407961, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09121132543448876, "3000–6000 Hz_40ms_envelope_correlation": 0.995080956307919, "3000–6000 Hz_40ms_modulation_mae_db": 2.068157768722949, "mr_stft_db": 5.234832254226589, "band_mae_db": 0.1677508913162296, "rms_gain_error_db": -0.11824357596969304, "output_peak": 0.37136663148528504}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7038063051473257, "全帯域_10ms_rms_envelope_nrmse": 0.05373948634981456, "全帯域_10ms_envelope_correlation": 0.9976790773497028, "全帯域_10ms_modulation_mae_db": 0.47056404394012047, "全帯域_40ms_log_rms_mae_db": 0.42973602680249884, "全帯域_40ms_rms_envelope_nrmse": 0.03101636400928898, "全帯域_40ms_envelope_correlation": 0.9993276512766398, "全帯域_40ms_modulation_mae_db": 0.44215842086826046, "300–1000 Hz_10ms_log_rms_mae_db": 0.8550548034564129, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05528675312918762, "300–1000 Hz_10ms_envelope_correlation": 0.997802013379268, "300–1000 Hz_10ms_modulation_mae_db": 0.19409218042958684, "300–1000 Hz_40ms_log_rms_mae_db": 0.5699354032049249, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029429205029407948, "300–1000 Hz_40ms_envelope_correlation": 0.9993795829038287, "300–1000 Hz_40ms_modulation_mae_db": 0.31613463572893613, "1000–3000 Hz_10ms_log_rms_mae_db": 0.845548851961358, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09480973285175325, "1000–3000 Hz_10ms_envelope_correlation": 0.9963456433361261, "1000–3000 Hz_10ms_modulation_mae_db": 0.4563586578436138, "1000–3000 Hz_40ms_log_rms_mae_db": 0.549731367775505, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06867506364234915, "1000–3000 Hz_40ms_envelope_correlation": 0.9989546675675604, "1000–3000 Hz_40ms_modulation_mae_db": 0.3305698385113832, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1536540069692076, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15549116851611872, "3000–6000 Hz_10ms_envelope_correlation": 0.9827450006077786, "3000–6000 Hz_10ms_modulation_mae_db": 0.7627900779370419, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7720716175617321, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08735698742880153, "3000–6000 Hz_40ms_envelope_correlation": 0.9949862808000262, "3000–6000 Hz_40ms_modulation_mae_db": 0.9711050000336275, "mr_stft_db": 5.252967501673714, "band_mae_db": 0.19668858118566887, "rms_gain_error_db": -0.12819596373650513, "output_peak": 0.3748399556713108}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7192187964302916, "全帯域_10ms_rms_envelope_nrmse": 0.04456123154296024, "全帯域_10ms_envelope_correlation": 0.998288161475347, "全帯域_10ms_modulation_mae_db": 0.3230190559668556, "全帯域_40ms_log_rms_mae_db": 0.4123359672125829, "全帯域_40ms_rms_envelope_nrmse": 0.021710163183939906, "全帯域_40ms_envelope_correlation": 0.9995764758016322, "全帯域_40ms_modulation_mae_db": 0.2743976850645826, "300–1000 Hz_10ms_log_rms_mae_db": 0.8676059727514044, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.04937793075243149, "300–1000 Hz_10ms_envelope_correlation": 0.998266046858897, "300–1000 Hz_10ms_modulation_mae_db": 0.28899073829567845, "300–1000 Hz_40ms_log_rms_mae_db": 0.5758114951939479, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.026998965367264496, "300–1000 Hz_40ms_envelope_correlation": 0.9994842343751665, "300–1000 Hz_40ms_modulation_mae_db": 0.12551686578286927, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8245513724764091, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06886597392865298, "1000–3000 Hz_10ms_envelope_correlation": 0.9975209281654547, "1000–3000 Hz_10ms_modulation_mae_db": 1.4573820030128264, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5730798986922255, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04047917754009496, "1000–3000 Hz_40ms_envelope_correlation": 0.9993462702197307, "1000–3000 Hz_40ms_modulation_mae_db": 1.4041159873377742, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1349857440605144, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1454917551685308, "3000–6000 Hz_10ms_envelope_correlation": 0.9854462283027989, "3000–6000 Hz_10ms_modulation_mae_db": 1.2204399889358044, "3000–6000 Hz_40ms_log_rms_mae_db": 0.765749413094224, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09399255237354603, "3000–6000 Hz_40ms_envelope_correlation": 0.9945875657160709, "3000–6000 Hz_40ms_modulation_mae_db": 1.3731343765898807, "mr_stft_db": 5.244911143337536, "band_mae_db": 0.1075398277652184, "rms_gain_error_db": -0.006994493445961007, "output_peak": 0.3789096569030065}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7351044459258275, "全帯域_10ms_rms_envelope_nrmse": 0.05574981635452004, "全帯域_10ms_envelope_correlation": 0.9973949426277874, "全帯域_10ms_modulation_mae_db": 0.2688439329649071, "全帯域_40ms_log_rms_mae_db": 0.45655455898018954, "全帯域_40ms_rms_envelope_nrmse": 0.030910772329547174, "全帯域_40ms_envelope_correlation": 0.9992396499763662, "全帯域_40ms_modulation_mae_db": 0.3210373297306546, "300–1000 Hz_10ms_log_rms_mae_db": 0.8468921424027248, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06290870041990627, "300–1000 Hz_10ms_envelope_correlation": 0.9971489778195838, "300–1000 Hz_10ms_modulation_mae_db": 0.9558439269758118, "300–1000 Hz_40ms_log_rms_mae_db": 0.5815661735561811, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03531532094049348, "300–1000 Hz_40ms_envelope_correlation": 0.9991024327375659, "300–1000 Hz_40ms_modulation_mae_db": 0.6822629215892904, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8298763033916633, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07658345323822713, "1000–3000 Hz_10ms_envelope_correlation": 0.997378027326351, "1000–3000 Hz_10ms_modulation_mae_db": 0.4034949426412105, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5532170160408797, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.048873761801210336, "1000–3000 Hz_40ms_envelope_correlation": 0.9994600197143738, "1000–3000 Hz_40ms_modulation_mae_db": 0.6087525681873173, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1131994688455544, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15639381888549492, "3000–6000 Hz_10ms_envelope_correlation": 0.9839946415994573, "3000–6000 Hz_10ms_modulation_mae_db": 1.1656640403572278, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7604713369331946, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10586141352662941, "3000–6000 Hz_40ms_envelope_correlation": 0.9940149982622463, "3000–6000 Hz_40ms_modulation_mae_db": 1.474908200343582, "mr_stft_db": 5.239092218519766, "band_mae_db": 0.18366488588205176, "rms_gain_error_db": -0.09489880696384421, "output_peak": 0.36524733614130817}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.5654387531413905, "spectral_convergence": 0.198785626144917, "spectral_convergence_status": "ok", "amplitude_floor": 9.086732072822267e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.155393121502505, "spectral_convergence": 0.20171016026137945, "spectral_convergence_status": "ok", "amplitude_floor": 8.520258431312163e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.031875756308102, "spectral_convergence": 0.20553209092995076, "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": 3.084847104327967e-05, "delta_db": -0.06578895531157558, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0004897019472039064, "output_power": 0.0004845106687610039, "delta_db": -0.04628486398989606, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.00038033005135275084, "output_power": 0.00037654417759717674, "delta_db": -0.043447054502883525, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0002067238728943134, "output_power": 0.0001936314285866787, "delta_db": -0.28414783100061364, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.323291799953591e-05, "output_power": 1.2306130580392216e-05, "delta_db": -0.3153410223580172, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.500515826026349e-05, "output_power": 2.488398827279065e-05, "delta_db": -0.021096195891986254, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.8390290595099542e-05, "output_power": 2.9136473873141353e-05, "delta_db": 0.11267153971078528, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.1269682089665368, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.08528088234161214, "pitch": null, "output_rms_dbfs": -29.38599798218062, "output_peak": 0.365251386156346, "reference_rms_dbfs": -29.30071709983901, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.250902543650666}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.8930983107313022, "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"}}, "level": {"reference": {"rms": 0.03427394890906224, "rms_dbfs": -29.30071709983901, "peak": 0.37799072265625, "peak_dbfs": -8.450377185723308, "crest_factor_db": 20.8503399141157, "mean": -4.2978922526041666e-07, "zero_energy": false}, "output": {"rms": 0.033939082761831725, "rms_dbfs": -29.38599798218062, "peak": 0.365251386156346, "peak_dbfs": -8.748162544209531, "crest_factor_db": 20.63783543797109, "mean": -2.1990223469206137e-05, "zero_energy": false}, "rms_difference_db": -0.08528088234161046}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 2.1519445744343104e-06, "threshold_dbfs": -56.67168918566671, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 230, "quiet_samples": 55200, "reference_mean_power": 7.20824607634458e-08, "output_mean_power": 1.9205388301431036e-07, "output_rms_dbfs": -67.1657690768839, "output_zero_energy": false, "output_peak": 0.010480095494050276, "output_energy_fraction": 6.391451182626728e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 317, "output_estimated_voiced_frames": 295, "both_estimated_voiced_frames": 291, "reference_voiced_output_unvoiced_frames": 26, "reference_unvoiced_output_voiced_frames": 4, "paired_voiced_fraction": 0.917981072555205, "absolute_difference_cents_median": 1.870487660922267, "absolute_difference_cents_p95": 9.928263321918925, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.7231890315381387, "rms_envelope_nrmse": 0.0603758037020363, "envelope_correlation": 0.9969127219033088, "rms_gain_error_db": -0.08528100540788552, "reference_mean_power": 0.0011756832947918806, "output_mean_power": 0.0011528219762399618}, "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": 0.00014559402676254566, "reference_active": true, "delta_db": -0.14998966966778188}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2413420104691182e-05, "output_power": 1.2366925521293522e-05, "reference_active": true, "delta_db": -0.01629708076533049}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0999366671117794e-06, "output_power": 2.370158007306279e-06, "reference_active": true, "delta_db": -1.1657552177376247}], "active_band_count": 3, "active_band_mae_db": 0.4440139893902457}}, {"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": 0.4605754211924222, "rms_envelope_nrmse": 0.03314413693469261, "envelope_correlation": 0.9990918012492291, "rms_gain_error_db": -0.08528123881542063, "reference_mean_power": 0.0011815960953402045, "output_mean_power": 0.0011586197393236685}, "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": 0.00013630386160039194, "output_power": 0.00013210953388447422, "reference_active": true, "delta_db": -0.13573999664351413}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.09070162469366e-06, "output_power": 5.286754890821531e-06, "reference_active": true, "delta_db": 0.16411532737587836}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.569083691066088e-07, "output_power": 1.2802276276181362e-07, "reference_active": true, "delta_db": -0.8835891326495853}], "active_band_count": 3, "active_band_mae_db": 0.39448148555632595}}]}, {"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": 9.549209054072811e-05, "log_rms_mae_db": 0.855780604541179, "rms_envelope_nrmse": 0.05362709431328453, "envelope_correlation": 0.9979269770558421, "rms_gain_error_db": -0.044308774480488713, "reference_mean_power": 0.0006895778722497405, "output_mean_power": 0.0006825782405580796}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.48267581801043e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.030686777059307e-05, "output_power": 6.885597578004397e-05, "reference_active": true, "delta_db": -0.09056112990733196}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.045775397952225e-06, "output_power": 6.5228670630545814e-06, "reference_active": true, "delta_db": 0.32986518635914475}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.002295743692013e-06, "output_power": 1.209479478183602e-06, "reference_active": true, "delta_db": 0.816026177737811}], "active_band_count": 3, "active_band_mae_db": 0.4121508313347626}}, {"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": 8.872309512115069e-05, "log_rms_mae_db": 0.5862068535644422, "rms_envelope_nrmse": 0.028301894501476046, "envelope_correlation": 0.9994228271668238, "rms_gain_error_db": -0.04430879586970491, "reference_mean_power": 0.0006930459912916038, "output_mean_power": 0.0006860111527193755}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.440447414854182e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.43293436790663e-05, "output_power": 6.296404879848377e-05, "reference_active": true, "delta_db": -0.09316473694484644}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6389748271852193e-06, "output_power": 2.8672599286519697e-06, "reference_active": true, "delta_db": 0.36031817708773733}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.49082443996622e-08, "output_power": 6.716151081123154e-08, "reference_active": true, "delta_db": -0.4740916165610714}], "active_band_count": 3, "active_band_mae_db": 0.30919151019788504}}]}, {"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": 0.8458534931237796, "rms_envelope_nrmse": 0.11572794413974491, "envelope_correlation": 0.9923662981404767, "rms_gain_error_db": -0.19710866867262647, "reference_mean_power": 0.0001528560580614903, "output_mean_power": 0.00014607361885607157}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.6939080235935487e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.743995800608424e-06, "output_power": 7.861430747542628e-06, "reference_active": true, "delta_db": -0.46208347353923607}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.018682293764139e-06, "output_power": 1.5250878913354041e-06, "reference_active": true, "delta_db": -1.217731008185826}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.212055898483429e-07, "output_power": 2.315846450975079e-07, "reference_active": true, "delta_db": -2.597843653940451}], "active_band_count": 3, "active_band_mae_db": 1.4258860452218378}}, {"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": 0.5716463276983605, "rms_envelope_nrmse": 0.07568032739720595, "envelope_correlation": 0.9968541624830833, "rms_gain_error_db": -0.1971086738252264, "reference_mean_power": 0.00015362482187073777, "output_mean_power": 0.00014680827135504586}, "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": 7.421981349496691e-06, "reference_active": true, "delta_db": -0.5468883785223534}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.917412489595775e-07, "output_power": 7.541040128401055e-07, "reference_active": true, "delta_db": -1.1896712516471668}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.978602825033769e-08, "output_power": 1.1378381632127424e-08, "reference_active": true, "delta_db": -2.4027812886508046}], "active_band_count": 3, "active_band_mae_db": 1.3797803062734417}}]}, {"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": 1.1505176864270241, "rms_envelope_nrmse": 0.16701092252718674, "envelope_correlation": 0.9801157853488748, "rms_gain_error_db": -0.3711114249473707, "reference_mean_power": 1.1577512969913926e-05, "output_mean_power": 1.0629287003852487e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.302605621158198e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.645490651287569e-07, "output_power": 7.763486043732361e-07, "reference_active": true, "delta_db": -0.4673286889192466}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.59009391584252e-07, "output_power": 2.935553019978374e-07, "reference_active": true, "delta_db": -1.9413164281330966}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3044874644069092e-07, "output_power": 1.1138762172493765e-07, "reference_active": true, "delta_db": -3.157374187839135}], "active_band_count": 3, "active_band_mae_db": 1.8553397682971593}}, {"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": 0.7996534890637776, "rms_envelope_nrmse": 0.10173122867465535, "envelope_correlation": 0.993126033719959, "rms_gain_error_db": -0.37111141548260906, "reference_mean_power": 1.1635739617517738e-05, "output_mean_power": 1.0682744773219846e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.177196911262555e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.600495243066517e-07, "output_power": 7.224421718951507e-07, "reference_active": true, "delta_db": -0.7572037039553443}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5501826725164145e-07, "output_power": 1.4970403037194162e-07, "reference_active": true, "delta_db": -2.313377978685486}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.780810925112428e-08, "output_power": 8.02486336162847e-09, "reference_active": true, "delta_db": -3.4618016489520924}], "active_band_count": 3, "active_band_mae_db": 2.1774611105309742}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9960092199959656, "standard_deviation": 0.0016731235324673158, "minimum": 0.9923662981404767, "maximum": 0.9975209281654547, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.8366909679541865, "standard_deviation": 0.0193737961575338, "minimum": 0.8105554724145251, "maximum": 0.8679625691321584, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8182919068059069, "standard_deviation": 0.5578131924121625, "minimum": 0.23350032317454814, "maximum": 1.529517121741769, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08570854060568296, "standard_deviation": 0.015224952881463043, "minimum": 0.06886597392865298, "maximum": 0.11572794413974491, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9987164234529047, "standard_deviation": 0.0008799913721043418, "minimum": 0.9968541624830833, "maximum": 0.9994600197143738, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5666539445130123, "standard_deviation": 0.0145678722707195, "minimum": 0.549731367775505, "maximum": 0.5953391661467277, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7588981942159609, "standard_deviation": 0.5258262026300603, "minimum": 0.13326375564103168, "maximum": 1.4041159873377742, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05265255514872896, "standard_deviation": 0.014139945084528099, "minimum": 0.03775154005491573, "maximum": 0.07568032739720595, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9834309637667512, "standard_deviation": 0.0016956610110464153, "minimum": 0.9801157853488748, "maximum": 0.9854462283027989, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.142247642425955, "standard_deviation": 0.01442295654382932, "minimum": 1.1131994688455544, "maximum": 1.1596387200527736, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.2336731889907584, "standard_deviation": 0.4977654876471772, "minimum": 0.6267959221594556, "maximum": 1.9482448407801556, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15459698768508304, "standard_deviation": 0.006647958141486836, "minimum": 0.1454917551685308, "maximum": 0.16701092252718674, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9944255748990398, "standard_deviation": 0.0008062269533492489, "minimum": 0.993126033719959, "maximum": 0.9955249028278892, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7839620356518113, "standard_deviation": 0.027309744349952654, "minimum": 0.7559379465235058, "maximum": 0.825024511602742, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.515423363595846, "standard_deviation": 0.6630050074412773, "minimum": 0.6761880716938871, "maximum": 2.481446521397898, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09515628311506644, "standard_deviation": 0.00927017789965198, "minimum": 0.07897200872344294, "maximum": 0.10586141352662941, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9976500386387509, "standard_deviation": 0.0005884381067730514, "minimum": 0.9964518957039393, "maximum": 0.998266046858897, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8651470406682871, "standard_deviation": 0.01990598725986893, "minimum": 0.8468921424027248, "maximum": 0.8993929514821319, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.516113151648226, "standard_deviation": 0.24154712238147574, "minimum": 0.19409218042958684, "maximum": 0.9558439269758118, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.05692503721794195, "standard_deviation": 0.006644109306438364, "minimum": 0.04937793075243149, "maximum": 0.07013681051628333, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9992880711474008, "standard_deviation": 0.0002510996552615456, "minimum": 0.9987518735817904, "maximum": 0.9995039973116465, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.575001483889894, "standard_deviation": 0.017023235260833238, "minimum": 0.5422347649734748, "maximum": 0.5922037482022742, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.4594678645243873, "standard_deviation": 0.31045167929273504, "minimum": 0.07675975469144573, "maximum": 0.9689500995767656, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03132807271052314, "standard_deviation": 0.004849111254515475, "minimum": 0.026998965367264496, "maximum": 0.04151541700692019, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.15053861834346283, "standard_deviation": 0.042399393734381695, "minimum": 0.1075398277652184, "maximum": 0.2056681330494882, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.243349701950932, "standard_deviation": 0.007176351658116669, "minimum": 5.234832254226589, "maximum": 5.252967501673714, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3737260726120831, "standard_deviation": 0.006017353632679186, "minimum": 0.36524733614130817, "maximum": 0.38160986437601946, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07304314946947998, "standard_deviation": 0.04819787468190936, "minimum": -0.12819596373650513, "maximum": -0.0013343867028563572, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9975317531349264, "standard_deviation": 0.00041091441822079037, "minimum": 0.9969127219033088, "maximum": 0.998288161475347, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7124030442861349, "standard_deviation": 0.013767249009813121, "minimum": 0.6966918857432857, "maximum": 0.7351044459258275, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4251352904792365, "standard_deviation": 0.20754521052315142, "minimum": 0.10562117883053873, "maximum": 0.7242092419836501, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.054035565088470947, "standard_deviation": 0.004683931514479217, "minimum": 0.04456123154296024, "maximum": 0.0603758037020363, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9993513848208888, "standard_deviation": 0.0001520740136646384, "minimum": 0.9990918012492291, "maximum": 0.9995764758016322, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4342044824467066, "standard_deviation": 0.019842304732878145, "minimum": 0.40903180926183264, "maximum": 0.4605754211924222, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4478357834431117, "standard_deviation": 0.14837164069344153, "minimum": 0.2743976850645826, "maximum": 0.7296970718536374, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0283295015463384, "standard_deviation": 0.0036427225468246716, "minimum": 0.021710163183939906, "maximum": 0.03314413693469261, "valid_count": 8, "planned_count": 8}}, "seconds": 5.447272108998732, "rtf_including_measurement": 0.907878684833122}, {"case": "jvs_jvs018_falset10_VOICEACTRESS100_004", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs018", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.1763219833374023, "predicted_mos": 2.1763219833374023, "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": 3.643979609005328}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6359773207792045, "全帯域_10ms_rms_envelope_nrmse": 0.059906280934444195, "全帯域_10ms_envelope_correlation": 0.9969465784220098, "全帯域_10ms_modulation_mae_db": 0.4119159338895509, "全帯域_40ms_log_rms_mae_db": 0.4137202360885373, "全帯域_40ms_rms_envelope_nrmse": 0.03386544525459576, "全帯域_40ms_envelope_correlation": 0.9990305096874875, "全帯域_40ms_modulation_mae_db": 0.3526725719954791, "300–1000 Hz_10ms_log_rms_mae_db": 0.8153622316879527, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05326063000849336, "300–1000 Hz_10ms_envelope_correlation": 0.99795100389157, "300–1000 Hz_10ms_modulation_mae_db": 0.5411887694479984, "300–1000 Hz_40ms_log_rms_mae_db": 0.5670326230747852, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.028981597626128612, "300–1000 Hz_40ms_envelope_correlation": 0.999387905057288, "300–1000 Hz_40ms_modulation_mae_db": 0.22851309444372211, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8215535214124924, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11669865284842854, "1000–3000 Hz_10ms_envelope_correlation": 0.992203298133501, "1000–3000 Hz_10ms_modulation_mae_db": 1.2621997852040152, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5774061365792994, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07499922250935998, "1000–3000 Hz_40ms_envelope_correlation": 0.9968784971724863, "1000–3000 Hz_40ms_modulation_mae_db": 1.203762027914709, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0682620071762001, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1629928316471794, "3000–6000 Hz_10ms_envelope_correlation": 0.9809267708406442, "3000–6000 Hz_10ms_modulation_mae_db": 1.720423040478553, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7541305762404519, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10047890828041273, "3000–6000 Hz_40ms_envelope_correlation": 0.993053756412999, "3000–6000 Hz_40ms_modulation_mae_db": 2.0934884323210983, "mr_stft_db": 5.223902532623515, "band_mae_db": 0.11197726259369394, "rms_gain_error_db": -0.07603983678969509, "output_peak": 0.3637118031190991}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6129964819307565, "全帯域_10ms_rms_envelope_nrmse": 0.052519307442863074, "全帯域_10ms_envelope_correlation": 0.9976228552605128, "全帯域_10ms_modulation_mae_db": 0.33672082752854365, "全帯域_40ms_log_rms_mae_db": 0.36505932525687557, "全帯域_40ms_rms_envelope_nrmse": 0.02609692254370711, "全帯域_40ms_envelope_correlation": 0.9993888126954226, "全帯域_40ms_modulation_mae_db": 0.45831264315864756, "300–1000 Hz_10ms_log_rms_mae_db": 0.8196628243891788, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05404363986831551, "300–1000 Hz_10ms_envelope_correlation": 0.9979006355305912, "300–1000 Hz_10ms_modulation_mae_db": 0.5432690999197394, "300–1000 Hz_40ms_log_rms_mae_db": 0.5274103246875592, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029024007389028595, "300–1000 Hz_40ms_envelope_correlation": 0.9993832124154782, "300–1000 Hz_40ms_modulation_mae_db": 0.1379409561854355, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7833879124734586, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07679575992919316, "1000–3000 Hz_10ms_envelope_correlation": 0.9965870292627871, "1000–3000 Hz_10ms_modulation_mae_db": 0.23210557695634274, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5514759804242803, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03865120252845147, "1000–3000 Hz_40ms_envelope_correlation": 0.9991222669675579, "1000–3000 Hz_40ms_modulation_mae_db": 0.11158550440073974, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0840126552532094, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14679718154544946, "3000–6000 Hz_10ms_envelope_correlation": 0.9843828475140692, "3000–6000 Hz_10ms_modulation_mae_db": 0.47763711931768643, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7807332410368417, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07759380317239102, "3000–6000 Hz_40ms_envelope_correlation": 0.9956932997382759, "3000–6000 Hz_40ms_modulation_mae_db": 0.7035411822558979, "mr_stft_db": 5.21509912519238, "band_mae_db": 0.09836481402583029, "rms_gain_error_db": 0.0021519499430591674, "output_peak": 0.37504780174817637}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6072415547535962, "全帯域_10ms_rms_envelope_nrmse": 0.05297687782459769, "全帯域_10ms_envelope_correlation": 0.9975928111648401, "全帯域_10ms_modulation_mae_db": 0.19002680867426172, "全帯域_40ms_log_rms_mae_db": 0.38252978546841493, "全帯域_40ms_rms_envelope_nrmse": 0.02823981904104653, "全帯域_40ms_envelope_correlation": 0.9993056479604491, "全帯域_40ms_modulation_mae_db": 0.5222441056675011, "300–1000 Hz_10ms_log_rms_mae_db": 0.8616351318534352, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0567892396434155, "300–1000 Hz_10ms_envelope_correlation": 0.9976720744550255, "300–1000 Hz_10ms_modulation_mae_db": 0.8165495205581061, "300–1000 Hz_40ms_log_rms_mae_db": 0.5778017632393565, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.030843642775678786, "300–1000 Hz_40ms_envelope_correlation": 0.99930995237482, "300–1000 Hz_40ms_modulation_mae_db": 0.7058864886431163, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7814083767156006, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0776353966008715, "1000–3000 Hz_10ms_envelope_correlation": 0.9965479425075978, "1000–3000 Hz_10ms_modulation_mae_db": 0.6870638787018689, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5641338689462929, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04475431695819305, "1000–3000 Hz_40ms_envelope_correlation": 0.9988857586671875, "1000–3000 Hz_40ms_modulation_mae_db": 0.5355506316133818, "3000–6000 Hz_10ms_log_rms_mae_db": 1.057469011097499, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14904925485814985, "3000–6000 Hz_10ms_envelope_correlation": 0.9842714411579457, "3000–6000 Hz_10ms_modulation_mae_db": 0.7167484901388255, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7035508354052765, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09186207193580498, "3000–6000 Hz_40ms_envelope_correlation": 0.9944204666513174, "3000–6000 Hz_40ms_modulation_mae_db": 0.7531227005394331, "mr_stft_db": 5.224618450662562, "band_mae_db": 0.11089423102425496, "rms_gain_error_db": -0.04729644446804299, "output_peak": 0.38069898045437434}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.605474764333455, "全帯域_10ms_rms_envelope_nrmse": 0.055586896651105756, "全帯域_10ms_envelope_correlation": 0.997394120881029, "全帯域_10ms_modulation_mae_db": 0.6641762618935909, "全帯域_40ms_log_rms_mae_db": 0.3806092907638193, "全帯域_40ms_rms_envelope_nrmse": 0.028440231447674758, "全帯域_40ms_envelope_correlation": 0.9993568845831646, "全帯域_40ms_modulation_mae_db": 0.6835650336120033, "300–1000 Hz_10ms_log_rms_mae_db": 0.8518924218481276, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06682205035000409, "300–1000 Hz_10ms_envelope_correlation": 0.9967701673081599, "300–1000 Hz_10ms_modulation_mae_db": 0.4634694901473148, "300–1000 Hz_40ms_log_rms_mae_db": 0.5687046027276503, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038491232023202336, "300–1000 Hz_40ms_envelope_correlation": 0.9989151312118744, "300–1000 Hz_40ms_modulation_mae_db": 0.7921851744310174, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8353653789162915, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09537459895279712, "1000–3000 Hz_10ms_envelope_correlation": 0.9948301946266028, "1000–3000 Hz_10ms_modulation_mae_db": 1.485906259099574, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6060200871550103, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06187632569174375, "1000–3000 Hz_40ms_envelope_correlation": 0.9978985869468856, "1000–3000 Hz_40ms_modulation_mae_db": 1.3035408485165785, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0474047313991108, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1553099049019643, "3000–6000 Hz_10ms_envelope_correlation": 0.984425610947211, "3000–6000 Hz_10ms_modulation_mae_db": 1.8291976281435238, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7669785172451948, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10432842103646886, "3000–6000 Hz_40ms_envelope_correlation": 0.9944563206574716, "3000–6000 Hz_40ms_modulation_mae_db": 2.3103091814641865, "mr_stft_db": 5.204390585406798, "band_mae_db": 0.19923783747650115, "rms_gain_error_db": -0.0851756472426343, "output_peak": 0.3762278261404141}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.630962720796151, "全帯域_10ms_rms_envelope_nrmse": 0.05283479951683047, "全帯域_10ms_envelope_correlation": 0.9977324911492786, "全帯域_10ms_modulation_mae_db": 0.6135254645996877, "全帯域_40ms_log_rms_mae_db": 0.3864132349325126, "全帯域_40ms_rms_envelope_nrmse": 0.0276884155724496, "全帯域_40ms_envelope_correlation": 0.9994789193215494, "全帯域_40ms_modulation_mae_db": 0.43599434366316886, "300–1000 Hz_10ms_log_rms_mae_db": 0.8249083774555178, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.053042265176583045, "300–1000 Hz_10ms_envelope_correlation": 0.9980510857102848, "300–1000 Hz_10ms_modulation_mae_db": 0.3193842152220197, "300–1000 Hz_40ms_log_rms_mae_db": 0.5607771392390732, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02945528261756661, "300–1000 Hz_40ms_envelope_correlation": 0.9994614183368876, "300–1000 Hz_40ms_modulation_mae_db": 0.3486125122713935, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8239451491123474, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08032102580127652, "1000–3000 Hz_10ms_envelope_correlation": 0.996433917831956, "1000–3000 Hz_10ms_modulation_mae_db": 0.3492994398738903, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5720004045436592, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04316408815936352, "1000–3000 Hz_40ms_envelope_correlation": 0.9991301116116226, "1000–3000 Hz_40ms_modulation_mae_db": 0.3600582826777549, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0555113747881044, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14859739015405335, "3000–6000 Hz_10ms_envelope_correlation": 0.9843669295648384, "3000–6000 Hz_10ms_modulation_mae_db": 1.2832610360800725, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7375273629306961, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0953725691231412, "3000–6000 Hz_40ms_envelope_correlation": 0.9938927651979338, "3000–6000 Hz_40ms_modulation_mae_db": 1.8503745056117378, "mr_stft_db": 5.206727832632919, "band_mae_db": 0.16484470029564244, "rms_gain_error_db": -0.12163673800408391, "output_peak": 0.36920511235584713}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6311019903901663, "全帯域_10ms_rms_envelope_nrmse": 0.05374356635312121, "全帯域_10ms_envelope_correlation": 0.9976906167685328, "全帯域_10ms_modulation_mae_db": 0.3728571746965763, "全帯域_40ms_log_rms_mae_db": 0.3759349535802974, "全帯域_40ms_rms_envelope_nrmse": 0.031164155791756007, "全帯域_40ms_envelope_correlation": 0.9993352450823396, "全帯域_40ms_modulation_mae_db": 0.29683356706986475, "300–1000 Hz_10ms_log_rms_mae_db": 0.8179666780106105, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.055836743792921896, "300–1000 Hz_10ms_envelope_correlation": 0.9977633697906647, "300–1000 Hz_10ms_modulation_mae_db": 0.39188078017691597, "300–1000 Hz_40ms_log_rms_mae_db": 0.5587507515026484, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.029797163433637783, "300–1000 Hz_40ms_envelope_correlation": 0.9993719845918589, "300–1000 Hz_40ms_modulation_mae_db": 0.3331368579332139, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8360556183145981, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09553094780691584, "1000–3000 Hz_10ms_envelope_correlation": 0.9962824471027946, "1000–3000 Hz_10ms_modulation_mae_db": 0.48291300084270494, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5693064845015993, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07014456714612012, "1000–3000 Hz_40ms_envelope_correlation": 0.9988516420077722, "1000–3000 Hz_40ms_modulation_mae_db": 0.3741041608060334, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0552655849844201, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14455706717421277, "3000–6000 Hz_10ms_envelope_correlation": 0.9852192863453247, "3000–6000 Hz_10ms_modulation_mae_db": 0.7485125462656649, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7333040871550254, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07997557420326945, "3000–6000 Hz_40ms_envelope_correlation": 0.9959847491703308, "3000–6000 Hz_40ms_modulation_mae_db": 1.0465056066944591, "mr_stft_db": 5.228050266607134, "band_mae_db": 0.1899779285672383, "rms_gain_error_db": -0.1328728924806132, "output_peak": 0.3739775726907395}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6352853597530985, "全帯域_10ms_rms_envelope_nrmse": 0.04467272369637496, "全帯域_10ms_envelope_correlation": 0.9982792660439229, "全帯域_10ms_modulation_mae_db": 0.2055418946992739, "全帯域_40ms_log_rms_mae_db": 0.36743816021016346, "全帯域_40ms_rms_envelope_nrmse": 0.022149648431059293, "全帯域_40ms_envelope_correlation": 0.999558863138852, "全帯域_40ms_modulation_mae_db": 0.1403436821285958, "300–1000 Hz_10ms_log_rms_mae_db": 0.778563115242343, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.04843322315931049, "300–1000 Hz_10ms_envelope_correlation": 0.998332898371361, "300–1000 Hz_10ms_modulation_mae_db": 0.39477759013221264, "300–1000 Hz_40ms_log_rms_mae_db": 0.5363358027477406, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.026881969709501234, "300–1000 Hz_40ms_envelope_correlation": 0.999489044688455, "300–1000 Hz_40ms_modulation_mae_db": 0.26247181279506987, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8127061789111066, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07037163340685917, "1000–3000 Hz_10ms_envelope_correlation": 0.9973687597518511, "1000–3000 Hz_10ms_modulation_mae_db": 1.5031589747502954, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5880391684021496, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.040559745536525325, "1000–3000 Hz_40ms_envelope_correlation": 0.9993099259735598, "1000–3000 Hz_40ms_modulation_mae_db": 1.4975925531240915, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0386607925412656, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13956769878731384, "3000–6000 Hz_10ms_envelope_correlation": 0.9862917880012364, "3000–6000 Hz_10ms_modulation_mae_db": 0.6450446574350037, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7179890128520559, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08335736955537962, "3000–6000 Hz_40ms_envelope_correlation": 0.9955378027574816, "3000–6000 Hz_40ms_modulation_mae_db": 0.6644234984259337, "mr_stft_db": 5.2221818736606815, "band_mae_db": 0.11176554073515085, "rms_gain_error_db": -0.003261194089513133, "output_peak": 0.3777086039125587}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6457281540624642, "全帯域_10ms_rms_envelope_nrmse": 0.053863411201155655, "全帯域_10ms_envelope_correlation": 0.997571771889465, "全帯域_10ms_modulation_mae_db": 0.18798241550750472, "全帯域_40ms_log_rms_mae_db": 0.40670065833656716, "全帯域_40ms_rms_envelope_nrmse": 0.03074090279970889, "全帯域_40ms_envelope_correlation": 0.9992453783918492, "全帯域_40ms_modulation_mae_db": 0.0954136138839174, "300–1000 Hz_10ms_log_rms_mae_db": 0.7961718902167131, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05980833706171113, "300–1000 Hz_10ms_envelope_correlation": 0.9974227484014102, "300–1000 Hz_10ms_modulation_mae_db": 0.743691333270136, "300–1000 Hz_40ms_log_rms_mae_db": 0.5688285138057586, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03413282525032083, "300–1000 Hz_40ms_envelope_correlation": 0.9991589964719233, "300–1000 Hz_40ms_modulation_mae_db": 0.34404417378231744, "1000–3000 Hz_10ms_log_rms_mae_db": 0.798755297900244, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07708782421080741, "1000–3000 Hz_10ms_envelope_correlation": 0.9973373644304985, "1000–3000 Hz_10ms_modulation_mae_db": 0.4430660166856442, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5550226617064322, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04953487186539888, "1000–3000 Hz_40ms_envelope_correlation": 0.9994266525229805, "1000–3000 Hz_40ms_modulation_mae_db": 0.6226808821910237, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0312826486933806, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14415296893888296, "3000–6000 Hz_10ms_envelope_correlation": 0.9860989862845629, "3000–6000 Hz_10ms_modulation_mae_db": 0.7107843622839668, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7281390517940429, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09884066791743253, "3000–6000 Hz_40ms_envelope_correlation": 0.9942917173690055, "3000–6000 Hz_40ms_modulation_mae_db": 0.9102154865965582, "mr_stft_db": 5.212451462971853, "band_mae_db": 0.19036548230229536, "rms_gain_error_db": -0.09322816526767934, "output_peak": 0.36286196237115625}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.114685704996071, "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": 0.3637118031190991, "reference_rms_dbfs": -29.30071709983901, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.223902532623515}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"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"}}, "level": {"reference": {"rms": 0.03427394890906224, "rms_dbfs": -29.30071709983901, "peak": 0.37799072265625, "peak_dbfs": -8.450377185723308, "crest_factor_db": 20.8503399141157, "mean": -4.2978922526041666e-07, "zero_energy": false}, "output": {"rms": 0.033975210265313964, "rms_dbfs": -29.376756936628702, "peak": 0.3637118031190991, "peak_dbfs": -8.784852101186843, "crest_factor_db": 20.59190483544186, "mean": -2.616510113309268e-05, "zero_energy": false}, "rms_difference_db": -0.07603983678969328}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 2.1519445744343104e-06, "threshold_dbfs": -56.67168918566671, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 230, "quiet_samples": 55200, "reference_mean_power": 7.20824607634458e-08, "output_mean_power": 1.3910360380075357e-07, "output_rms_dbfs": -68.56661618458658, "output_zero_energy": false, "output_peak": 0.010730674575133088, "output_energy_fraction": 4.619454149197137e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 317, "output_estimated_voiced_frames": 297, "both_estimated_voiced_frames": 292, "reference_voiced_output_unvoiced_frames": 25, "reference_unvoiced_output_voiced_frames": 5, "paired_voiced_fraction": 0.9211356466876972, "absolute_difference_cents_median": 1.915063029068821, "absolute_difference_cents_p95": 10.158611175492819, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.059906280934444195, "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": 3.0999366671117794e-06, "output_power": 2.493567747376119e-06, "reference_active": true, "delta_db": -0.9453164912532852}], "active_band_count": 3, "active_band_mae_db": 0.4119159338895509}}, {"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": 0.4137202360885373, "rms_envelope_nrmse": 0.03386544525459576, "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": 0.00013630386160039194, "output_power": 0.0001320275537153355, "reference_active": true, "delta_db": -0.13843583436544793}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.09070162469366e-06, "output_power": 5.473660143927216e-06, "reference_active": true, "delta_db": 0.3150018585170328}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.569083691066088e-07, "output_power": 1.365174306893958e-07, "reference_active": true, "delta_db": -0.6045800231039565}], "active_band_count": 3, "active_band_mae_db": 0.3526725719954791}}]}, {"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": 9.549209054072811e-05, "log_rms_mae_db": 0.8153622316879527, "rms_envelope_nrmse": 0.05326063000849336, "envelope_correlation": 0.99795100389157, "rms_gain_error_db": -0.03680902433079864, "reference_mean_power": 0.0006895778722497405, "output_mean_power": 0.0006837579905012497}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.48267581801043e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.030686777059307e-05, "output_power": 6.867606944667046e-05, "reference_active": true, "delta_db": -0.10192319062269167}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.045775397952225e-06, "output_power": 6.777728113971989e-06, "reference_active": true, "delta_db": 0.4963213429576706}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.002295743692013e-06, "output_power": 1.269194155577327e-06, "reference_active": true, "delta_db": 1.025321774763633}], "active_band_count": 3, "active_band_mae_db": 0.5411887694479984}}, {"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": 8.872309512115069e-05, "log_rms_mae_db": 0.5670326230747852, "rms_envelope_nrmse": 0.028981597626128612, "envelope_correlation": 0.999387905057288, "rms_gain_error_db": -0.03680904495264842, "reference_mean_power": 0.0006930459912916038, "output_mean_power": 0.0006871968361373723}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.440447414854182e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.43293436790663e-05, "output_power": 6.28375279300461e-05, "reference_active": true, "delta_db": -0.10190029256550326}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6389748271852193e-06, "output_power": 2.996287098958456e-06, "reference_active": true, "delta_db": 0.5514817678942328}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.49082443996622e-08, "output_power": 7.435563664622727e-08, "reference_active": true, "delta_db": -0.0321572228714303}], "active_band_count": 3, "active_band_mae_db": 0.22851309444372211}}]}, {"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": 0.8215535214124924, "rms_envelope_nrmse": 0.11669865284842854, "envelope_correlation": 0.992203298133501, "rms_gain_error_db": -0.1810970263960834, "reference_mean_power": 0.0001528560580614903, "output_mean_power": 0.0001466131595227615}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.6939080235935487e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.743995800608424e-06, "output_power": 7.934591529560342e-06, "reference_active": true, "delta_db": -0.4218536605337119}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.018682293764139e-06, "output_power": 1.5550180949641115e-06, "reference_active": true, "delta_db": -1.1333252670285656}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.212055898483429e-07, "output_power": 2.5197188404418606e-07, "reference_active": true, "delta_db": -2.231420428049768}], "active_band_count": 3, "active_band_mae_db": 1.2621997852040152}}, {"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": 0.5774061365792994, "rms_envelope_nrmse": 0.07499922250935998, "envelope_correlation": 0.9968784971724863, "rms_gain_error_db": -0.18109703479549683, "reference_mean_power": 0.00015362482187073777, "output_mean_power": 0.00014735052543987857}, "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": 7.4928215659315015e-06, "reference_active": true, "delta_db": -0.5056330610755593}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.917412489595775e-07, "output_power": 7.749608109697189e-07, "reference_active": true, "delta_db": -1.071186357823498}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.978602825033769e-08, "output_power": 1.2385454789097191e-08, "reference_active": true, "delta_db": -2.0344666648450698}], "active_band_count": 3, "active_band_mae_db": 1.203762027914709}}]}, {"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": 1.0682620071762001, "rms_envelope_nrmse": 0.1629928316471794, "envelope_correlation": 0.9809267708406442, "rms_gain_error_db": -0.32393749085307094, "reference_mean_power": 1.1577512969913926e-05, "output_mean_power": 1.0745373779885703e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.302605621158198e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.645490651287569e-07, "output_power": 7.816590984078881e-07, "reference_active": true, "delta_db": -0.43772258128625036}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.59009391584252e-07, "output_power": 3.082658938766715e-07, "reference_active": true, "delta_db": -1.7289609390397465}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3044874644069092e-07, "output_power": 1.1564205215494784e-07, "reference_active": true, "delta_db": -2.9945856011096623}], "active_band_count": 3, "active_band_mae_db": 1.720423040478553}}, {"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": 0.7541305762404519, "rms_envelope_nrmse": 0.10047890828041273, "envelope_correlation": 0.993053756412999, "rms_gain_error_db": -0.323937500951186, "reference_mean_power": 1.1635739617517738e-05, "output_mean_power": 1.0799415334696378e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.177196911262555e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.600495243066517e-07, "output_power": 7.297762834768084e-07, "reference_active": true, "delta_db": -0.713337145755727}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5501826725164145e-07, "output_power": 1.5720163810404573e-07, "reference_active": true, "delta_db": -2.1011422331172818}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.780810925112428e-08, "output_power": 8.017135421483275e-09, "reference_active": true, "delta_db": -3.4659859180902863}], "active_band_count": 3, "active_band_mae_db": 2.0934884323210983}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9959488692059486, "standard_deviation": 0.0017045077666470302, "minimum": 0.992203298133501, "maximum": 0.9973687597518511, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.8116471792195173, "standard_deviation": 0.021672873081462887, "minimum": 0.7814083767156006, "maximum": 0.8360556183145981, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8057141165142919, "standard_deviation": 0.5270677706575394, "minimum": 0.23210557695634274, "maximum": 1.5031589747502954, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08622697994464366, "standard_deviation": 0.015265859631837223, "minimum": 0.07037163340685917, "maximum": 0.11669865284842854, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9986879302337566, "standard_deviation": 0.0008684806562498695, "minimum": 0.9968784971724863, "maximum": 0.9994266525229805, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5729255990323404, "standard_deviation": 0.0177908087665206, "minimum": 0.5514759804242803, "maximum": 0.6060200871550103, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7511093614055391, "standard_deviation": 0.5119034802106444, "minimum": 0.11158550440073974, "maximum": 1.4975925531240915, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.052960542549394515, "standard_deviation": 0.014112153626543908, "minimum": 0.03865120252845147, "maximum": 0.07499922250935998, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.984497957581979, "standard_deviation": 0.0016536441490061294, "minimum": 0.9809267708406442, "maximum": 0.9862917880012364, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.0547336007416488, "standard_deviation": 0.016521180624202245, "minimum": 1.0312826486933806, "maximum": 1.0840126552532094, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.016451110017912, "standard_deviation": 0.5224433096819292, "minimum": 0.47763711931768643, "maximum": 1.8291976281435238, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14887803725090076, "standard_deviation": 0.007296905766167901, "minimum": 0.13956769878731384, "maximum": 0.1629928316471794, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9946663597443519, "standard_deviation": 0.000999717397349961, "minimum": 0.993053756412999, "maximum": 0.9959847491703308, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7402940855824481, "standard_deviation": 0.02560880161889688, "minimum": 0.7035508354052765, "maximum": 0.7807332410368417, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.291497574238663, "standard_deviation": 0.6790401909486005, "minimum": 0.6644234984259337, "maximum": 2.3103091814641865, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09147617315303755, "standard_deviation": 0.010047708070801365, "minimum": 0.07759380317239102, "maximum": 0.10432842103646886, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9977329979323835, "standard_deviation": 0.00047277615301081436, "minimum": 0.9967701673081599, "maximum": 0.998332898371361, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8207703338379848, "standard_deviation": 0.026940428584317982, "minimum": 0.778563115242343, "maximum": 0.8616351318534352, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5267763498593054, "standard_deviation": 0.1749040849042471, "minimum": 0.3193842152220197, "maximum": 0.8165495205581061, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.05600451613259438, "standard_deviation": 0.005472077087379233, "minimum": 0.04843322315931049, "maximum": 0.06682205035000409, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9993097056435732, "standard_deviation": 0.0001885957858182492, "minimum": 0.9989151312118744, "maximum": 0.999489044688455, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5582051901280716, "standard_deviation": 0.017396831905202137, "minimum": 0.5274103246875592, "maximum": 0.5778017632393565, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.3940988838106607, "standard_deviation": 0.23125010617684438, "minimum": 0.1379409561854355, "maximum": 0.7921851744310174, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0309509651031331, "standard_deviation": 0.0036782759839575057, "minimum": 0.026881969709501234, "maximum": 0.038491232023202336, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1471784746275759, "standard_deviation": 0.042947982972348246, "minimum": 0.09836481402583029, "maximum": 0.19923783747650115, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.21717776621973, "standard_deviation": 0.00880917070963816, "minimum": 5.204390585406798, "maximum": 5.228050266607134, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3724299578490457, "standard_deviation": 0.006523203078938529, "minimum": 0.36286196237115625, "maximum": 0.38069898045437434, "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": 0.9976038139474489, "standard_deviation": 0.0003698973083287385, "minimum": 0.9969465784220098, "maximum": 0.9982792660439229, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.6255960433498615, "standard_deviation": 0.014959824309677773, "minimum": 0.605474764333455, "maximum": 0.6457281540624642, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3728433476861237, "standard_deviation": 0.18563384824613746, "minimum": 0.18798241550750472, "maximum": 0.6641762618935909, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05326298295256163, "standard_deviation": 0.004221310933687324, "minimum": 0.04467272369637496, "maximum": 0.059906280934444195, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9993375326076392, "standard_deviation": 0.00015845634358750094, "minimum": 0.9990305096874875, "maximum": 0.999558863138852, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.38480070557964846, "standard_deviation": 0.017366034583566593, "minimum": 0.36505932525687557, "maximum": 0.4137202360885373, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.3731724451473972, "standard_deviation": 0.19543666622412514, "minimum": 0.0954136138839174, "maximum": 0.6835650336120033, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.028548192610249743, "standard_deviation": 0.003539985391484689, "minimum": 0.022149648431059293, "maximum": 0.03386544525459576, "valid_count": 8, "planned_count": 8}}, "seconds": 6.651314581999031, "rtf_including_measurement": 1.108552430333172}, {"case": "jvs_jvs018_falset10_VOICEACTRESS100_004", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs018", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.1748111248016357, "predicted_mos": 2.1748111248016357, "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": "b6e781047c19ec2f0abc515b62bb7164b5618e5c990fbb477fb34efa7fa6031f", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 7.905992432002677}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2718728069746528, "全帯域_10ms_rms_envelope_nrmse": 0.16967571271608983, "全帯域_10ms_envelope_correlation": 0.9924870467212662, "全帯域_10ms_modulation_mae_db": 1.160453568944012, "全帯域_40ms_log_rms_mae_db": 1.1191948212370344, "全帯域_40ms_rms_envelope_nrmse": 0.15984501357051667, "全帯域_40ms_envelope_correlation": 0.9947304968853119, "全帯域_40ms_modulation_mae_db": 1.333440172432694, "300–1000 Hz_10ms_log_rms_mae_db": 1.0131973180775846, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.14098955595919815, "300–1000 Hz_10ms_envelope_correlation": 0.9957982754746135, "300–1000 Hz_10ms_modulation_mae_db": 1.054105751543432, "300–1000 Hz_40ms_log_rms_mae_db": 0.8671121176419014, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1318182149373995, "300–1000 Hz_40ms_envelope_correlation": 0.9973509330341924, "300–1000 Hz_40ms_modulation_mae_db": 1.0769083610485575, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8678976706941094, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18215808946896622, "1000–3000 Hz_10ms_envelope_correlation": 0.9968443432485815, "1000–3000 Hz_10ms_modulation_mae_db": 2.249241714382505, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7985340208898156, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.17582730525883938, "1000–3000 Hz_40ms_envelope_correlation": 0.9979296782221333, "1000–3000 Hz_40ms_modulation_mae_db": 2.3355487486998694, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0762745238762503, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14543968001540278, "3000–6000 Hz_10ms_envelope_correlation": 0.9882244947209909, "3000–6000 Hz_10ms_modulation_mae_db": 0.5219272875164186, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8883889075980844, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09622965615839496, "3000–6000 Hz_40ms_envelope_correlation": 0.9961744193173185, "3000–6000 Hz_40ms_modulation_mae_db": 0.6251725461316603, "mr_stft_db": 5.172736441326658, "band_mae_db": 1.0938756422291427, "rms_gain_error_db": 1.1175980524199254, "output_peak": 0.39456530063273204}}], "planned_noise_seeds": [0], "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": 5.446134998801629, "spectral_convergence": 0.3612483721517316, "spectral_convergence_status": "ok", "amplitude_floor": 9.086732072822267e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 4.981493260432632, "spectral_convergence": 0.24443588803206523, "spectral_convergence_status": "ok", "amplitude_floor": 8.520258431312163e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.090581064745712, "spectral_convergence": 0.26264769555018547, "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": 5.737787091988346e-05, "delta_db": 2.6293188985043194, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0004897019472039064, "output_power": 0.0005865862240128621, "delta_db": 0.7840002844261234, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.00038033005135275084, "output_power": 0.0005185558890947753, "delta_db": 1.3463492872844594, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0002067238728943134, "output_power": 0.0002832381168282431, "delta_db": 1.3676106548496505, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.323291799953591e-05, "output_power": 1.62287406419461e-05, "delta_db": 0.8862919836134939, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.500515826026349e-05, "output_power": 2.719241921862098e-05, "delta_db": 0.3641823944673218, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.8390290595099542e-05, "output_power": 3.0276623279326933e-05, "delta_db": 0.2793759924586315, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.0938756422291427, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 1.1175980524199254, "pitch": null, "output_rms_dbfs": -28.18311904741908, "output_peak": 0.39456530063273204, "reference_rms_dbfs": -29.30071709983901, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.172736441326658}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.9223432131341783, "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"}}, "level": {"reference": {"rms": 0.03427394890906224, "rms_dbfs": -29.30071709983901, "peak": 0.37799072265625, "peak_dbfs": -8.450377185723308, "crest_factor_db": 20.8503399141157, "mean": -4.2978922526041666e-07, "zero_energy": false}, "output": {"rms": 0.038980198614112505, "rms_dbfs": -28.183119047419083, "peak": 0.39456530063273204, "peak_dbfs": -8.077622213726828, "crest_factor_db": 20.105496833692253, "mean": 2.414054858577523e-09, "zero_energy": false}, "rms_difference_db": 1.1175980524199254}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 2.1519445744343104e-06, "threshold_dbfs": -56.67168918566671, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 230, "quiet_samples": 55200, "reference_mean_power": 7.20824607634458e-08, "output_mean_power": 1.501102432958891e-07, "output_rms_dbfs": -68.23589671147172, "output_zero_energy": false, "output_peak": 0.006008000081507324, "output_energy_fraction": 3.787030642757065e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 317, "output_estimated_voiced_frames": 328, "both_estimated_voiced_frames": 311, "reference_voiced_output_unvoiced_frames": 6, "reference_unvoiced_output_voiced_frames": 17, "paired_voiced_fraction": 0.9810725552050473, "absolute_difference_cents_median": 4.394907446562953, "absolute_difference_cents_p95": 16.977183066295495, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.2718728069746528, "rms_envelope_nrmse": 0.16967571271608983, "envelope_correlation": 0.9924870467212662, "rms_gain_error_db": 1.1175980878922243, "reference_mean_power": 0.0011756832947918806, "output_mean_power": 0.0015207231461526716}, "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": 0.00022422214719589864, "reference_active": true, "delta_db": 1.7253598248878166}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2413420104691182e-05, "output_power": 1.701282387848642e-05, "reference_active": true, "delta_db": 1.3688495271796939}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0999366671117794e-06, "output_power": 3.388971812160135e-06, "reference_active": true, "delta_db": 0.3871513547645261}], "active_band_count": 3, "active_band_mae_db": 1.160453568944012}}, {"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": 1.1191948212370344, "rms_envelope_nrmse": 0.15984501357051667, "envelope_correlation": 0.9947304968853119, "rms_gain_error_db": 1.1175983868922161, "reference_mean_power": 0.0011815960953402045, "output_mean_power": 0.0015283713422294695}, "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": 0.00013630386160039194, "output_power": 0.00020362171063265672, "reference_active": true, "delta_db": 1.7431592171897172}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.09070162469366e-06, "output_power": 7.473603775422218e-06, "reference_active": true, "delta_db": 1.6675242634358827}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.569083691066088e-07, "output_power": 1.797255461715747e-07, "reference_active": true, "delta_db": 0.5896370366724825}], "active_band_count": 3, "active_band_mae_db": 1.333440172432694}}]}, {"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": 9.549209054072811e-05, "log_rms_mae_db": 1.0131973180775846, "rms_envelope_nrmse": 0.14098955595919815, "envelope_correlation": 0.9957982754746135, "rms_gain_error_db": 0.9516892861631489, "reference_mean_power": 0.0006895778722497405, "output_mean_power": 0.0008585236151189462}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.48267581801043e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.030686777059307e-05, "output_power": 8.856000503461954e-05, "reference_active": true, "delta_db": 1.002398823741041}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.045775397952225e-06, "output_power": 8.978220482142295e-06, "reference_active": true, "delta_db": 1.717382573644724}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.002295743692013e-06, "output_power": 1.1098121417109288e-06, "reference_active": true, "delta_db": 0.4425358572445307}], "active_band_count": 3, "active_band_mae_db": 1.054105751543432}}, {"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": 8.872309512115069e-05, "log_rms_mae_db": 0.8671121176419014, "rms_envelope_nrmse": 0.1318182149373995, "envelope_correlation": 0.9973509330341924, "rms_gain_error_db": 0.9516892309448234, "reference_mean_power": 0.0006930459912916038, "output_mean_power": 0.000862841408151798}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.440447414854182e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.43293436790663e-05, "output_power": 8.126813481059342e-05, "reference_active": true, "delta_db": 1.0151117182271965}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6389748271852193e-06, "output_power": 4.109102271441418e-06, "reference_active": true, "delta_db": 1.9231170298622495}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.49082443996622e-08, "output_power": 7.002933225342809e-08, "reference_active": true, "delta_db": -0.2924963350562263}], "active_band_count": 3, "active_band_mae_db": 1.0769083610485575}}]}, {"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": 0.8678976706941094, "rms_envelope_nrmse": 0.18215808946896622, "envelope_correlation": 0.9968443432485815, "rms_gain_error_db": 1.3166860686229434, "reference_mean_power": 0.0001528560580614903, "output_mean_power": 0.00020699090455617955}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.6939080235935487e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.743995800608424e-06, "output_power": 1.2111703844563568e-05, "reference_active": true, "delta_db": 1.414953025477982}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.018682293764139e-06, "output_power": 3.4464921263329377e-06, "reference_active": true, "delta_db": 2.3230931690421066}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.212055898483429e-07, "output_power": 8.422907299297453e-07, "reference_active": true, "delta_db": 3.0096789486274265}], "active_band_count": 3, "active_band_mae_db": 2.249241714382505}}, {"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": 0.7985340208898156, "rms_envelope_nrmse": 0.17582730525883938, "envelope_correlation": 0.9979296782221333, "rms_gain_error_db": 1.3166860789953025, "reference_mean_power": 0.00015362482187073777, "output_mean_power": 0.0002080319309586028}, "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": 1.1919034753373352e-05, "reference_active": true, "delta_db": 1.5103238954822542}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.917412489595775e-07, "output_power": 1.7093412919404872e-06, "reference_active": true, "delta_db": 2.3643040686356}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.978602825033769e-08, "output_power": 4.0696817911601873e-08, "reference_active": true, "delta_db": 3.1320182819817544}], "active_band_count": 3, "active_band_mae_db": 2.3355487486998694}}]}, {"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": 1.0762745238762503, "rms_envelope_nrmse": 0.14543968001540278, "envelope_correlation": 0.9882244947209909, "rms_gain_error_db": 0.5298657241176431, "reference_mean_power": 1.1577512969913926e-05, "output_mean_power": 1.307982244512623e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.302605621158198e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.645490651287569e-07, "output_power": 9.507577380024202e-07, "reference_active": true, "delta_db": 0.41280223212205025}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.59009391584252e-07, "output_power": 4.4650685595446046e-07, "reference_active": true, "delta_db": -0.11993439818245152}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3044874644069092e-07, "output_power": 1.8166439917669205e-07, "reference_active": true, "delta_db": -1.0330452322447539}], "active_band_count": 3, "active_band_mae_db": 0.5219272875164186}}, {"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": 0.8883889075980844, "rms_envelope_nrmse": 0.09622965615839496, "envelope_correlation": 0.9961744193173185, "rms_gain_error_db": 0.5298657948508418, "reference_mean_power": 1.1635739617517738e-05, "output_mean_power": 1.3145604853919377e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.177196911262555e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.600495243066517e-07, "output_power": 9.061118017687771e-07, "reference_active": true, "delta_db": 0.22658326984991953}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5501826725164145e-07, "output_power": 2.3838992479421504e-07, "reference_active": true, "delta_db": -0.2928339393400336}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.780810925112428e-08, "output_power": 1.303190089034781e-08, "reference_active": true, "delta_db": -1.3561004292050276}], "active_band_count": 3, "active_band_mae_db": 0.6251725461316603}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1234628, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9968443432485815, "standard_deviation": null, "minimum": 0.9968443432485815, "maximum": 0.9968443432485815, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.8678976706941094, "standard_deviation": null, "minimum": 0.8678976706941094, "maximum": 0.8678976706941094, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 2.249241714382505, "standard_deviation": null, "minimum": 2.249241714382505, "maximum": 2.249241714382505, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.18215808946896622, "standard_deviation": null, "minimum": 0.18215808946896622, "maximum": 0.18215808946896622, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9979296782221333, "standard_deviation": null, "minimum": 0.9979296782221333, "maximum": 0.9979296782221333, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7985340208898156, "standard_deviation": null, "minimum": 0.7985340208898156, "maximum": 0.7985340208898156, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 2.3355487486998694, "standard_deviation": null, "minimum": 2.3355487486998694, "maximum": 2.3355487486998694, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.17582730525883938, "standard_deviation": null, "minimum": 0.17582730525883938, "maximum": 0.17582730525883938, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9882244947209909, "standard_deviation": null, "minimum": 0.9882244947209909, "maximum": 0.9882244947209909, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.0762745238762503, "standard_deviation": null, "minimum": 1.0762745238762503, "maximum": 1.0762745238762503, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5219272875164186, "standard_deviation": null, "minimum": 0.5219272875164186, "maximum": 0.5219272875164186, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14543968001540278, "standard_deviation": null, "minimum": 0.14543968001540278, "maximum": 0.14543968001540278, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9961744193173185, "standard_deviation": null, "minimum": 0.9961744193173185, "maximum": 0.9961744193173185, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8883889075980844, "standard_deviation": null, "minimum": 0.8883889075980844, "maximum": 0.8883889075980844, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6251725461316603, "standard_deviation": null, "minimum": 0.6251725461316603, "maximum": 0.6251725461316603, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09622965615839496, "standard_deviation": null, "minimum": 0.09622965615839496, "maximum": 0.09622965615839496, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9957982754746135, "standard_deviation": null, "minimum": 0.9957982754746135, "maximum": 0.9957982754746135, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0131973180775846, "standard_deviation": null, "minimum": 1.0131973180775846, "maximum": 1.0131973180775846, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 1.054105751543432, "standard_deviation": null, "minimum": 1.054105751543432, "maximum": 1.054105751543432, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14098955595919815, "standard_deviation": null, "minimum": 0.14098955595919815, "maximum": 0.14098955595919815, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9973509330341924, "standard_deviation": null, "minimum": 0.9973509330341924, "maximum": 0.9973509330341924, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.8671121176419014, "standard_deviation": null, "minimum": 0.8671121176419014, "maximum": 0.8671121176419014, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.0769083610485575, "standard_deviation": null, "minimum": 1.0769083610485575, "maximum": 1.0769083610485575, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1318182149373995, "standard_deviation": null, "minimum": 0.1318182149373995, "maximum": 0.1318182149373995, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 1.0938756422291427, "standard_deviation": null, "minimum": 1.0938756422291427, "maximum": 1.0938756422291427, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 5.172736441326658, "standard_deviation": null, "minimum": 5.172736441326658, "maximum": 5.172736441326658, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.39456530063273204, "standard_deviation": null, "minimum": 0.39456530063273204, "maximum": 0.39456530063273204, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 1.1175980524199254, "standard_deviation": null, "minimum": 1.1175980524199254, "maximum": 1.1175980524199254, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9924870467212662, "standard_deviation": null, "minimum": 0.9924870467212662, "maximum": 0.9924870467212662, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.2718728069746528, "standard_deviation": null, "minimum": 1.2718728069746528, "maximum": 1.2718728069746528, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 1.160453568944012, "standard_deviation": null, "minimum": 1.160453568944012, "maximum": 1.160453568944012, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.16967571271608983, "standard_deviation": null, "minimum": 0.16967571271608983, "maximum": 0.16967571271608983, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9947304968853119, "standard_deviation": null, "minimum": 0.9947304968853119, "maximum": 0.9947304968853119, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 1.1191948212370344, "standard_deviation": null, "minimum": 1.1191948212370344, "maximum": 1.1191948212370344, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 1.333440172432694, "standard_deviation": null, "minimum": 1.333440172432694, "maximum": 1.333440172432694, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.15984501357051667, "standard_deviation": null, "minimum": 0.15984501357051667, "maximum": 0.15984501357051667, "valid_count": 1, "planned_count": 1}}, "seconds": 2.347823069001606, "rtf_including_measurement": 0.39130384483360103}, {"case": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "normal", "speaker": "jvs_jvs018", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.1873247623443604, "predicted_mos": 2.1873247623443604, "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": "4c1b1548281bae3e4a0761883b3701a405b8890baed81bdd954b3dc4678e22d3", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 5.807911712996429}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9315617601646522, "全帯域_10ms_rms_envelope_nrmse": 0.05039786642740051, "全帯域_10ms_envelope_correlation": 0.9977600185397406, "全帯域_10ms_modulation_mae_db": 0.2800328978830039, "全帯域_40ms_log_rms_mae_db": 0.5645988316936609, "全帯域_40ms_rms_envelope_nrmse": 0.025132955909861053, "全帯域_40ms_envelope_correlation": 0.9995128558275873, "全帯域_40ms_modulation_mae_db": 0.3718235261399552, "300–1000 Hz_10ms_log_rms_mae_db": 1.1223015885580876, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06630481325437254, "300–1000 Hz_10ms_envelope_correlation": 0.9969117681551721, "300–1000 Hz_10ms_modulation_mae_db": 1.0766396245398038, "300–1000 Hz_40ms_log_rms_mae_db": 0.7791573626681991, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03666776686006897, "300–1000 Hz_40ms_envelope_correlation": 0.9990603633996447, "300–1000 Hz_40ms_modulation_mae_db": 0.9801700938572049, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2777110452589409, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09982430566281507, "1000–3000 Hz_10ms_envelope_correlation": 0.9936332075163384, "1000–3000 Hz_10ms_modulation_mae_db": 0.390138736426581, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8505344410223883, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06503961854776755, "1000–3000 Hz_40ms_envelope_correlation": 0.9976671456038424, "1000–3000 Hz_40ms_modulation_mae_db": 0.7186800193318038, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2352021138324725, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12241198927194766, "3000–6000 Hz_10ms_envelope_correlation": 0.9897616712636855, "3000–6000 Hz_10ms_modulation_mae_db": 0.22364198776591096, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8341980204049442, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06421454839140847, "3000–6000 Hz_40ms_envelope_correlation": 0.997242147338838, "3000–6000 Hz_40ms_modulation_mae_db": 0.4081756155927714, "mr_stft_db": 5.106115564422344, "band_mae_db": 0.16821511479630424, "rms_gain_error_db": -0.09996433116726672, "output_peak": 0.3361929615352868}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9130635627207029, "全帯域_10ms_rms_envelope_nrmse": 0.05070705429652051, "全帯域_10ms_envelope_correlation": 0.9977081324846542, "全帯域_10ms_modulation_mae_db": 0.30340546307662236, "全帯域_40ms_log_rms_mae_db": 0.5242890472854366, "全帯域_40ms_rms_envelope_nrmse": 0.027334414161718463, "全帯域_40ms_envelope_correlation": 0.9993688485364296, "全帯域_40ms_modulation_mae_db": 0.39210888120634535, "300–1000 Hz_10ms_log_rms_mae_db": 1.1019722616271301, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05994655821471743, "300–1000 Hz_10ms_envelope_correlation": 0.9974538798017156, "300–1000 Hz_10ms_modulation_mae_db": 0.8151777728516855, "300–1000 Hz_40ms_log_rms_mae_db": 0.7641524828763685, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035567078013554444, "300–1000 Hz_40ms_envelope_correlation": 0.999073744164893, "300–1000 Hz_40ms_modulation_mae_db": 0.7252416778785573, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2717997027592611, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10070075427700682, "1000–3000 Hz_10ms_envelope_correlation": 0.9932612853968639, "1000–3000 Hz_10ms_modulation_mae_db": 0.6911171233102786, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8046485490271789, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05660311134845108, "1000–3000 Hz_40ms_envelope_correlation": 0.9981488254561951, "1000–3000 Hz_40ms_modulation_mae_db": 0.5864152389022187, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2304420337208444, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12350624251190484, "3000–6000 Hz_10ms_envelope_correlation": 0.99023678201632, "3000–6000 Hz_10ms_modulation_mae_db": 0.5613821760680779, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8703538023002315, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07906598557400395, "3000–6000 Hz_40ms_envelope_correlation": 0.9965329509587615, "3000–6000 Hz_40ms_modulation_mae_db": 0.7195085600691504, "mr_stft_db": 5.101712233035221, "band_mae_db": 0.15827094805716357, "rms_gain_error_db": -0.09367390893853926, "output_peak": 0.31498890699572596}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9231940735314873, "全帯域_10ms_rms_envelope_nrmse": 0.05345815102137684, "全帯域_10ms_envelope_correlation": 0.9974305534467669, "全帯域_10ms_modulation_mae_db": 0.6872281018452533, "全帯域_40ms_log_rms_mae_db": 0.5349670290380295, "全帯域_40ms_rms_envelope_nrmse": 0.030524157006221027, "全帯域_40ms_envelope_correlation": 0.9991625581077827, "全帯域_40ms_modulation_mae_db": 0.7116258802737492, "300–1000 Hz_10ms_log_rms_mae_db": 1.1690589007951715, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06246979147222877, "300–1000 Hz_10ms_envelope_correlation": 0.9972753917737694, "300–1000 Hz_10ms_modulation_mae_db": 0.8836877115780438, "300–1000 Hz_40ms_log_rms_mae_db": 0.8064778526101911, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03547647903459117, "300–1000 Hz_40ms_envelope_correlation": 0.9991219051276077, "300–1000 Hz_40ms_modulation_mae_db": 0.916281257537774, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3232622562339844, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11319259569357483, "1000–3000 Hz_10ms_envelope_correlation": 0.9912739089405612, "1000–3000 Hz_10ms_modulation_mae_db": 0.6726343363558511, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8655255521470778, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0635931023093798, "1000–3000 Hz_40ms_envelope_correlation": 0.9974301808091635, "1000–3000 Hz_40ms_modulation_mae_db": 0.24298540168264748, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2671641296392697, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1402177892882291, "3000–6000 Hz_10ms_envelope_correlation": 0.9874751393613, "3000–6000 Hz_10ms_modulation_mae_db": 0.5454076392566367, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8758819629389087, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08313098558151168, "3000–6000 Hz_40ms_envelope_correlation": 0.9965380636604645, "3000–6000 Hz_40ms_modulation_mae_db": 0.5385852485204863, "mr_stft_db": 5.102660652770453, "band_mae_db": 0.16991810294559362, "rms_gain_error_db": -0.08571882376734473, "output_peak": 0.3152503362045257}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8784191853403587, "全帯域_10ms_rms_envelope_nrmse": 0.048305522001110816, "全帯域_10ms_envelope_correlation": 0.9979182597563687, "全帯域_10ms_modulation_mae_db": 0.5317963914566872, "全帯域_40ms_log_rms_mae_db": 0.5087738561504862, "全帯域_40ms_rms_envelope_nrmse": 0.02601173920672434, "全帯域_40ms_envelope_correlation": 0.9994237568834813, "全帯域_40ms_modulation_mae_db": 0.5055621129156195, "300–1000 Hz_10ms_log_rms_mae_db": 1.1118759085727081, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06207187967323825, "300–1000 Hz_10ms_envelope_correlation": 0.9973686612100648, "300–1000 Hz_10ms_modulation_mae_db": 1.288558041079119, "300–1000 Hz_40ms_log_rms_mae_db": 0.7473278055589977, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03437307358395508, "300–1000 Hz_40ms_envelope_correlation": 0.9992554550844992, "300–1000 Hz_40ms_modulation_mae_db": 1.2544476848239727, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2622925030375869, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11384121860173273, "1000–3000 Hz_10ms_envelope_correlation": 0.9909887368909178, "1000–3000 Hz_10ms_modulation_mae_db": 0.15001948279713667, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8403252754440454, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06717892101348981, "1000–3000 Hz_40ms_envelope_correlation": 0.9968140394953133, "1000–3000 Hz_40ms_modulation_mae_db": 0.31678116738413425, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2625385942405405, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12052829133951934, "3000–6000 Hz_10ms_envelope_correlation": 0.9904841008462619, "3000–6000 Hz_10ms_modulation_mae_db": 0.6399648328926695, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8577648752509233, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06963916925776466, "3000–6000 Hz_40ms_envelope_correlation": 0.997252645698538, "3000–6000 Hz_40ms_modulation_mae_db": 0.8005668798655948, "mr_stft_db": 5.089870898326121, "band_mae_db": 0.0882879838654587, "rms_gain_error_db": -0.08112150481716672, "output_peak": 0.30611101431479026}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9213829016727456, "全帯域_10ms_rms_envelope_nrmse": 0.04810531423778764, "全帯域_10ms_envelope_correlation": 0.9979443101055043, "全帯域_10ms_modulation_mae_db": 0.5715618018505345, "全帯域_40ms_log_rms_mae_db": 0.5544868084289187, "全帯域_40ms_rms_envelope_nrmse": 0.026191848286274456, "全帯域_40ms_envelope_correlation": 0.9994225473012999, "全帯域_40ms_modulation_mae_db": 0.2800024995564733, "300–1000 Hz_10ms_log_rms_mae_db": 1.125292466393023, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05667609355748784, "300–1000 Hz_10ms_envelope_correlation": 0.9977536914051, "300–1000 Hz_10ms_modulation_mae_db": 0.7244957069488688, "300–1000 Hz_40ms_log_rms_mae_db": 0.7778766397400264, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.030135946445043478, "300–1000 Hz_40ms_envelope_correlation": 0.999363991663004, "300–1000 Hz_40ms_modulation_mae_db": 0.6732031503370134, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2952672322450516, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10859123558461307, "1000–3000 Hz_10ms_envelope_correlation": 0.9921394499310912, "1000–3000 Hz_10ms_modulation_mae_db": 0.36163105253394257, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8446734153607428, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06451703294021983, "1000–3000 Hz_40ms_envelope_correlation": 0.9975097256176785, "1000–3000 Hz_40ms_modulation_mae_db": 0.18960309753603324, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2676577064934418, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1315936191036173, "3000–6000 Hz_10ms_envelope_correlation": 0.9882010245019164, "3000–6000 Hz_10ms_modulation_mae_db": 0.37530191968202287, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8609723503962712, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07993787785346337, "3000–6000 Hz_40ms_envelope_correlation": 0.9957026256268106, "3000–6000 Hz_40ms_modulation_mae_db": 0.35446892546097114, "mr_stft_db": 5.096347588803612, "band_mae_db": 0.19519429177119388, "rms_gain_error_db": -0.08734571327253594, "output_peak": 0.30117074091398427}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9396534635267507, "全帯域_10ms_rms_envelope_nrmse": 0.05219614800006956, "全帯域_10ms_envelope_correlation": 0.9975370017878618, "全帯域_10ms_modulation_mae_db": 0.31351696151025515, "全帯域_40ms_log_rms_mae_db": 0.5399926984741195, "全帯域_40ms_rms_envelope_nrmse": 0.029492279942325884, "全帯域_40ms_envelope_correlation": 0.9992172455043692, "全帯域_40ms_modulation_mae_db": 0.3037215789335568, "300–1000 Hz_10ms_log_rms_mae_db": 1.1231790024625166, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.061618080276282905, "300–1000 Hz_10ms_envelope_correlation": 0.9973131749254778, "300–1000 Hz_10ms_modulation_mae_db": 0.2213728403421047, "300–1000 Hz_40ms_log_rms_mae_db": 0.7564228635552537, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035608271305461334, "300–1000 Hz_40ms_envelope_correlation": 0.9990787041153115, "300–1000 Hz_40ms_modulation_mae_db": 0.2666021554279366, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2742739988635423, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10509690833777531, "1000–3000 Hz_10ms_envelope_correlation": 0.9927763198870626, "1000–3000 Hz_10ms_modulation_mae_db": 0.5429522944155796, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8091200188088865, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.061982599969753895, "1000–3000 Hz_40ms_envelope_correlation": 0.9978668847221043, "1000–3000 Hz_40ms_modulation_mae_db": 0.6234386709329213, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2592960504335566, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1319627528291412, "3000–6000 Hz_10ms_envelope_correlation": 0.9885886716496791, "3000–6000 Hz_10ms_modulation_mae_db": 0.4387211322923677, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8545837034940083, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07861088601727682, "3000–6000 Hz_40ms_envelope_correlation": 0.9964691254477855, "3000–6000 Hz_40ms_modulation_mae_db": 0.2641834034476016, "mr_stft_db": 5.095894589360184, "band_mae_db": 0.1370418931394505, "rms_gain_error_db": -0.0718005557127549, "output_peak": 0.3182325030065118}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9499192042594169, "全帯域_10ms_rms_envelope_nrmse": 0.05370320986436941, "全帯域_10ms_envelope_correlation": 0.9973684800555944, "全帯域_10ms_modulation_mae_db": 0.3081031397924447, "全帯域_40ms_log_rms_mae_db": 0.5323795795666979, "全帯域_40ms_rms_envelope_nrmse": 0.02772258891685975, "全帯域_40ms_envelope_correlation": 0.9992883840921126, "全帯域_40ms_modulation_mae_db": 0.07210196592078773, "300–1000 Hz_10ms_log_rms_mae_db": 1.171988702034532, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06551609897377908, "300–1000 Hz_10ms_envelope_correlation": 0.9969780498551049, "300–1000 Hz_10ms_modulation_mae_db": 0.7451647223684548, "300–1000 Hz_40ms_log_rms_mae_db": 0.8081192140895781, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.036909212130570794, "300–1000 Hz_40ms_envelope_correlation": 0.9990208356322297, "300–1000 Hz_40ms_modulation_mae_db": 0.6195399794508548, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2531500026090472, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10263991243594496, "1000–3000 Hz_10ms_envelope_correlation": 0.9926952787786484, "1000–3000 Hz_10ms_modulation_mae_db": 0.24475671506586436, "1000–3000 Hz_40ms_log_rms_mae_db": 0.825776554864761, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05890412115225967, "1000–3000 Hz_40ms_envelope_correlation": 0.997563701266298, "1000–3000 Hz_40ms_modulation_mae_db": 0.3391465805494283, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2132536418470312, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12122350621316552, "3000–6000 Hz_10ms_envelope_correlation": 0.9903943364322271, "3000–6000 Hz_10ms_modulation_mae_db": 0.6948755960305105, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8088312012834253, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07445638875354911, "3000–6000 Hz_40ms_envelope_correlation": 0.996779336209801, "3000–6000 Hz_40ms_modulation_mae_db": 0.8867673732838056, "mr_stft_db": 5.096902866504645, "band_mae_db": 0.16755127838723943, "rms_gain_error_db": -0.06366703014940127, "output_peak": 0.31007225721754794}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8907655575467596, "全帯域_10ms_rms_envelope_nrmse": 0.05139609189554884, "全帯域_10ms_envelope_correlation": 0.9975733415834888, "全帯域_10ms_modulation_mae_db": 0.7253593473537702, "全帯域_40ms_log_rms_mae_db": 0.5102613113308151, "全帯域_40ms_rms_envelope_nrmse": 0.028189195171905046, "全帯域_40ms_envelope_correlation": 0.999244478366425, "全帯域_40ms_modulation_mae_db": 0.704034341295324, "300–1000 Hz_10ms_log_rms_mae_db": 1.1713110734876258, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0686078837144048, "300–1000 Hz_10ms_envelope_correlation": 0.996628012769861, "300–1000 Hz_10ms_modulation_mae_db": 0.726052028095498, "300–1000 Hz_40ms_log_rms_mae_db": 0.826880803739617, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04106710257723557, "300–1000 Hz_40ms_envelope_correlation": 0.9987381423017664, "300–1000 Hz_40ms_modulation_mae_db": 0.5900503637193782, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2563552917242633, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09869708246959817, "1000–3000 Hz_10ms_envelope_correlation": 0.9932110937542165, "1000–3000 Hz_10ms_modulation_mae_db": 0.46972158802961167, "1000–3000 Hz_40ms_log_rms_mae_db": 0.84326366309421, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0582626742599604, "1000–3000 Hz_40ms_envelope_correlation": 0.9975827397815499, "1000–3000 Hz_40ms_modulation_mae_db": 0.7965982293171797, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2305101417168263, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11566255596743671, "3000–6000 Hz_10ms_envelope_correlation": 0.9909225020959024, "3000–6000 Hz_10ms_modulation_mae_db": 0.7266831784394574, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8268587229672837, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06752049077466524, "3000–6000 Hz_40ms_envelope_correlation": 0.9969859158249926, "3000–6000 Hz_40ms_modulation_mae_db": 0.7733084663500854, "mr_stft_db": 5.0888092832280485, "band_mae_db": 0.076966871671067, "rms_gain_error_db": -0.040720882885044864, "output_peak": 0.32212777982216234}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.621511035692552, "spectral_convergence": 0.19289832649738942, "spectral_convergence_status": "ok", "amplitude_floor": 8.606911899432486e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.089275722301053, "spectral_convergence": 0.19439014124982965, "spectral_convergence_status": "ok", "amplitude_floor": 7.696353352907002e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.607559935273427, "spectral_convergence": 0.1982913194347469, "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": 0.00012076751766060169, "delta_db": 0.036007304042239834, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0009579981539513103, "output_power": 0.0009406541050738955, "delta_db": -0.07934717076417261, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0008712676276581917, "output_power": 0.0008507501189150415, "delta_db": -0.1034955945432367, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00010621716934048885, "output_power": 0.0001012430364823659, "delta_db": -0.20829561357223927, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.322826988453831e-05, "output_power": 4.808496948515952e-05, "delta_db": -0.44133005448829415, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 7.685697629736477e-05, "output_power": 7.278439174532972e-05, "delta_db": -0.2364503749367022, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.3518932532436965e-05, "output_power": 3.408381100329417e-05, "delta_db": 0.07257969122724495, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.16821511479630424, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.09996433116726672, "pitch": null, "output_rms_dbfs": -26.638670204479794, "output_peak": 0.3361929615352868, "reference_rms_dbfs": -26.53870587331253, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.106115564422344}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.9392697742205003, "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"}}, "level": {"reference": {"rms": 0.04710475034036298, "rms_dbfs": -26.53870587331253, "peak": 0.300323486328125, "peak_dbfs": -10.448214063056167, "crest_factor_db": 16.09049181025636, "mean": -1.2700610690646702e-05, "zero_energy": false}, "output": {"rms": 0.04656573794503517, "rms_dbfs": -26.638670204479794, "peak": 0.3361929615352868, "peak_dbfs": -9.468227661975197, "crest_factor_db": 17.1704425425046, "mean": 3.6858993457048646e-06, "zero_energy": false}, "rms_difference_db": -0.09996433116726422}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.984813836558412e-06, "threshold_dbfs": -57.022802211663084, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 222, "quiet_samples": 53280, "reference_mean_power": 8.965192877270795e-08, "output_mean_power": 8.021793292507804e-07, "output_rms_dbfs": -60.95728533214488, "output_zero_energy": false, "output_peak": 0.01900340425540954, "output_energy_fraction": 0.000136880067689957, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 312, "output_estimated_voiced_frames": 295, "both_estimated_voiced_frames": 292, "reference_voiced_output_unvoiced_frames": 20, "reference_unvoiced_output_voiced_frames": 3, "paired_voiced_fraction": 0.9358974358974359, "absolute_difference_cents_median": 1.809761596448264, "absolute_difference_cents_p95": 11.346236740582595, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.9315617601646522, "rms_envelope_nrmse": 0.05039786642740051, "envelope_correlation": 0.9977600185397406, "rms_gain_error_db": -0.10203273142478056, "reference_mean_power": 0.002217082801939853, "output_mean_power": 0.0021656019807093484}, "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": 0.0003394610101718172, "reference_active": true, "delta_db": -0.13132500698391048}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.422870023578459e-05, "output_power": 7.99274672422706e-05, "reference_active": true, "delta_db": -0.22764047807885202}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2432690798089742e-05, "output_power": 1.112888903144309e-05, "reference_active": true, "delta_db": -0.4811332085862492}], "active_band_count": 3, "active_band_mae_db": 0.2800328978830039}}, {"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": 0.5645988316936609, "rms_envelope_nrmse": 0.025132955909861053, "envelope_correlation": 0.9995128558275873, "rms_gain_error_db": -0.10147557986646555, "reference_mean_power": 0.002205255256660357, "output_mean_power": 0.002154325430162197}, "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": 0.00029633227983582444, "output_power": 0.0002886775949898329, "reference_active": true, "delta_db": -0.11365883805650442}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2550897730277714e-05, "output_power": 4.169109667051372e-05, "reference_active": true, "delta_db": -0.08865407925540282}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.293923839625808e-07, "output_power": 7.531532303366119e-07, "reference_active": true, "delta_db": -0.9131576611079584}], "active_band_count": 3, "active_band_mae_db": 0.3718235261399552}}]}, {"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": 0.0001225394829970324, "log_rms_mae_db": 1.1223015885580876, "rms_envelope_nrmse": 0.06630481325437254, "envelope_correlation": 0.9969117681551721, "rms_gain_error_db": -0.06520070683368417, "reference_mean_power": 0.0009458112547504992, "output_mean_power": 0.000931717830893223}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 7.572635748614322e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021454762051170177, "output_power": 0.000201246016721848, "reference_active": true, "delta_db": -0.27796409155140234}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.152647446601543e-05, "output_power": 4.992905804981952e-05, "reference_active": true, "delta_db": -0.9070865742215017}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.926247906815996e-06, "output_power": 4.325249963473752e-06, "reference_active": true, "delta_db": -2.044868207846507}], "active_band_count": 3, "active_band_mae_db": 1.0766396245398038}}, {"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": 0.00011593520090475494, "log_rms_mae_db": 0.7791573626681991, "rms_envelope_nrmse": 0.03666776686006897, "envelope_correlation": 0.9990603633996447, "rms_gain_error_db": -0.06567015327883496, "reference_mean_power": 0.0009490323754435319, "output_mean_power": 0.0009347899033629005}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 7.167599035150244e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00018822421406971727, "output_power": 0.00017743451062545917, "reference_active": true, "delta_db": -0.25637399378533093}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6896254802287652e-05, "output_power": 2.248881685340147e-05, "reference_active": true, "delta_db": -0.7772520280171479}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.519942395248385e-07, "output_power": 4.847592309545343e-07, "reference_active": true, "delta_db": -1.9068842597691358}], "active_band_count": 3, "active_band_mae_db": 0.9801700938572049}}]}, {"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": 1.2777110452589409, "rms_envelope_nrmse": 0.09982430566281507, "envelope_correlation": 0.9936332075163384, "rms_gain_error_db": -0.29877089718101874, "reference_mean_power": 0.00014098678071692043, "output_mean_power": 0.00013161376238215124}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.160899550412932e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.7499181258859675e-05, "output_power": 3.443613663213341e-05, "reference_active": true, "delta_db": -0.37007363332757093}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.267009960974534e-06, "output_power": 7.318101167856832e-06, "reference_active": true, "delta_db": -0.5295005188936213}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.898653312592319e-07, "output_power": 7.421109615506456e-07, "reference_active": true, "delta_db": -0.2708420570585508}], "active_band_count": 3, "active_band_mae_db": 0.390138736426581}}, {"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": 0.8505344410223883, "rms_envelope_nrmse": 0.06503961854776755, "envelope_correlation": 0.9976671456038424, "rms_gain_error_db": -0.29876089198868283, "reference_mean_power": 0.00014167955800585476, "output_mean_power": 0.00013226078746937265}, "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": 3.3910555465812715e-05, "output_power": 3.1196442688567604e-05, "reference_active": true, "delta_db": -0.3622982921429186}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.965549503856846e-06, "output_power": 3.5618234591360157e-06, "reference_active": true, "delta_db": -0.4663098578754482}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.243578010746913e-08, "output_power": 4.599285313903749e-08, "reference_active": true, "delta_db": -1.3274319079770447}], "active_band_count": 3, "active_band_mae_db": 0.7186800193318038}}]}, {"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": 4.041281383552759e-05, "log_rms_mae_db": 1.2352021138324725, "rms_envelope_nrmse": 0.12241198927194766, "envelope_correlation": 0.9897616712636855, "rms_gain_error_db": -0.16374308710654784, "reference_mean_power": 5.063950126149288e-05, "output_mean_power": 4.8765772810022354e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.808534933602363e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3975319757086051e-05, "output_power": 1.3643743117114875e-05, "reference_active": true, "delta_db": -0.10428219420985996}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.037166885946861e-06, "output_power": 3.7247581364798603e-06, "reference_active": true, "delta_db": -0.34978624869082}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.222770754615436e-07, "output_power": 7.822263303367103e-07, "reference_active": true, "delta_db": -0.21685752039705303}], "active_band_count": 3, "active_band_mae_db": 0.22364198776591096}}, {"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": 3.6032760748614396e-05, "log_rms_mae_db": 0.8341980204049442, "rms_envelope_nrmse": 0.06421454839140847, "envelope_correlation": 0.997242147338838, "rms_gain_error_db": -0.16090021477768035, "reference_mean_power": 5.078542798446868e-05, "output_mean_power": 4.893832437791244e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.512050765202737e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2965326164159417e-05, "output_power": 1.2735461531222273e-05, "reference_active": true, "delta_db": -0.07768758284702823}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.904625885804089e-06, "output_power": 1.7483255327386103e-06, "reference_active": true, "delta_db": -0.3718738243817835}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.69464596815875e-08, "output_power": 4.763982807822827e-08, "reference_active": true, "delta_db": -0.7749654395495025}], "active_band_count": 3, "active_band_mae_db": 0.4081756155927714}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9924974101369625, "standard_deviation": 0.0009562586099108667, "minimum": 0.9909887368909178, "maximum": 0.9936332075163384, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.2767640040914596, "standard_deviation": 0.023051988307144496, "minimum": 1.2531500026090472, "maximum": 1.3232622562339844, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4403714161168557, "standard_deviation": 0.19253810991724063, "minimum": 0.15001948279713667, "maximum": 0.6911171233102786, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10532300163288262, "standard_deviation": 0.005951297610450367, "minimum": 0.09869708246959817, "maximum": 0.11384121860173273, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9975729053440181, "standard_deviation": 0.00038310943142548883, "minimum": 0.9968140394953133, "maximum": 0.9981488254561951, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8354834337211613, "standard_deviation": 0.020831076099567185, "minimum": 0.8046485490271789, "maximum": 0.8655255521470778, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.47670605070454586, "standard_deviation": 0.23176373402871853, "minimum": 0.18960309753603324, "maximum": 0.7965982293171797, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06201014769266026, "standard_deviation": 0.003734240966480524, "minimum": 0.05660311134845108, "maximum": 0.06717892101348981, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9895080285209117, "standard_deviation": 0.0012547353498972536, "minimum": 0.9874751393613, "maximum": 0.9909225020959024, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.245758051490498, "standard_deviation": 0.020831715930366305, "minimum": 1.2132536418470312, "maximum": 1.2676577064934418, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5257473078034567, "standard_deviation": 0.1711960496538296, "minimum": 0.22364198776591096, "maximum": 0.7266831784394574, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1258883433156202, "standard_deviation": 0.007996415943428363, "minimum": 0.11566255596743671, "maximum": 0.1402177892882291, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.996687851345749, "standard_deviation": 0.0005054545110638677, "minimum": 0.9957026256268106, "maximum": 0.997252645698538, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8486805798794995, "standard_deviation": 0.02315171596913395, "minimum": 0.8088312012834253, "maximum": 0.8758819629389087, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.5931955590738083, "standard_deviation": 0.2330042850690638, "minimum": 0.2641834034476016, "maximum": 0.8867673732838056, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07457204152545541, "standard_deviation": 0.006760221437413685, "minimum": 0.06421454839140847, "maximum": 0.08313098558151168, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9972103287370333, "standard_deviation": 0.0003538812563265049, "minimum": 0.996628012769861, "maximum": 0.9977536914051, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.1371224879913493, "standard_deviation": 0.02886273961908941, "minimum": 1.1019722616271301, "maximum": 1.171988702034532, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.8101435559754473, "standard_deviation": 0.3095191671398242, "minimum": 0.2213728403421047, "maximum": 1.288558041079119, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06290139989206395, "standard_deviation": 0.0037983202786148872, "minimum": 0.05667609355748784, "maximum": 0.0686078837144048, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9990891426861195, "standard_deviation": 0.00018256763932275233, "minimum": 0.9987381423017664, "maximum": 0.999363991663004, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7833018781047789, "standard_deviation": 0.0279848775360645, "minimum": 0.7473278055589977, "maximum": 0.826880803739617, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7531920453790866, "standard_deviation": 0.2970814203178648, "minimum": 0.2666021554279366, "maximum": 1.2544476848239727, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.035725616243810106, "standard_deviation": 0.00302359239781901, "minimum": 0.030135946445043478, "maximum": 0.04106710257723557, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.14518081057918386, "standard_deviation": 0.041870255047850476, "minimum": 0.076966871671067, "maximum": 0.19519429177119388, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.097289209556329, "standard_deviation": 0.006050282723577494, "minimum": 5.0888092832280485, "maximum": 5.106115564422344, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3155183125013169, "standard_deviation": 0.010709506259823354, "minimum": 0.30117074091398427, "maximum": 0.3361929615352868, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07800159383875681, "standard_deviation": 0.018967526162376857, "minimum": -0.09996433116726672, "maximum": -0.040720882885044864, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9976550122199974, "standard_deviation": 0.0002137821316687138, "minimum": 0.9973684800555944, "maximum": 0.9979443101055043, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.9184949635953592, "standard_deviation": 0.024026224041321834, "minimum": 0.8784191853403587, "maximum": 0.9499192042594169, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4651255130960714, "standard_deviation": 0.1855026867049599, "minimum": 0.2800328978830039, "maximum": 0.7253593473537702, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05103366971802302, "standard_deviation": 0.0021049682391939624, "minimum": 0.04810531423778764, "maximum": 0.05370320986436941, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9993300843274359, "standard_deviation": 0.0001207695319354454, "minimum": 0.9991625581077827, "maximum": 0.9995128558275873, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.5337186452460205, "standard_deviation": 0.019599650707731692, "minimum": 0.5087738561504862, "maximum": 0.5645988316936609, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4176225982802264, "standard_deviation": 0.21720586697188776, "minimum": 0.07210196592078773, "maximum": 0.7116258802737492, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.027574897325236252, "standard_deviation": 0.001818588989635375, "minimum": 0.025132955909861053, "maximum": 0.030524157006221027, "valid_count": 8, "planned_count": 8}}, "seconds": 7.097684388005291, "rtf_including_measurement": 1.1829473980008818}, {"case": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "normal", "speaker": "jvs_jvs018", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.2190749645233154, "predicted_mos": 2.2190749645233154, "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": 5.799760021000111}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8054006941291437, "全帯域_10ms_rms_envelope_nrmse": 0.050079613898469405, "全帯域_10ms_envelope_correlation": 0.9977966536590509, "全帯域_10ms_modulation_mae_db": 0.2382658355087047, "全帯域_40ms_log_rms_mae_db": 0.49572942676650317, "全帯域_40ms_rms_envelope_nrmse": 0.025534620545626774, "全帯域_40ms_envelope_correlation": 0.9995036219833192, "全帯域_40ms_modulation_mae_db": 0.2902244852851626, "300–1000 Hz_10ms_log_rms_mae_db": 1.0714909391756526, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06460877814060423, "300–1000 Hz_10ms_envelope_correlation": 0.9970623847670621, "300–1000 Hz_10ms_modulation_mae_db": 1.0408652940853627, "300–1000 Hz_40ms_log_rms_mae_db": 0.7259206821132828, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03580876154828011, "300–1000 Hz_40ms_envelope_correlation": 0.999102008428226, "300–1000 Hz_40ms_modulation_mae_db": 0.9510099086607186, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2010882444539313, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10074382388840461, "1000–3000 Hz_10ms_envelope_correlation": 0.9934701641017061, "1000–3000 Hz_10ms_modulation_mae_db": 0.5022613784290338, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8248372754968422, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06644680202182118, "1000–3000 Hz_40ms_envelope_correlation": 0.9974929353211758, "1000–3000 Hz_40ms_modulation_mae_db": 0.8094665772555275, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1155237142757544, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1198564434384114, "3000–6000 Hz_10ms_envelope_correlation": 0.99019328491992, "3000–6000 Hz_10ms_modulation_mae_db": 0.1825679426804621, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7463025905206048, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06295863554603899, "3000–6000 Hz_40ms_envelope_correlation": 0.9973632253286389, "3000–6000 Hz_40ms_modulation_mae_db": 0.3491205906334171, "mr_stft_db": 5.064201768301377, "band_mae_db": 0.16131237765097742, "rms_gain_error_db": -0.10184515498814611, "output_peak": 0.33627799876877545}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7943167855795308, "全帯域_10ms_rms_envelope_nrmse": 0.050055842068324856, "全帯域_10ms_envelope_correlation": 0.9977669694538995, "全帯域_10ms_modulation_mae_db": 0.2575049540389149, "全帯域_40ms_log_rms_mae_db": 0.4552699456998581, "全帯域_40ms_rms_envelope_nrmse": 0.0271214212640677, "全帯域_40ms_envelope_correlation": 0.9993761846842025, "全帯域_40ms_modulation_mae_db": 0.3598514781664181, "300–1000 Hz_10ms_log_rms_mae_db": 1.0174683534915614, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05971705217379404, "300–1000 Hz_10ms_envelope_correlation": 0.9974664895296799, "300–1000 Hz_10ms_modulation_mae_db": 0.8178383048043193, "300–1000 Hz_40ms_log_rms_mae_db": 0.7009089735950675, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03545230147756176, "300–1000 Hz_40ms_envelope_correlation": 0.9990744321590709, "300–1000 Hz_40ms_modulation_mae_db": 0.709496371768714, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1453879173756067, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09860079010571415, "1000–3000 Hz_10ms_envelope_correlation": 0.9935498853319813, "1000–3000 Hz_10ms_modulation_mae_db": 0.6924926748644603, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7428102205713547, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0540690309117867, "1000–3000 Hz_40ms_envelope_correlation": 0.9983438925692206, "1000–3000 Hz_40ms_modulation_mae_db": 0.5889692863643027, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1231010334760987, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11971388164360115, "3000–6000 Hz_10ms_envelope_correlation": 0.9906685423712605, "3000–6000 Hz_10ms_modulation_mae_db": 0.4484537990719691, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8036038606377747, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07574034487810895, "3000–6000 Hz_40ms_envelope_correlation": 0.9966537717571515, "3000–6000 Hz_40ms_modulation_mae_db": 0.5462955983204908, "mr_stft_db": 5.060666031214149, "band_mae_db": 0.1527092723325838, "rms_gain_error_db": -0.09264401728815577, "output_peak": 0.3137143532524691}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7963341727253602, "全帯域_10ms_rms_envelope_nrmse": 0.05082776679238323, "全帯域_10ms_envelope_correlation": 0.9976757635400623, "全帯域_10ms_modulation_mae_db": 0.584144059467199, "全帯域_40ms_log_rms_mae_db": 0.47515968715502593, "全帯域_40ms_rms_envelope_nrmse": 0.029449453554351794, "全帯域_40ms_envelope_correlation": 0.9992197181510706, "全帯域_40ms_modulation_mae_db": 0.6086687142011314, "300–1000 Hz_10ms_log_rms_mae_db": 1.1039307448604347, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06048457036861605, "300–1000 Hz_10ms_envelope_correlation": 0.9974404501889127, "300–1000 Hz_10ms_modulation_mae_db": 0.7994283261570322, "300–1000 Hz_40ms_log_rms_mae_db": 0.7597803180443239, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03459709115082876, "300–1000 Hz_40ms_envelope_correlation": 0.999158274016801, "300–1000 Hz_40ms_modulation_mae_db": 0.8646214071120198, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2103487202538439, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11187643489683426, "1000–3000 Hz_10ms_envelope_correlation": 0.991466600410337, "1000–3000 Hz_10ms_modulation_mae_db": 0.7042120468958443, "1000–3000 Hz_40ms_log_rms_mae_db": 0.795197808618398, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06391758211344117, "1000–3000 Hz_40ms_envelope_correlation": 0.9973746127409001, "1000–3000 Hz_40ms_modulation_mae_db": 0.2709087289196013, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1571802806691542, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13715160788341804, "3000–6000 Hz_10ms_envelope_correlation": 0.9878530819216844, "3000–6000 Hz_10ms_modulation_mae_db": 0.6143269392978712, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8021910856894621, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07670634785209432, "3000–6000 Hz_40ms_envelope_correlation": 0.9970368492564912, "3000–6000 Hz_40ms_modulation_mae_db": 0.47216902044219117, "mr_stft_db": 5.062966491908099, "band_mae_db": 0.15266899576614507, "rms_gain_error_db": -0.08134726815964645, "output_peak": 0.31469479559009667}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7748821251031404, "全帯域_10ms_rms_envelope_nrmse": 0.04765430774892811, "全帯域_10ms_envelope_correlation": 0.9979716666601903, "全帯域_10ms_modulation_mae_db": 0.39664051516466303, "全帯域_40ms_log_rms_mae_db": 0.46807594986770623, "全帯域_40ms_rms_envelope_nrmse": 0.02590821427137571, "全帯域_40ms_envelope_correlation": 0.9994260951643359, "全帯域_40ms_modulation_mae_db": 0.3334907098081208, "300–1000 Hz_10ms_log_rms_mae_db": 1.0674780592408775, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06094297483741437, "300–1000 Hz_10ms_envelope_correlation": 0.9974659895695418, "300–1000 Hz_10ms_modulation_mae_db": 1.2048864328495885, "300–1000 Hz_40ms_log_rms_mae_db": 0.7130593092427354, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03402877299916801, "300–1000 Hz_40ms_envelope_correlation": 0.9992719877994203, "300–1000 Hz_40ms_modulation_mae_db": 1.1518033770751812, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1570483681012809, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11218655853214977, "1000–3000 Hz_10ms_envelope_correlation": 0.9912467098057474, "1000–3000 Hz_10ms_modulation_mae_db": 0.1719362287026683, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7856177766863718, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06560819350237014, "1000–3000 Hz_40ms_envelope_correlation": 0.9969610889692176, "1000–3000 Hz_40ms_modulation_mae_db": 0.2122938378646386, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1536854593683694, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11715775493531418, "3000–6000 Hz_10ms_envelope_correlation": 0.9907501919536026, "3000–6000 Hz_10ms_modulation_mae_db": 0.46814686867193706, "3000–6000 Hz_40ms_log_rms_mae_db": 0.794475912547895, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06780603926625117, "3000–6000 Hz_40ms_envelope_correlation": 0.9970646846193765, "3000–6000 Hz_40ms_modulation_mae_db": 0.57933304133626, "mr_stft_db": 5.054149328293198, "band_mae_db": 0.09285792987809065, "rms_gain_error_db": -0.08044470192226914, "output_peak": 0.30351948135654105}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8032621533724257, "全帯域_10ms_rms_envelope_nrmse": 0.0471299101706417, "全帯域_10ms_envelope_correlation": 0.9980208051626133, "全帯域_10ms_modulation_mae_db": 0.5550707309000826, "全帯域_40ms_log_rms_mae_db": 0.48754620244226493, "全帯域_40ms_rms_envelope_nrmse": 0.025901893415360176, "全帯域_40ms_envelope_correlation": 0.999427415611601, "全帯域_40ms_modulation_mae_db": 0.2582002542876867, "300–1000 Hz_10ms_log_rms_mae_db": 1.0430842332832615, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05561785571453657, "300–1000 Hz_10ms_envelope_correlation": 0.9978285521117964, "300–1000 Hz_10ms_modulation_mae_db": 0.6202416320254188, "300–1000 Hz_40ms_log_rms_mae_db": 0.7295188141335849, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.02972813105925289, "300–1000 Hz_40ms_envelope_correlation": 0.99937451180654, "300–1000 Hz_40ms_modulation_mae_db": 0.6334914779417731, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1905477939562812, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10684582628100822, "1000–3000 Hz_10ms_envelope_correlation": 0.9924649483798866, "1000–3000 Hz_10ms_modulation_mae_db": 0.35765520542310875, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7861385819857805, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06308553737447713, "1000–3000 Hz_40ms_envelope_correlation": 0.9977119765525566, "1000–3000 Hz_40ms_modulation_mae_db": 0.27152390843323276, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1616197544880773, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13050904136239833, "3000–6000 Hz_10ms_envelope_correlation": 0.9882834072861884, "3000–6000 Hz_10ms_modulation_mae_db": 0.23929446207413965, "3000–6000 Hz_40ms_log_rms_mae_db": 0.80122204526875, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07746097602432181, "3000–6000 Hz_40ms_envelope_correlation": 0.9957844332837643, "3000–6000 Hz_40ms_modulation_mae_db": 0.22872045059016746, "mr_stft_db": 5.053422073955791, "band_mae_db": 0.19079089304467511, "rms_gain_error_db": -0.08403167792769742, "output_peak": 0.3030136071340809}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8121409975944787, "全帯域_10ms_rms_envelope_nrmse": 0.051000101829806396, "全帯域_10ms_envelope_correlation": 0.9976478084023318, "全帯域_10ms_modulation_mae_db": 0.3549410088400549, "全帯域_40ms_log_rms_mae_db": 0.4839785141885801, "全帯域_40ms_rms_envelope_nrmse": 0.029139988977402127, "全帯域_40ms_envelope_correlation": 0.9992345508815912, "全帯域_40ms_modulation_mae_db": 0.2819747275548714, "300–1000 Hz_10ms_log_rms_mae_db": 1.046394985074936, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06060437803482626, "300–1000 Hz_10ms_envelope_correlation": 0.9973948064844252, "300–1000 Hz_10ms_modulation_mae_db": 0.23399553001386, "300–1000 Hz_40ms_log_rms_mae_db": 0.6963128471346439, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.035538750281556244, "300–1000 Hz_40ms_envelope_correlation": 0.9990774737951524, "300–1000 Hz_40ms_modulation_mae_db": 0.22387093488490425, "1000–3000 Hz_10ms_log_rms_mae_db": 1.178698372311241, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10357361508579846, "1000–3000 Hz_10ms_envelope_correlation": 0.992940270209339, "1000–3000 Hz_10ms_modulation_mae_db": 0.5618827066029483, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7767597902953248, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06142461791387585, "1000–3000 Hz_40ms_envelope_correlation": 0.9978393170079204, "1000–3000 Hz_40ms_modulation_mae_db": 0.6419357919338582, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1368531892854812, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13143074171756017, "3000–6000 Hz_10ms_envelope_correlation": 0.9885889037122585, "3000–6000 Hz_10ms_modulation_mae_db": 0.47511456917036504, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7763119610764904, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07695741111924505, "3000–6000 Hz_40ms_envelope_correlation": 0.9965498128443253, "3000–6000 Hz_40ms_modulation_mae_db": 0.33879800693678663, "mr_stft_db": 5.053509560390146, "band_mae_db": 0.13384349141332835, "rms_gain_error_db": -0.07102099642938096, "output_peak": 0.31518044488678637}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8284165722766251, "全帯域_10ms_rms_envelope_nrmse": 0.05197455813011981, "全帯域_10ms_envelope_correlation": 0.9975367215660634, "全帯域_10ms_modulation_mae_db": 0.29152629521974466, "全帯域_40ms_log_rms_mae_db": 0.4820051836069116, "全帯域_40ms_rms_envelope_nrmse": 0.027101584717179928, "全帯域_40ms_envelope_correlation": 0.9993218401373678, "全帯域_40ms_modulation_mae_db": 0.10872710450245589, "300–1000 Hz_10ms_log_rms_mae_db": 1.1128194968010015, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06504708282340076, "300–1000 Hz_10ms_envelope_correlation": 0.9970197488190525, "300–1000 Hz_10ms_modulation_mae_db": 0.6687072167054234, "300–1000 Hz_40ms_log_rms_mae_db": 0.7768137228515916, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03714849824755732, "300–1000 Hz_40ms_envelope_correlation": 0.9990068087632101, "300–1000 Hz_40ms_modulation_mae_db": 0.5601271342521948, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1440299600777417, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0987366130100674, "1000–3000 Hz_10ms_envelope_correlation": 0.9932362145085831, "1000–3000 Hz_10ms_modulation_mae_db": 0.22200249438958097, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7748234984502915, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05617615772967214, "1000–3000 Hz_40ms_envelope_correlation": 0.9977842988898822, "1000–3000 Hz_40ms_modulation_mae_db": 0.46389102686724776, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1003489631565784, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1188419382283815, "3000–6000 Hz_10ms_envelope_correlation": 0.9906713128411375, "3000–6000 Hz_10ms_modulation_mae_db": 0.5416043979826318, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7497633872687502, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07393124318394605, "3000–6000 Hz_40ms_envelope_correlation": 0.9966836775505792, "3000–6000 Hz_40ms_modulation_mae_db": 0.6792981146493097, "mr_stft_db": 5.059744503856016, "band_mae_db": 0.17292964259555246, "rms_gain_error_db": -0.06152759467313456, "output_peak": 0.31054619352095}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7740060811404208, "全帯域_10ms_rms_envelope_nrmse": 0.04990864460847159, "全帯域_10ms_envelope_correlation": 0.9977150815997889, "全帯域_10ms_modulation_mae_db": 0.6792090300671453, "全帯域_40ms_log_rms_mae_db": 0.4579023890727187, "全帯域_40ms_rms_envelope_nrmse": 0.02768886354102735, "全帯域_40ms_envelope_correlation": 0.9992768255364484, "全帯域_40ms_modulation_mae_db": 0.6614035551958816, "300–1000 Hz_10ms_log_rms_mae_db": 1.1103538278043572, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06679826053320488, "300–1000 Hz_10ms_envelope_correlation": 0.9967978634973376, "300–1000 Hz_10ms_modulation_mae_db": 0.7111148912988252, "300–1000 Hz_40ms_log_rms_mae_db": 0.7891679515493553, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04005250641939942, "300–1000 Hz_40ms_envelope_correlation": 0.9987969312217637, "300–1000 Hz_40ms_modulation_mae_db": 0.6477560376202559, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1513778431982147, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10004878977640604, "1000–3000 Hz_10ms_envelope_correlation": 0.9930231172162187, "1000–3000 Hz_10ms_modulation_mae_db": 0.47854902837693175, "1000–3000 Hz_40ms_log_rms_mae_db": 0.778035821440629, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0594338460851991, "1000–3000 Hz_40ms_envelope_correlation": 0.9974826573364278, "1000–3000 Hz_40ms_modulation_mae_db": 0.8103660554231817, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1127221345359077, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11267201393048425, "3000–6000 Hz_10ms_envelope_correlation": 0.9913618067771117, "3000–6000 Hz_10ms_modulation_mae_db": 0.6437905340400834, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7458886524598267, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06663035217571806, "3000–6000 Hz_40ms_envelope_correlation": 0.9970256646130056, "3000–6000 Hz_40ms_modulation_mae_db": 0.6420948970463747, "mr_stft_db": 5.050578077398522, "band_mae_db": 0.08362379809425283, "rms_gain_error_db": -0.04369199175174741, "output_peak": 0.3238341286628957}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 0.192696148457932, "spectral_convergence_status": "ok", "amplitude_floor": 8.606911899432486e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.034811284077626, "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": 4.612015597387077, "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": 0.0008505088259725378, "delta_db": -0.10472753156809878, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00010621716934048885, "output_power": 0.00010172574351048508, "delta_db": -0.1876385062149559, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.322826988453831e-05, "output_power": 4.78449847095818e-05, "delta_db": -0.46305930101467463, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 7.685697629736477e-05, "output_power": 7.296701533807863e-05, "delta_db": -0.22556712355833408, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.3518932532436965e-05, "output_power": 3.374884311009262e-05, "delta_db": 0.029687107401901863, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.16131237765097742, "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": 5.064201768301377}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.9404104532266406, "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"}}, "level": {"reference": {"rms": 0.04710475034036298, "rms_dbfs": -26.53870587331253, "peak": 0.300323486328125, "peak_dbfs": -10.448214063056167, "crest_factor_db": 16.09049181025636, "mean": -1.2700610690646702e-05, "zero_energy": false}, "output": {"rms": 0.0465556557921304, "rms_dbfs": -26.640551028300674, "peak": 0.33627799876877545, "peak_dbfs": -9.466030915728158, "crest_factor_db": 17.174520112572516, "mean": 8.097685537339237e-06, "zero_energy": false}, "rms_difference_db": -0.10184515498814406}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.984813836558412e-06, "threshold_dbfs": -57.022802211663084, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 222, "quiet_samples": 53280, "reference_mean_power": 8.965192877270795e-08, "output_mean_power": 5.843514261039347e-07, "output_rms_dbfs": -62.33325891731191, "output_zero_energy": false, "output_peak": 0.016371430625663, "output_energy_fraction": 9.975414145336482e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 312, "output_estimated_voiced_frames": 295, "both_estimated_voiced_frames": 293, "reference_voiced_output_unvoiced_frames": 19, "reference_unvoiced_output_voiced_frames": 2, "paired_voiced_fraction": 0.9391025641025641, "absolute_difference_cents_median": 1.866136541467764, "absolute_difference_cents_p95": 12.28537200444775, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.8054006941291437, "rms_envelope_nrmse": 0.050079613898469405, "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": 7.987261035805468e-05, "reference_active": true, "delta_db": -0.23062220917723247}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2432690798089742e-05, "output_power": 1.136599851000058e-05, "reference_active": true, "delta_db": -0.3895753807281938}], "active_band_count": 3, "active_band_mae_db": 0.2382658355087047}}, {"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": 0.49572942676650317, "rms_envelope_nrmse": 0.025534620545626774, "envelope_correlation": 0.9995036219833192, "rms_gain_error_db": -0.10515698647239743, "reference_mean_power": 0.002205255256660357, "output_mean_power": 0.0021525000357084417}, "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": 0.00029633227983582444, "output_power": 0.00029075238200612066, "reference_active": true, "delta_db": -0.08255680884938332}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2550897730277714e-05, "output_power": 4.1812170263650644e-05, "reference_active": true, "delta_db": -0.07606016953633515}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.293923839625808e-07, "output_power": 7.88848241103349e-07, "reference_active": true, "delta_db": -0.7120564774697693}], "active_band_count": 3, "active_band_mae_db": 0.2902244852851626}}]}, {"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": 0.0001225394829970324, "log_rms_mae_db": 1.0714909391756526, "rms_envelope_nrmse": 0.06460877814060423, "envelope_correlation": 0.9970623847670621, "rms_gain_error_db": -0.06747448509213802, "reference_mean_power": 0.0009458112547504992, "output_mean_power": 0.0009312301513694842}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 7.572635748614322e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021454762051170177, "output_power": 0.00020199830246256647, "reference_active": true, "delta_db": -0.2617598248328345}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.152647446601543e-05, "output_power": 5.0099117332311296e-05, "reference_active": true, "delta_db": -0.8923195590564502}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.926247906815996e-06, "output_power": 4.4019629416530875e-06, "reference_active": true, "delta_db": -1.9685164983668038}], "active_band_count": 3, "active_band_mae_db": 1.0408652940853627}}, {"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": 0.00011593520090475494, "log_rms_mae_db": 0.7259206821132828, "rms_envelope_nrmse": 0.03580876154828011, "envelope_correlation": 0.999102008428226, "rms_gain_error_db": -0.06806139853981848, "reference_mean_power": 0.0009490323754435319, "output_mean_power": 0.0009342753454428718}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 7.167599035150244e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00018822421406971727, "output_power": 0.00017814588783910196, "reference_active": true, "delta_db": -0.23899690483711056}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6896254802287652e-05, "output_power": 2.26522373544366e-05, "reference_active": true, "delta_db": -0.7458070681540176}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.519942395248385e-07, "output_power": 4.890935533378495e-07, "reference_active": true, "delta_db": -1.8682257529910276}], "active_band_count": 3, "active_band_mae_db": 0.9510099086607186}}]}, {"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": 1.2010882444539313, "rms_envelope_nrmse": 0.10074382388840461, "envelope_correlation": 0.9934701641017061, "rms_gain_error_db": -0.2923565348136402, "reference_mean_power": 0.00014098678071692043, "output_mean_power": 0.00013180829446711212}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.160899550412932e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.7499181258859675e-05, "output_power": 3.4362024811803566e-05, "reference_active": true, "delta_db": -0.379430385423153}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.267009960974534e-06, "output_power": 7.228076520401931e-06, "reference_active": true, "delta_db": -0.5832571931837117}, {"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": 0.5022613784290338}}, {"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": 0.8248372754968422, "rms_envelope_nrmse": 0.06644680202182118, "envelope_correlation": 0.9974929353211758, "rms_gain_error_db": -0.2923746300355439, "reference_mean_power": 0.00014167955800585476, "output_mean_power": 0.00013245541885460103}, "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": 3.3910555465812715e-05, "output_power": 3.1105835802767675e-05, "reference_active": true, "delta_db": -0.37493028545690976}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.965549503856846e-06, "output_power": 3.4974304008640756e-06, "reference_active": true, "delta_db": -0.5455429499785167}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.243578010746913e-08, "output_power": 4.412054747257015e-08, "reference_active": true, "delta_db": -1.507926496331156}], "active_band_count": 3, "active_band_mae_db": 0.8094665772555275}}]}, {"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": 4.041281383552759e-05, "log_rms_mae_db": 1.1155237142757544, "rms_envelope_nrmse": 0.1198564434384114, "envelope_correlation": 0.99019328491992, "rms_gain_error_db": -0.16560587210316136, "reference_mean_power": 5.063950126149288e-05, "output_mean_power": 4.874486057769279e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.808534933602363e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3975319757086051e-05, "output_power": 1.3538644554064454e-05, "reference_active": true, "delta_db": -0.13786567038486378}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.037166885946861e-06, "output_power": 3.732599343398189e-06, "reference_active": true, "delta_db": -0.3406532705272392}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.222770754615436e-07, "output_power": 8.092816513957444e-07, "reference_active": true, "delta_db": -0.06918488712928325}], "active_band_count": 3, "active_band_mae_db": 0.1825679426804621}}, {"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": 3.6032760748614396e-05, "log_rms_mae_db": 0.7463025905206048, "rms_envelope_nrmse": 0.06295863554603899, "envelope_correlation": 0.9973632253286389, "rms_gain_error_db": -0.1645434399094052, "reference_mean_power": 5.078542798446868e-05, "output_mean_power": 4.889728803553739e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.512050765202737e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2965326164159417e-05, "output_power": 1.2616852126945849e-05, "reference_active": true, "delta_db": -0.11832433600746184}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.904625885804089e-06, "output_power": 1.7568874678754194e-06, "reference_active": true, "delta_db": -0.35065737574424494}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.69464596815875e-08, "output_power": 4.9845817546823937e-08, "reference_active": true, "delta_db": -0.5783800601485445}], "active_band_count": 3, "active_band_mae_db": 0.3491205906334171}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9926747387454748, "standard_deviation": 0.0008822527562981459, "minimum": 0.9912467098057474, "maximum": 0.9935498853319813, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1723159024660177, "standard_deviation": 0.026306412934307435, "minimum": 1.1440299600777417, "maximum": 1.2103487202538439, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.46137397046057205, "standard_deviation": 0.19866894494865395, "minimum": 0.1719362287026683, "maximum": 0.7042120468958443, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10407655644704786, "standard_deviation": 0.005610717635199179, "minimum": 0.09860079010571415, "maximum": 0.11218655853214977, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9976238474234127, "standard_deviation": 0.0004029964347758639, "minimum": 0.9969610889692176, "maximum": 0.9983438925692206, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.783027596693124, "standard_deviation": 0.02287074971965697, "minimum": 0.7428102205713547, "maximum": 0.8248372754968422, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5086694016326988, "standard_deviation": 0.24151885880879795, "minimum": 0.2122938378646386, "maximum": 0.8103660554231817, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06127022095658042, "standard_deviation": 0.004425923978344816, "minimum": 0.0540690309117867, "maximum": 0.06644680202182118, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9897963164728953, "standard_deviation": 0.0013399104041598117, "minimum": 0.9878530819216844, "maximum": 0.9913618067771117, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.1326293161569276, "standard_deviation": 0.023071641531610922, "minimum": 1.1003489631565784, "maximum": 1.1616197544880773, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.45166243912368237, "standard_deviation": 0.16466699743980878, "minimum": 0.1825679426804621, "maximum": 0.6437905340400834, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12341667789244612, "standard_deviation": 0.008494630851314527, "minimum": 0.11267201393048425, "maximum": 0.13715160788341804, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9967702649066665, "standard_deviation": 0.0004804926607808656, "minimum": 0.9957844332837643, "maximum": 0.9973632253286389, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7774699369336943, "standard_deviation": 0.026417683024825986, "minimum": 0.7458886524598267, "maximum": 0.8036038606377747, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.47947871499437467, "standard_deviation": 0.16059026769042792, "minimum": 0.22872045059016746, "maximum": 0.6792981146493097, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07227391875571555, "standard_deviation": 0.005629466074601306, "minimum": 0.06295863554603899, "maximum": 0.07746097602432181, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.997309535620976, "standard_deviation": 0.0003272763198500864, "minimum": 0.9967978634973376, "maximum": 0.9978285521117964, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0716275799665103, "standard_deviation": 0.03513617638443618, "minimum": 1.0174683534915614, "maximum": 1.1128194968010015, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7621347034924788, "standard_deviation": 0.28997780414768193, "minimum": 0.23399553001386, "maximum": 1.2048864328495885, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06172761907829964, "standard_deviation": 0.003582206355652944, "minimum": 0.05561785571453657, "maximum": 0.06679826053320488, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.999107803498773, "standard_deviation": 0.00017301763267004296, "minimum": 0.9987969312217637, "maximum": 0.99937451180654, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7364353273330732, "standard_deviation": 0.03491398090937562, "minimum": 0.6963128471346439, "maximum": 0.7891679515493553, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7177720811644702, "standard_deviation": 0.2790831929010119, "minimum": 0.22387093488490425, "maximum": 1.1518033770751812, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03529435164795056, "standard_deviation": 0.0029154236640759213, "minimum": 0.02972813105925289, "maximum": 0.04005250641939942, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1425920500969507, "standard_deviation": 0.03746450968366928, "minimum": 0.08362379809425283, "maximum": 0.19079089304467511, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.057404729414662, "standard_deviation": 0.005091705776055153, "minimum": 5.050578077398522, "maximum": 5.064201768301377, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.3150976253965744, "standard_deviation": 0.010874673900873509, "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": 0.00016276042153226804, "minimum": 0.9975367215660634, "maximum": 0.9980208051626133, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7985949477401407, "standard_deviation": 0.018249265512379657, "minimum": 0.7740060811404208, "maximum": 0.8284165722766251, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.41966280365081365, "standard_deviation": 0.16608584847658567, "minimum": 0.2382658355087047, "maximum": 0.6792090300671453, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.049828843155893136, "standard_deviation": 0.0016521593792804305, "minimum": 0.0471299101706417, "maximum": 0.05197455813011981, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.999348281518742, "standard_deviation": 0.00010176634025289621, "minimum": 0.9992197181510706, "maximum": 0.9995036219833192, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4757084123499461, "standard_deviation": 0.014354487461915248, "minimum": 0.4552699456998581, "maximum": 0.49572942676650317, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.36281762862521605, "standard_deviation": 0.18430460292542283, "minimum": 0.10872710450245589, "maximum": 0.6614035551958816, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.027230755035798946, "standard_deviation": 0.0014734875585301458, "minimum": 0.025534620545626774, "maximum": 0.029449453554351794, "valid_count": 8, "planned_count": 8}}, "seconds": 7.905928197003959, "rtf_including_measurement": 1.31765469950066}, {"case": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "normal", "speaker": "jvs_jvs018", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.800823926925659, "predicted_mos": 2.800823926925659, "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": "67db5e36eb6b0857a0b2de5c0ff2e6a7f607bd811ab48888041ef5b45d76cbc7", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 6.035442198997771}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3263702721006023, "全帯域_10ms_rms_envelope_nrmse": 0.18310928003549862, "全帯域_10ms_envelope_correlation": 0.9904721212918542, "全帯域_10ms_modulation_mae_db": 0.9066320869707307, "全帯域_40ms_log_rms_mae_db": 1.020260443221776, "全帯域_40ms_rms_envelope_nrmse": 0.17001568064723424, "全帯域_40ms_envelope_correlation": 0.9934138878000783, "全帯域_40ms_modulation_mae_db": 0.7988744875673874, "300–1000 Hz_10ms_log_rms_mae_db": 1.3503513756597845, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.160565728591517, "300–1000 Hz_10ms_envelope_correlation": 0.9947616066198147, "300–1000 Hz_10ms_modulation_mae_db": 1.198856709743602, "300–1000 Hz_40ms_log_rms_mae_db": 1.2294147347780169, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14767532605065348, "300–1000 Hz_40ms_envelope_correlation": 0.9971201666990055, "300–1000 Hz_40ms_modulation_mae_db": 1.0310431799843371, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1881821116896527, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17577971715591403, "1000–3000 Hz_10ms_envelope_correlation": 0.9920690403629682, "1000–3000 Hz_10ms_modulation_mae_db": 0.9964143847792005, "1000–3000 Hz_40ms_log_rms_mae_db": 1.016219280841194, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.16143323239692434, "1000–3000 Hz_40ms_envelope_correlation": 0.9948063638341439, "1000–3000 Hz_40ms_modulation_mae_db": 0.8602553893811643, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1934677304274517, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1624484153880629, "3000–6000 Hz_10ms_envelope_correlation": 0.9853706888803502, "3000–6000 Hz_10ms_modulation_mae_db": 0.9046694282265078, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8868930142527952, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10122996777453307, "3000–6000 Hz_40ms_envelope_correlation": 0.9956855302479934, "3000–6000 Hz_40ms_modulation_mae_db": 0.5992389334923891, "mr_stft_db": 5.080375941939627, "band_mae_db": 0.838645214526167, "rms_gain_error_db": 1.185799200230835, "output_peak": 0.42893521845566823}}], "planned_noise_seeds": [0], "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": 5.921107084475092, "spectral_convergence": 0.4587202461226308, "spectral_convergence_status": "ok", "amplitude_floor": 8.606911899432486e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 4.77582389625198, "spectral_convergence": 0.26173640724131225, "spectral_convergence_status": "ok", "amplitude_floor": 7.696353352907002e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.544196845091809, "spectral_convergence": 0.2832712835504907, "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": 0.00015819083784764643, "delta_db": 1.20831917072425, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0009579981539513103, "output_power": 0.001251282038694615, "delta_db": 1.1599053840725018, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0008712676276581917, "output_power": 0.0011899822752807559, "delta_db": 1.3538891472233496, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00010621716934048885, "output_power": 0.0001360731878305363, "delta_db": 1.0757783585958463, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.322826988453831e-05, "output_power": 6.07471200441615e-05, "delta_db": 0.5738334309589994, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 7.685697629736477e-05, "output_power": 8.533768191398699e-05, "delta_db": 0.4545754716800017, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.3518932532436965e-05, "output_power": 3.3861931994203993e-05, "delta_db": 0.04421553842821957, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.838645214526167, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 1.185799200230835, "pitch": null, "output_rms_dbfs": -25.352906673081694, "output_peak": 0.42893521845566823, "reference_rms_dbfs": -26.53870587331253, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.080375941939627}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.9479249023435052, "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"}}, "level": {"reference": {"rms": 0.04710475034036298, "rms_dbfs": -26.53870587331253, "peak": 0.300323486328125, "peak_dbfs": -10.448214063056167, "crest_factor_db": 16.09049181025636, "mean": -1.2700610690646702e-05, "zero_energy": false}, "output": {"rms": 0.05399513935166671, "rms_dbfs": -25.35290667308169, "peak": 0.42893521845566823, "peak_dbfs": -7.352165876196748, "crest_factor_db": 18.000740796884944, "mean": 2.0511339847470194e-05, "zero_energy": false}, "rms_difference_db": 1.1857992002308393}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.984813836558412e-06, "threshold_dbfs": -57.022802211663084, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 222, "quiet_samples": 53280, "reference_mean_power": 8.965192877270795e-08, "output_mean_power": 8.897379799086305e-07, "output_rms_dbfs": -60.507378704717595, "output_zero_energy": false, "output_peak": 0.05084146781398838, "output_energy_fraction": 0.00011291574932212664, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 312, "output_estimated_voiced_frames": 298, "both_estimated_voiced_frames": 284, "reference_voiced_output_unvoiced_frames": 28, "reference_unvoiced_output_voiced_frames": 14, "paired_voiced_fraction": 0.9102564102564102, "absolute_difference_cents_median": 4.672449714342463, "absolute_difference_cents_p95": 24.754877368870066, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.3263702721006023, "rms_envelope_nrmse": 0.18310928003549862, "envelope_correlation": 0.9904721212918542, "rms_gain_error_db": 1.1861817755079898, "reference_mean_power": 0.002217082801939853, "output_mean_power": 0.002913399830827184}, "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": 0.0004490129157281803, "reference_active": true, "delta_db": 1.083364335756578}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.422870023578459e-05, "output_power": 9.98695989096124e-05, "reference_active": true, "delta_db": 0.7397320670744846}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2432690798089742e-05, "output_power": 1.5284284699026118e-05, "reference_active": true, "delta_db": 0.8967998580811293}], "active_band_count": 3, "active_band_mae_db": 0.9066320869707307}}, {"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": 1.020260443221776, "rms_envelope_nrmse": 0.17001568064723424, "envelope_correlation": 0.9934138878000783, "rms_gain_error_db": 1.1714922173052824, "reference_mean_power": 0.002205255256660357, "output_mean_power": 0.0028880724765360214}, "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": 0.00029633227983582444, "output_power": 0.00038732422778167154, "reference_active": true, "delta_db": 1.1629570140251295}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2550897730277714e-05, "output_power": 4.8192403444076644e-05, "reference_active": true, "delta_db": 0.54069858733569}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.293923839625808e-07, "output_power": 1.0901741889021732e-06, "reference_active": true, "delta_db": 0.6929678613413428}], "active_band_count": 3, "active_band_mae_db": 0.7988744875673874}}]}, {"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": 0.0001225394829970324, "log_rms_mae_db": 1.3503513756597845, "rms_envelope_nrmse": 0.160565728591517, "envelope_correlation": 0.9947616066198147, "rms_gain_error_db": 1.0806358507707643, "reference_mean_power": 0.0009458112547504992, "output_mean_power": 0.0012130202827473641}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 7.572635748614322e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021454762051170177, "output_power": 0.0002754665319850898, "reference_active": true, "delta_db": 1.0854513920047677}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.152647446601543e-05, "output_power": 8.032252586981596e-05, "reference_active": true, "delta_db": 1.1577532684343415}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.926247906815996e-06, "output_power": 9.45876811677515e-06, "reference_active": true, "delta_db": 1.3533654687916974}], "active_band_count": 3, "active_band_mae_db": 1.198856709743602}}, {"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": 0.00011593520090475494, "log_rms_mae_db": 1.2294147347780169, "rms_envelope_nrmse": 0.14767532605065348, "envelope_correlation": 0.9971201666990055, "rms_gain_error_db": 1.078122862385516, "reference_mean_power": 0.0009490323754435319, "output_mean_power": 0.0012164473440418446}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 7.167599035150244e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00018822421406971727, "output_power": 0.000244438787991862, "reference_active": true, "delta_db": 1.1349462925813456}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6896254802287652e-05, "output_power": 3.5105303756822406e-05, "reference_active": true, "delta_db": 1.1568092480753904}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.519942395248385e-07, "output_power": 9.043820078460554e-07, "reference_active": true, "delta_db": 0.8013739992962752}], "active_band_count": 3, "active_band_mae_db": 1.0310431799843371}}]}, {"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": 1.1881821116896527, "rms_envelope_nrmse": 0.17577971715591403, "envelope_correlation": 0.9920690403629682, "rms_gain_error_db": 1.093386243567541, "reference_mean_power": 0.00014098678071692043, "output_mean_power": 0.00018134977385772977}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.160899550412932e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.7499181258859675e-05, "output_power": 4.96979852256713e-05, "reference_active": true, "delta_db": 1.2231699700392509}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.267009960974534e-06, "output_power": 1.037500791234804e-05, "reference_active": true, "delta_db": 0.9863997568023415}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.898653312592319e-07, "output_power": 9.451927787112371e-07, "reference_active": true, "delta_db": 0.7796734274960091}], "active_band_count": 3, "active_band_mae_db": 0.9964143847792005}}, {"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": 1.016219280841194, "rms_envelope_nrmse": 0.16143323239692434, "envelope_correlation": 0.9948063638341439, "rms_gain_error_db": 1.093385711309317, "reference_mean_power": 0.00014167955800585476, "output_mean_power": 0.00018224086346995175}, "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": 3.3910555465812715e-05, "output_power": 4.504008756940641e-05, "reference_active": true, "delta_db": 1.232643225034983}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.965549503856846e-06, "output_power": 5.056967125527979e-06, "reference_active": true, "delta_db": 1.0558675461424463}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.243578010746913e-08, "output_power": 6.678194784926029e-08, "reference_active": true, "delta_db": 0.29225539696606384}], "active_band_count": 3, "active_band_mae_db": 0.8602553893811643}}]}, {"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": 4.041281383552759e-05, "log_rms_mae_db": 1.1934677304274517, "rms_envelope_nrmse": 0.1624484153880629, "envelope_correlation": 0.9853706888803502, "rms_gain_error_db": 0.5200104172945452, "reference_mean_power": 5.063950126149288e-05, "output_mean_power": 5.708085392195968e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.808534933602363e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3975319757086051e-05, "output_power": 1.5419945423886838e-05, "reference_active": true, "delta_db": 0.4272108322585038}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.037166885946861e-06, "output_power": 4.870667069210705e-06, "reference_active": true, "delta_db": 0.8151174233090609}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.222770754615436e-07, "output_power": 1.1539478584161238e-06, "reference_active": true, "delta_db": 1.4716800291119583}], "active_band_count": 3, "active_band_mae_db": 0.9046694282265078}}, {"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": 3.6032760748614396e-05, "log_rms_mae_db": 0.8868930142527952, "rms_envelope_nrmse": 0.10122996777453307, "envelope_correlation": 0.9956855302479934, "rms_gain_error_db": 0.5220334753551839, "reference_mean_power": 5.078542798446868e-05, "output_mean_power": 5.72720151473726e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.512050765202737e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2965326164159417e-05, "output_power": 1.4447419406047378e-05, "reference_active": true, "delta_db": 0.470068338261283}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.904625885804089e-06, "output_power": 2.251285910734118e-06, "reference_active": true, "delta_db": 0.726209708670862}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.69464596815875e-08, "output_power": 6.540494802047247e-08, "reference_active": true, "delta_db": 0.6014387535450223}], "active_band_count": 3, "active_band_mae_db": 0.5992389334923891}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1234628, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9920690403629682, "standard_deviation": null, "minimum": 0.9920690403629682, "maximum": 0.9920690403629682, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1881821116896527, "standard_deviation": null, "minimum": 1.1881821116896527, "maximum": 1.1881821116896527, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.9964143847792005, "standard_deviation": null, "minimum": 0.9964143847792005, "maximum": 0.9964143847792005, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17577971715591403, "standard_deviation": null, "minimum": 0.17577971715591403, "maximum": 0.17577971715591403, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9948063638341439, "standard_deviation": null, "minimum": 0.9948063638341439, "maximum": 0.9948063638341439, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.016219280841194, "standard_deviation": null, "minimum": 1.016219280841194, "maximum": 1.016219280841194, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8602553893811643, "standard_deviation": null, "minimum": 0.8602553893811643, "maximum": 0.8602553893811643, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.16143323239692434, "standard_deviation": null, "minimum": 0.16143323239692434, "maximum": 0.16143323239692434, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9853706888803502, "standard_deviation": null, "minimum": 0.9853706888803502, "maximum": 0.9853706888803502, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.1934677304274517, "standard_deviation": null, "minimum": 1.1934677304274517, "maximum": 1.1934677304274517, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.9046694282265078, "standard_deviation": null, "minimum": 0.9046694282265078, "maximum": 0.9046694282265078, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1624484153880629, "standard_deviation": null, "minimum": 0.1624484153880629, "maximum": 0.1624484153880629, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9956855302479934, "standard_deviation": null, "minimum": 0.9956855302479934, "maximum": 0.9956855302479934, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8868930142527952, "standard_deviation": null, "minimum": 0.8868930142527952, "maximum": 0.8868930142527952, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.5992389334923891, "standard_deviation": null, "minimum": 0.5992389334923891, "maximum": 0.5992389334923891, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.10122996777453307, "standard_deviation": null, "minimum": 0.10122996777453307, "maximum": 0.10122996777453307, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9947616066198147, "standard_deviation": null, "minimum": 0.9947616066198147, "maximum": 0.9947616066198147, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.3503513756597845, "standard_deviation": null, "minimum": 1.3503513756597845, "maximum": 1.3503513756597845, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 1.198856709743602, "standard_deviation": null, "minimum": 1.198856709743602, "maximum": 1.198856709743602, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.160565728591517, "standard_deviation": null, "minimum": 0.160565728591517, "maximum": 0.160565728591517, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9971201666990055, "standard_deviation": null, "minimum": 0.9971201666990055, "maximum": 0.9971201666990055, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.2294147347780169, "standard_deviation": null, "minimum": 1.2294147347780169, "maximum": 1.2294147347780169, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.0310431799843371, "standard_deviation": null, "minimum": 1.0310431799843371, "maximum": 1.0310431799843371, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.14767532605065348, "standard_deviation": null, "minimum": 0.14767532605065348, "maximum": 0.14767532605065348, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 0.838645214526167, "standard_deviation": null, "minimum": 0.838645214526167, "maximum": 0.838645214526167, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 5.080375941939627, "standard_deviation": null, "minimum": 5.080375941939627, "maximum": 5.080375941939627, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.42893521845566823, "standard_deviation": null, "minimum": 0.42893521845566823, "maximum": 0.42893521845566823, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 1.185799200230835, "standard_deviation": null, "minimum": 1.185799200230835, "maximum": 1.185799200230835, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9904721212918542, "standard_deviation": null, "minimum": 0.9904721212918542, "maximum": 0.9904721212918542, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.3263702721006023, "standard_deviation": null, "minimum": 1.3263702721006023, "maximum": 1.3263702721006023, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 0.9066320869707307, "standard_deviation": null, "minimum": 0.9066320869707307, "maximum": 0.9066320869707307, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.18310928003549862, "standard_deviation": null, "minimum": 0.18310928003549862, "maximum": 0.18310928003549862, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9934138878000783, "standard_deviation": null, "minimum": 0.9934138878000783, "maximum": 0.9934138878000783, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 1.020260443221776, "standard_deviation": null, "minimum": 1.020260443221776, "maximum": 1.020260443221776, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7988744875673874, "standard_deviation": null, "minimum": 0.7988744875673874, "maximum": 0.7988744875673874, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.17001568064723424, "standard_deviation": null, "minimum": 0.17001568064723424, "maximum": 0.17001568064723424, "valid_count": 1, "planned_count": 1}}, "seconds": 2.5760569460035185, "rtf_including_measurement": 0.42934282433391974}, {"case": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "whisper", "speaker": "jvs_jvs018", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.742032527923584, "predicted_mos": 1.742032527923584, "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": "c16d2fcd4f753a7e33b036ecd285dd45e47a8b1932af63ac848b955a8448ae43", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 4.85195850799937}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7148975936188247, "全帯域_10ms_rms_envelope_nrmse": 0.12609520253390105, "全帯域_10ms_envelope_correlation": 0.9878336309898084, "全帯域_10ms_modulation_mae_db": 0.8244879638179666, "全帯域_40ms_log_rms_mae_db": 0.9290294038610443, "全帯域_40ms_rms_envelope_nrmse": 0.061824335890667936, "全帯域_40ms_envelope_correlation": 0.9969182151876063, "全帯域_40ms_modulation_mae_db": 1.3453624244778517, "300–1000 Hz_10ms_log_rms_mae_db": 2.5089066402909923, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25650758474384594, "300–1000 Hz_10ms_envelope_correlation": 0.9568237295901575, "300–1000 Hz_10ms_modulation_mae_db": 0.33824408943321044, "300–1000 Hz_40ms_log_rms_mae_db": 1.8733202478454183, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14288921354807507, "300–1000 Hz_40ms_envelope_correlation": 0.9867725506349381, "300–1000 Hz_40ms_modulation_mae_db": 0.33538563922789577, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6715064215141515, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18057256411307476, "1000–3000 Hz_10ms_envelope_correlation": 0.9795898170941143, "1000–3000 Hz_10ms_modulation_mae_db": 0.8523259030263358, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9465467571393406, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08559723445026231, "1000–3000 Hz_40ms_envelope_correlation": 0.9955277342004162, "1000–3000 Hz_40ms_modulation_mae_db": 1.1475494248036509, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3792053395854569, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15731184566967385, "3000–6000 Hz_10ms_envelope_correlation": 0.9855879293334453, "3000–6000 Hz_10ms_modulation_mae_db": 1.0108674277777911, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9243751869635541, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08535032504020677, "3000–6000 Hz_40ms_envelope_correlation": 0.9960757076150117, "3000–6000 Hz_40ms_modulation_mae_db": 1.9247750003820006, "mr_stft_db": 6.076750905666287, "band_mae_db": 0.5943027456088897, "rms_gain_error_db": -0.049807898818143806, "output_peak": 0.04111148487549973}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7038909253896448, "全帯域_10ms_rms_envelope_nrmse": 0.14314398538291798, "全帯域_10ms_envelope_correlation": 0.9843281641020805, "全帯域_10ms_modulation_mae_db": 0.7451940703348261, "全帯域_40ms_log_rms_mae_db": 0.8754860374103184, "全帯域_40ms_rms_envelope_nrmse": 0.06672901645376986, "全帯域_40ms_envelope_correlation": 0.9965805486539321, "全帯域_40ms_modulation_mae_db": 1.1426803975454647, "300–1000 Hz_10ms_log_rms_mae_db": 2.488701497396005, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24377826445473688, "300–1000 Hz_10ms_envelope_correlation": 0.962025044791577, "300–1000 Hz_10ms_modulation_mae_db": 0.9606219547390227, "300–1000 Hz_40ms_log_rms_mae_db": 1.7787849954682315, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1363415538199833, "300–1000 Hz_40ms_envelope_correlation": 0.9887055476073354, "300–1000 Hz_40ms_modulation_mae_db": 0.9913883600234992, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6617012587644304, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16654294299162628, "1000–3000 Hz_10ms_envelope_correlation": 0.9819335828397988, "1000–3000 Hz_10ms_modulation_mae_db": 0.6173364333957402, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9820251739623933, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08925733020972457, "1000–3000 Hz_40ms_envelope_correlation": 0.9949679996944752, "1000–3000 Hz_40ms_modulation_mae_db": 1.1001389141166167, "3000–6000 Hz_10ms_log_rms_mae_db": 1.398907213408475, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19610760840878302, "3000–6000 Hz_10ms_envelope_correlation": 0.97734027484844, "3000–6000 Hz_10ms_modulation_mae_db": 1.47935816278347, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8870420500781981, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10014145215587743, "3000–6000 Hz_40ms_envelope_correlation": 0.9945948035775398, "3000–6000 Hz_40ms_modulation_mae_db": 2.3258208082909326, "mr_stft_db": 6.081486040307053, "band_mae_db": 0.5978554845595946, "rms_gain_error_db": -0.13733157728054, "output_peak": 0.03181054769234618}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7566722434273698, "全帯域_10ms_rms_envelope_nrmse": 0.15258494109914408, "全帯域_10ms_envelope_correlation": 0.9825532398037088, "全帯域_10ms_modulation_mae_db": 0.43037802949349596, "全帯域_40ms_log_rms_mae_db": 0.9160418071133285, "全帯域_40ms_rms_envelope_nrmse": 0.09034079046460113, "全帯域_40ms_envelope_correlation": 0.9935876337152634, "全帯域_40ms_modulation_mae_db": 1.1011911406238413, "300–1000 Hz_10ms_log_rms_mae_db": 2.4424670534851063, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2718468379600887, "300–1000 Hz_10ms_envelope_correlation": 0.9482609804907755, "300–1000 Hz_10ms_modulation_mae_db": 0.3038285430826322, "300–1000 Hz_40ms_log_rms_mae_db": 1.8319800446410233, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1682507493230006, "300–1000 Hz_40ms_envelope_correlation": 0.978932454117074, "300–1000 Hz_40ms_modulation_mae_db": 0.32215750610177296, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6193166022173167, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18513658353444776, "1000–3000 Hz_10ms_envelope_correlation": 0.9775013412662533, "1000–3000 Hz_10ms_modulation_mae_db": 0.25715999779228466, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9219772795018296, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09730949935705936, "1000–3000 Hz_40ms_envelope_correlation": 0.9936673712570703, "1000–3000 Hz_40ms_modulation_mae_db": 0.6741788348401488, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3803918658574992, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1908461649434229, "3000–6000 Hz_10ms_envelope_correlation": 0.9808602035913946, "3000–6000 Hz_10ms_modulation_mae_db": 0.7695210631074914, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8766993115434927, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11597430295784435, "3000–6000 Hz_40ms_envelope_correlation": 0.9935673092710409, "3000–6000 Hz_40ms_modulation_mae_db": 1.1972840901570596, "mr_stft_db": 6.08080580022067, "band_mae_db": 0.5651874494720619, "rms_gain_error_db": 0.09334470418618333, "output_peak": 0.03766743638286887}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6929095695184924, "全帯域_10ms_rms_envelope_nrmse": 0.1473756038402929, "全帯域_10ms_envelope_correlation": 0.9836094212995088, "全帯域_10ms_modulation_mae_db": 0.5678138222953811, "全帯域_40ms_log_rms_mae_db": 0.8802363397654454, "全帯域_40ms_rms_envelope_nrmse": 0.07144763370927151, "全帯域_40ms_envelope_correlation": 0.9959537943389577, "全帯域_40ms_modulation_mae_db": 0.9498826653278475, "300–1000 Hz_10ms_log_rms_mae_db": 2.550255074278787, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.279204101848926, "300–1000 Hz_10ms_envelope_correlation": 0.9483130097624931, "300–1000 Hz_10ms_modulation_mae_db": 0.29725499445805187, "300–1000 Hz_40ms_log_rms_mae_db": 1.9179754598845176, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1730220543834948, "300–1000 Hz_40ms_envelope_correlation": 0.9797119771782647, "300–1000 Hz_40ms_modulation_mae_db": 0.6318199321193417, "1000–3000 Hz_10ms_log_rms_mae_db": 1.630884976230013, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21525942784796212, "1000–3000 Hz_10ms_envelope_correlation": 0.972860027875834, "1000–3000 Hz_10ms_modulation_mae_db": 0.6350847930395739, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8982272512818472, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10781381528079162, "1000–3000 Hz_40ms_envelope_correlation": 0.9941164183760482, "1000–3000 Hz_40ms_modulation_mae_db": 0.2487865568301455, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3713697169663621, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16581131178824346, "3000–6000 Hz_10ms_envelope_correlation": 0.9838463959019225, "3000–6000 Hz_10ms_modulation_mae_db": 0.7460588633446606, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8627837532228105, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07499645791780989, "3000–6000 Hz_40ms_envelope_correlation": 0.9965964347800296, "3000–6000 Hz_40ms_modulation_mae_db": 1.2348599235063953, "mr_stft_db": 6.061536228962602, "band_mae_db": 0.5241171427647604, "rms_gain_error_db": 0.06835042105279776, "output_peak": 0.03344933663720311}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6927331887024888, "全帯域_10ms_rms_envelope_nrmse": 0.15349691820414385, "全帯域_10ms_envelope_correlation": 0.9819685953554773, "全帯域_10ms_modulation_mae_db": 0.7093173360224156, "全帯域_40ms_log_rms_mae_db": 0.8670280274034808, "全帯域_40ms_rms_envelope_nrmse": 0.07429293718963392, "全帯域_40ms_envelope_correlation": 0.9956202368923577, "全帯域_40ms_modulation_mae_db": 1.1070046372119393, "300–1000 Hz_10ms_log_rms_mae_db": 2.461043516432789, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26912999267297455, "300–1000 Hz_10ms_envelope_correlation": 0.9495953262743898, "300–1000 Hz_10ms_modulation_mae_db": 0.39472570031706256, "300–1000 Hz_40ms_log_rms_mae_db": 1.7740606230611908, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13844175777416456, "300–1000 Hz_40ms_envelope_correlation": 0.985931193273275, "300–1000 Hz_40ms_modulation_mae_db": 0.6596532335747048, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6016073869666168, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1732751099355235, "1000–3000 Hz_10ms_envelope_correlation": 0.9803896347377604, "1000–3000 Hz_10ms_modulation_mae_db": 0.7662847660033504, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9049643444948442, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08471741417493055, "1000–3000 Hz_40ms_envelope_correlation": 0.995241045450697, "1000–3000 Hz_40ms_modulation_mae_db": 1.1446892334443375, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3477668021337035, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18746581908839927, "3000–6000 Hz_10ms_envelope_correlation": 0.9791406021969411, "3000–6000 Hz_10ms_modulation_mae_db": 0.9151466374220568, "3000–6000 Hz_40ms_log_rms_mae_db": 0.828583926284126, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0960516389002392, "3000–6000 Hz_40ms_envelope_correlation": 0.9944090141707339, "3000–6000 Hz_40ms_modulation_mae_db": 1.2949660207112714, "mr_stft_db": 6.07904135504878, "band_mae_db": 0.5932689149566385, "rms_gain_error_db": -0.06468836251477912, "output_peak": 0.033680279271852666}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.741180085917989, "全帯域_10ms_rms_envelope_nrmse": 0.13825808135837409, "全帯域_10ms_envelope_correlation": 0.9853732665583901, "全帯域_10ms_modulation_mae_db": 0.5952892423759886, "全帯域_40ms_log_rms_mae_db": 0.9106060738562937, "全帯域_40ms_rms_envelope_nrmse": 0.0738127928929452, "全帯域_40ms_envelope_correlation": 0.9956821752637433, "全帯域_40ms_modulation_mae_db": 1.0068064501066083, "300–1000 Hz_10ms_log_rms_mae_db": 2.4965843870069437, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2516523067463831, "300–1000 Hz_10ms_envelope_correlation": 0.9580027726228444, "300–1000 Hz_10ms_modulation_mae_db": 0.6437044967231095, "300–1000 Hz_40ms_log_rms_mae_db": 1.771258086518472, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14280192493578803, "300–1000 Hz_40ms_envelope_correlation": 0.9864270784089002, "300–1000 Hz_40ms_modulation_mae_db": 0.896494792353638, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6458687802565746, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.189796889772692, "1000–3000 Hz_10ms_envelope_correlation": 0.9765218089858305, "1000–3000 Hz_10ms_modulation_mae_db": 0.23310576782961692, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9679924906369214, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10113867959506602, "1000–3000 Hz_40ms_envelope_correlation": 0.9931189041114281, "1000–3000 Hz_40ms_modulation_mae_db": 0.7536586041987543, "3000–6000 Hz_10ms_log_rms_mae_db": 1.396088763491764, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.167559799375517, "3000–6000 Hz_10ms_envelope_correlation": 0.9836553016114801, "3000–6000 Hz_10ms_modulation_mae_db": 0.6973170163658994, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8725489943212653, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09737729720857721, "3000–6000 Hz_40ms_envelope_correlation": 0.9948164781126034, "3000–6000 Hz_40ms_modulation_mae_db": 1.0601047243540338, "mr_stft_db": 6.072749687328094, "band_mae_db": 0.41665796646263537, "rms_gain_error_db": -0.11185233426895008, "output_peak": 0.032392137161090885}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7136501008129577, "全帯域_10ms_rms_envelope_nrmse": 0.15461126188278296, "全帯域_10ms_envelope_correlation": 0.9816710395560746, "全帯域_10ms_modulation_mae_db": 0.7028448367893594, "全帯域_40ms_log_rms_mae_db": 0.8913805496097126, "全帯域_40ms_rms_envelope_nrmse": 0.07695989696268221, "全帯域_40ms_envelope_correlation": 0.9952128939312469, "全帯域_40ms_modulation_mae_db": 1.3066846720635346, "300–1000 Hz_10ms_log_rms_mae_db": 2.413235323980405, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.30443003209335545, "300–1000 Hz_10ms_envelope_correlation": 0.9365198492856796, "300–1000 Hz_10ms_modulation_mae_db": 0.2221053360419111, "300–1000 Hz_40ms_log_rms_mae_db": 1.7659294209120722, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1832643068214108, "300–1000 Hz_40ms_envelope_correlation": 0.9757705530082951, "300–1000 Hz_40ms_modulation_mae_db": 0.4770069314297232, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6432973435645952, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17153053659775827, "1000–3000 Hz_10ms_envelope_correlation": 0.9807147510086334, "1000–3000 Hz_10ms_modulation_mae_db": 0.519033919449969, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0102194000599072, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10008686443200594, "1000–3000 Hz_40ms_envelope_correlation": 0.9933354073961732, "1000–3000 Hz_40ms_modulation_mae_db": 0.6310048507771027, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3588973997348144, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.20174912903083472, "3000–6000 Hz_10ms_envelope_correlation": 0.9765448904973735, "3000–6000 Hz_10ms_modulation_mae_db": 0.8175328451629215, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8564359059380773, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09397637850756141, "3000–6000 Hz_40ms_envelope_correlation": 0.9948767572206076, "3000–6000 Hz_40ms_modulation_mae_db": 1.2625165953050062, "mr_stft_db": 6.070946983147111, "band_mae_db": 0.4982766114776154, "rms_gain_error_db": -0.05797850125102745, "output_peak": 0.036446988801156904}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6751956323402015, "全帯域_10ms_rms_envelope_nrmse": 0.14664487282750066, "全帯域_10ms_envelope_correlation": 0.9835673126295135, "全帯域_10ms_modulation_mae_db": 0.6358329969066006, "全帯域_40ms_log_rms_mae_db": 0.9133980091634446, "全帯域_40ms_rms_envelope_nrmse": 0.06657507228437866, "全帯域_40ms_envelope_correlation": 0.9964821401530213, "全帯域_40ms_modulation_mae_db": 0.6523328000189664, "300–1000 Hz_10ms_log_rms_mae_db": 2.490821785131062, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2840154751961728, "300–1000 Hz_10ms_envelope_correlation": 0.9495390743909813, "300–1000 Hz_10ms_modulation_mae_db": 0.7927810693017939, "300–1000 Hz_40ms_log_rms_mae_db": 1.8041452570441483, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16372474287525626, "300–1000 Hz_40ms_envelope_correlation": 0.9843038522077135, "300–1000 Hz_40ms_modulation_mae_db": 0.7009552052802439, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5990012380839038, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17243812510443857, "1000–3000 Hz_10ms_envelope_correlation": 0.9806106842884941, "1000–3000 Hz_10ms_modulation_mae_db": 0.48848787233910834, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9437619085211021, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08355479044268942, "1000–3000 Hz_40ms_envelope_correlation": 0.9954191719821259, "1000–3000 Hz_40ms_modulation_mae_db": 0.6524025384218527, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3621396245672657, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16714783363050198, "3000–6000 Hz_10ms_envelope_correlation": 0.9834433680307432, "3000–6000 Hz_10ms_modulation_mae_db": 0.5921177268126846, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8767334991695042, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07251051577823764, "3000–6000 Hz_40ms_envelope_correlation": 0.9969414768790248, "3000–6000 Hz_40ms_modulation_mae_db": 0.8458097613078502, "mr_stft_db": 6.065657041976217, "band_mae_db": 0.584819994022978, "rms_gain_error_db": -0.032990904605276594, "output_peak": 0.035374862427154465}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 6.346622072426298, "spectral_convergence": 0.6184867265811703, "spectral_convergence_status": "ok", "amplitude_floor": 9.167242110941195e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.934749058648641, "spectral_convergence": 0.6170814533425584, "spectral_convergence_status": "ok", "amplitude_floor": 5.84028801806317e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.948881585923926, "spectral_convergence": 0.6437418299301237, "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": 1.2704491015201036e-07, "delta_db": -0.37276810060062104, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.81286342317638e-08, "output_power": 1.3966977469601196e-07, "delta_db": 3.1177274981161887, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 9.335883160942139e-07, "output_power": 9.481723377084538e-07, "delta_db": 0.06731873064193399, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.7505166473017637e-06, "output_power": 1.7381543980156344e-06, "delta_db": -0.030778935881226363, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.470519881244434e-07, "output_power": 5.748361662304407e-07, "delta_db": 0.2151548356351236, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.7292398267785066e-06, "output_power": 2.5835164235189228e-06, "delta_db": -0.2383047343331637, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.57439203602588e-07, "output_power": 9.317610843101064e-07, "delta_db": -0.11806638405397107, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.5943027456088897, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.049807898818143806, "pitch": null, "output_rms_dbfs": -51.52232748069255, "output_peak": 0.04111148487549973, "reference_rms_dbfs": -51.47251958187441, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.076750905666287}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.5287434130848788, "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"}}, "level": {"reference": {"rms": 0.0026691563923850765, "rms_dbfs": -51.47251958187441, "peak": 0.036651611328125, "peak_dbfs": -28.71813855113624, "crest_factor_db": 22.754381030738173, "mean": -1.292758517795139e-07, "zero_energy": false}, "output": {"rms": 0.002653894326199064, "rms_dbfs": -51.52232748069255, "peak": 0.04111148487549973, "peak_dbfs": -27.720736739464833, "crest_factor_db": 23.80159074122772, "mean": 4.451592033375618e-07, "zero_energy": false}, "rms_difference_db": -0.049807898818144736}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 361, "quiet_samples": 86640, "reference_mean_power": 1.2447742146757172e-07, "output_mean_power": 1.5669147366982942e-07, "output_rms_dbfs": -68.04954634921897, "output_zero_energy": false, "output_peak": 0.008793945987674663, "output_energy_fraction": 0.013385483549818875, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 0, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.7148975936188247, "rms_envelope_nrmse": 0.12609520253390105, "envelope_correlation": 0.9878336309898084, "rms_gain_error_db": -0.049810899962776274, "reference_mean_power": 7.130327548553108e-06, "output_mean_power": 7.049014284781281e-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": 1.262369325137822e-06, "reference_active": true, "delta_db": -0.05014048045097172}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.124025700263392e-07, "output_power": 2.1779097483443437e-07, "reference_active": true, "delta_db": 0.10880111500687706}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.509706557401959e-07, "output_power": 8.860134441385431e-08, "reference_active": true, "delta_db": -2.314522295996051}], "active_band_count": 3, "active_band_mae_db": 0.8244879638179666}}, {"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": 0.9290294038610443, "rms_envelope_nrmse": 0.061824335890667936, "envelope_correlation": 0.9969182151876063, "rms_gain_error_db": -0.04982005900042357, "reference_mean_power": 7.166117032249278e-06, "output_mean_power": 7.08438068958792e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.171922661595566e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0939532041259814e-06, "output_power": 1.0942079978630196e-06, "reference_active": true, "delta_db": 0.001011401851185969}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.164609293708589e-07, "output_power": 1.055014393931094e-07, "reference_active": true, "delta_db": -0.4292186659700382}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0690330771826296e-08, "output_power": 4.660209302461157e-09, "reference_active": true, "delta_db": -3.6058572056123306}], "active_band_count": 3, "active_band_mae_db": 1.3453624244778517}}]}, {"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": 6.5560927718001166e-06, "log_rms_mae_db": 2.5089066402909923, "rms_envelope_nrmse": 0.25650758474384594, "envelope_correlation": 0.9568237295901575, "rms_gain_error_db": 0.3892719034771124, "reference_mean_power": 7.945163829144028e-07, "output_mean_power": 8.690205513229652e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.079115524536589e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.4868570435085094e-07, "output_power": 1.6710062001418058e-07, "reference_active": true, "delta_db": 0.5070884679248864}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.530749650867309e-08, "output_power": 3.652340264047477e-08, "reference_active": true, "delta_db": 0.14704306210213658}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.491869757314003e-08, "output_power": 2.293323204883657e-08, "reference_active": true, "delta_db": -0.3606007382726083}], "active_band_count": 3, "active_band_mae_db": 0.33824408943321044}}, {"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": 4.158309417730709e-06, "log_rms_mae_db": 1.8733202478454183, "rms_envelope_nrmse": 0.14288921354807507, "envelope_correlation": 0.9867725506349381, "rms_gain_error_db": 0.38924851132765326, "reference_mean_power": 7.985041710031804e-07, "output_mean_power": 8.733775819468317e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.703673751837486e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.314092622690957e-07, "output_power": 1.517787731825683e-07, "reference_active": true, "delta_db": 0.6258506095552443}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9292191287469542e-08, "output_power": 1.8262257010760357e-08, "reference_active": true, "delta_db": -0.23827108965341975}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4692549483461508e-09, "output_power": 1.4219804979583632e-09, "reference_active": true, "delta_db": -0.14203521847502326}], "active_band_count": 3, "active_band_mae_db": 0.33538563922789577}}]}, {"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": 1.6715064215141515, "rms_envelope_nrmse": 0.18057256411307476, "envelope_correlation": 0.9795898170941143, "rms_gain_error_db": 0.1960190623320514, "reference_mean_power": 1.4849128654353035e-06, "output_mean_power": 1.5534700197502474e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.418114993045289e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.69138926350769e-07, "output_power": 2.704431236317787e-07, "reference_active": true, "delta_db": 0.020994278274604847}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.5217312260061476e-08, "output_power": 4.590845161819545e-08, "reference_active": true, "delta_db": 0.06587901210697306}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6338303134826183e-08, "output_power": 1.4913423469408115e-08, "reference_active": true, "delta_db": -2.4701044186974292}], "active_band_count": 3, "active_band_mae_db": 0.8523259030263358}}, {"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": 0.9465467571393406, "rms_envelope_nrmse": 0.08559723445026231, "envelope_correlation": 0.9955277342004162, "rms_gain_error_db": 0.19601397052440653, "reference_mean_power": 1.4923708236731126e-06, "output_mean_power": 1.5612704750432662e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.994698288619124e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.5519066781428626e-07, "output_power": 2.5530761336175787e-07, "reference_active": true, "delta_db": 0.001989773862568443}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4359212852663977e-08, "output_power": 2.1465065994971637e-08, "reference_active": true, "delta_db": -0.5493102226059037}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5357702928828264e-09, "output_power": 7.89207919761776e-10, "reference_active": true, "delta_db": -2.8913482779424804}], "active_band_count": 3, "active_band_mae_db": 1.1475494248036509}}]}, {"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": 1.0774952268311021e-05, "log_rms_mae_db": 1.3792053395854569, "rms_envelope_nrmse": 0.15731184566967385, "envelope_correlation": 0.9855879293334453, "rms_gain_error_db": -0.27827396832607204, "reference_mean_power": 1.9952232017025357e-06, "output_mean_power": 1.8713890741494072e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.5794872115033738e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.151593028482198e-07, "output_power": 6.82520260077036e-07, "reference_active": true, "delta_db": -0.20287244754985567}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2474197679576507e-07, "output_power": 1.2018081353882796e-07, "reference_active": true, "delta_db": -0.16177482515288164}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.137663053230785e-08, "output_power": 4.402549042289146e-08, "reference_active": true, "delta_db": -2.667955010630636}], "active_band_count": 3, "active_band_mae_db": 1.0108674277777911}}, {"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": 7.143885674653837e-06, "log_rms_mae_db": 0.9243751869635541, "rms_envelope_nrmse": 0.08535032504020677, "envelope_correlation": 0.9960757076150117, "rms_gain_error_db": -0.2782739703892766, "reference_mean_power": 2.0052568878051227e-06, "output_mean_power": 1.8808000156155285e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.5118360803946562e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.45069205976456e-07, "output_power": 6.18946537894158e-07, "reference_active": true, "delta_db": -0.1795317220008909}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.385509447185756e-08, "output_power": 6.765221108641756e-08, "reference_active": true, "delta_db": -0.9324745728573812}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.7337556623287715e-09, "output_power": 1.9597799553942193e-09, "reference_active": true, "delta_db": -4.66231870628773}], "active_band_count": 3, "active_band_mae_db": 1.9247750003820006}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9787652060120899, "standard_deviation": 0.0029776595013073968, "minimum": 0.972860027875834, "maximum": 0.9819335828397988, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.6341480009497003, "standard_deviation": 0.02645947024127226, "minimum": 1.5990012380839038, "maximum": 1.6715064215141515, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5461024316094973, "standard_deviation": 0.22063285659661025, "minimum": 0.23310576782961692, "maximum": 0.8523259030263358, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1818190224871904, "standard_deviation": 0.015559462765911842, "minimum": 0.16654294299162628, "maximum": 0.21525942784796212, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9944242565585543, "standard_deviation": 0.0009803423246270498, "minimum": 0.9931189041114281, "maximum": 0.9955277342004162, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.9469643256997733, "standard_deviation": 0.03863147198638581, "minimum": 0.8982272512818472, "maximum": 1.0102194000599072, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7940511196790762, "standard_deviation": 0.3165800838216482, "minimum": 0.2487865568301455, "maximum": 1.1475494248036509, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09368445349281623, "standard_deviation": 0.009081823091952369, "minimum": 0.08355479044268942, "maximum": 0.10781381528079162, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9813023707514675, "standard_deviation": 0.00334148826340352, "minimum": 0.9765448904973735, "maximum": 0.9855879293334453, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.3743458407181675, "standard_deviation": 0.017885083627731127, "minimum": 1.3477668021337035, "maximum": 1.398907213408475, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.8784899678471219, "standard_deviation": 0.2746090156249228, "minimum": 0.5921177268126846, "maximum": 1.47935816278347, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17924993899192204, "standard_deviation": 0.016636297110399066, "minimum": 0.15731184566967385, "maximum": 0.20174912903083472, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.995234747703324, "standard_deviation": 0.001174074204261285, "minimum": 0.9935673092710409, "maximum": 0.9969414768790248, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8731503284401285, "standard_deviation": 0.02729668755290084, "minimum": 0.828583926284126, "maximum": 0.9243751869635541, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.3932671155018188, "standard_deviation": 0.48596365878658404, "minimum": 0.8458097613078502, "maximum": 2.3258208082909326, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09204729605829423, "standard_deviation": 0.014159541663679824, "minimum": 0.07251051577823764, "maximum": 0.11597430295784435, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9511349734011123, "standard_deviation": 0.007863703615609625, "minimum": 0.9365198492856796, "maximum": 0.962025044791577, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.481501909750261, "standard_deviation": 0.04216766659373745, "minimum": 2.413235323980405, "maximum": 2.550255074278787, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.49415827301209925, "standard_deviation": 0.27053734643922045, "minimum": 0.2221053360419111, "maximum": 0.9606219547390227, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2700705744645604, "standard_deviation": 0.019555658863532412, "minimum": 0.24377826445473688, "maximum": 0.30443003209335545, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9833194008044746, "standard_deviation": 0.004592338265275343, "minimum": 0.9757705530082951, "maximum": 0.9887055476073354, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.8146817669218842, "standard_deviation": 0.05570248736933384, "minimum": 1.7659294209120722, "maximum": 1.9179754598845176, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6268577000138524, "standard_deviation": 0.2427317149042071, "minimum": 0.32215750610177296, "maximum": 0.9913883600234992, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1560920379351467, "standard_deviation": 0.0180618215683197, "minimum": 0.1363415538199833, "maximum": 0.1832643068214108, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.5468107886656468, "standard_deviation": 0.06393314683878414, "minimum": 0.41665796646263537, "maximum": 0.5978554845595946, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.073621755332102, "standard_deviation": 0.007270612445667375, "minimum": 6.061536228962602, "maximum": 6.081486040307053, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.035241634156146597, "standard_deviation": 0.0031018989672487117, "minimum": 0.03181054769234618, "maximum": 0.04111148487549973, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.03661930668746699, "standard_deviation": 0.08030606550906204, "minimum": -0.13733157728054, "maximum": 0.09334470418618333, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9838630837868202, "standard_deviation": 0.0020186225011640294, "minimum": 0.9816710395560746, "maximum": 0.9878336309898084, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.711391167465996, "standard_deviation": 0.02675607630712693, "minimum": 1.6751956323402015, "maximum": 1.7566722434273698, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.6513947872545043, "standard_deviation": 0.12188159882897832, "minimum": 0.43037802949349596, "maximum": 0.8244879638179666, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.14527635839113218, "standard_deviation": 0.009532898213405513, "minimum": 0.12609520253390105, "maximum": 0.15461126188278296, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9957547047670161, "standard_deviation": 0.0010431868471254342, "minimum": 0.9935876337152634, "maximum": 0.9969182151876063, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8979007810228836, "standard_deviation": 0.022391867411815026, "minimum": 0.8670280274034808, "maximum": 0.9290294038610443, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 1.0764931484220068, "standard_deviation": 0.21778067944790538, "minimum": 0.6523328000189664, "maximum": 1.3453624244778517, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0727478094809938, "standard_deviation": 0.00866946658818556, "minimum": 0.061824335890667936, "maximum": 0.09034079046460113, "valid_count": 8, "planned_count": 8}}, "seconds": 8.109204478998436, "rtf_including_measurement": 1.3515340798330726}, {"case": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "whisper", "speaker": "jvs_jvs018", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.8279340267181396, "predicted_mos": 1.8279340267181396, "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": 3.79568769299658}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6372452691482853, "全帯域_10ms_rms_envelope_nrmse": 0.12173118268926661, "全帯域_10ms_envelope_correlation": 0.9886892503851505, "全帯域_10ms_modulation_mae_db": 0.6726912549506707, "全帯域_40ms_log_rms_mae_db": 0.8843192840771211, "全帯域_40ms_rms_envelope_nrmse": 0.06163244128666299, "全帯域_40ms_envelope_correlation": 0.9969337697055167, "全帯域_40ms_modulation_mae_db": 1.1001444423072728, "300–1000 Hz_10ms_log_rms_mae_db": 2.4311075316882236, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24832489819722905, "300–1000 Hz_10ms_envelope_correlation": 0.9595447724730569, "300–1000 Hz_10ms_modulation_mae_db": 0.3093569726129626, "300–1000 Hz_40ms_log_rms_mae_db": 1.7927030465180112, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14095486352061115, "300–1000 Hz_40ms_envelope_correlation": 0.9870934587949295, "300–1000 Hz_40ms_modulation_mae_db": 0.4460849436265934, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5956431500047696, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.183873917582355, "1000–3000 Hz_10ms_envelope_correlation": 0.9793399030507568, "1000–3000 Hz_10ms_modulation_mae_db": 0.7320573187459672, "1000–3000 Hz_40ms_log_rms_mae_db": 0.905472591318115, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0910181175526891, "1000–3000 Hz_40ms_envelope_correlation": 0.9952681147465839, "1000–3000 Hz_40ms_modulation_mae_db": 0.7968685691190295, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2947800063776302, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15126018401020896, "3000–6000 Hz_10ms_envelope_correlation": 0.98666809922525, "3000–6000 Hz_10ms_modulation_mae_db": 0.8367190881403643, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8959413768075092, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0859472790266767, "3000–6000 Hz_40ms_envelope_correlation": 0.9959386547796278, "3000–6000 Hz_40ms_modulation_mae_db": 1.685020735867968, "mr_stft_db": 6.038882086343409, "band_mae_db": 0.597820435709525, "rms_gain_error_db": -0.025136467348846957, "output_peak": 0.04170952340722672}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5790652628177297, "全帯域_10ms_rms_envelope_nrmse": 0.13443368429908956, "全帯域_10ms_envelope_correlation": 0.9861966030219507, "全帯域_10ms_modulation_mae_db": 0.6000749087864273, "全帯域_40ms_log_rms_mae_db": 0.8238585592638884, "全帯域_40ms_rms_envelope_nrmse": 0.06367300752412626, "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": 2.427891378720596, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24634536524656178, "300–1000 Hz_10ms_envelope_correlation": 0.9603536282914191, "300–1000 Hz_10ms_modulation_mae_db": 1.0039775771179602, "300–1000 Hz_40ms_log_rms_mae_db": 1.719866688900265, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14179983146652453, "300–1000 Hz_40ms_envelope_correlation": 0.9869477035822987, "300–1000 Hz_40ms_modulation_mae_db": 1.0927210871966544, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5766815533567902, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16277024794145087, "1000–3000 Hz_10ms_envelope_correlation": 0.9827301989964906, "1000–3000 Hz_10ms_modulation_mae_db": 0.5115939160301733, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9573644739080629, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08901928456822011, "1000–3000 Hz_40ms_envelope_correlation": 0.9949368309183648, "1000–3000 Hz_40ms_modulation_mae_db": 0.9446289925454071, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2692725190720022, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17993947537224136, "3000–6000 Hz_10ms_envelope_correlation": 0.9811231277236012, "3000–6000 Hz_10ms_modulation_mae_db": 1.242641821404823, "3000–6000 Hz_40ms_log_rms_mae_db": 0.811261608154835, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09635329878809029, "3000–6000 Hz_40ms_envelope_correlation": 0.9951407707554709, "3000–6000 Hz_40ms_modulation_mae_db": 1.935533819126042, "mr_stft_db": 6.036496231208797, "band_mae_db": 0.5593109633526566, "rms_gain_error_db": -0.14231887980989588, "output_peak": 0.03243966078625741}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6395869570430075, "全帯域_10ms_rms_envelope_nrmse": 0.14541860351467478, "全帯域_10ms_envelope_correlation": 0.9842456388997626, "全帯域_10ms_modulation_mae_db": 0.22896090815144907, "全帯域_40ms_log_rms_mae_db": 0.9073270886955219, "全帯域_40ms_rms_envelope_nrmse": 0.08630434293732618, "全帯域_40ms_envelope_correlation": 0.9942009769335143, "全帯域_40ms_modulation_mae_db": 0.5019298598941729, "300–1000 Hz_10ms_log_rms_mae_db": 2.35929375538427, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2674656285150553, "300–1000 Hz_10ms_envelope_correlation": 0.9500990423809138, "300–1000 Hz_10ms_modulation_mae_db": 0.47136211202045314, "300–1000 Hz_40ms_log_rms_mae_db": 1.7767787334636689, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17339960445363448, "300–1000 Hz_40ms_envelope_correlation": 0.9777126616087116, "300–1000 Hz_40ms_modulation_mae_db": 0.38572007250897206, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5361354337233122, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17922607591772496, "1000–3000 Hz_10ms_envelope_correlation": 0.9790016213363237, "1000–3000 Hz_10ms_modulation_mae_db": 0.11901157339682293, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8806424782218357, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08981514243356785, "1000–3000 Hz_40ms_envelope_correlation": 0.9946123519732899, "1000–3000 Hz_40ms_modulation_mae_db": 0.45169857511888806, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2495702125522303, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18435871599927028, "3000–6000 Hz_10ms_envelope_correlation": 0.9819712451312668, "3000–6000 Hz_10ms_modulation_mae_db": 0.5109660649011067, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8049039699444422, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11248996886078806, "3000–6000 Hz_40ms_envelope_correlation": 0.9937909293462766, "3000–6000 Hz_40ms_modulation_mae_db": 0.7074488167548453, "mr_stft_db": 6.038001627941855, "band_mae_db": 0.5683109249737491, "rms_gain_error_db": 0.10271157564986878, "output_peak": 0.03809881832744406}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5862549675760482, "全帯域_10ms_rms_envelope_nrmse": 0.13863870862549166, "全帯域_10ms_envelope_correlation": 0.9854760731224599, "全帯域_10ms_modulation_mae_db": 0.3853296090137199, "全帯域_40ms_log_rms_mae_db": 0.8530561446101476, "全帯域_40ms_rms_envelope_nrmse": 0.06749901960229707, "全帯域_40ms_envelope_correlation": 0.9963704309614192, "全帯域_40ms_modulation_mae_db": 0.6988316222984668, "300–1000 Hz_10ms_log_rms_mae_db": 2.429937186826575, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2746531546493096, "300–1000 Hz_10ms_envelope_correlation": 0.9490855864732491, "300–1000 Hz_10ms_modulation_mae_db": 0.2569507677005216, "300–1000 Hz_40ms_log_rms_mae_db": 1.8272623744580547, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.170374110398811, "300–1000 Hz_40ms_envelope_correlation": 0.9796565722633118, "300–1000 Hz_40ms_modulation_mae_db": 0.5456034379139586, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5462319259668944, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20941099741818803, "1000–3000 Hz_10ms_envelope_correlation": 0.973744888176874, "1000–3000 Hz_10ms_modulation_mae_db": 0.7385093578280862, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8922524756834852, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.1062972178979933, "1000–3000 Hz_40ms_envelope_correlation": 0.9938113237473278, "1000–3000 Hz_40ms_modulation_mae_db": 0.35684784567267774, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2458355399280845, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1491490430791642, "3000–6000 Hz_10ms_envelope_correlation": 0.9870334461906408, "3000–6000 Hz_10ms_modulation_mae_db": 0.52197773920634, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7818430771475071, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06523284378548071, "3000–6000 Hz_40ms_envelope_correlation": 0.9974689935366178, "3000–6000 Hz_40ms_modulation_mae_db": 1.0184533285320285, "mr_stft_db": 6.021958836694753, "band_mae_db": 0.5002836520499556, "rms_gain_error_db": 0.05088077398004688, "output_peak": 0.03324638718415392}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5713302871543653, "全帯域_10ms_rms_envelope_nrmse": 0.14484732857324928, "全帯域_10ms_envelope_correlation": 0.983942966068325, "全帯域_10ms_modulation_mae_db": 0.5845528147060888, "全帯域_40ms_log_rms_mae_db": 0.8100951721432064, "全帯域_40ms_rms_envelope_nrmse": 0.07036022717940843, "全帯域_40ms_envelope_correlation": 0.9960360707883198, "全帯域_40ms_modulation_mae_db": 0.9490419014943757, "300–1000 Hz_10ms_log_rms_mae_db": 2.3977541740399815, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2610897370235974, "300–1000 Hz_10ms_envelope_correlation": 0.9527937363643323, "300–1000 Hz_10ms_modulation_mae_db": 0.24444007636218604, "300–1000 Hz_40ms_log_rms_mae_db": 1.7300239266491226, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13730617828705036, "300–1000 Hz_40ms_envelope_correlation": 0.9862733630801077, "300–1000 Hz_40ms_modulation_mae_db": 0.48234560109232455, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5040802122930517, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17019927398615609, "1000–3000 Hz_10ms_envelope_correlation": 0.981203775007816, "1000–3000 Hz_10ms_modulation_mae_db": 0.6261662656516043, "1000–3000 Hz_40ms_log_rms_mae_db": 0.85950492566921, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08557590146302639, "1000–3000 Hz_40ms_envelope_correlation": 0.9951455157850824, "1000–3000 Hz_40ms_modulation_mae_db": 0.9414402009480213, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2731274086183317, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18260909513357898, "3000–6000 Hz_10ms_envelope_correlation": 0.9802065237281655, "3000–6000 Hz_10ms_modulation_mae_db": 0.8528253477837029, "3000–6000 Hz_40ms_log_rms_mae_db": 0.795947156307095, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09684310889146036, "3000–6000 Hz_40ms_envelope_correlation": 0.9943141349852516, "3000–6000 Hz_40ms_modulation_mae_db": 1.2132104959504204, "mr_stft_db": 6.040650905869218, "band_mae_db": 0.6017333093413707, "rms_gain_error_db": -0.047163770236387174, "output_peak": 0.0337998754075715}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.615293312981596, "全帯域_10ms_rms_envelope_nrmse": 0.13123582780358742, "全帯域_10ms_envelope_correlation": 0.9868202694080875, "全帯域_10ms_modulation_mae_db": 0.44709707368635687, "全帯域_40ms_log_rms_mae_db": 0.8688528275843227, "全帯域_40ms_rms_envelope_nrmse": 0.07288811677323762, "全帯域_40ms_envelope_correlation": 0.9957720248778584, "全帯域_40ms_modulation_mae_db": 0.7189990498827449, "300–1000 Hz_10ms_log_rms_mae_db": 2.4304987117770063, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25080755821022216, "300–1000 Hz_10ms_envelope_correlation": 0.9579158534073814, "300–1000 Hz_10ms_modulation_mae_db": 0.6015400322653023, "300–1000 Hz_40ms_log_rms_mae_db": 1.7080296637231176, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14596462257568185, "300–1000 Hz_40ms_envelope_correlation": 0.9854625637772289, "300–1000 Hz_40ms_modulation_mae_db": 0.7444767148158699, "1000–3000 Hz_10ms_log_rms_mae_db": 1.554207365971205, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1864005172537816, "1000–3000 Hz_10ms_envelope_correlation": 0.9773987646790759, "1000–3000 Hz_10ms_modulation_mae_db": 0.21136217919761258, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9405901860464042, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10060682308515538, "1000–3000 Hz_40ms_envelope_correlation": 0.9932086900475756, "1000–3000 Hz_40ms_modulation_mae_db": 0.6928567956920118, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2688513342308612, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1544769484400846, "3000–6000 Hz_10ms_envelope_correlation": 0.9862189732611824, "3000–6000 Hz_10ms_modulation_mae_db": 0.5075370878904515, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8059059884250058, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09619142341022746, "3000–6000 Hz_40ms_envelope_correlation": 0.9949560790847025, "3000–6000 Hz_40ms_modulation_mae_db": 0.9538877385344703, "mr_stft_db": 6.028013112066435, "band_mae_db": 0.39425544215155234, "rms_gain_error_db": -0.10630227664047168, "output_peak": 0.03271614405410099}}, {"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": 0.4665210395835853, "全帯域_40ms_log_rms_mae_db": 0.8138722552593574, "全帯域_40ms_rms_envelope_nrmse": 0.07747636650399665, "全帯域_40ms_envelope_correlation": 0.9951510351465332, "全帯域_40ms_modulation_mae_db": 0.8558927123001162, "300–1000 Hz_10ms_log_rms_mae_db": 2.3105186876604122, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.30685981925509187, "300–1000 Hz_10ms_envelope_correlation": 0.9355877538479115, "300–1000 Hz_10ms_modulation_mae_db": 0.22301601062306278, "300–1000 Hz_40ms_log_rms_mae_db": 1.6968186460166723, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19308597692699697, "300–1000 Hz_40ms_envelope_correlation": 0.9730789718876273, "300–1000 Hz_40ms_modulation_mae_db": 0.19441994547023977, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5448587720880451, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17044913106628362, "1000–3000 Hz_10ms_envelope_correlation": 0.9809788723606302, "1000–3000 Hz_10ms_modulation_mae_db": 0.4892299449785013, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9765856885780442, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10248110593208117, "1000–3000 Hz_40ms_envelope_correlation": 0.9929570461385219, "1000–3000 Hz_40ms_modulation_mae_db": 0.5845972848806372, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2349163635969262, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19183648039507006, "3000–6000 Hz_10ms_envelope_correlation": 0.9788468009378765, "3000–6000 Hz_10ms_modulation_mae_db": 0.677298257744424, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7887447490839778, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09776955683744055, "3000–6000 Hz_40ms_envelope_correlation": 0.9944575465826404, "3000–6000 Hz_40ms_modulation_mae_db": 0.9538544770985394, "mr_stft_db": 6.0342031247548675, "band_mae_db": 0.5420004941554193, "rms_gain_error_db": -0.052062455652493955, "output_peak": 0.03682187189337933}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.5458178098325375, "全帯域_10ms_rms_envelope_nrmse": 0.139335655197926, "全帯域_10ms_envelope_correlation": 0.9851534696110865, "全帯域_10ms_modulation_mae_db": 0.5920221158002082, "全帯域_40ms_log_rms_mae_db": 0.8324574325525403, "全帯域_40ms_rms_envelope_nrmse": 0.06452248265307609, "全帯域_40ms_envelope_correlation": 0.9966578424244745, "全帯域_40ms_modulation_mae_db": 0.6725502559725284, "300–1000 Hz_10ms_log_rms_mae_db": 2.4001338659143627, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.27757407194333816, "300–1000 Hz_10ms_envelope_correlation": 0.9514728358634543, "300–1000 Hz_10ms_modulation_mae_db": 0.807539456359519, "300–1000 Hz_40ms_log_rms_mae_db": 1.7543932104496422, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1611355641655958, "300–1000 Hz_40ms_envelope_correlation": 0.9844962447301553, "300–1000 Hz_40ms_modulation_mae_db": 0.7704852204882395, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5127782700000978, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16643623604008617, "1000–3000 Hz_10ms_envelope_correlation": 0.9819544750253049, "1000–3000 Hz_10ms_modulation_mae_db": 0.5069638340161721, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8920356382727938, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08263194699945556, "1000–3000 Hz_40ms_envelope_correlation": 0.9954973387884104, "1000–3000 Hz_40ms_modulation_mae_db": 0.5627998031518505, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2610246141484185, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15684047777901144, "3000–6000 Hz_10ms_envelope_correlation": 0.9854318142695729, "3000–6000 Hz_10ms_modulation_mae_db": 0.4530840060231762, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8298502056240166, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06994128691959915, "3000–6000 Hz_40ms_envelope_correlation": 0.997132427080072, "3000–6000 Hz_40ms_modulation_mae_db": 0.5846390912650818, "mr_stft_db": 6.021342176009587, "band_mae_db": 0.5855603870918635, "rms_gain_error_db": -0.029052862226222102, "output_peak": 0.03495121979802746}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.88519975673, "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": 1.3067880076125317e-07, "delta_db": -0.2502894018865869, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.81286342317638e-08, "output_power": 1.4105800645307407e-07, "delta_db": 3.1606805898113723, "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": 5.910179383134748e-07, "delta_db": 0.33572061886511967, "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": 0.597820435709525, "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}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.531331709966364, "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"}}, "level": {"reference": {"rms": 0.0026691563923850765, "rms_dbfs": -51.47251958187441, "peak": 0.036651611328125, "peak_dbfs": -28.71813855113624, "crest_factor_db": 22.754381030738173, "mean": -1.292758517795139e-07, "zero_energy": false}, "output": {"rms": 0.0026614431727847465, "rms_dbfs": -51.49765604922326, "peak": 0.04170952340722672, "peak_dbfs": -27.595295451606066, "crest_factor_db": 23.90236059761719, "mean": 2.3207000177787272e-07, "zero_energy": false}, "rms_difference_db": -0.025136467348851}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 361, "quiet_samples": 86640, "reference_mean_power": 1.2447742146757172e-07, "output_mean_power": 1.4839237682414303e-07, "output_rms_dbfs": -68.28588408950833, "output_zero_energy": false, "output_peak": 0.00966067713395061, "output_energy_fraction": 0.012604718396409746, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 0, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.6372452691482853, "rms_envelope_nrmse": 0.12173118268926661, "envelope_correlation": 0.9886892503851505, "rms_gain_error_db": -0.025137707970267282, "reference_mean_power": 7.130327548553108e-06, "output_mean_power": 7.08917520553976e-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": 1.290607416633775e-06, "reference_active": true, "delta_db": 0.04593675576928088}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.124025700263392e-07, "output_power": 2.214986437596337e-07, "reference_active": true, "delta_db": 0.18211304061001218}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.509706557401959e-07, "output_power": 9.997470804941732e-08, "reference_active": true, "delta_db": -1.7900239684727193}], "active_band_count": 3, "active_band_mae_db": 0.6726912549506707}}, {"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": 0.8843192840771211, "rms_envelope_nrmse": 0.06163244128666299, "envelope_correlation": 0.9969337697055167, "rms_gain_error_db": -0.025144793274276784, "reference_mean_power": 7.166117032249278e-06, "output_mean_power": 7.124746508261425e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.171922661595566e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0939532041259814e-06, "output_power": 1.1212496528732195e-06, "reference_active": true, "delta_db": 0.10703576955201564}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.164609293708589e-07, "output_power": 1.0706771345323817e-07, "reference_active": true, "delta_db": -0.3652172355672409}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0690330771826296e-08, "output_power": 5.574078887947957e-09, "reference_active": true, "delta_db": -2.828180321802562}], "active_band_count": 3, "active_band_mae_db": 1.1001444423072728}}]}, {"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": 6.5560927718001166e-06, "log_rms_mae_db": 2.4311075316882236, "rms_envelope_nrmse": 0.24832489819722905, "envelope_correlation": 0.9595447724730569, "rms_gain_error_db": 0.3845205715587109, "reference_mean_power": 7.945163829144028e-07, "output_mean_power": 8.680703326484401e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.079115524536589e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.4868570435085094e-07, "output_power": 1.6669115816852137e-07, "reference_active": true, "delta_db": 0.496433495517517}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.530749650867309e-08, "output_power": 3.710518778836011e-08, "reference_active": true, "delta_db": 0.21567709042129057}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.491869757314003e-08, "output_power": 2.6189148152798796e-08, "reference_active": true, "delta_db": 0.21596033190008018}], "active_band_count": 3, "active_band_mae_db": 0.3093569726129626}}, {"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": 4.158309417730709e-06, "log_rms_mae_db": 1.7927030465180112, "rms_envelope_nrmse": 0.14095486352061115, "envelope_correlation": 0.9870934587949295, "rms_gain_error_db": 0.3844971018649308, "reference_mean_power": 7.985041710031804e-07, "output_mean_power": 8.724225835592557e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.703673751837486e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.314092622690957e-07, "output_power": 1.517648499731943e-07, "reference_active": true, "delta_db": 0.6254521974296396}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9292191287469542e-08, "output_power": 1.896791823047438e-08, "reference_active": true, "delta_db": -0.07361890664942543}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4692549483461508e-09, "output_power": 1.7022193958045825e-09, "reference_active": true, "delta_db": 0.6391837268007152}], "active_band_count": 3, "active_band_mae_db": 0.4460849436265934}}]}, {"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": 1.5956431500047696, "rms_envelope_nrmse": 0.183873917582355, "envelope_correlation": 0.9793399030507568, "rms_gain_error_db": 0.2729960164792753, "reference_mean_power": 1.4849128654353035e-06, "output_mean_power": 1.5812501207507195e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.418114993045289e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.69138926350769e-07, "output_power": 2.726803443486657e-07, "reference_active": true, "delta_db": 0.05677318177605966}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.5217312260061476e-08, "output_power": 4.824142991286266e-08, "reference_active": true, "delta_db": 0.28115428050734914}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6338303134826183e-08, "output_power": 1.7169725121318745e-08, "reference_active": true, "delta_db": -1.8582444939544929}], "active_band_count": 3, "active_band_mae_db": 0.7320573187459672}}, {"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": 0.905472591318115, "rms_envelope_nrmse": 0.0910181175526891, "envelope_correlation": 0.9952681147465839, "rms_gain_error_db": 0.27299105147534986, "reference_mean_power": 1.4923708236731126e-06, "output_mean_power": 1.5891901149566645e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.994698288619124e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.5519066781428626e-07, "output_power": 2.5779376311060776e-07, "reference_active": true, "delta_db": 0.044076176916079776}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4359212852663977e-08, "output_power": 2.2828357259342045e-08, "reference_active": true, "delta_db": -0.2818858977505032}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5357702928828264e-09, "output_power": 9.546889575433475e-10, "reference_active": true, "delta_db": -2.064643632690505}], "active_band_count": 3, "active_band_mae_db": 0.7968685691190295}}]}, {"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": 1.0774952268311021e-05, "log_rms_mae_db": 1.2947800063776302, "rms_envelope_nrmse": 0.15126018401020896, "envelope_correlation": 0.98666809922525, "rms_gain_error_db": -0.26079927841580786, "reference_mean_power": 1.9952232017025357e-06, "output_mean_power": 1.8789341443284903e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.5794872115033738e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.151593028482198e-07, "output_power": 6.981887202962117e-07, "reference_active": true, "delta_db": -0.10429964130963826}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2474197679576507e-07, "output_power": 1.1752664879387198e-07, "reference_active": true, "delta_db": -0.2587626940136217}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.137663053230785e-08, "output_power": 4.963524965729768e-08, "reference_active": true, "delta_db": -2.147094929097833}], "active_band_count": 3, "active_band_mae_db": 0.8367190881403643}}, {"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": 7.143885674653837e-06, "log_rms_mae_db": 0.8959413768075092, "rms_envelope_nrmse": 0.0859472790266767, "envelope_correlation": 0.9959386547796278, "rms_gain_error_db": -0.2607993040357214, "reference_mean_power": 2.0052568878051227e-06, "output_mean_power": 1.888383018604231e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.5118360803946562e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.45069205976456e-07, "output_power": 6.360127446299475e-07, "reference_active": true, "delta_db": -0.06140491964803165}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.385509447185756e-08, "output_power": 6.62462971127065e-08, "reference_active": true, "delta_db": -1.023678444909452}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.7337556623287715e-09, "output_power": 2.2984830092250605e-09, "reference_active": true, "delta_db": -3.9699788430464205}], "active_band_count": 3, "active_band_mae_db": 1.685020735867968}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.979544062329159, "standard_deviation": 0.0029116398994481615, "minimum": 0.973744888176874, "maximum": 0.9827301989964906, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.5463270854255209, "standard_deviation": 0.030312474660189805, "minimum": 1.5040802122930517, "maximum": 1.5956431500047696, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.4918617987306175, "standard_deviation": 0.22516288635620407, "minimum": 0.11901157339682293, "maximum": 0.7385093578280862, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17859579965075328, "standard_deviation": 0.01499485022908497, "minimum": 0.16277024794145087, "maximum": 0.20941099741818803, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9944296515181446, "standard_deviation": 0.0009774377210996959, "minimum": 0.9929570461385219, "maximum": 0.9954973387884104, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.9130560572122439, "standard_deviation": 0.04072187524889999, "minimum": 0.85950492566921, "maximum": 0.9765856885780442, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6664672583910654, "standard_deviation": 0.21716497379037758, "minimum": 0.35684784567267774, "maximum": 0.9446289925454071, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09343069249152361, "standard_deviation": 0.008582525402599786, "minimum": 0.08263194699945556, "maximum": 0.1062972178979933, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9834375038084445, "standard_deviation": 0.003253600888478032, "minimum": 0.9788468009378765, "maximum": 0.9870334461906408, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2621722498155605, "standard_deviation": 0.018701432790287083, "minimum": 1.2349163635969262, "maximum": 1.2947800063776302, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7003811766367986, "standard_deviation": 0.26791717367164225, "minimum": 0.4530840060231762, "maximum": 1.242641821404823, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16880880252607872, "standard_deviation": 0.01744180816004328, "minimum": 0.1491490430791642, "maximum": 0.19183648039507006, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9953999420188324, "standard_deviation": 0.0013359256828203631, "minimum": 0.9937909293462766, "maximum": 0.9974689935366178, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8142997664367986, "standard_deviation": 0.03609204403766858, "minimum": 0.7818430771475071, "maximum": 0.8959413768075092, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.1315060628911744, "standard_deviation": 0.4651101327124327, "minimum": 0.5846390912650818, "maximum": 1.935533819126042, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09009609581497041, "standard_deviation": 0.015692608136516756, "minimum": 0.06523284378548071, "maximum": 0.11248996886078806, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9521066511377149, "standard_deviation": 0.00796411785440307, "minimum": 0.9355877538479115, "maximum": 0.9603536282914191, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.3983919115014283, "standard_deviation": 0.0434581765837948, "minimum": 2.3105186876604122, "maximum": 2.4311075316882236, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.48977287563274596, "standard_deviation": 0.29186992401385353, "minimum": 0.22301601062306278, "maximum": 1.0039775771179602, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2666400291300507, "standard_deviation": 0.020109936726480857, "minimum": 0.24634536524656178, "maximum": 0.30685981925509187, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9825901924655464, "standard_deviation": 0.005176545460904912, "minimum": 0.9730789718876273, "maximum": 0.9870934587949295, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.7507345362723195, "standard_deviation": 0.045390267502365335, "minimum": 1.6968186460166723, "maximum": 1.8272623744580547, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5827321278891066, "standard_deviation": 0.2780621261837302, "minimum": 0.19441994547023977, "maximum": 1.0927210871966544, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15800259397436325, "standard_deviation": 0.019846520444098736, "minimum": 0.13730617828705036, "maximum": 0.19308597692699697, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.5436594511032615, "standard_deviation": 0.06878549335547338, "minimum": 0.39425544215155234, "maximum": 0.6017333093413707, "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": 0.003216906412243882, "minimum": 0.03243966078625741, "maximum": 0.04170952340722672, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.03105554528555026, "standard_deviation": 0.07872974992657703, "minimum": -0.14231887980989588, "maximum": 0.10271157564986878, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.985467320825631, "standard_deviation": 0.0017620611422904376, "minimum": 0.9832142960882263, "maximum": 0.9886892503851505, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.5927761709910988, "standard_deviation": 0.034235236805303014, "minimum": 1.5458178098325375, "maximum": 1.6395869570430075, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.49715621558481327, "standard_deviation": 0.14438087357495114, "minimum": 0.22896090815144907, "maximum": 0.6726912549506707, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.1379699628352811, "standard_deviation": 0.008698453674963545, "minimum": 0.12173118268926661, "maximum": 0.1481187119789634, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9960021288979626, "standard_deviation": 0.0009451511795877027, "minimum": 0.9942009769335143, "maximum": 0.9969337697055167, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8492298455232632, "standard_deviation": 0.03528042396299779, "minimum": 0.8100951721432064, "maximum": 0.9073270886955219, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7822445623286476, "standard_deviation": 0.18374771305983212, "minimum": 0.5019298598941729, "maximum": 1.1001444423072728, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0705445005575164, "standard_deviation": 0.008230012687249625, "minimum": 0.06163244128666299, "maximum": 0.08630434293732618, "valid_count": 8, "planned_count": 8}}, "seconds": 7.498832580000453, "rtf_including_measurement": 1.2498054300000756}, {"case": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "whisper", "speaker": "jvs_jvs018", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.1754355430603027, "predicted_mos": 2.1754355430603027, "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": "c99bc4c845889649af0629991647d1bea640fe464c1adc93074ad26569e72691", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 4.136045726998418}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 2.7817463965723994, "全帯域_10ms_rms_envelope_nrmse": 0.22103386018404503, "全帯域_10ms_envelope_correlation": 0.9705789219695965, "全帯域_10ms_modulation_mae_db": 0.6339411125396719, "全帯域_40ms_log_rms_mae_db": 2.2641415589629243, "全帯域_40ms_rms_envelope_nrmse": 0.1492359417247092, "全帯域_40ms_envelope_correlation": 0.9883886794723451, "全帯域_40ms_modulation_mae_db": 0.6938273755927513, "300–1000 Hz_10ms_log_rms_mae_db": 3.4451682603730336, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.36120671191487497, "300–1000 Hz_10ms_envelope_correlation": 0.9347618121576037, "300–1000 Hz_10ms_modulation_mae_db": 0.7697576279607441, "300–1000 Hz_40ms_log_rms_mae_db": 3.04734991675588, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2711679343598602, "300–1000 Hz_40ms_envelope_correlation": 0.9673678940190074, "300–1000 Hz_40ms_modulation_mae_db": 0.9770358732805503, "1000–3000 Hz_10ms_log_rms_mae_db": 1.709665600285926, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2914512954801079, "1000–3000 Hz_10ms_envelope_correlation": 0.9662589868975582, "1000–3000 Hz_10ms_modulation_mae_db": 1.8056004694882386, "1000–3000 Hz_40ms_log_rms_mae_db": 1.148744043793385, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.20226847438295883, "1000–3000 Hz_40ms_envelope_correlation": 0.9904899075821301, "1000–3000 Hz_40ms_modulation_mae_db": 1.8064008338140107, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3428243189099311, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2538155677637981, "3000–6000 Hz_10ms_envelope_correlation": 0.9688360986255782, "3000–6000 Hz_10ms_modulation_mae_db": 0.7500871517142915, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9581723483707866, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.17312446184632999, "3000–6000 Hz_40ms_envelope_correlation": 0.9870921241979602, "3000–6000 Hz_40ms_modulation_mae_db": 0.702951335759915, "mr_stft_db": 6.236022559185845, "band_mae_db": 2.0572122609384045, "rms_gain_error_db": 0.6669951161233235, "output_peak": 0.03716772868037832}}], "planned_noise_seeds": [0], "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": 6.3233503704893845, "spectral_convergence": 0.6745268031877393, "spectral_convergence_status": "ok", "amplitude_floor": 9.167242110941195e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.190922397696387, "spectral_convergence": 0.6802992977557909, "spectral_convergence_status": "ok", "amplitude_floor": 5.84028801806317e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.193794909371765, "spectral_convergence": 0.6984597409379842, "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": 2.0632780850299794e-08, "delta_db": -8.266763151193278, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.81286342317638e-08, "output_power": 1.3016278182537302e-07, "delta_db": 2.811571389576943, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 9.335883160942139e-07, "output_power": 1.2070175754598215e-06, "delta_db": 1.1155818607946262, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.7505166473017637e-06, "output_power": 2.1683717855095614e-06, "delta_db": 0.9296750244473586, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.470519881244434e-07, "output_power": 6.26121390515231e-07, "delta_db": 0.5862994036231142, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.7292398267785066e-06, "output_power": 3.1978532592814126e-06, "delta_db": 0.6881683113290906, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.57439203602588e-07, "output_power": 9.569043695137953e-07, "delta_db": -0.002426685604420532, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 2.0572122609384045, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.6669951161233235, "pitch": null, "output_rms_dbfs": -50.805524465751084, "output_peak": 0.03716772868037832, "reference_rms_dbfs": -51.47251958187441, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.236022559185845}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.5012954390849118, "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"}}, "level": {"reference": {"rms": 0.0026691563923850765, "rms_dbfs": -51.47251958187441, "peak": 0.036651611328125, "peak_dbfs": -28.71813855113624, "crest_factor_db": 22.754381030738173, "mean": -1.292758517795139e-07, "zero_energy": false}, "output": {"rms": 0.0028821977626380005, "rms_dbfs": -50.805524465751084, "peak": 0.03716772868037832, "peak_dbfs": -28.596679556518538, "crest_factor_db": 22.208844909232553, "mean": 1.4449699180898777e-09, "zero_energy": false}, "rms_difference_db": 0.6669951161233243}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 361, "quiet_samples": 86640, "reference_mean_power": 1.2447742146757172e-07, "output_mean_power": 1.3956070792161476e-07, "output_rms_dbfs": -68.55236836259817, "output_zero_energy": false, "output_peak": 0.007288791587930656, "output_energy_fraction": 0.01010814729601848, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 0, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 2.7817463965723994, "rms_envelope_nrmse": 0.22103386018404503, "envelope_correlation": 0.9705789219695965, "rms_gain_error_db": 0.6669985656096982, "reference_mean_power": 7.130327548553108e-06, "output_mean_power": 8.313986925839702e-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": 1.5848094391511978e-06, "reference_active": true, "delta_db": 0.9377656827545887}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.124025700263392e-07, "output_power": 2.1517923473558895e-07, "reference_active": true, "delta_db": 0.0564059134091667}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.509706557401959e-07, "output_power": 1.8606201312307247e-07, "reference_active": true, "delta_db": 0.9076517414552603}], "active_band_count": 3, "active_band_mae_db": 0.6339411125396719}}, {"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": 2.2641415589629243, "rms_envelope_nrmse": 0.1492359417247092, "envelope_correlation": 0.9883886794723451, "rms_gain_error_db": 0.6670214308708156, "reference_mean_power": 7.166117032249278e-06, "output_mean_power": 8.35576158164227e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.171922661595566e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0939532041259814e-06, "output_power": 1.3999952015083943e-06, "reference_active": true, "delta_db": 1.0712780248986677}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.164609293708589e-07, "output_power": 1.0475199667095335e-07, "reference_active": true, "delta_db": -0.4601794172701967}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0690330771826296e-08, "output_power": 9.418650344333922e-09, "reference_active": true, "delta_db": -0.5500246846093895}], "active_band_count": 3, "active_band_mae_db": 0.6938273755927513}}]}, {"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": 6.5560927718001166e-06, "log_rms_mae_db": 3.4451682603730336, "rms_envelope_nrmse": 0.36120671191487497, "envelope_correlation": 0.9347618121576037, "rms_gain_error_db": 1.2326719629885934, "reference_mean_power": 7.945163829144028e-07, "output_mean_power": 1.0552856998831574e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.079115524536589e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.4868570435085094e-07, "output_power": 1.623275093129391e-07, "reference_active": true, "delta_db": 0.38122910545422584}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.530749650867309e-08, "output_power": 4.484016785763688e-08, "reference_active": true, "delta_db": 1.0380030485144307}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.491869757314003e-08, "output_power": 3.058647384176594e-08, "reference_active": true, "delta_db": 0.8900407299135757}], "active_band_count": 3, "active_band_mae_db": 0.7697576279607441}}, {"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": 4.158309417730709e-06, "log_rms_mae_db": 3.04734991675588, "rms_envelope_nrmse": 0.2711679343598602, "envelope_correlation": 0.9673678940190074, "rms_gain_error_db": 1.2326586937390154, "reference_mean_power": 7.985041710031804e-07, "output_mean_power": 1.060579084942824e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.703673751837486e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.314092622690957e-07, "output_power": 1.4740535371853977e-07, "reference_active": true, "delta_db": 0.49887280079188423}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9292191287469542e-08, "output_power": 2.3691803545693884e-08, "reference_active": true, "delta_db": 0.8921656335730921}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4692549483461508e-09, "output_power": 2.0946143793821277e-09, "reference_active": true, "delta_db": 1.5400691854766744}], "active_band_count": 3, "active_band_mae_db": 0.9770358732805503}}]}, {"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": 1.709665600285926, "rms_envelope_nrmse": 0.2914512954801079, "envelope_correlation": 0.9662589868975582, "rms_gain_error_db": 1.2561847594446938, "reference_mean_power": 1.4849128654353035e-06, "output_mean_power": 1.982985077257941e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.418114993045289e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.69138926350769e-07, "output_power": 3.711100637484704e-07, "reference_active": true, "delta_db": 1.3952621610071452}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.5217312260061476e-08, "output_power": 6.39578953231748e-08, "reference_active": true, "delta_db": 1.505894197906859}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6338303134826183e-08, "output_power": 4.7005891817248515e-08, "reference_active": true, "delta_db": 2.515645049550712}], "active_band_count": 3, "active_band_mae_db": 1.8056004694882386}}, {"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": 1.148744043793385, "rms_envelope_nrmse": 0.20226847438295883, "envelope_correlation": 0.9904899075821301, "rms_gain_error_db": 1.2561883380109893, "reference_mean_power": 1.4923708236731126e-06, "output_mean_power": 1.992946239779692e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.994698288619124e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.5519066781428626e-07, "output_power": 3.618835561914113e-07, "reference_active": true, "delta_db": 1.5170406100806755}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4359212852663977e-08, "output_power": 3.3237259043290016e-08, "reference_active": true, "delta_db": 1.3496195156221378}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5357702928828264e-09, "output_power": 2.7642702525132953e-09, "reference_active": true, "delta_db": 2.552542375739219}], "active_band_count": 3, "active_band_mae_db": 1.8064008338140107}}]}, {"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": 1.0774952268311021e-05, "log_rms_mae_db": 1.3428243189099311, "rms_envelope_nrmse": 0.2538155677637981, "envelope_correlation": 0.9688360986255782, "rms_gain_error_db": 0.6925943538804373, "reference_mean_power": 1.9952232017025357e-06, "output_mean_power": 2.3401889362796667e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.5794872115033738e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.151593028482198e-07, "output_power": 8.918391361356011e-07, "reference_active": true, "delta_db": 0.9588373401245788}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2474197679576507e-07, "output_power": 1.1529596277265891e-07, "reference_active": true, "delta_db": -0.34198521852620056}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.137663053230785e-08, "output_power": 1.0126132206189934e-07, "reference_active": true, "delta_db": 0.9494388964920951}], "active_band_count": 3, "active_band_mae_db": 0.7500871517142915}}, {"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": 7.143885674653837e-06, "log_rms_mae_db": 0.9581723483707866, "rms_envelope_nrmse": 0.17312446184632999, "envelope_correlation": 0.9870921241979602, "rms_gain_error_db": 0.6925948761156218, "reference_mean_power": 2.0052568878051227e-06, "output_mean_power": 2.351957687504039e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.5118360803946562e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.45069205976456e-07, "output_power": 8.300282544370125e-07, "reference_active": true, "delta_db": 1.0948656592157742}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.385509447185756e-08, "output_power": 6.812922647196001e-08, "reference_active": true, "delta_db": -0.9019599449774663}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.7337556623287715e-09, "output_power": 5.587741952028211e-09, "reference_active": true, "delta_db": -0.11202840308650416}], "active_band_count": 3, "active_band_mae_db": 0.702951335759915}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1234628, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9662589868975582, "standard_deviation": null, "minimum": 0.9662589868975582, "maximum": 0.9662589868975582, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.709665600285926, "standard_deviation": null, "minimum": 1.709665600285926, "maximum": 1.709665600285926, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 1.8056004694882386, "standard_deviation": null, "minimum": 1.8056004694882386, "maximum": 1.8056004694882386, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2914512954801079, "standard_deviation": null, "minimum": 0.2914512954801079, "maximum": 0.2914512954801079, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9904899075821301, "standard_deviation": null, "minimum": 0.9904899075821301, "maximum": 0.9904899075821301, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.148744043793385, "standard_deviation": null, "minimum": 1.148744043793385, "maximum": 1.148744043793385, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.8064008338140107, "standard_deviation": null, "minimum": 1.8064008338140107, "maximum": 1.8064008338140107, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.20226847438295883, "standard_deviation": null, "minimum": 0.20226847438295883, "maximum": 0.20226847438295883, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9688360986255782, "standard_deviation": null, "minimum": 0.9688360986255782, "maximum": 0.9688360986255782, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.3428243189099311, "standard_deviation": null, "minimum": 1.3428243189099311, "maximum": 1.3428243189099311, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7500871517142915, "standard_deviation": null, "minimum": 0.7500871517142915, "maximum": 0.7500871517142915, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2538155677637981, "standard_deviation": null, "minimum": 0.2538155677637981, "maximum": 0.2538155677637981, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9870921241979602, "standard_deviation": null, "minimum": 0.9870921241979602, "maximum": 0.9870921241979602, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9581723483707866, "standard_deviation": null, "minimum": 0.9581723483707866, "maximum": 0.9581723483707866, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.702951335759915, "standard_deviation": null, "minimum": 0.702951335759915, "maximum": 0.702951335759915, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.17312446184632999, "standard_deviation": null, "minimum": 0.17312446184632999, "maximum": 0.17312446184632999, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9347618121576037, "standard_deviation": null, "minimum": 0.9347618121576037, "maximum": 0.9347618121576037, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 3.4451682603730336, "standard_deviation": null, "minimum": 3.4451682603730336, "maximum": 3.4451682603730336, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7697576279607441, "standard_deviation": null, "minimum": 0.7697576279607441, "maximum": 0.7697576279607441, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.36120671191487497, "standard_deviation": null, "minimum": 0.36120671191487497, "maximum": 0.36120671191487497, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9673678940190074, "standard_deviation": null, "minimum": 0.9673678940190074, "maximum": 0.9673678940190074, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 3.04734991675588, "standard_deviation": null, "minimum": 3.04734991675588, "maximum": 3.04734991675588, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.9770358732805503, "standard_deviation": null, "minimum": 0.9770358732805503, "maximum": 0.9770358732805503, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.2711679343598602, "standard_deviation": null, "minimum": 0.2711679343598602, "maximum": 0.2711679343598602, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 2.0572122609384045, "standard_deviation": null, "minimum": 2.0572122609384045, "maximum": 2.0572122609384045, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 6.236022559185845, "standard_deviation": null, "minimum": 6.236022559185845, "maximum": 6.236022559185845, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.03716772868037832, "standard_deviation": null, "minimum": 0.03716772868037832, "maximum": 0.03716772868037832, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 0.6669951161233235, "standard_deviation": null, "minimum": 0.6669951161233235, "maximum": 0.6669951161233235, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9705789219695965, "standard_deviation": null, "minimum": 0.9705789219695965, "maximum": 0.9705789219695965, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 2.7817463965723994, "standard_deviation": null, "minimum": 2.7817463965723994, "maximum": 2.7817463965723994, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 0.6339411125396719, "standard_deviation": null, "minimum": 0.6339411125396719, "maximum": 0.6339411125396719, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.22103386018404503, "standard_deviation": null, "minimum": 0.22103386018404503, "maximum": 0.22103386018404503, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9883886794723451, "standard_deviation": null, "minimum": 0.9883886794723451, "maximum": 0.9883886794723451, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 2.2641415589629243, "standard_deviation": null, "minimum": 2.2641415589629243, "maximum": 2.2641415589629243, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6938273755927513, "standard_deviation": null, "minimum": 0.6938273755927513, "maximum": 0.6938273755927513, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.1492359417247092, "standard_deviation": null, "minimum": 0.1492359417247092, "maximum": 0.1492359417247092, "valid_count": 1, "planned_count": 1}}, "seconds": 2.4117845489963656, "rtf_including_measurement": 0.40196409149939427}, {"case": "jvs_jvs066_falset10_BASIC5000_1205", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs066", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.738166570663452, "predicted_mos": 2.738166570663452, "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": "bfebc5175e804b8635bcd9fdfda46f5b1e2448486e36f6f25b984924df4d9273", "internal_samples": 65179, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 4.279942047003715}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8027931544835808, "全帯域_10ms_rms_envelope_nrmse": 0.07000670587260102, "全帯域_10ms_envelope_correlation": 0.9964258563836245, "全帯域_10ms_modulation_mae_db": 1.1828467701463832, "全帯域_40ms_log_rms_mae_db": 0.44990238295889434, "全帯域_40ms_rms_envelope_nrmse": 0.04045168176953702, "全帯域_40ms_envelope_correlation": 0.9987384363063, "全帯域_40ms_modulation_mae_db": 1.309851332076917, "300–1000 Hz_10ms_log_rms_mae_db": 0.9667729963534121, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0697752073894011, "300–1000 Hz_10ms_envelope_correlation": 0.9965523472915018, "300–1000 Hz_10ms_modulation_mae_db": 0.972021869940434, "300–1000 Hz_40ms_log_rms_mae_db": 0.614229207481633, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04198953994933963, "300–1000 Hz_40ms_envelope_correlation": 0.9986754377825061, "300–1000 Hz_40ms_modulation_mae_db": 1.038844692264634, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0350266377874058, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12262279174517116, "1000–3000 Hz_10ms_envelope_correlation": 0.9911136864661153, "1000–3000 Hz_10ms_modulation_mae_db": 1.1104496171186427, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5997305126256481, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06202793669208283, "1000–3000 Hz_40ms_envelope_correlation": 0.9976514262514213, "1000–3000 Hz_40ms_modulation_mae_db": 1.448794219361064, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7162912666127252, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1560903346977762, "3000–6000 Hz_10ms_envelope_correlation": 0.9841395662262037, "3000–6000 Hz_10ms_modulation_mae_db": 0.6456549411747614, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0200485203667449, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09425431443366104, "3000–6000 Hz_40ms_envelope_correlation": 0.9954576936105128, "3000–6000 Hz_40ms_modulation_mae_db": 0.5337248044579265, "mr_stft_db": 5.168269326194313, "band_mae_db": 1.4495067967508153, "rms_gain_error_db": -0.024821969812647462, "output_peak": 0.6613258400199898}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8116765681435627, "全帯域_10ms_rms_envelope_nrmse": 0.07829381407282618, "全帯域_10ms_envelope_correlation": 0.9955394894889356, "全帯域_10ms_modulation_mae_db": 0.6937622115441294, "全帯域_40ms_log_rms_mae_db": 0.43994706892902286, "全帯域_40ms_rms_envelope_nrmse": 0.042458831761479424, "全帯域_40ms_envelope_correlation": 0.9986502548965398, "全帯域_40ms_modulation_mae_db": 0.6454224697720948, "300–1000 Hz_10ms_log_rms_mae_db": 0.993191088240309, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08983630132658889, "300–1000 Hz_10ms_envelope_correlation": 0.9942816001744031, "300–1000 Hz_10ms_modulation_mae_db": 0.5261221030297145, "300–1000 Hz_40ms_log_rms_mae_db": 0.6434517494960273, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.051454829749756854, "300–1000 Hz_40ms_envelope_correlation": 0.9980442948393927, "300–1000 Hz_40ms_modulation_mae_db": 0.45463720779741107, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0197420062402947, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.104231168267522, "1000–3000 Hz_10ms_envelope_correlation": 0.9935704533477622, "1000–3000 Hz_10ms_modulation_mae_db": 1.073430943744411, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5728128489612715, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04965447217681477, "1000–3000 Hz_40ms_envelope_correlation": 0.9985220650703376, "1000–3000 Hz_40ms_modulation_mae_db": 1.8130944479933884, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6849077816502676, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13649294266564974, "3000–6000 Hz_10ms_envelope_correlation": 0.9867541318843899, "3000–6000 Hz_10ms_modulation_mae_db": 0.7643301428546202, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9395282279326995, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07286610429239294, "3000–6000 Hz_40ms_envelope_correlation": 0.9960592161964119, "3000–6000 Hz_40ms_modulation_mae_db": 0.9170753879607849, "mr_stft_db": 5.165299292362742, "band_mae_db": 1.543106010681131, "rms_gain_error_db": -0.07253444109812987, "output_peak": 0.6724670207324631}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8413191644214923, "全帯域_10ms_rms_envelope_nrmse": 0.06286686980256206, "全帯域_10ms_envelope_correlation": 0.997116452971075, "全帯域_10ms_modulation_mae_db": 0.30473167838761167, "全帯域_40ms_log_rms_mae_db": 0.45666741352919465, "全帯域_40ms_rms_envelope_nrmse": 0.0373129420957188, "全帯域_40ms_envelope_correlation": 0.9989335830686561, "全帯域_40ms_modulation_mae_db": 0.37112919612215967, "300–1000 Hz_10ms_log_rms_mae_db": 0.9256659738594619, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06983284628174027, "300–1000 Hz_10ms_envelope_correlation": 0.9965425069695938, "300–1000 Hz_10ms_modulation_mae_db": 0.38755692539630066, "300–1000 Hz_40ms_log_rms_mae_db": 0.5756903627880344, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04106608916363359, "300–1000 Hz_40ms_envelope_correlation": 0.9987330071536068, "300–1000 Hz_40ms_modulation_mae_db": 0.5828234513961337, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0528754303031072, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08964529606250109, "1000–3000 Hz_10ms_envelope_correlation": 0.9952860660633484, "1000–3000 Hz_10ms_modulation_mae_db": 0.4543971406970251, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6372146164259022, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05656122521738324, "1000–3000 Hz_40ms_envelope_correlation": 0.9981184116040698, "1000–3000 Hz_40ms_modulation_mae_db": 0.2509454643357641, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6887233418974, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15555954789390136, "3000–6000 Hz_10ms_envelope_correlation": 0.9829217288955605, "3000–6000 Hz_10ms_modulation_mae_db": 0.8341137014696612, "3000–6000 Hz_40ms_log_rms_mae_db": 0.962728402041744, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08390067747527741, "3000–6000 Hz_40ms_envelope_correlation": 0.9950991819501173, "3000–6000 Hz_40ms_modulation_mae_db": 0.9170731579860636, "mr_stft_db": 5.164872102163891, "band_mae_db": 1.4790033374159477, "rms_gain_error_db": -0.03515630486601371, "output_peak": 0.6323779588637083}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7715820818561462, "全帯域_10ms_rms_envelope_nrmse": 0.07355303596948691, "全帯域_10ms_envelope_correlation": 0.9960677503508714, "全帯域_10ms_modulation_mae_db": 1.1434094999455764, "全帯域_40ms_log_rms_mae_db": 0.43070314370780227, "全帯域_40ms_rms_envelope_nrmse": 0.04643527422822473, "全帯域_40ms_envelope_correlation": 0.9983740491559707, "全帯域_40ms_modulation_mae_db": 1.096744109351057, "300–1000 Hz_10ms_log_rms_mae_db": 0.934664858343688, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08372546235935364, "300–1000 Hz_10ms_envelope_correlation": 0.9950259193319988, "300–1000 Hz_10ms_modulation_mae_db": 1.2070455317555366, "300–1000 Hz_40ms_log_rms_mae_db": 0.5893110503006651, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05541436409927082, "300–1000 Hz_40ms_envelope_correlation": 0.9977027151411338, "300–1000 Hz_40ms_modulation_mae_db": 1.2065138244574862, "1000–3000 Hz_10ms_log_rms_mae_db": 1.051736888661159, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11494683590079349, "1000–3000 Hz_10ms_envelope_correlation": 0.9923816664880807, "1000–3000 Hz_10ms_modulation_mae_db": 1.2667409488732273, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6190071952317547, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07024936773384306, "1000–3000 Hz_40ms_envelope_correlation": 0.9973093588724028, "1000–3000 Hz_40ms_modulation_mae_db": 0.9627362808102985, "3000–6000 Hz_10ms_log_rms_mae_db": 1.694567992430183, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17668387921205364, "3000–6000 Hz_10ms_envelope_correlation": 0.978424899952215, "3000–6000 Hz_10ms_modulation_mae_db": 1.2567363439924704, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9452355552711875, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10190174980490545, "3000–6000 Hz_40ms_envelope_correlation": 0.9934754215907357, "3000–6000 Hz_40ms_modulation_mae_db": 1.3024548520856978, "mr_stft_db": 5.151570099717543, "band_mae_db": 1.532399550539014, "rms_gain_error_db": -0.07049432945645034, "output_peak": 0.6292725725039428}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8097870466480985, "全帯域_10ms_rms_envelope_nrmse": 0.07842055739846183, "全帯域_10ms_envelope_correlation": 0.9955063092934744, "全帯域_10ms_modulation_mae_db": 0.8552260686510351, "全帯域_40ms_log_rms_mae_db": 0.46084583583065064, "全帯域_40ms_rms_envelope_nrmse": 0.0470081947681646, "全帯域_40ms_envelope_correlation": 0.9982915340120083, "全帯域_40ms_modulation_mae_db": 0.8109673392233677, "300–1000 Hz_10ms_log_rms_mae_db": 0.9703484177469061, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08811652836524586, "300–1000 Hz_10ms_envelope_correlation": 0.9945024547287374, "300–1000 Hz_10ms_modulation_mae_db": 0.9654881320561514, "300–1000 Hz_40ms_log_rms_mae_db": 0.637554555839954, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05831721141455655, "300–1000 Hz_40ms_envelope_correlation": 0.997445974290614, "300–1000 Hz_40ms_modulation_mae_db": 0.9195899483316001, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0397887158623176, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10128887902125247, "1000–3000 Hz_10ms_envelope_correlation": 0.9939523554836397, "1000–3000 Hz_10ms_modulation_mae_db": 0.6028364093656068, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5955792140165392, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05160109021035196, "1000–3000 Hz_40ms_envelope_correlation": 0.998445839718941, "1000–3000 Hz_40ms_modulation_mae_db": 0.492874837979479, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6603303016435234, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1581478956973624, "3000–6000 Hz_10ms_envelope_correlation": 0.9824680349841647, "3000–6000 Hz_10ms_modulation_mae_db": 0.6973546690947847, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9450365272428068, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08042641742226495, "3000–6000 Hz_40ms_envelope_correlation": 0.9957813593960555, "3000–6000 Hz_40ms_modulation_mae_db": 0.541484001775019, "mr_stft_db": 5.159379877913337, "band_mae_db": 1.4633663890727768, "rms_gain_error_db": -0.015903046962667963, "output_peak": 0.6612511325417624}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8184060745209462, "全帯域_10ms_rms_envelope_nrmse": 0.06289115478152658, "全帯域_10ms_envelope_correlation": 0.9971148828687881, "全帯域_10ms_modulation_mae_db": 0.6198651336461151, "全帯域_40ms_log_rms_mae_db": 0.47273394009606867, "全帯域_40ms_rms_envelope_nrmse": 0.03728053458526622, "全帯域_40ms_envelope_correlation": 0.9989386662761972, "全帯域_40ms_modulation_mae_db": 0.7633719698370326, "300–1000 Hz_10ms_log_rms_mae_db": 0.9262597994892928, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07280656346315663, "300–1000 Hz_10ms_envelope_correlation": 0.9962458312638401, "300–1000 Hz_10ms_modulation_mae_db": 0.6706475907312878, "300–1000 Hz_40ms_log_rms_mae_db": 0.5780711431589965, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04499212866121635, "300–1000 Hz_40ms_envelope_correlation": 0.9984979111249463, "300–1000 Hz_40ms_modulation_mae_db": 0.9541858482268828, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9972648689882153, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07648561049976459, "1000–3000 Hz_10ms_envelope_correlation": 0.9965489142335534, "1000–3000 Hz_10ms_modulation_mae_db": 0.40298451128292984, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5930311781145803, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04729651753173657, "1000–3000 Hz_40ms_envelope_correlation": 0.9986534648468345, "1000–3000 Hz_40ms_modulation_mae_db": 0.5414816669418779, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6551862901332088, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14687816946789498, "3000–6000 Hz_10ms_envelope_correlation": 0.9846734610347234, "3000–6000 Hz_10ms_modulation_mae_db": 0.21903289774511184, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9037420813027688, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08821536183628315, "3000–6000 Hz_40ms_envelope_correlation": 0.994103775644825, "3000–6000 Hz_40ms_modulation_mae_db": 0.21549441453788418, "mr_stft_db": 5.151006639334992, "band_mae_db": 1.4768910227692142, "rms_gain_error_db": -0.036182817773737413, "output_peak": 0.6675695740473431}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.842959727497172, "全帯域_10ms_rms_envelope_nrmse": 0.07772880839280157, "全帯域_10ms_envelope_correlation": 0.9956025735457661, "全帯域_10ms_modulation_mae_db": 0.8948453500916966, "全帯域_40ms_log_rms_mae_db": 0.4934031901898213, "全帯域_40ms_rms_envelope_nrmse": 0.04474373740778811, "全帯域_40ms_envelope_correlation": 0.9984812480036268, "全帯域_40ms_modulation_mae_db": 1.1461270909960308, "300–1000 Hz_10ms_log_rms_mae_db": 1.0000804166834332, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08738126406637432, "300–1000 Hz_10ms_envelope_correlation": 0.9945870644354282, "300–1000 Hz_10ms_modulation_mae_db": 0.6869911748324419, "300–1000 Hz_40ms_log_rms_mae_db": 0.6379941440948438, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04889006587335722, "300–1000 Hz_40ms_envelope_correlation": 0.998206528233491, "300–1000 Hz_40ms_modulation_mae_db": 0.9222441939813321, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0662367130834172, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09562492521695416, "1000–3000 Hz_10ms_envelope_correlation": 0.9947240121691294, "1000–3000 Hz_10ms_modulation_mae_db": 0.7076430572892775, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6360279173844657, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0518005073337939, "1000–3000 Hz_40ms_envelope_correlation": 0.9985728292591818, "1000–3000 Hz_40ms_modulation_mae_db": 0.5023610459489394, "3000–6000 Hz_10ms_log_rms_mae_db": 1.706415526259582, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16512622166828883, "3000–6000 Hz_10ms_envelope_correlation": 0.9808148400197778, "3000–6000 Hz_10ms_modulation_mae_db": 0.748937230413033, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9674732986833957, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09038612464305651, "3000–6000 Hz_40ms_envelope_correlation": 0.9944515427134183, "3000–6000 Hz_40ms_modulation_mae_db": 1.0700290357501816, "mr_stft_db": 5.155888543319553, "band_mae_db": 1.541546325636012, "rms_gain_error_db": -0.05686039907173317, "output_peak": 0.6573183030790143}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7778544589481988, "全帯域_10ms_rms_envelope_nrmse": 0.07178710615750732, "全帯域_10ms_envelope_correlation": 0.9962719855302459, "全帯域_10ms_modulation_mae_db": 0.45268943221004493, "全帯域_40ms_log_rms_mae_db": 0.44184739840712584, "全帯域_40ms_rms_envelope_nrmse": 0.042461742885485945, "全帯域_40ms_envelope_correlation": 0.9986632356936967, "全帯域_40ms_modulation_mae_db": 0.4651060046518464, "300–1000 Hz_10ms_log_rms_mae_db": 0.9539631229092209, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08195128666888801, "300–1000 Hz_10ms_envelope_correlation": 0.9953021180194479, "300–1000 Hz_10ms_modulation_mae_db": 0.6964079645948007, "300–1000 Hz_40ms_log_rms_mae_db": 0.6346735502962881, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04897657058881225, "300–1000 Hz_40ms_envelope_correlation": 0.9982986615961355, "300–1000 Hz_40ms_modulation_mae_db": 0.7933228019342043, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0634047220907275, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11115753732599895, "1000–3000 Hz_10ms_envelope_correlation": 0.9926910276505102, "1000–3000 Hz_10ms_modulation_mae_db": 0.6942836734524754, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6081534559622417, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06504951015178446, "1000–3000 Hz_40ms_envelope_correlation": 0.9974607837183291, "1000–3000 Hz_40ms_modulation_mae_db": 0.6679101599544571, "3000–6000 Hz_10ms_log_rms_mae_db": 1.705299532270586, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1534681658083241, "3000–6000 Hz_10ms_envelope_correlation": 0.9833773213698065, "3000–6000 Hz_10ms_modulation_mae_db": 0.2935254228286506, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9600182101642224, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0878040913524096, "3000–6000 Hz_40ms_envelope_correlation": 0.9942615288719773, "3000–6000 Hz_40ms_modulation_mae_db": 0.6306101077804672, "mr_stft_db": 5.163228392741758, "band_mae_db": 1.6732982752063699, "rms_gain_error_db": -0.08282854138513226, "output_peak": 0.6988328875449192}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.71292382658742, "spectral_convergence": 0.18320321041102694, "spectral_convergence_status": "ok", "amplitude_floor": 1.7496801023785185e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.1777737893827345, "spectral_convergence": 0.19139292060942284, "spectral_convergence_status": "ok", "amplitude_floor": 1.6784480256181157e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.6141103626127835, "spectral_convergence": 0.19244047340344753, "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": 4.029177729893594e-06, "delta_db": 9.046195004989624, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0014282687361772438, "output_power": 0.0014495052973407016, "delta_db": 0.06409876970171471, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.002893798215697645, "output_power": 0.0028842759827012723, "delta_db": -0.01431430905016368, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0011796153749935407, "output_power": 0.0011362924031307984, "delta_db": -0.1625032132865712, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.624359886340766e-05, "output_power": 1.4716131987544101e-05, "delta_db": -0.4288858170247825, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.5152799044228294e-05, "output_power": 2.298818977025502e-05, "delta_db": -0.39081547445436826, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2062863831028078e-05, "output_power": 1.2173737258363227e-05, "delta_db": 0.0397349887484804, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.4495067967508153, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.024821969812647462, "pitch": null, "output_rms_dbfs": -22.577478299744556, "output_peak": 0.6613258400199898, "reference_rms_dbfs": -22.552656329931906, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.168269326194313}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 97768, "output_samples": 97768, "intelligibility": {"estoi": {"value": 0.8370459784366839, "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"}}, "level": {"reference": {"rms": 0.07453618896376232, "rms_dbfs": -22.552656329931906, "peak": 0.618865966796875, "peak_dbfs": -4.1680679948339865, "crest_factor_db": 18.38458833509792, "mean": -4.1983207775678136e-07, "zero_energy": false}, "output": {"rms": 0.0743234883621985, "rms_dbfs": -22.577478299744556, "peak": 0.6613258400199898, "peak_dbfs": -3.59169015505847, "crest_factor_db": 18.985788144686083, "mean": -2.9913941274166913e-05, "zero_energy": false}, "rms_difference_db": -0.02482196981264906}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 407, "uncovered_tail_samples": 88, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.062095803557895e-05, "threshold_dbfs": -49.73836307096394, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 176, "quiet_samples": 42240, "reference_mean_power": 5.006247330598082e-07, "output_mean_power": 1.0479632479679538e-06, "output_rms_dbfs": -59.79653947776522, "output_zero_energy": false, "output_peak": 0.019079957654743, "output_energy_fraction": 8.196360668665863e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 400, "reference_estimated_voiced_frames": 224, "output_estimated_voiced_frames": 198, "both_estimated_voiced_frames": 198, "reference_voiced_output_unvoiced_frames": 26, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 0.8839285714285714, "absolute_difference_cents_median": 1.9351971082222321, "absolute_difference_cents_p95": 13.108720913935466, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 88, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.8027931544835808, "rms_envelope_nrmse": 0.07000670587260102, "envelope_correlation": 0.9964258563836245, "rms_gain_error_db": -0.024821844660306236, "reference_mean_power": 0.005567487969490699, "output_mean_power": 0.0055357580822868015}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 4.765376195527078e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0029556164553593994, "output_power": 0.0029027915510562684, "reference_active": true, "delta_db": -0.07832225480753288}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00036953756834478597, "output_power": 0.0003175973780183522, "reference_active": true, "delta_db": -0.6578168833590756}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 0.00011202447087610656, "output_power": 5.862364045212817e-05, "reference_active": true, "delta_db": -2.812401172272541}], "active_band_count": 3, "active_band_mae_db": 1.1828467701463832}}, {"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": 0.44990238295889434, "rms_envelope_nrmse": 0.04045168176953702, "envelope_correlation": 0.9987384363063, "rms_gain_error_db": -0.024821846337569255, "reference_mean_power": 0.005608881493358216, "output_mean_power": 0.005576915696558843}, "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": 0.0026460689490936024, "reference_active": true, "delta_db": -0.09805440136668729}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0001811755718908924, "output_power": 0.00015085546202379168, "reference_active": true, "delta_db": -0.7953860157124731}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.701057462757455e-06, "output_power": 4.821783640694009e-06, "reference_active": true, "delta_db": -3.03611357915159}], "active_band_count": 3, "active_band_mae_db": 1.309851332076917}}]}, {"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": 0.000250633951078475, "log_rms_mae_db": 0.9667729963534121, "rms_envelope_nrmse": 0.0697752073894011, "envelope_correlation": 0.9965523472915018, "rms_gain_error_db": -0.016967758958826646, "reference_mean_power": 0.0041004048785232994, "output_mean_power": 0.0040844159704877805}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 3.4168869077487372e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0021098794264420902, "output_power": 0.002070193737009554, "reference_active": true, "delta_db": -0.08246646949414545}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00027960522877585665, "output_power": 0.0002499401620862991, "reference_active": true, "delta_db": -0.487092415749876}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.021566680060555e-05, "output_power": 5.255708756990137e-05, "reference_active": true, "delta_db": -2.3465067245772806}], "active_band_count": 3, "active_band_mae_db": 0.972021869940434}}, {"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": 0.00024415679244648494, "log_rms_mae_db": 0.614229207481633, "rms_envelope_nrmse": 0.04198953994933963, "envelope_correlation": 0.9986754377825061, "rms_gain_error_db": -0.016967773506961333, "reference_mean_power": 0.004130891145990155, "output_mean_power": 0.004114783347586341}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 3.1086003931775325e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0019093077513610537, "output_power": 0.0018684752516502116, "reference_active": true, "delta_db": -0.09388585797433521}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00014045819894614964, "output_power": 0.00012199003461177647, "reference_active": true, "delta_db": -0.6122274075841149}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.796438388581158e-06, "output_power": 4.4756299366500115e-06, "reference_active": true, "delta_db": -2.4104208112354515}], "active_band_count": 3, "active_band_mae_db": 1.038844692264634}}]}, {"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": 1.0350266377874058, "rms_envelope_nrmse": 0.12262279174517116, "envelope_correlation": 0.9911136864661153, "rms_gain_error_db": -0.004954200427938624, "reference_mean_power": 0.0008784725402011367, "output_mean_power": 0.0008774709968196675}, "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": 0.0006954976604735218, "reference_active": true, "delta_db": -0.037875487268265694}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.449911857407873e-05, "output_power": 6.652647083516684e-05, "reference_active": true, "delta_db": -1.0385769361175918}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6127775103534608e-05, "output_power": 1.5545789629303866e-05, "reference_active": true, "delta_db": -2.2548964279700705}], "active_band_count": 3, "active_band_mae_db": 1.1104496171186427}}, {"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": 0.5997305126256481, "rms_envelope_nrmse": 0.06202793669208283, "envelope_correlation": 0.9976514262514213, "rms_gain_error_db": -0.004954203651232891, "reference_mean_power": 0.0008850039267330396, "output_mean_power": 0.0008839949362851987}, "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": 0.0006663297556846925, "reference_active": true, "delta_db": -0.0778626455662488}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3933140159486266e-05, "output_power": 2.5891955961702756e-05, "reference_active": true, "delta_db": -1.174591912685163}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.944075796645493e-06, "output_power": 9.534993107313005e-07, "reference_active": true, "delta_db": -3.0939280998317797}], "active_band_count": 3, "active_band_mae_db": 1.448794219361064}}]}, {"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": 2.2340226127796087e-05, "log_rms_mae_db": 1.7162912666127252, "rms_envelope_nrmse": 0.1560903346977762, "envelope_correlation": 0.9841395662262037, "rms_gain_error_db": -0.5114983893615633, "reference_mean_power": 1.7310253593278313e-05, "output_mean_power": 1.5386987159013134e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.3633964732936542e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.958677073783262e-06, "output_power": 7.051037060627047e-06, "reference_active": true, "delta_db": -0.5258788604492088}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3383871013961868e-06, "output_power": 1.0925668494470088e-06, "reference_active": true, "delta_db": -0.8813372343532719}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5351180848670046e-07, "output_power": 4.014336061469413e-07, "reference_active": true, "delta_db": -0.5297487287218035}], "active_band_count": 3, "active_band_mae_db": 0.6456549411747614}}, {"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": 1.65910250564749e-05, "log_rms_mae_db": 1.0200485203667449, "rms_envelope_nrmse": 0.09425431443366104, "envelope_correlation": 0.9954576936105128, "rms_gain_error_db": -0.5114985232141513, "reference_mean_power": 1.743895029874837e-05, "output_mean_power": 1.5501384459641758e-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": 7.384237970170298e-06, "output_power": 6.49184360412804e-06, "reference_active": true, "delta_db": -0.5593763551981172}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.219739967436263e-07, "output_power": 3.699433857899458e-07, "reference_active": true, "delta_db": -0.5715042232082017}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.2063085962498154e-08, "output_power": 2.8772389835045647e-08, "reference_active": true, "delta_db": -0.4702938349674607}], "active_band_count": 3, "active_band_mae_db": 0.5337248044579265}}]}], "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"]}}, "output_samples": 97768, "representation_scalars": 918513, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9937835227377674, "standard_deviation": 0.0017382348263046722, "minimum": 0.9911136864661153, "maximum": 0.9965489142335534, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.0407594978770804, "standard_deviation": 0.02328862199427374, "minimum": 0.9972648689882153, "maximum": 1.0662367130834172, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7890957877279494, "standard_deviation": 0.32153231498027585, "minimum": 0.40298451128292984, "maximum": 1.2667409488732273, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10200038050499474, "standard_deviation": 0.014767380811642064, "minimum": 0.07648561049976459, "maximum": 0.12262279174517116, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9980917724176898, "standard_deviation": 0.0005427919329606889, "minimum": 0.9973093588724028, "maximum": 0.9986534648468345, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6076946173403004, "standard_deviation": 0.022182217348960896, "minimum": 0.5728128489612715, "maximum": 0.6372146164259022, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8350247654156586, "standard_deviation": 0.5388637082924151, "minimum": 0.2509454643357641, "maximum": 1.8130944479933884, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05678007838097385, "standard_deviation": 0.008191663074539243, "minimum": 0.04729651753173657, "maximum": 0.07024936773384306, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9829467480458551, "standard_deviation": 0.0025158881477934944, "minimum": 0.978424899952215, "maximum": 0.9867541318843899, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.6889652541121845, "standard_deviation": 0.021800795501502226, "minimum": 1.6551862901332088, "maximum": 1.7162912666127252, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6824606686966366, "standard_deviation": 0.3232701998629552, "minimum": 0.21903289774511184, "maximum": 1.2567363439924704, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1560558946389064, "standard_deviation": 0.011868593997428975, "minimum": 0.13649294266564974, "maximum": 0.17668387921205364, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9948362149967567, "standard_deviation": 0.0009032386301930596, "minimum": 0.9934754215907357, "maximum": 0.9960592161964119, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9554763528756962, "standard_deviation": 0.03280103144532744, "minimum": 0.9037420813027688, "maximum": 1.0200485203667449, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7659932202917531, "standard_deviation": 0.3487959610088096, "minimum": 0.21549441453788418, "maximum": 1.3024548520856978, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08746935515753138, "standard_deviation": 0.008775771633355975, "minimum": 0.07286610429239294, "maximum": 0.10190174980490545, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9953799802768689, "standard_deviation": 0.0009420523046195341, "minimum": 0.9942816001744031, "maximum": 0.9965523472915018, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.9588683342032155, "standard_deviation": 0.02889969302613283, "minimum": 0.9256659738594619, "maximum": 1.0000804166834332, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7640351615420835, "standard_deviation": 0.266637500324514, "minimum": 0.38755692539630066, "maximum": 1.2070455317555366, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08042818249009359, "standard_deviation": 0.008392145231239203, "minimum": 0.0697752073894011, "maximum": 0.08983630132658889, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9982005662702282, "standard_deviation": 0.0004549339058114823, "minimum": 0.997445974290614, "maximum": 0.9987330071536068, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.6138719704320552, "standard_deviation": 0.02876832082062554, "minimum": 0.5756903627880344, "maximum": 0.6434517494960273, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8590202460487105, "standard_deviation": 0.2431746967340401, "minimum": 0.45463720779741107, "maximum": 1.2065138244574862, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04888759993749291, "standard_deviation": 0.006118458870482545, "minimum": 0.04106608916363359, "maximum": 0.05831721141455655, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.5198897135089102, "standard_deviation": 0.07207923463586854, "minimum": 1.4495067967508153, "maximum": 1.6732982752063699, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.159939284218516, "standard_deviation": 0.006544649346231139, "minimum": 5.151006639334992, "maximum": 5.168269326194313, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.6600519111666429, "standard_deviation": 0.022162913984390922, "minimum": 0.6292725725039428, "maximum": 0.6988328875449192, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.04934773130331402, "standard_deviation": 0.02466048998818532, "minimum": -0.08282854138513226, "maximum": -0.015903046962667963, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9962056625540976, "standard_deviation": 0.0006573455807467925, "minimum": 0.9955063092934744, "maximum": 0.997116452971075, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.8095472845648997, "standard_deviation": 0.025912829893612533, "minimum": 0.7715820818561462, "maximum": 0.842959727497172, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.7684220180778241, "standard_deviation": 0.3112693643505791, "minimum": 0.30473167838761167, "maximum": 1.1828467701463832, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07194350655597168, "standard_deviation": 0.006396929629845974, "minimum": 0.06286686980256206, "maximum": 0.07842055739846183, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9986338759266244, "standard_deviation": 0.00023987731622743502, "minimum": 0.9982915340120083, "maximum": 0.9989386662761972, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.45575629670607254, "standard_deviation": 0.02013376844483564, "minimum": 0.43070314370780227, "maximum": 0.4934031901898213, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.8260899390038132, "standard_deviation": 0.33462221631318684, "minimum": 0.37112919612215967, "maximum": 1.309851332076917, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0422691174377081, "standard_deviation": 0.003756237892501889, "minimum": 0.03728053458526622, "maximum": 0.0470081947681646, "valid_count": 8, "planned_count": 8}}, "seconds": 4.670121576004021, "rtf_including_measurement": 1.1464172103765702}, {"case": "jvs_jvs066_falset10_BASIC5000_1205", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs066", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.734682321548462, "predicted_mos": 2.734682321548462, "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": 3.854254342004424}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7210890024773213, "全帯域_10ms_rms_envelope_nrmse": 0.06658727124187336, "全帯域_10ms_envelope_correlation": 0.9967667026032996, "全帯域_10ms_modulation_mae_db": 1.1509589464913603, "全帯域_40ms_log_rms_mae_db": 0.3915257642076716, "全帯域_40ms_rms_envelope_nrmse": 0.03847630118630525, "全帯域_40ms_envelope_correlation": 0.9988623917609479, "全帯域_40ms_modulation_mae_db": 1.2687715599392482, "300–1000 Hz_10ms_log_rms_mae_db": 0.8985972779146507, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0680429877272807, "300–1000 Hz_10ms_envelope_correlation": 0.9967199619613762, "300–1000 Hz_10ms_modulation_mae_db": 0.8922079935806074, "300–1000 Hz_40ms_log_rms_mae_db": 0.571089124703223, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04053226331709468, "300–1000 Hz_40ms_envelope_correlation": 0.998767211605044, "300–1000 Hz_40ms_modulation_mae_db": 0.9478758232387693, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9705335818051178, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11535740658714275, "1000–3000 Hz_10ms_envelope_correlation": 0.992132953520124, "1000–3000 Hz_10ms_modulation_mae_db": 1.1660343821987211, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5948677068133775, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.057673798711894986, "1000–3000 Hz_40ms_envelope_correlation": 0.9979726099574879, "1000–3000 Hz_40ms_modulation_mae_db": 1.5079227184355286, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6817599874825362, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17035788799422807, "3000–6000 Hz_10ms_envelope_correlation": 0.9799778040263797, "3000–6000 Hz_10ms_modulation_mae_db": 0.4168415152771696, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0165880640136586, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10336974881273066, "3000–6000 Hz_40ms_envelope_correlation": 0.9931523229571662, "3000–6000 Hz_40ms_modulation_mae_db": 0.44652624462152996, "mr_stft_db": 5.171905367438742, "band_mae_db": 1.4308115705270874, "rms_gain_error_db": -0.032579830216698566, "output_peak": 0.6629035877838274}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.710613644514568, "全帯域_10ms_rms_envelope_nrmse": 0.07801324366428235, "全帯域_10ms_envelope_correlation": 0.995585313122485, "全帯域_10ms_modulation_mae_db": 0.712719871575289, "全帯域_40ms_log_rms_mae_db": 0.39704184473231807, "全帯域_40ms_rms_envelope_nrmse": 0.04260985682880738, "全帯域_40ms_envelope_correlation": 0.9986596239894558, "全帯域_40ms_modulation_mae_db": 0.6238364778455426, "300–1000 Hz_10ms_log_rms_mae_db": 0.8988602600584403, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08933766731973627, "300–1000 Hz_10ms_envelope_correlation": 0.9943537007958756, "300–1000 Hz_10ms_modulation_mae_db": 0.5162213664569567, "300–1000 Hz_40ms_log_rms_mae_db": 0.6011127790911268, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.051452689362917386, "300–1000 Hz_40ms_envelope_correlation": 0.9980586908086393, "300–1000 Hz_40ms_modulation_mae_db": 0.4092899731311104, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9754240117187148, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10084741011421451, "1000–3000 Hz_10ms_envelope_correlation": 0.9940139280321116, "1000–3000 Hz_10ms_modulation_mae_db": 1.1701817089956827, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5796519935737448, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04989922411491055, "1000–3000 Hz_40ms_envelope_correlation": 0.9985526486050232, "1000–3000 Hz_40ms_modulation_mae_db": 1.8004644387064133, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6396320197890182, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15150252316232696, "3000–6000 Hz_10ms_envelope_correlation": 0.9837217857098018, "3000–6000 Hz_10ms_modulation_mae_db": 0.2754630639842189, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9530505678860314, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08181291631075434, "3000–6000 Hz_40ms_envelope_correlation": 0.9948748105383414, "3000–6000 Hz_40ms_modulation_mae_db": 0.4448653883618121, "mr_stft_db": 5.166221021232249, "band_mae_db": 1.554264653558754, "rms_gain_error_db": -0.08580059362523872, "output_peak": 0.6548201018810721}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7245693801994892, "全帯域_10ms_rms_envelope_nrmse": 0.06103593317977836, "全帯域_10ms_envelope_correlation": 0.9972870036578356, "全帯域_10ms_modulation_mae_db": 0.27986560784030046, "全帯域_40ms_log_rms_mae_db": 0.4030491301036544, "全帯域_40ms_rms_envelope_nrmse": 0.03571411454030712, "全帯域_40ms_envelope_correlation": 0.9990313689306923, "全帯域_40ms_modulation_mae_db": 0.34265793221639873, "300–1000 Hz_10ms_log_rms_mae_db": 0.824100158188064, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06858763686999157, "300–1000 Hz_10ms_envelope_correlation": 0.9966644237789573, "300–1000 Hz_10ms_modulation_mae_db": 0.3374365669447303, "300–1000 Hz_40ms_log_rms_mae_db": 0.5318484723883649, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.040334493381555724, "300–1000 Hz_40ms_envelope_correlation": 0.9987809449742701, "300–1000 Hz_40ms_modulation_mae_db": 0.5209870934653091, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9740540122021254, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08924012931930343, "1000–3000 Hz_10ms_envelope_correlation": 0.9953419410090576, "1000–3000 Hz_10ms_modulation_mae_db": 0.45849761850206366, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6289889765536996, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05631714846012392, "1000–3000 Hz_40ms_envelope_correlation": 0.9981519468624968, "1000–3000 Hz_40ms_modulation_mae_db": 0.25425752468108714, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6568375324609772, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15293426234473834, "3000–6000 Hz_10ms_envelope_correlation": 0.9833355643777522, "3000–6000 Hz_10ms_modulation_mae_db": 0.8017398324621666, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9609177085773839, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08014861224528624, "3000–6000 Hz_40ms_envelope_correlation": 0.9952387489322987, "3000–6000 Hz_40ms_modulation_mae_db": 0.7623651040845854, "mr_stft_db": 5.169771973406962, "band_mae_db": 1.5388752499298195, "rms_gain_error_db": -0.043693976724620616, "output_peak": 0.617380149095918}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6983149182661923, "全帯域_10ms_rms_envelope_nrmse": 0.07403386405498454, "全帯域_10ms_envelope_correlation": 0.9960248706156438, "全帯域_10ms_modulation_mae_db": 1.0901929827440193, "全帯域_40ms_log_rms_mae_db": 0.40275933506429434, "全帯域_40ms_rms_envelope_nrmse": 0.04823577597326204, "全帯域_40ms_envelope_correlation": 0.9982558479229517, "全帯域_40ms_modulation_mae_db": 1.0314835591366747, "300–1000 Hz_10ms_log_rms_mae_db": 0.875403676753854, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08349779078222902, "300–1000 Hz_10ms_envelope_correlation": 0.9950576874913873, "300–1000 Hz_10ms_modulation_mae_db": 1.100310442255119, "300–1000 Hz_40ms_log_rms_mae_db": 0.5507268284922806, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.057351684196528564, "300–1000 Hz_40ms_envelope_correlation": 0.997548373804841, "300–1000 Hz_40ms_modulation_mae_db": 1.0717855867197532, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0241482129486463, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11989620027023687, "1000–3000 Hz_10ms_envelope_correlation": 0.9916569891383333, "1000–3000 Hz_10ms_modulation_mae_db": 1.3280709876070143, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6464399190702201, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07251021332963187, "1000–3000 Hz_40ms_envelope_correlation": 0.9970816771245987, "1000–3000 Hz_40ms_modulation_mae_db": 1.0503340599016615, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6587719971639474, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17907683395411408, "3000–6000 Hz_10ms_envelope_correlation": 0.9774556354345627, "3000–6000 Hz_10ms_modulation_mae_db": 1.0866655981351308, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9448034181119773, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10260525641074619, "3000–6000 Hz_40ms_envelope_correlation": 0.9928399163543236, "3000–6000 Hz_40ms_modulation_mae_db": 1.013772394431158, "mr_stft_db": 5.155279085307807, "band_mae_db": 1.545416983802167, "rms_gain_error_db": -0.07942682244930388, "output_peak": 0.6306174197238718}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7413975224522882, "全帯域_10ms_rms_envelope_nrmse": 0.07971327319644562, "全帯域_10ms_envelope_correlation": 0.9953630521693825, "全帯域_10ms_modulation_mae_db": 0.7688050130606369, "全帯域_40ms_log_rms_mae_db": 0.43114270596505455, "全帯域_40ms_rms_envelope_nrmse": 0.04942585546280603, "全帯域_40ms_envelope_correlation": 0.9981132633006253, "全帯域_40ms_modulation_mae_db": 0.7153693414878489, "300–1000 Hz_10ms_log_rms_mae_db": 0.9079247687823363, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09034525319918091, "300–1000 Hz_10ms_envelope_correlation": 0.9942249266027487, "300–1000 Hz_10ms_modulation_mae_db": 0.8754333910306672, "300–1000 Hz_40ms_log_rms_mae_db": 0.6141185110058734, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.06069814322879299, "300–1000 Hz_40ms_envelope_correlation": 0.9972369231340267, "300–1000 Hz_40ms_modulation_mae_db": 0.8005574038633482, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9884355570008766, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0951938378106821, "1000–3000 Hz_10ms_envelope_correlation": 0.9946376913771062, "1000–3000 Hz_10ms_modulation_mae_db": 0.5579829896699727, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6160668131832016, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.048072805078681044, "1000–3000 Hz_40ms_envelope_correlation": 0.998610366503929, "1000–3000 Hz_40ms_modulation_mae_db": 0.4131544468073949, "3000–6000 Hz_10ms_log_rms_mae_db": 1.636964582513463, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16592830318814364, "3000–6000 Hz_10ms_envelope_correlation": 0.980340755267509, "3000–6000 Hz_10ms_modulation_mae_db": 0.35645803823474637, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9197940812620425, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08362439153503282, "3000–6000 Hz_40ms_envelope_correlation": 0.9948400386642655, "3000–6000 Hz_40ms_modulation_mae_db": 0.28902791637227265, "mr_stft_db": 5.1628797201685686, "band_mae_db": 1.520762643449689, "rms_gain_error_db": 0.0013534136349177455, "output_peak": 0.6496695351418701}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7260102603870447, "全帯域_10ms_rms_envelope_nrmse": 0.06180469274393781, "全帯域_10ms_envelope_correlation": 0.9972165200490481, "全帯域_10ms_modulation_mae_db": 0.48058415101486385, "全帯域_40ms_log_rms_mae_db": 0.43369186382790065, "全帯域_40ms_rms_envelope_nrmse": 0.03718557635108822, "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": 0.8326791229965892, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0715605356224793, "300–1000 Hz_10ms_envelope_correlation": 0.9963813697175775, "300–1000 Hz_10ms_modulation_mae_db": 0.4948551556104805, "300–1000 Hz_40ms_log_rms_mae_db": 0.5314379822359155, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04538593757525435, "300–1000 Hz_40ms_envelope_correlation": 0.998480564650114, "300–1000 Hz_40ms_modulation_mae_db": 0.7494801360563605, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9553852442414303, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.07595662861199756, "1000–3000 Hz_10ms_envelope_correlation": 0.9965917841706476, "1000–3000 Hz_10ms_modulation_mae_db": 0.22731346339073846, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5942514251053638, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04563792221424522, "1000–3000 Hz_40ms_envelope_correlation": 0.9987365600952866, "1000–3000 Hz_40ms_modulation_mae_db": 0.28602326863573935, "3000–6000 Hz_10ms_log_rms_mae_db": 1.619502964565434, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15519473355225002, "3000–6000 Hz_10ms_envelope_correlation": 0.9829462221860827, "3000–6000 Hz_10ms_modulation_mae_db": 0.10526431062602744, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9588783730587044, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09739202192149361, "3000–6000 Hz_40ms_envelope_correlation": 0.9927448947595771, "3000–6000 Hz_40ms_modulation_mae_db": 0.03481254717061713, "mr_stft_db": 5.1531810861590115, "band_mae_db": 1.4958629907381442, "rms_gain_error_db": -0.03763643347457537, "output_peak": 0.6480511783724467}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7586224720125089, "全帯域_10ms_rms_envelope_nrmse": 0.07683651070624997, "全帯域_10ms_envelope_correlation": 0.9957012201609535, "全帯域_10ms_modulation_mae_db": 0.7979321707046906, "全帯域_40ms_log_rms_mae_db": 0.4497285609529178, "全帯域_40ms_rms_envelope_nrmse": 0.04523563215241413, "全帯域_40ms_envelope_correlation": 0.9984478534581002, "全帯域_40ms_modulation_mae_db": 1.0353707017145044, "300–1000 Hz_10ms_log_rms_mae_db": 0.8882553258856586, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08708569707156524, "300–1000 Hz_10ms_envelope_correlation": 0.9946176962186353, "300–1000 Hz_10ms_modulation_mae_db": 0.6028423511647436, "300–1000 Hz_40ms_log_rms_mae_db": 0.5832881626427378, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04956153143348103, "300–1000 Hz_40ms_envelope_correlation": 0.998157734696996, "300–1000 Hz_40ms_modulation_mae_db": 0.835404670328297, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0529317301409553, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09436263127184509, "1000–3000 Hz_10ms_envelope_correlation": 0.9948280185968247, "1000–3000 Hz_10ms_modulation_mae_db": 0.6601620374999871, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6681059120346156, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05273630197701067, "1000–3000 Hz_40ms_envelope_correlation": 0.9984581108407332, "1000–3000 Hz_40ms_modulation_mae_db": 0.4607783345435454, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6643767559192648, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1756771682632097, "3000–6000 Hz_10ms_envelope_correlation": 0.9779029437951835, "3000–6000 Hz_10ms_modulation_mae_db": 0.34482049727515607, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9640333192500112, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10272034871708027, "3000–6000 Hz_40ms_envelope_correlation": 0.9919827460260441, "3000–6000 Hz_40ms_modulation_mae_db": 0.45322162019267886, "mr_stft_db": 5.159961731026381, "band_mae_db": 1.60191950191463, "rms_gain_error_db": -0.05970143947349943, "output_peak": 0.647002455143995}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.6801335441088254, "全帯域_10ms_rms_envelope_nrmse": 0.07272992269202158, "全帯域_10ms_envelope_correlation": 0.9961939537802609, "全帯域_10ms_modulation_mae_db": 0.494256401732748, "全帯域_40ms_log_rms_mae_db": 0.38930045623855697, "全帯域_40ms_rms_envelope_nrmse": 0.04227825015691595, "全帯域_40ms_envelope_correlation": 0.9987067383631378, "全帯域_40ms_modulation_mae_db": 0.4561331875734555, "300–1000 Hz_10ms_log_rms_mae_db": 0.8536998467214163, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08330281629158055, "300–1000 Hz_10ms_envelope_correlation": 0.9951558745863716, "300–1000 Hz_10ms_modulation_mae_db": 0.655438170720755, "300–1000 Hz_40ms_log_rms_mae_db": 0.5712860861826069, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.052399678260984364, "300–1000 Hz_40ms_envelope_correlation": 0.9980570854996996, "300–1000 Hz_40ms_modulation_mae_db": 0.7340326418052939, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9861004986926386, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11280507265898634, "1000–3000 Hz_10ms_envelope_correlation": 0.9925044381866139, "1000–3000 Hz_10ms_modulation_mae_db": 0.8886913088332428, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6014216949669893, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.060292092446755575, "1000–3000 Hz_40ms_envelope_correlation": 0.9978847448627236, "1000–3000 Hz_40ms_modulation_mae_db": 0.7452573274010693, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6392810180530595, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1549558993004368, "3000–6000 Hz_10ms_envelope_correlation": 0.9831525366059135, "3000–6000 Hz_10ms_modulation_mae_db": 0.06672541760117394, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8857583986553641, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08179725304660045, "3000–6000 Hz_40ms_envelope_correlation": 0.994974024637818, "3000–6000 Hz_40ms_modulation_mae_db": 0.13843915076328595, "mr_stft_db": 5.163288124809829, "band_mae_db": 1.7786963069329444, "rms_gain_error_db": -0.10101362479224828, "output_peak": 0.7131623124296222}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.695276455671774, "spectral_convergence": 0.17961685568136956, "spectral_convergence_status": "ok", "amplitude_floor": 1.7496801023785185e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.166511298181185, "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": 4.6539283484632685, "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": 4.011224278116921e-06, "delta_db": 9.026800208589155, "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": 0.002880031606312601, "delta_db": -0.020709906611130462, "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": 2.359853097776593e-05, "delta_db": -0.277013523464914, "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}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 97768, "output_samples": 97768, "intelligibility": {"estoi": {"value": 0.8474961261810459, "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"}}, "level": {"reference": {"rms": 0.07453618896376232, "rms_dbfs": -22.552656329931906, "peak": 0.618865966796875, "peak_dbfs": -4.1680679948339865, "crest_factor_db": 18.38458833509792, "mean": -4.1983207775678136e-07, "zero_energy": false}, "output": {"rms": 0.07425713547781347, "rms_dbfs": -22.585236160148607, "peak": 0.6629035877838274, "peak_dbfs": -3.5709926095271456, "crest_factor_db": 19.014243550621458, "mean": -6.221711320534438e-05, "zero_energy": false}, "rms_difference_db": -0.032579830216700856}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 407, "uncovered_tail_samples": 88, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.062095803557895e-05, "threshold_dbfs": -49.73836307096394, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 176, "quiet_samples": 42240, "reference_mean_power": 5.006247330598082e-07, "output_mean_power": 9.004700300604761e-07, "output_rms_dbfs": -60.45530737032071, "output_zero_energy": false, "output_peak": 0.018794892331865105, "output_energy_fraction": 7.055374277756859e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 400, "reference_estimated_voiced_frames": 224, "output_estimated_voiced_frames": 196, "both_estimated_voiced_frames": 196, "reference_voiced_output_unvoiced_frames": 28, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 0.875, "absolute_difference_cents_median": 1.9635949521516876, "absolute_difference_cents_p95": 14.366286632405336, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 88, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.7210890024773213, "rms_envelope_nrmse": 0.06658727124187336, "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": 4.765376195527078e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0029556164553593994, "output_power": 0.0028960651561540365, "reference_active": true, "delta_db": -0.08839747358530838}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00036953756834478597, "output_power": 0.00032495433368632154, "reference_active": true, "delta_db": -0.5583626349009397}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 0.00011202447087610656, "output_power": 5.8708532968234874e-05, "reference_active": true, "delta_db": -2.8061167309878328}], "active_band_count": 3, "active_band_mae_db": 1.1509589464913603}}, {"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": 0.3915257642076716, "rms_envelope_nrmse": 0.03847630118630525, "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": 0.0001811755718908924, "output_power": 0.00015476514925981174, "reference_active": true, "delta_db": -0.6842646997385403}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.701057462757455e-06, "output_power": 4.845706228681972e-06, "reference_active": true, "delta_db": -3.014619956085956}], "active_band_count": 3, "active_band_mae_db": 1.2687715599392482}}]}, {"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": 0.000250633951078475, "log_rms_mae_db": 0.8985972779146507, "rms_envelope_nrmse": 0.0680429877272807, "envelope_correlation": 0.9967199619613762, "rms_gain_error_db": -0.02183480032040126, "reference_mean_power": 0.0041004048785232994, "output_mean_power": 0.004079841220527532}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 3.4168869077487372e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0021098794264420902, "output_power": 0.0020692848519253725, "reference_active": true, "delta_db": -0.08437358786476586}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00027960522877585665, "output_power": 0.0002551188203159091, "reference_active": true, "delta_db": -0.3980279066503372}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.021566680060555e-05, "output_power": 5.4432679675315476e-05, "reference_active": true, "delta_db": -2.1942224862267192}], "active_band_count": 3, "active_band_mae_db": 0.8922079935806074}}, {"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": 0.00024415679244648494, "log_rms_mae_db": 0.571089124703223, "rms_envelope_nrmse": 0.04053226331709468, "envelope_correlation": 0.998767211605044, "rms_gain_error_db": -0.021834816215583197, "reference_mean_power": 0.004130891145990155, "output_mean_power": 0.00411017458337162}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 3.1086003931775325e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0019093077513610537, "output_power": 0.0018693735979507795, "reference_active": true, "delta_db": -0.09179831048707726}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00014045819894614964, "output_power": 0.00012501844932819714, "reference_active": true, "delta_db": -0.5057298747696847}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.796438388581158e-06, "output_power": 4.648216230166259e-06, "reference_active": true, "delta_db": -2.2460992844595458}], "active_band_count": 3, "active_band_mae_db": 0.9478758232387693}}]}, {"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": 0.9705335818051178, "rms_envelope_nrmse": 0.11535740658714275, "envelope_correlation": 0.992132953520124, "rms_gain_error_db": -0.017000678253898907, "reference_mean_power": 0.0008784725402011367, "output_mean_power": 0.0008750404367425958}, "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": 0.0006926778566065262, "reference_active": true, "delta_db": -0.055519177547583363}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.449911857407873e-05, "output_power": 6.614973771327966e-05, "reference_active": true, "delta_db": -1.0632405223777233}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6127775103534608e-05, "output_power": 1.510664711969358e-05, "reference_active": true, "delta_db": -2.3793434466708567}], "active_band_count": 3, "active_band_mae_db": 1.1660343821987211}}, {"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": 0.5948677068133775, "rms_envelope_nrmse": 0.057673798711894986, "envelope_correlation": 0.9979726099574879, "rms_gain_error_db": -0.017000684071361544, "reference_mean_power": 0.0008850039267330396, "output_mean_power": 0.0008815463046263646}, "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": 0.0006626575144877003, "reference_active": true, "delta_db": -0.1018634495294868}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3933140159486266e-05, "output_power": 2.5698626215755673e-05, "reference_active": true, "delta_db": -1.2071414329019827}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.944075796645493e-06, "output_power": 9.273354583444833e-07, "reference_active": true, "delta_db": -3.2147632728751163}], "active_band_count": 3, "active_band_mae_db": 1.5079227184355286}}]}, {"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": 2.2340226127796087e-05, "log_rms_mae_db": 1.6817599874825362, "rms_envelope_nrmse": 0.17035788799422807, "envelope_correlation": 0.9799778040263797, "rms_gain_error_db": -0.3985504252204004, "reference_mean_power": 1.7310253593278313e-05, "output_mean_power": 1.579240917129135e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.3633964732936542e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.958677073783262e-06, "output_power": 7.0020704817562795e-06, "reference_active": true, "delta_db": -0.5561440541097106}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3383871013961868e-06, "output_power": 1.179787482927361e-06, "reference_active": true, "delta_db": -0.5477795832742339}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5351180848670046e-07, "output_power": 4.38458515180317e-07, "reference_active": true, "delta_db": -0.1466009084475643}], "active_band_count": 3, "active_band_mae_db": 0.4168415152771696}}, {"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": 1.65910250564749e-05, "log_rms_mae_db": 1.0165880640136586, "rms_envelope_nrmse": 0.10336974881273066, "envelope_correlation": 0.9931523229571662, "rms_gain_error_db": -0.39855047798823473, "reference_mean_power": 1.743895029874837e-05, "output_mean_power": 1.590982095122944e-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": 7.384237970170298e-06, "output_power": 6.386887905930635e-06, "reference_active": true, "delta_db": -0.6301639008158864}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.219739967436263e-07, "output_power": 4.153972036768943e-07, "reference_active": true, "delta_db": -0.06822120630687684}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.2063085962498154e-08, "output_power": 3.7164190885357994e-08, "reference_active": true, "delta_db": 0.6411936267418267}], "active_band_count": 3, "active_band_mae_db": 0.44652624462152996}}]}], "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"]}}, "output_samples": 97768, "representation_scalars": 918513, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9939634680038523, "standard_deviation": 0.001724288707920525, "minimum": 0.9916569891383333, "maximum": 0.9965917841706476, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.9908766060938132, "standard_deviation": 0.03203093573251525, "minimum": 0.9553852442414303, "maximum": 1.0529317301409553, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8071168120871779, "standard_deviation": 0.39280242680996835, "minimum": 0.22731346339073846, "maximum": 1.3280709876070143, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10045741458055109, "standard_deviation": 0.01484905255816349, "minimum": 0.07595662861199756, "maximum": 0.11989620027023687, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9981810831065349, "standard_deviation": 0.000540959999570232, "minimum": 0.9970816771245987, "maximum": 0.9987365600952866, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6162243051626515, "standard_deviation": 0.029912274330826338, "minimum": 0.5796519935737448, "maximum": 0.6681059120346156, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.814774014889055, "standard_deviation": 0.5846524178771179, "minimum": 0.25425752468108714, "maximum": 1.8004644387064133, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05539243829165673, "standard_deviation": 0.008527624051479164, "minimum": 0.04563792221424522, "maximum": 0.07251021332963187, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9811041559253981, "standard_deviation": 0.002530701510029608, "minimum": 0.9774556354345627, "maximum": 0.9837217857098018, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.6496408572434627, "standard_deviation": 0.019495196107448914, "minimum": 1.619502964565434, "maximum": 1.6817599874825362, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.4317472841994737, "standard_deviation": 0.34713444392315984, "minimum": 0.06672541760117394, "maximum": 1.0866655981351308, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16320345146993095, "standard_deviation": 0.010959003532756025, "minimum": 0.15150252316232696, "maximum": 0.17907683395411408, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9938309378587293, "standard_deviation": 0.0012780833016002122, "minimum": 0.9919827460260441, "maximum": 0.9952387489322987, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9504779913518967, "standard_deviation": 0.03761228841562967, "minimum": 0.8857583986553641, "maximum": 1.0165880640136586, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.4478787957497425, "standard_deviation": 0.3186549590374069, "minimum": 0.03481254717061713, "maximum": 1.013772394431158, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09168381862496557, "standard_deviation": 0.010713286755122581, "minimum": 0.08014861224528624, "maximum": 0.10336974881273066, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9953969551441162, "standard_deviation": 0.0010398072085467554, "minimum": 0.9942249266027487, "maximum": 0.9967199619613762, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8724400546626261, "standard_deviation": 0.032002613842200316, "minimum": 0.824100158188064, "maximum": 0.9079247687823363, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.6843431797205075, "standard_deviation": 0.2520614299175204, "minimum": 0.3374365669447303, "maximum": 1.100310442255119, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08022004811050545, "standard_deviation": 0.009347389993579406, "minimum": 0.0680429877272807, "maximum": 0.09034525319918091, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9981359411467038, "standard_deviation": 0.0005476478591240999, "minimum": 0.9972369231340267, "maximum": 0.9987809449742701, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.569363493342766, "standard_deviation": 0.030248130521131893, "minimum": 0.5314379822359155, "maximum": 0.6141185110058734, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7586766660760301, "standard_deviation": 0.21405406470710295, "minimum": 0.4092899731311104, "maximum": 1.0717855867197532, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.049714552594576134, "standard_deviation": 0.007370368591982954, "minimum": 0.040334493381555724, "maximum": 0.06069814322879299, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.5583262376066545, "standard_deviation": 0.10183845576207487, "minimum": 1.4308115705270874, "maximum": 1.7786963069329444, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.162811013693695, "standard_deviation": 0.0065531518962934476, "minimum": 5.1531810861590115, "maximum": 5.171905367438742, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.652950842446578, "standard_deviation": 0.0281886131550292, "minimum": 0.617380149095918, "maximum": 0.7131623124296222, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.05481241339015839, "standard_deviation": 0.03336403700864284, "minimum": -0.10101362479224828, "maximum": 0.0013534136349177455, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9962673295198636, "standard_deviation": 0.0007423500813856264, "minimum": 0.9953630521693825, "maximum": 0.9972870036578356, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.7200938430522799, "standard_deviation": 0.02436434161243635, "minimum": 0.6801335441088254, "maximum": 0.7586224720125089, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.7219143931454886, "standard_deviation": 0.30077183941394026, "minimum": 0.27986560784030046, "maximum": 1.1509589464913603, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07134433893494671, "standard_deviation": 0.007306831061667383, "minimum": 0.06103593317977836, "maximum": 0.07971327319644562, "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": 0.412279957636546, "standard_deviation": 0.02262588731320692, "minimum": 0.38930045623855697, "maximum": 0.4497285609529178, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.759592551549336, "standard_deviation": 0.32072093587891176, "minimum": 0.34265793221639873, "maximum": 1.2687715599392482, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.04239517033148826, "standard_deviation": 0.005054066297214918, "minimum": 0.03571411454030712, "maximum": 0.04942585546280603, "valid_count": 8, "planned_count": 8}}, "seconds": 5.277870558005816, "rtf_including_measurement": 1.2956068794711928}, {"case": "jvs_jvs066_falset10_BASIC5000_1205", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs066", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.408630609512329, "predicted_mos": 2.408630609512329, "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": "855e823713e676dd00063d9f6609d6d6cd5b230829917ef460ca9db928962c7f", "internal_samples": 65179, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.1777377539983718}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.281051353903311, "全帯域_10ms_rms_envelope_nrmse": 0.1978213175455746, "全帯域_10ms_envelope_correlation": 0.9955295999396525, "全帯域_10ms_modulation_mae_db": 1.3453967858412106, "全帯域_40ms_log_rms_mae_db": 1.0522841661395825, "全帯域_40ms_rms_envelope_nrmse": 0.19184893224728697, "全帯域_40ms_envelope_correlation": 0.9967998799201206, "全帯域_40ms_modulation_mae_db": 1.2404499951826795, "300–1000 Hz_10ms_log_rms_mae_db": 1.0874899359333512, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.1324766643648859, "300–1000 Hz_10ms_envelope_correlation": 0.9953149953594295, "300–1000 Hz_10ms_modulation_mae_db": 0.7291963401096601, "300–1000 Hz_40ms_log_rms_mae_db": 0.9383335813158775, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1268517873044987, "300–1000 Hz_40ms_envelope_correlation": 0.9960510867651321, "300–1000 Hz_40ms_modulation_mae_db": 0.6580526194158635, "1000–3000 Hz_10ms_log_rms_mae_db": 1.225069601144376, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.4460664126066819, "1000–3000 Hz_10ms_envelope_correlation": 0.9952684745862312, "1000–3000 Hz_10ms_modulation_mae_db": 3.519423608536569, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0993142668333866, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.44339816855346825, "1000–3000 Hz_40ms_envelope_correlation": 0.9961564923075931, "1000–3000 Hz_40ms_modulation_mae_db": 3.58680023459693, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6226758300285846, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.30239893644293886, "3000–6000 Hz_10ms_envelope_correlation": 0.9667250414131506, "3000–6000 Hz_10ms_modulation_mae_db": 2.3656415471815175, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2649493821757096, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.24714061218844488, "3000–6000 Hz_40ms_envelope_correlation": 0.983292545522119, "3000–6000 Hz_40ms_modulation_mae_db": 2.460185131278349, "mr_stft_db": 5.064250011257688, "band_mae_db": 3.3083262075485225, "rms_gain_error_db": 1.427304593284996, "output_peak": 0.8023816747344805}}], "planned_noise_seeds": [0], "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": 5.452055207132193, "spectral_convergence": 0.2807816979409667, "spectral_convergence_status": "ok", "amplitude_floor": 1.7496801023785185e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.111561456803631, "spectral_convergence": 0.27109761058213977, "spectral_convergence_status": "ok", "amplitude_floor": 1.6784480256181157e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 4.629133369837237, "spectral_convergence": 0.289983721431204, "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": 1.6493292761560697e-05, "delta_db": 15.167104435695633, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0014282687361772438, "output_power": 0.0019358775208474176, "delta_db": 1.3206794699628106, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.002893798215697645, "output_power": 0.00327662167765043, "delta_db": 0.5395805563587386, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0011796153749935407, "output_power": 0.00242150592239213, "delta_db": 3.123451110892837, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.624359886340766e-05, "output_power": 2.545422387149355e-05, "delta_db": 1.9507760341429, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.5152799044228294e-05, "output_power": 2.7008740262513393e-05, "delta_db": 0.30918007289000304, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2062863831028078e-05, "output_power": 1.4328528857967285e-05, "delta_db": 0.7475117728967338, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 3.3083262075485225, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 1.427304593284996, "pitch": null, "output_rms_dbfs": -21.12535173664691, "output_peak": 0.8023816747344805, "reference_rms_dbfs": -22.552656329931906, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.064250011257688}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 97768, "output_samples": 97768, "intelligibility": {"estoi": {"value": 0.8744044876184903, "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"}}, "level": {"reference": {"rms": 0.07453618896376232, "rms_dbfs": -22.552656329931906, "peak": 0.618865966796875, "peak_dbfs": -4.1680679948339865, "crest_factor_db": 18.38458833509792, "mean": -4.1983207775678136e-07, "zero_energy": false}, "output": {"rms": 0.0878481081439214, "rms_dbfs": -21.12535173664691, "peak": 0.8023816747344805, "peak_dbfs": -1.9123799709535383, "crest_factor_db": 19.21297176569337, "mean": 3.3540529051970965e-08, "zero_energy": false}, "rms_difference_db": 1.4273045932849975}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 407, "uncovered_tail_samples": 88, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.062095803557895e-05, "threshold_dbfs": -49.73836307096394, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 176, "quiet_samples": 42240, "reference_mean_power": 5.006247330598082e-07, "output_mean_power": 1.0386448350429713e-06, "output_rms_dbfs": -59.83532934204386, "output_zero_energy": false, "output_peak": 0.01750649866123496, "output_energy_fraction": 5.814728183188808e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 400, "reference_estimated_voiced_frames": 224, "output_estimated_voiced_frames": 230, "both_estimated_voiced_frames": 222, "reference_voiced_output_unvoiced_frames": 2, "reference_unvoiced_output_voiced_frames": 8, "paired_voiced_fraction": 0.9910714285714286, "absolute_difference_cents_median": 4.608931764353466, "absolute_difference_cents_p95": 20.620460321413812, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 88, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.281051353903311, "rms_envelope_nrmse": 0.1978213175455746, "envelope_correlation": 0.9955295999396525, "rms_gain_error_db": 1.4273047613142817, "reference_mean_power": 0.005567487969490699, "output_mean_power": 0.007733743488914556}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 4.765376195527078e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0029556164553593994, "output_power": 0.004203082364866036, "reference_active": true, "delta_db": 1.5291982483128852}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00036953756834478597, "output_power": 0.0005249529573134242, "reference_active": true, "delta_db": 1.5246178994395336}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 0.00011202447087610656, "output_power": 0.00014045924261083502, "reference_active": true, "delta_db": 0.9823742097712131}], "active_band_count": 3, "active_band_mae_db": 1.3453967858412106}}, {"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": 1.0522841661395825, "rms_envelope_nrmse": 0.19184893224728697, "envelope_correlation": 0.9967998799201206, "rms_gain_error_db": 1.4273049708670438, "reference_mean_power": 0.005608881493358216, "output_mean_power": 0.007791243207005783}, "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": 0.0038572567304091527, "reference_active": true, "delta_db": 1.5387194887572728}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0001811755718908924, "output_power": 0.0002589836905599349, "reference_active": true, "delta_db": 1.5517277447693014}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.701057462757455e-06, "output_power": 1.1217842864446916e-05, "reference_active": true, "delta_db": 0.6309027520214643}], "active_band_count": 3, "active_band_mae_db": 1.2404499951826795}}]}, {"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": 0.000250633951078475, "log_rms_mae_db": 1.0874899359333512, "rms_envelope_nrmse": 0.1324766643648859, "envelope_correlation": 0.9953149953594295, "rms_gain_error_db": 0.8281952388652737, "reference_mean_power": 0.0041004048785232994, "output_mean_power": 0.004961880097370545}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 3.4168869077487372e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0021098794264420902, "output_power": 0.0023051785886150635, "reference_active": true, "delta_db": 0.3844693971116777}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00027960522877585665, "output_power": 0.00035739176595292444, "reference_active": true, "delta_db": 1.0659925375308343}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.021566680060555e-05, "output_power": 0.00010690417639252983, "reference_active": true, "delta_db": 0.737127085686468}], "active_band_count": 3, "active_band_mae_db": 0.7291963401096601}}, {"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": 0.00024415679244648494, "log_rms_mae_db": 0.9383335813158775, "rms_envelope_nrmse": 0.1268517873044987, "envelope_correlation": 0.9960510867651321, "rms_gain_error_db": 0.8281952118669675, "reference_mean_power": 0.004130891145990155, "output_mean_power": 0.004998771351002071}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 3.1086003931775325e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0019093077513610537, "output_power": 0.002057962662799901, "reference_active": true, "delta_db": 0.3256155548205474}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00014045819894614964, "output_power": 0.00018376130681002804, "reference_active": true, "delta_db": 1.1670697537649446}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.796438388581158e-06, "output_power": 8.710508445891812e-06, "reference_active": true, "delta_db": 0.4814725496620982}], "active_band_count": 3, "active_band_mae_db": 0.6580526194158635}}]}, {"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": 1.225069601144376, "rms_envelope_nrmse": 0.4460664126066819, "envelope_correlation": 0.9952684745862312, "rms_gain_error_db": 3.115695257302018, "reference_mean_power": 0.0008784725402011367, "output_mean_power": 0.0018001044948961144}, "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": 0.0015305066424062576, "reference_active": true, "delta_db": 3.3875199660718107}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.449911857407873e-05, "output_power": 0.00020293255331725227, "reference_active": true, "delta_db": 3.8049954097199667}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6127775103534608e-05, "output_power": 5.671239316813752e-05, "reference_active": true, "delta_db": 3.3657554498179296}], "active_band_count": 3, "active_band_mae_db": 3.519423608536569}}, {"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": 1.0993142668333866, "rms_envelope_nrmse": 0.44339816855346825, "envelope_correlation": 0.9961564923075931, "rms_gain_error_db": 3.115695274674766, "reference_mean_power": 0.0008850039267330396, "output_mean_power": 0.0018134881626702306}, "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": 0.0014947662471194248, "reference_active": true, "delta_db": 3.4309781045798764}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3933140159486266e-05, "output_power": 8.496622162313423e-05, "reference_active": true, "delta_db": 3.986222550239382}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.944075796645493e-06, "output_power": 4.197910724138523e-06, "reference_active": true, "delta_db": 3.3432000489715303}], "active_band_count": 3, "active_band_mae_db": 3.58680023459693}}]}, {"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": 2.2340226127796087e-05, "log_rms_mae_db": 1.6226758300285846, "rms_envelope_nrmse": 0.30239893644293886, "envelope_correlation": 0.9667250414131506, "rms_gain_error_db": 1.4809313400992363, "reference_mean_power": 1.7310253593278313e-05, "output_mean_power": 2.4344259248788953e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.3633964732936542e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.958677073783262e-06, "output_power": 1.254404577804949e-05, "reference_active": true, "delta_db": 1.9759674684798485}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3383871013961868e-06, "output_power": 2.1604438472319223e-06, "reference_active": true, "delta_db": 2.079612404164704}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5351180848670046e-07, "output_power": 9.135305522535027e-07, "reference_active": true, "delta_db": 3.0413447689}], "active_band_count": 3, "active_band_mae_db": 2.3656415471815175}}, {"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": 1.65910250564749e-05, "log_rms_mae_db": 1.2649493821757096, "rms_envelope_nrmse": 0.24714061218844488, "envelope_correlation": 0.983292545522119, "rms_gain_error_db": 1.4809316159985262, "reference_mean_power": 1.743895029874837e-05, "output_mean_power": 2.4525253300417638e-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": 7.384237970170298e-06, "output_power": 1.1772065368351708e-05, "reference_active": true, "delta_db": 2.0254698084680407}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.219739967436263e-07, "output_power": 7.102788060330754e-07, "reference_active": true, "delta_db": 2.2614316667227246}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.2063085962498154e-08, "output_power": 6.536882991153593e-08, "reference_active": true, "delta_db": 3.093653918644282}], "active_band_count": 3, "active_band_mae_db": 2.460185131278349}}]}], "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"]}}, "output_samples": 97768, "representation_scalars": 837820, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9952684745862312, "standard_deviation": null, "minimum": 0.9952684745862312, "maximum": 0.9952684745862312, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.225069601144376, "standard_deviation": null, "minimum": 1.225069601144376, "maximum": 1.225069601144376, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 3.519423608536569, "standard_deviation": null, "minimum": 3.519423608536569, "maximum": 3.519423608536569, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.4460664126066819, "standard_deviation": null, "minimum": 0.4460664126066819, "maximum": 0.4460664126066819, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9961564923075931, "standard_deviation": null, "minimum": 0.9961564923075931, "maximum": 0.9961564923075931, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.0993142668333866, "standard_deviation": null, "minimum": 1.0993142668333866, "maximum": 1.0993142668333866, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 3.58680023459693, "standard_deviation": null, "minimum": 3.58680023459693, "maximum": 3.58680023459693, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.44339816855346825, "standard_deviation": null, "minimum": 0.44339816855346825, "maximum": 0.44339816855346825, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9667250414131506, "standard_deviation": null, "minimum": 0.9667250414131506, "maximum": 0.9667250414131506, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.6226758300285846, "standard_deviation": null, "minimum": 1.6226758300285846, "maximum": 1.6226758300285846, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 2.3656415471815175, "standard_deviation": null, "minimum": 2.3656415471815175, "maximum": 2.3656415471815175, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.30239893644293886, "standard_deviation": null, "minimum": 0.30239893644293886, "maximum": 0.30239893644293886, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.983292545522119, "standard_deviation": null, "minimum": 0.983292545522119, "maximum": 0.983292545522119, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.2649493821757096, "standard_deviation": null, "minimum": 1.2649493821757096, "maximum": 1.2649493821757096, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 2.460185131278349, "standard_deviation": null, "minimum": 2.460185131278349, "maximum": 2.460185131278349, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.24714061218844488, "standard_deviation": null, "minimum": 0.24714061218844488, "maximum": 0.24714061218844488, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9953149953594295, "standard_deviation": null, "minimum": 0.9953149953594295, "maximum": 0.9953149953594295, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.0874899359333512, "standard_deviation": null, "minimum": 1.0874899359333512, "maximum": 1.0874899359333512, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.7291963401096601, "standard_deviation": null, "minimum": 0.7291963401096601, "maximum": 0.7291963401096601, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1324766643648859, "standard_deviation": null, "minimum": 0.1324766643648859, "maximum": 0.1324766643648859, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9960510867651321, "standard_deviation": null, "minimum": 0.9960510867651321, "maximum": 0.9960510867651321, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.9383335813158775, "standard_deviation": null, "minimum": 0.9383335813158775, "maximum": 0.9383335813158775, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6580526194158635, "standard_deviation": null, "minimum": 0.6580526194158635, "maximum": 0.6580526194158635, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1268517873044987, "standard_deviation": null, "minimum": 0.1268517873044987, "maximum": 0.1268517873044987, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 3.3083262075485225, "standard_deviation": null, "minimum": 3.3083262075485225, "maximum": 3.3083262075485225, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 5.064250011257688, "standard_deviation": null, "minimum": 5.064250011257688, "maximum": 5.064250011257688, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.8023816747344805, "standard_deviation": null, "minimum": 0.8023816747344805, "maximum": 0.8023816747344805, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 1.427304593284996, "standard_deviation": null, "minimum": 1.427304593284996, "maximum": 1.427304593284996, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9955295999396525, "standard_deviation": null, "minimum": 0.9955295999396525, "maximum": 0.9955295999396525, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.281051353903311, "standard_deviation": null, "minimum": 1.281051353903311, "maximum": 1.281051353903311, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 1.3453967858412106, "standard_deviation": null, "minimum": 1.3453967858412106, "maximum": 1.3453967858412106, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.1978213175455746, "standard_deviation": null, "minimum": 0.1978213175455746, "maximum": 0.1978213175455746, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9967998799201206, "standard_deviation": null, "minimum": 0.9967998799201206, "maximum": 0.9967998799201206, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 1.0522841661395825, "standard_deviation": null, "minimum": 1.0522841661395825, "maximum": 1.0522841661395825, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 1.2404499951826795, "standard_deviation": null, "minimum": 1.2404499951826795, "maximum": 1.2404499951826795, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.19184893224728697, "standard_deviation": null, "minimum": 0.19184893224728697, "maximum": 0.19184893224728697, "valid_count": 1, "planned_count": 1}}, "seconds": 1.6298223770063487, "rtf_including_measurement": 0.40008731945168524}, {"case": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "normal", "speaker": "jvs_jvs066", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.7718417644500732, "predicted_mos": 2.7718417644500732, "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": "44e89563e35e25eef13836d23ec85864f7b3efdea6890165c466d7694ac9c25e", "internal_samples": 82402, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.2233770469974843}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.049109233362817, "全帯域_10ms_rms_envelope_nrmse": 0.0520372381608414, "全帯域_10ms_envelope_correlation": 0.9972597677942939, "全帯域_10ms_modulation_mae_db": 0.4099879727182521, "全帯域_40ms_log_rms_mae_db": 0.691764901980195, "全帯域_40ms_rms_envelope_nrmse": 0.02750848298468261, "全帯域_40ms_envelope_correlation": 0.9991938023694865, "全帯域_40ms_modulation_mae_db": 0.3412411143682586, "300–1000 Hz_10ms_log_rms_mae_db": 1.0078728294089903, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08300230630110786, "300–1000 Hz_10ms_envelope_correlation": 0.9938009516148052, "300–1000 Hz_10ms_modulation_mae_db": 0.45530133856289434, "300–1000 Hz_40ms_log_rms_mae_db": 0.6955685020698031, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.049501898813869044, "300–1000 Hz_40ms_envelope_correlation": 0.9976529432354525, "300–1000 Hz_40ms_modulation_mae_db": 0.16986267903229382, "1000–3000 Hz_10ms_log_rms_mae_db": 1.192982675375049, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09633490155837277, "1000–3000 Hz_10ms_envelope_correlation": 0.9934580290511347, "1000–3000 Hz_10ms_modulation_mae_db": 1.4974397956907641, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7134439024279955, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05501355631461208, "1000–3000 Hz_40ms_envelope_correlation": 0.9979447364588556, "1000–3000 Hz_40ms_modulation_mae_db": 1.1106568001399946, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5525820269658297, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12883967472756222, "3000–6000 Hz_10ms_envelope_correlation": 0.9862221915894895, "3000–6000 Hz_10ms_modulation_mae_db": 0.44368834882513314, "3000–6000 Hz_40ms_log_rms_mae_db": 0.945951543088404, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07446953019457021, "3000–6000 Hz_40ms_envelope_correlation": 0.9955865066506032, "3000–6000 Hz_40ms_modulation_mae_db": 0.5460533889214417, "mr_stft_db": 5.412415856054025, "band_mae_db": 0.1339064221668973, "rms_gain_error_db": -0.03679140588323153, "output_peak": 0.4940550430321574}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0202506040218595, "全帯域_10ms_rms_envelope_nrmse": 0.05192473257665187, "全帯域_10ms_envelope_correlation": 0.9973141282935143, "全帯域_10ms_modulation_mae_db": 0.4925477173465606, "全帯域_40ms_log_rms_mae_db": 0.6540355089167237, "全帯域_40ms_rms_envelope_nrmse": 0.028939181767602944, "全帯域_40ms_envelope_correlation": 0.9991629496809266, "全帯域_40ms_modulation_mae_db": 0.6900900270635804, "300–1000 Hz_10ms_log_rms_mae_db": 1.0030091825533718, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0731643033764707, "300–1000 Hz_10ms_envelope_correlation": 0.9952260436890367, "300–1000 Hz_10ms_modulation_mae_db": 0.22805738812921686, "300–1000 Hz_40ms_log_rms_mae_db": 0.7142435775769274, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04073086075409737, "300–1000 Hz_40ms_envelope_correlation": 0.9984635322796913, "300–1000 Hz_40ms_modulation_mae_db": 0.520988571447217, "1000–3000 Hz_10ms_log_rms_mae_db": 1.186964711717184, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09704778389757539, "1000–3000 Hz_10ms_envelope_correlation": 0.9932417957883001, "1000–3000 Hz_10ms_modulation_mae_db": 0.9068131261998977, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7658967755669296, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.052289655671736414, "1000–3000 Hz_40ms_envelope_correlation": 0.9980299148811216, "1000–3000 Hz_40ms_modulation_mae_db": 0.7328007589043545, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5440971789484215, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14058948443874925, "3000–6000 Hz_10ms_envelope_correlation": 0.9857080316704306, "3000–6000 Hz_10ms_modulation_mae_db": 1.0164682327726993, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9678666756885096, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09075472043012497, "3000–6000 Hz_40ms_envelope_correlation": 0.99585567726263, "3000–6000 Hz_40ms_modulation_mae_db": 1.1081455026293499, "mr_stft_db": 5.404680727475333, "band_mae_db": 0.2171560577513623, "rms_gain_error_db": -0.07592008302319037, "output_peak": 0.44236961049926127}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0101129005828164, "全帯域_10ms_rms_envelope_nrmse": 0.05137522728101294, "全帯域_10ms_envelope_correlation": 0.99735244546018, "全帯域_10ms_modulation_mae_db": 0.2410816526541668, "全帯域_40ms_log_rms_mae_db": 0.6427472450205256, "全帯域_40ms_rms_envelope_nrmse": 0.02703841250037219, "全帯域_40ms_envelope_correlation": 0.9992535520770257, "全帯域_40ms_modulation_mae_db": 0.5021579916962261, "300–1000 Hz_10ms_log_rms_mae_db": 1.027641356972985, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07185690912973666, "300–1000 Hz_10ms_envelope_correlation": 0.9953673533636704, "300–1000 Hz_10ms_modulation_mae_db": 0.4239093093726847, "300–1000 Hz_40ms_log_rms_mae_db": 0.7214570514216821, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03603250067251126, "300–1000 Hz_40ms_envelope_correlation": 0.9987682350326876, "300–1000 Hz_40ms_modulation_mae_db": 0.5398222022561562, "1000–3000 Hz_10ms_log_rms_mae_db": 1.114614050250851, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10435301409013106, "1000–3000 Hz_10ms_envelope_correlation": 0.9921273515668333, "1000–3000 Hz_10ms_modulation_mae_db": 0.964717996395486, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6972136438902173, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05835888049383821, "1000–3000 Hz_40ms_envelope_correlation": 0.997455009985255, "1000–3000 Hz_40ms_modulation_mae_db": 1.2383658256246493, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5716214701044846, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13718282231743167, "3000–6000 Hz_10ms_envelope_correlation": 0.9850877778350183, "3000–6000 Hz_10ms_modulation_mae_db": 0.47338373675976175, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9631545587672521, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08830095907300287, "3000–6000 Hz_40ms_envelope_correlation": 0.9944779117882385, "3000–6000 Hz_40ms_modulation_mae_db": 0.4851074682237552, "mr_stft_db": 5.401250240340858, "band_mae_db": 0.25532963132897957, "rms_gain_error_db": -0.06144312458213627, "output_peak": 0.48063084494475516}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0199088579292368, "全帯域_10ms_rms_envelope_nrmse": 0.048159760482909056, "全帯域_10ms_envelope_correlation": 0.9976884404427859, "全帯域_10ms_modulation_mae_db": 0.7729596808846887, "全帯域_40ms_log_rms_mae_db": 0.6067709653133923, "全帯域_40ms_rms_envelope_nrmse": 0.026646348254904164, "全帯域_40ms_envelope_correlation": 0.9992799548890131, "全帯域_40ms_modulation_mae_db": 0.8809067443680701, "300–1000 Hz_10ms_log_rms_mae_db": 1.0463429098888957, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08200987282026617, "300–1000 Hz_10ms_envelope_correlation": 0.9940244052951823, "300–1000 Hz_10ms_modulation_mae_db": 0.5371503759599447, "300–1000 Hz_40ms_log_rms_mae_db": 0.7108942056558032, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04395000413069768, "300–1000 Hz_40ms_envelope_correlation": 0.9982344960770407, "300–1000 Hz_40ms_modulation_mae_db": 1.2499989360050217, "1000–3000 Hz_10ms_log_rms_mae_db": 1.17969079391448, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08035893217827103, "1000–3000 Hz_10ms_envelope_correlation": 0.9955928387459642, "1000–3000 Hz_10ms_modulation_mae_db": 0.30845717432515846, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7291164600333098, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05157459763952381, "1000–3000 Hz_40ms_envelope_correlation": 0.9982807812309262, "1000–3000 Hz_40ms_modulation_mae_db": 0.315674117304229, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5499750894522588, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1403927351139136, "3000–6000 Hz_10ms_envelope_correlation": 0.9847112672917242, "3000–6000 Hz_10ms_modulation_mae_db": 0.953710905813301, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9385606676242755, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08781904319752566, "3000–6000 Hz_40ms_envelope_correlation": 0.9950993897548006, "3000–6000 Hz_40ms_modulation_mae_db": 0.959177885365004, "mr_stft_db": 5.404455880718025, "band_mae_db": 0.2007934142258914, "rms_gain_error_db": -0.06177048434549806, "output_peak": 0.48528542811624814}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0602407392427105, "全帯域_10ms_rms_envelope_nrmse": 0.05742782354891619, "全帯域_10ms_envelope_correlation": 0.9967592191548648, "全帯域_10ms_modulation_mae_db": 0.5406488134636548, "全帯域_40ms_log_rms_mae_db": 0.6665642194226192, "全帯域_40ms_rms_envelope_nrmse": 0.03378570224035034, "全帯域_40ms_envelope_correlation": 0.9988992171465143, "全帯域_40ms_modulation_mae_db": 0.7415337084636553, "300–1000 Hz_10ms_log_rms_mae_db": 1.0266449039118073, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07688689573988683, "300–1000 Hz_10ms_envelope_correlation": 0.9948150355742928, "300–1000 Hz_10ms_modulation_mae_db": 0.46467840894306683, "300–1000 Hz_40ms_log_rms_mae_db": 0.6952310742107545, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04821172233058352, "300–1000 Hz_40ms_envelope_correlation": 0.9979272267783281, "300–1000 Hz_40ms_modulation_mae_db": 0.8657996635176293, "1000–3000 Hz_10ms_log_rms_mae_db": 1.155048035295629, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11309593071313595, "1000–3000 Hz_10ms_envelope_correlation": 0.9909326784604214, "1000–3000 Hz_10ms_modulation_mae_db": 0.8341115614663727, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7198222289436252, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0640895636577393, "1000–3000 Hz_40ms_envelope_correlation": 0.99719254580144, "1000–3000 Hz_40ms_modulation_mae_db": 0.8892854410464973, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5562566597692722, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12681082281957862, "3000–6000 Hz_10ms_envelope_correlation": 0.987865362329941, "3000–6000 Hz_10ms_modulation_mae_db": 0.9900805388475288, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9715287652349129, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08327200718369178, "3000–6000 Hz_40ms_envelope_correlation": 0.9957039238432259, "3000–6000 Hz_40ms_modulation_mae_db": 1.1017775303664756, "mr_stft_db": 5.410989510750338, "band_mae_db": 0.2846385986040471, "rms_gain_error_db": -0.10368595203355255, "output_peak": 0.42892179401569813}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0194647385385498, "全帯域_10ms_rms_envelope_nrmse": 0.05612592073833994, "全帯域_10ms_envelope_correlation": 0.9969650817582717, "全帯域_10ms_modulation_mae_db": 0.3503662859566033, "全帯域_40ms_log_rms_mae_db": 0.6182677693957666, "全帯域_40ms_rms_envelope_nrmse": 0.035416210148992766, "全帯域_40ms_envelope_correlation": 0.9988370950488965, "全帯域_40ms_modulation_mae_db": 0.6229045051138178, "300–1000 Hz_10ms_log_rms_mae_db": 1.0322713486856927, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08066503644478727, "300–1000 Hz_10ms_envelope_correlation": 0.9942850942338086, "300–1000 Hz_10ms_modulation_mae_db": 0.4335140722180327, "300–1000 Hz_40ms_log_rms_mae_db": 0.7299121375714727, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.054212363772506794, "300–1000 Hz_40ms_envelope_correlation": 0.9973541732156581, "300–1000 Hz_40ms_modulation_mae_db": 0.6996020978372561, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1829358283936409, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10772122394002936, "1000–3000 Hz_10ms_envelope_correlation": 0.992313532904523, "1000–3000 Hz_10ms_modulation_mae_db": 0.5266049821238928, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7308651814486958, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07248908777531869, "1000–3000 Hz_40ms_envelope_correlation": 0.9968836581414033, "1000–3000 Hz_40ms_modulation_mae_db": 0.6348975683814465, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5615827764753747, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1368214305903779, "3000–6000 Hz_10ms_envelope_correlation": 0.9863062515489929, "3000–6000 Hz_10ms_modulation_mae_db": 0.7945053661772233, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9416266028764667, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08582672519885128, "3000–6000 Hz_40ms_envelope_correlation": 0.9963130297054381, "3000–6000 Hz_40ms_modulation_mae_db": 1.113401544782584, "mr_stft_db": 5.400882368772638, "band_mae_db": 0.2151955432594271, "rms_gain_error_db": -0.12156806392928735, "output_peak": 0.4661184207245495}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0155546507619437, "全帯域_10ms_rms_envelope_nrmse": 0.051919098807269005, "全帯域_10ms_envelope_correlation": 0.9973465378850088, "全帯域_10ms_modulation_mae_db": 0.6358394549626659, "全帯域_40ms_log_rms_mae_db": 0.6444202639867401, "全帯域_40ms_rms_envelope_nrmse": 0.02884085623537833, "全帯域_40ms_envelope_correlation": 0.9992009949996244, "全帯域_40ms_modulation_mae_db": 0.7354760290939137, "300–1000 Hz_10ms_log_rms_mae_db": 1.062120807862872, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08077958335683412, "300–1000 Hz_10ms_envelope_correlation": 0.9941692776506158, "300–1000 Hz_10ms_modulation_mae_db": 0.6908067995887444, "300–1000 Hz_40ms_log_rms_mae_db": 0.7582329201718757, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04892842091530338, "300–1000 Hz_40ms_envelope_correlation": 0.9977518947723668, "300–1000 Hz_40ms_modulation_mae_db": 0.7766989060860975, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1827891826623569, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09257498973336213, "1000–3000 Hz_10ms_envelope_correlation": 0.9941288247862055, "1000–3000 Hz_10ms_modulation_mae_db": 1.068838205914292, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7189348250681229, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.051666813928613144, "1000–3000 Hz_40ms_envelope_correlation": 0.9983867675230379, "1000–3000 Hz_40ms_modulation_mae_db": 1.187382283551719, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5731148955989798, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13986330290150692, "3000–6000 Hz_10ms_envelope_correlation": 0.9843463314961102, "3000–6000 Hz_10ms_modulation_mae_db": 0.5457327772463629, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9769158877757739, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09018633695689005, "3000–6000 Hz_40ms_envelope_correlation": 0.9940526155470838, "3000–6000 Hz_40ms_modulation_mae_db": 0.44685134680866173, "mr_stft_db": 5.396708009337327, "band_mae_db": 0.2657640882782512, "rms_gain_error_db": -0.0893647371947891, "output_peak": 0.5273211927974283}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0528565732624178, "全帯域_10ms_rms_envelope_nrmse": 0.0539645882149957, "全帯域_10ms_envelope_correlation": 0.9971146898123595, "全帯域_10ms_modulation_mae_db": 0.28126901463799286, "全帯域_40ms_log_rms_mae_db": 0.7257473044825354, "全帯域_40ms_rms_envelope_nrmse": 0.029316432391092037, "全帯域_40ms_envelope_correlation": 0.999162232361935, "全帯域_40ms_modulation_mae_db": 0.6444213313205014, "300–1000 Hz_10ms_log_rms_mae_db": 1.0766503040736177, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07268225641175288, "300–1000 Hz_10ms_envelope_correlation": 0.995268873856639, "300–1000 Hz_10ms_modulation_mae_db": 0.3547542554687912, "300–1000 Hz_40ms_log_rms_mae_db": 0.7831942208671464, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04208349151033087, "300–1000 Hz_40ms_envelope_correlation": 0.9983203397230125, "300–1000 Hz_40ms_modulation_mae_db": 0.41217168337477883, "1000–3000 Hz_10ms_log_rms_mae_db": 1.128687563442622, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08339627036780677, "1000–3000 Hz_10ms_envelope_correlation": 0.9952738230239843, "1000–3000 Hz_10ms_modulation_mae_db": 0.7281357422484315, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6757516644372958, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04950890607760886, "1000–3000 Hz_40ms_envelope_correlation": 0.9985122317286776, "1000–3000 Hz_40ms_modulation_mae_db": 0.6946106269536251, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5614913945634026, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13594839998920313, "3000–6000 Hz_10ms_envelope_correlation": 0.9854032653826278, "3000–6000 Hz_10ms_modulation_mae_db": 0.40975758527739203, "3000–6000 Hz_40ms_log_rms_mae_db": 0.964491146115049, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09387684714447714, "3000–6000 Hz_40ms_envelope_correlation": 0.9934845188662679, "3000–6000 Hz_40ms_modulation_mae_db": 0.38687875824994933, "mr_stft_db": 5.4136666472926445, "band_mae_db": 0.18176852275932448, "rms_gain_error_db": -0.0803491741691318, "output_peak": 0.5101776125664701}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.590873420934425, "spectral_convergence": 0.15501802968486098, "spectral_convergence_status": "ok", "amplitude_floor": 1.160899353957536e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.396381361941013, "spectral_convergence": 0.1603419835366481, "spectral_convergence_status": "ok", "amplitude_floor": 1.2404642078999559e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.249992785286638, "spectral_convergence": 0.161280162053334, "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": 0.0001295127535676162, "delta_db": 0.2584590690167496, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.002976977856333367, "output_power": 0.0029404510024172666, "delta_db": -0.05361657220109516, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0005003734805512382, "output_power": 0.0005126508727890367, "delta_db": 0.10527416773886672, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0006045073176565132, "output_power": 0.0005872523708902618, "delta_db": -0.12576783619134096, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.799447769358915e-05, "output_power": 2.658550537446275e-05, "delta_db": -0.2242744866044544, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.1130460027276325e-05, "output_power": 2.055522044733362e-05, "delta_db": -0.1198681330563337, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 6.414014484484223e-06, "output_power": 6.488411799011655e-06, "delta_db": 0.0500846903594406, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.1339064221668973, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.03679140588323153, "pitch": null, "output_rms_dbfs": -23.74327898677165, "output_peak": 0.4940550430321574, "reference_rms_dbfs": -23.706487580888414, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.412415856054025}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 123603, "output_samples": 123603, "intelligibility": {"estoi": {"value": 0.9338862734563567, "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"}}, "level": {"reference": {"rms": 0.06526429048136644, "rms_dbfs": -23.706487580888414, "peak": 0.472930908203125, "peak_dbfs": -6.504046038430433, "crest_factor_db": 17.20244154245798, "mean": -4.952813582093477e-07, "zero_energy": false}, "output": {"rms": 0.06498843079568078, "rms_dbfs": -23.743278986771642, "peak": 0.4940550430321574, "peak_dbfs": -6.124493266326518, "crest_factor_db": 17.61878572044513, "mean": -4.607626390746676e-05, "zero_energy": false}, "rms_difference_db": -0.03679140588322838}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 515, "uncovered_tail_samples": 3, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 3.877530492221316e-06, "threshold_dbfs": -54.114447782851144, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 163, "quiet_samples": 39120, "reference_mean_power": 2.965885538280254e-07, "output_mean_power": 1.1667034638686615e-06, "output_rms_dbfs": -59.330395127381635, "output_zero_energy": false, "output_peak": 0.03205048831272608, "output_energy_fraction": 8.742954541438391e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 508, "reference_estimated_voiced_frames": 307, "output_estimated_voiced_frames": 293, "both_estimated_voiced_frames": 290, "reference_voiced_output_unvoiced_frames": 17, "reference_unvoiced_output_voiced_frames": 3, "paired_voiced_fraction": 0.9446254071661238, "absolute_difference_cents_median": 1.4235716577015398, "absolute_difference_cents_p95": 8.116114326716621, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 3, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.049109233362817, "rms_envelope_nrmse": 0.0520372381608414, "envelope_correlation": 0.9972597677942939, "rms_gain_error_db": -0.03679143052708731, "reference_mean_power": 0.004263670396682444, "output_mean_power": 0.004227703106862515}, "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": 0.0006363629931509891, "reference_active": true, "delta_db": -0.022658768492841326}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00010753471412479324, "output_power": 0.0001044165243647503, "reference_active": true, "delta_db": -0.12779451817309462}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.642399701776048e-05, "output_power": 2.060855058152356e-05, "reference_active": true, "delta_db": -1.0795106314888205}], "active_band_count": 3, "active_band_mae_db": 0.4099879727182521}}, {"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": 0.691764901980195, "rms_envelope_nrmse": 0.02750848298468261, "envelope_correlation": 0.9991938023694865, "rms_gain_error_db": -0.03679139436333028, "reference_mean_power": 0.004288676885881949, "output_mean_power": 0.004252498682792096}, "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": 0.0005583003201804159, "reference_active": true, "delta_db": -0.016077813112650156}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.355233098915975e-05, "output_power": 5.537537665115323e-05, "reference_active": true, "delta_db": 0.14538313965028052}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6814737983602469e-06, "output_power": 1.3786812373372077e-06, "reference_active": true, "delta_db": -0.8622623903418452}], "active_band_count": 3, "active_band_mae_db": 0.3412411143682586}}]}, {"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": 0.00013036665176469105, "log_rms_mae_db": 1.0078728294089903, "rms_envelope_nrmse": 0.08300230630110786, "envelope_correlation": 0.9938009516148052, "rms_gain_error_db": -0.025371410776678108, "reference_mean_power": 0.0015158717741492558, "output_mean_power": 0.0015070418937937306}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.187895246183773e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00036232449214344424, "output_power": 0.00034866878265928835, "reference_active": true, "delta_db": -0.1668462668910261}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.27378870003226e-05, "output_power": 4.9097253115532536e-05, "reference_active": true, "delta_db": -0.3106553036299407}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1888503336360718e-05, "output_power": 1.458704855329132e-05, "reference_active": true, "delta_db": 0.8884024451677162}], "active_band_count": 3, "active_band_mae_db": 0.45530133856289434}}, {"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": 0.00011772885872912566, "log_rms_mae_db": 0.6955685020698031, "rms_envelope_nrmse": 0.049501898813869044, "envelope_correlation": 0.9976529432354525, "rms_gain_error_db": -0.025371453369618116, "reference_mean_power": 0.001524762506178652, "output_mean_power": 0.0015158808228687877}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.112801089937839e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003193313097067297, "output_power": 0.0003049072040312605, "reference_active": true, "delta_db": -0.20073816664399644}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4777353739459925e-05, "output_power": 2.4500757966616757e-05, "reference_active": true, "delta_db": -0.0487540107528444}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.078329801445271e-06, "output_power": 1.1448832295589412e-06, "reference_active": true, "delta_db": 0.26009585970004073}], "active_band_count": 3, "active_band_mae_db": 0.16986267903229382}}]}, {"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": 1.192982675375049, "rms_envelope_nrmse": 0.09633490155837277, "envelope_correlation": 0.9934580290511347, "rms_gain_error_db": -0.18287440685545198, "reference_mean_power": 0.00046194923691890866, "output_mean_power": 0.0004429011555299284}, "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": 0.00021745730779534732, "output_power": 0.0002126483263878864, "reference_active": true, "delta_db": -0.09712037973891635}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.26315917085523e-05, "output_power": 5.66090009147325e-05, "reference_active": true, "delta_db": -0.43907958784648304}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.1826956188918756e-06, "output_power": 2.888520943456187e-06, "reference_active": true, "delta_db": -3.9561194194868934}], "active_band_count": 3, "active_band_mae_db": 1.4974397956907641}}, {"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": 0.7134439024279955, "rms_envelope_nrmse": 0.05501355631461208, "envelope_correlation": 0.9979447364588556, "rms_gain_error_db": -0.1828744201887186, "reference_mean_power": 0.00046465861059889405, "output_mean_power": 0.0004454988091375238}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 3.961591197471976e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00020060895095818542, "output_power": 0.0001945927694051011, "reference_active": true, "delta_db": -0.13223607971410525}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.461992258627009e-05, "output_power": 3.144883435929303e-05, "reference_active": true, "delta_db": -0.41721539315657574}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.414804941169707e-07, "output_power": 3.907039823619506e-07, "reference_active": true, "delta_db": -2.7825189275493027}], "active_band_count": 3, "active_band_mae_db": 1.1106568001399946}}]}, {"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": 1.8521534194293836e-05, "log_rms_mae_db": 1.5525820269658297, "rms_envelope_nrmse": 0.12883967472756222, "envelope_correlation": 0.9862221915894895, "rms_gain_error_db": -0.28153229037705696, "reference_mean_power": 1.684190350930034e-05, "output_mean_power": 1.5784758647750286e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.2347471453358601e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.2528634901423365e-06, "output_power": 5.740910142473202e-06, "reference_active": true, "delta_db": -0.3709819816867712}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0675239180772895e-06, "output_power": 1.7383220427357723e-06, "reference_active": true, "delta_db": -0.7532030511354535}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.652671220760481e-07, "output_power": 2.529271348179299e-07, "reference_active": true, "delta_db": -0.2068800136531748}], "active_band_count": 3, "active_band_mae_db": 0.44368834882513314}}, {"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": 1.438595762049439e-05, "log_rms_mae_db": 0.945951543088404, "rms_envelope_nrmse": 0.07446953019457021, "envelope_correlation": 0.9955865066506032, "rms_gain_error_db": -0.2815327919302232, "reference_mean_power": 1.694067457344735e-05, "output_mean_power": 1.5877328144207442e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.0973267407020905e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.499482122012408e-06, "output_power": 5.096504604583073e-06, "reference_active": true, "delta_db": -0.33049373635389184}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.267943787177926e-06, "output_power": 1.0651004210936491e-06, "reference_active": true, "delta_db": -0.7570944364283301}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8893101287704844e-08, "output_power": 1.66435533889388e-08, "reference_active": true, "delta_db": -0.5505719939821034}], "active_band_count": 3, "active_band_mae_db": 0.5460533889214417}}]}], "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"]}}, "output_samples": 123603, "representation_scalars": 1161513, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9933836092909207, "standard_deviation": 0.0015930611648328058, "minimum": 0.9909326784604214, "maximum": 0.9955928387459642, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1654641051314765, "standard_deviation": 0.02945723898785403, "minimum": 1.114614050250851, "maximum": 1.192982675375049, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8543898230455369, "standard_deviation": 0.3578224908027269, "minimum": 0.30845717432515846, "maximum": 1.4974397956907641, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.09686038080983556, "standard_deviation": 0.01140141876891311, "minimum": 0.08035893217827103, "maximum": 0.11309593071313595, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978357057188396, "standard_deviation": 0.000594502454289868, "minimum": 0.9968836581414033, "maximum": 0.9985122317286776, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.718880585227024, "standard_deviation": 0.02623774038564241, "minimum": 0.6757516644372958, "maximum": 0.7658967755669296, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8504591777383144, "standard_deviation": 0.31708339838677274, "minimum": 0.315674117304229, "maximum": 1.2383658256246493, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05687388269487381, "standard_deviation": 0.007856032435316221, "minimum": 0.04950890607760886, "maximum": 0.07248908777531869, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9857063098930419, "standard_deviation": 0.0011085153008625985, "minimum": 0.9843463314961102, "maximum": 0.987865362329941, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.558840186484753, "standard_deviation": 0.010166222945635234, "minimum": 1.5440971789484215, "maximum": 1.5731148955989798, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7034159364649253, "standard_deviation": 0.26256852955123156, "minimum": 0.40975758527739203, "maximum": 1.0164682327726993, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.13580608411229042, "standard_deviation": 0.005247740822788121, "minimum": 0.12681082281957862, "maximum": 0.14058948443874925, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.995071696677286, "standard_deviation": 0.0009806179464051379, "minimum": 0.9934845188662679, "maximum": 0.9963130297054381, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9587619808963305, "standard_deviation": 0.014606213030662585, "minimum": 0.9385606676242755, "maximum": 0.9769158877757739, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7684241781684026, "standard_deviation": 0.32963930837337513, "minimum": 0.38687875824994933, "maximum": 1.113401544782584, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08681327117239175, "standard_deviation": 0.005927095869582461, "minimum": 0.07446953019457021, "maximum": 0.09387684714447714, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9946196294097563, "standard_deviation": 0.000624017728656425, "minimum": 0.9938009516148052, "maximum": 0.9953673533636704, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.035319205419779, "standard_deviation": 0.025323143275671752, "minimum": 1.0030091825533718, "maximum": 1.0766503040736177, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4485214935304219, "standard_deviation": 0.13367976636847956, "minimum": 0.22805738812921686, "maximum": 0.6908067995887444, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07763089544760532, "standard_deviation": 0.004558816750132325, "minimum": 0.07185690912973666, "maximum": 0.08300230630110786, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9980591051392798, "standard_deviation": 0.0004689042892136012, "minimum": 0.9973541732156581, "maximum": 0.9987682350326876, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7260917111931832, "standard_deviation": 0.030671572015897566, "minimum": 0.6952310742107545, "maximum": 0.7831942208671464, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6543680924445563, "standard_deviation": 0.32531431131614036, "minimum": 0.16986267903229382, "maximum": 1.2499989360050217, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04545640786248749, "standard_deviation": 0.0058244071741696355, "minimum": 0.03603250067251126, "maximum": 0.054212363772506794, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.21931903479677256, "standard_deviation": 0.04897636032050108, "minimum": 0.1339064221668973, "maximum": 0.2846385986040471, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.405631155092649, "standard_deviation": 0.006129131558659359, "minimum": 5.396708009337327, "maximum": 5.4136666472926445, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.479359993337071, "standard_deviation": 0.03292917129198765, "minimum": 0.42892179401569813, "maximum": 0.5273211927974283, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07886162814510213, "standard_deviation": 0.026529451446619747, "minimum": -0.12156806392928735, "maximum": -0.03679140588323153, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9972250388251599, "standard_deviation": 0.0002807187490719189, "minimum": 0.9967592191548648, "maximum": 0.9976884404427859, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.030937287212794, "standard_deviation": 0.01966540993193277, "minimum": 1.0101129005828164, "maximum": 1.0602407392427105, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.46558757407807316, "standard_deviation": 0.18148902170136957, "minimum": 0.2410816526541668, "maximum": 0.7729596808846887, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.052866798726367015, "standard_deviation": 0.0029151024089613033, "minimum": 0.048159760482909056, "maximum": 0.05742782354891619, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9991237248216778, "standard_deviation": 0.00016376212555728326, "minimum": 0.9988370950488965, "maximum": 0.9992799548890131, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6562897723148122, "standard_deviation": 0.03857376938640999, "minimum": 0.6067709653133923, "maximum": 0.7257473044825354, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6448414314360029, "standard_deviation": 0.16403458512746108, "minimum": 0.3412411143682586, "maximum": 0.8809067443680701, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.029686453315421923, "standard_deviation": 0.00320807537967001, "minimum": 0.026646348254904164, "maximum": 0.035416210148992766, "valid_count": 8, "planned_count": 8}}, "seconds": 6.925677220999205, "rtf_including_measurement": 1.344759053615049}, {"case": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "normal", "speaker": "jvs_jvs066", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.7436912059783936, "predicted_mos": 2.7436912059783936, "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": 3.3938008039986016}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9391602958669893, "全帯域_10ms_rms_envelope_nrmse": 0.050446435733602066, "全帯域_10ms_envelope_correlation": 0.9974279432805429, "全帯域_10ms_modulation_mae_db": 0.42887741030679444, "全帯域_40ms_log_rms_mae_db": 0.6260002844552237, "全帯域_40ms_rms_envelope_nrmse": 0.02617658167970614, "全帯域_40ms_envelope_correlation": 0.9992771723517097, "全帯域_40ms_modulation_mae_db": 0.32416176862891993, "300–1000 Hz_10ms_log_rms_mae_db": 0.9188609985451879, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08170706998904456, "300–1000 Hz_10ms_envelope_correlation": 0.9939911280858044, "300–1000 Hz_10ms_modulation_mae_db": 0.4844192068167566, "300–1000 Hz_40ms_log_rms_mae_db": 0.6098419277655105, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04775923398827694, "300–1000 Hz_40ms_envelope_correlation": 0.9978237702948337, "300–1000 Hz_40ms_modulation_mae_db": 0.19858903491842128, "1000–3000 Hz_10ms_log_rms_mae_db": 1.119134087493373, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09620255118161417, "1000–3000 Hz_10ms_envelope_correlation": 0.9934465362390451, "1000–3000 Hz_10ms_modulation_mae_db": 1.5514452791588151, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6666041696097933, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05348534160985613, "1000–3000 Hz_40ms_envelope_correlation": 0.9980307304516328, "1000–3000 Hz_40ms_modulation_mae_db": 1.1590485693517225, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5189547295488528, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13497428981539536, "3000–6000 Hz_10ms_envelope_correlation": 0.984535025015691, "3000–6000 Hz_10ms_modulation_mae_db": 0.4516382991296619, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9092352522372645, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.078063537591977, "3000–6000 Hz_40ms_envelope_correlation": 0.9946863946190511, "3000–6000 Hz_40ms_modulation_mae_db": 0.3971676927246853, "mr_stft_db": 5.4099748533092225, "band_mae_db": 0.13042859411034757, "rms_gain_error_db": -0.0429407980749169, "output_peak": 0.4922653919690344}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9184599124599463, "全帯域_10ms_rms_envelope_nrmse": 0.05244065449399797, "全帯域_10ms_envelope_correlation": 0.9972532677632561, "全帯域_10ms_modulation_mae_db": 0.4999439189336156, "全帯域_40ms_log_rms_mae_db": 0.6393575823359062, "全帯域_40ms_rms_envelope_nrmse": 0.029281023265963067, "全帯域_40ms_envelope_correlation": 0.9991356361798595, "全帯域_40ms_modulation_mae_db": 0.6998089766356518, "300–1000 Hz_10ms_log_rms_mae_db": 0.9101695454202657, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07186036209911505, "300–1000 Hz_10ms_envelope_correlation": 0.9953790721394139, "300–1000 Hz_10ms_modulation_mae_db": 0.19524740158449228, "300–1000 Hz_40ms_log_rms_mae_db": 0.6482276971186975, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03906005381512842, "300–1000 Hz_40ms_envelope_correlation": 0.9985734790758151, "300–1000 Hz_40ms_modulation_mae_db": 0.5108514215639425, "1000–3000 Hz_10ms_log_rms_mae_db": 1.096546489062413, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09711852708774871, "1000–3000 Hz_10ms_envelope_correlation": 0.9932013823650044, "1000–3000 Hz_10ms_modulation_mae_db": 0.9226187135874194, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7028311570849489, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05229775487434391, "1000–3000 Hz_40ms_envelope_correlation": 0.9979855043963436, "1000–3000 Hz_40ms_modulation_mae_db": 0.7331670064090398, "3000–6000 Hz_10ms_log_rms_mae_db": 1.479362125012706, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14188477654563603, "3000–6000 Hz_10ms_envelope_correlation": 0.9847168784677715, "3000–6000 Hz_10ms_modulation_mae_db": 0.8697589138184333, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9273300975004455, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08861411985049761, "3000–6000 Hz_40ms_envelope_correlation": 0.9954350046224301, "3000–6000 Hz_40ms_modulation_mae_db": 1.0070556493672134, "mr_stft_db": 5.399291969504273, "band_mae_db": 0.17851077695849002, "rms_gain_error_db": -0.07316121078605164, "output_peak": 0.4382194775398731}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9047532321453396, "全帯域_10ms_rms_envelope_nrmse": 0.051335368451230705, "全帯域_10ms_envelope_correlation": 0.9973561694923915, "全帯域_10ms_modulation_mae_db": 0.20401383572810097, "全帯域_40ms_log_rms_mae_db": 0.5946366766077676, "全帯域_40ms_rms_envelope_nrmse": 0.02703620027795984, "全帯域_40ms_envelope_correlation": 0.9992550037753389, "全帯域_40ms_modulation_mae_db": 0.4814718027705495, "300–1000 Hz_10ms_log_rms_mae_db": 0.977472899388501, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07071100241333546, "300–1000 Hz_10ms_envelope_correlation": 0.9955111624551191, "300–1000 Hz_10ms_modulation_mae_db": 0.42243992726067825, "300–1000 Hz_40ms_log_rms_mae_db": 0.6849734756036417, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03581446364471069, "300–1000 Hz_40ms_envelope_correlation": 0.9987813970035843, "300–1000 Hz_40ms_modulation_mae_db": 0.5784297322918257, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0667556817334227, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10468282804556141, "1000–3000 Hz_10ms_envelope_correlation": 0.9920611841434286, "1000–3000 Hz_10ms_modulation_mae_db": 0.9320728826929954, "1000–3000 Hz_40ms_log_rms_mae_db": 0.683492072727814, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05897413001689995, "1000–3000 Hz_40ms_envelope_correlation": 0.9973711122062803, "1000–3000 Hz_40ms_modulation_mae_db": 1.2182260110914687, "3000–6000 Hz_10ms_log_rms_mae_db": 1.523066591798381, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.137940867095787, "3000–6000 Hz_10ms_envelope_correlation": 0.9846397054273037, "3000–6000 Hz_10ms_modulation_mae_db": 0.3315430793639047, "3000–6000 Hz_40ms_log_rms_mae_db": 0.90791291029377, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08560990130337952, "3000–6000 Hz_40ms_envelope_correlation": 0.9946110790139833, "3000–6000 Hz_40ms_modulation_mae_db": 0.4076536774328994, "mr_stft_db": 5.401186207873149, "band_mae_db": 0.21649405158673257, "rms_gain_error_db": -0.06268098947909678, "output_peak": 0.4800991516105175}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9258921149131997, "全帯域_10ms_rms_envelope_nrmse": 0.04782543324840088, "全帯域_10ms_envelope_correlation": 0.9977097980930592, "全帯域_10ms_modulation_mae_db": 0.7451902666618765, "全帯域_40ms_log_rms_mae_db": 0.5934413498328736, "全帯域_40ms_rms_envelope_nrmse": 0.026792904594765705, "全帯域_40ms_envelope_correlation": 0.9992618452510984, "全帯域_40ms_modulation_mae_db": 0.8504734549739498, "300–1000 Hz_10ms_log_rms_mae_db": 0.9726721097788524, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08072312846971083, "300–1000 Hz_10ms_envelope_correlation": 0.9941893564159314, "300–1000 Hz_10ms_modulation_mae_db": 0.4683157568440461, "300–1000 Hz_40ms_log_rms_mae_db": 0.6485071426606711, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043280791478191465, "300–1000 Hz_40ms_envelope_correlation": 0.9982707540785666, "300–1000 Hz_40ms_modulation_mae_db": 1.1697263676860303, "1000–3000 Hz_10ms_log_rms_mae_db": 1.108727055800543, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08054424978600107, "1000–3000 Hz_10ms_envelope_correlation": 0.9955178946968464, "1000–3000 Hz_10ms_modulation_mae_db": 0.170472382909337, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6763738873825309, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0506368540292873, "1000–3000 Hz_40ms_envelope_correlation": 0.9982928507898745, "1000–3000 Hz_40ms_modulation_mae_db": 0.17503139965793793, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5031205884709364, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1423444852593318, "3000–6000 Hz_10ms_envelope_correlation": 0.9837048426793317, "3000–6000 Hz_10ms_modulation_mae_db": 0.7147961969713411, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9121001460848825, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08665240328622097, "3000–6000 Hz_40ms_envelope_correlation": 0.9946565945090129, "3000–6000 Hz_40ms_modulation_mae_db": 0.7883438587022256, "mr_stft_db": 5.398211604335434, "band_mae_db": 0.2028538694282477, "rms_gain_error_db": -0.05750865267194159, "output_peak": 0.4626315004056094}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9710461353247846, "全帯域_10ms_rms_envelope_nrmse": 0.05838234052457022, "全帯域_10ms_envelope_correlation": 0.9966494163318691, "全帯域_10ms_modulation_mae_db": 0.5553492915157215, "全帯域_40ms_log_rms_mae_db": 0.6066853168182785, "全帯域_40ms_rms_envelope_nrmse": 0.033890134365547185, "全帯域_40ms_envelope_correlation": 0.9988978528528835, "全帯域_40ms_modulation_mae_db": 0.7411333733942165, "300–1000 Hz_10ms_log_rms_mae_db": 0.934299691627153, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.077671930904718, "300–1000 Hz_10ms_envelope_correlation": 0.9947122241326337, "300–1000 Hz_10ms_modulation_mae_db": 0.5003559719016759, "300–1000 Hz_40ms_log_rms_mae_db": 0.6154381546031112, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04906681233085793, "300–1000 Hz_40ms_envelope_correlation": 0.9978627312543451, "300–1000 Hz_40ms_modulation_mae_db": 0.8493360802446633, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0969354331775927, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1162458742714233, "1000–3000 Hz_10ms_envelope_correlation": 0.9903766974979941, "1000–3000 Hz_10ms_modulation_mae_db": 0.8577361250795533, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6946449035072226, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06431859148311853, "1000–3000 Hz_40ms_envelope_correlation": 0.9971420101146093, "1000–3000 Hz_40ms_modulation_mae_db": 0.9199263230085339, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5060849171778894, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13320197568780495, "3000–6000 Hz_10ms_envelope_correlation": 0.9857579716254904, "3000–6000 Hz_10ms_modulation_mae_db": 0.6917540072563733, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9352402496745021, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08333127308603784, "3000–6000 Hz_40ms_envelope_correlation": 0.9949334449731857, "3000–6000 Hz_40ms_modulation_mae_db": 0.7801019980998408, "mr_stft_db": 5.404457864664341, "band_mae_db": 0.24557354963724534, "rms_gain_error_db": -0.10595298121810176, "output_peak": 0.45136805851796036}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9327779141257245, "全帯域_10ms_rms_envelope_nrmse": 0.05673353975934261, "全帯域_10ms_envelope_correlation": 0.9969028109566346, "全帯域_10ms_modulation_mae_db": 0.29645010703945873, "全帯域_40ms_log_rms_mae_db": 0.5915697336410666, "全帯域_40ms_rms_envelope_nrmse": 0.03631474564469855, "全帯域_40ms_envelope_correlation": 0.9987791430843247, "全帯域_40ms_modulation_mae_db": 0.5662874475463066, "300–1000 Hz_10ms_log_rms_mae_db": 0.9581097415045958, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.081808672805129, "300–1000 Hz_10ms_envelope_correlation": 0.9941119173260716, "300–1000 Hz_10ms_modulation_mae_db": 0.42300198328227684, "300–1000 Hz_40ms_log_rms_mae_db": 0.6882417624144315, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.055854800954528966, "300–1000 Hz_40ms_envelope_correlation": 0.9971811420725046, "300–1000 Hz_40ms_modulation_mae_db": 0.6765482586849907, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1133465832599725, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1052793400648708, "1000–3000 Hz_10ms_envelope_correlation": 0.9926844941929774, "1000–3000 Hz_10ms_modulation_mae_db": 0.5595860345621166, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6920869828905875, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0704440840476382, "1000–3000 Hz_40ms_envelope_correlation": 0.9970930032765136, "1000–3000 Hz_40ms_modulation_mae_db": 0.6380393316349614, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5048032483179117, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1387372239359692, "3000–6000 Hz_10ms_envelope_correlation": 0.98511656212412, "3000–6000 Hz_10ms_modulation_mae_db": 0.6437184834190205, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8860506546256887, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08282333945379011, "3000–6000 Hz_40ms_envelope_correlation": 0.9959443326335354, "3000–6000 Hz_40ms_modulation_mae_db": 0.9948889341505266, "mr_stft_db": 5.395630665311298, "band_mae_db": 0.21171538509740415, "rms_gain_error_db": -0.1253778539520704, "output_peak": 0.4614110191027701}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9078770528711514, "全帯域_10ms_rms_envelope_nrmse": 0.05021676739723976, "全帯域_10ms_envelope_correlation": 0.9975505952993537, "全帯域_10ms_modulation_mae_db": 0.6450805690146842, "全帯域_40ms_log_rms_mae_db": 0.5759483417267605, "全帯域_40ms_rms_envelope_nrmse": 0.029502440928398425, "全帯域_40ms_envelope_correlation": 0.9991898961029231, "全帯域_40ms_modulation_mae_db": 0.7633556543528021, "300–1000 Hz_10ms_log_rms_mae_db": 1.00873985723897, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07947781359360973, "300–1000 Hz_10ms_envelope_correlation": 0.9943846239794997, "300–1000 Hz_10ms_modulation_mae_db": 0.7316624137220359, "300–1000 Hz_40ms_log_rms_mae_db": 0.7198905959298144, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05074093710106796, "300–1000 Hz_40ms_envelope_correlation": 0.9976143535821376, "300–1000 Hz_40ms_modulation_mae_db": 0.8537847420647687, "1000–3000 Hz_10ms_log_rms_mae_db": 1.1105056774130402, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.09440222358329985, "1000–3000 Hz_10ms_envelope_correlation": 0.9939276849470418, "1000–3000 Hz_10ms_modulation_mae_db": 1.184671186802455, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6791136705202265, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.054833256772771795, "1000–3000 Hz_40ms_envelope_correlation": 0.9981767692173967, "1000–3000 Hz_40ms_modulation_mae_db": 1.2620947921711456, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5447670447696942, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14344432172208188, "3000–6000 Hz_10ms_envelope_correlation": 0.9830512137496044, "3000–6000 Hz_10ms_modulation_mae_db": 0.4286558990950055, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9469267186195465, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0907209027938216, "3000–6000 Hz_40ms_envelope_correlation": 0.9934576067200767, "3000–6000 Hz_40ms_modulation_mae_db": 0.48043593157487496, "mr_stft_db": 5.397017376114561, "band_mae_db": 0.23847572567999434, "rms_gain_error_db": -0.10143860503225738, "output_peak": 0.49532978733127814}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.9389057626156001, "全帯域_10ms_rms_envelope_nrmse": 0.05226430807163375, "全帯域_10ms_envelope_correlation": 0.9973035671072947, "全帯域_10ms_modulation_mae_db": 0.3023632705389905, "全帯域_40ms_log_rms_mae_db": 0.662305692877853, "全帯域_40ms_rms_envelope_nrmse": 0.02872623814043082, "全帯域_40ms_envelope_correlation": 0.9992057157101425, "全帯域_40ms_modulation_mae_db": 0.5645618135975471, "300–1000 Hz_10ms_log_rms_mae_db": 1.004501609366721, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07005524737451842, "300–1000 Hz_10ms_envelope_correlation": 0.9955979506402813, "300–1000 Hz_10ms_modulation_mae_db": 0.38700235134504496, "300–1000 Hz_40ms_log_rms_mae_db": 0.713356047717202, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04062856063694469, "300–1000 Hz_40ms_envelope_correlation": 0.998431514024168, "300–1000 Hz_40ms_modulation_mae_db": 0.26408584620251657, "1000–3000 Hz_10ms_log_rms_mae_db": 1.0887684147271164, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.08223791125615178, "1000–3000 Hz_10ms_envelope_correlation": 0.9954481163908321, "1000–3000 Hz_10ms_modulation_mae_db": 0.9918436132311174, "1000–3000 Hz_40ms_log_rms_mae_db": 0.6456010149161306, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.049638922224626514, "1000–3000 Hz_40ms_envelope_correlation": 0.99853111538292, "1000–3000 Hz_40ms_modulation_mae_db": 0.9169420810144837, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5486052620392268, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13820026582299277, "3000–6000 Hz_10ms_envelope_correlation": 0.9844296733233208, "3000–6000 Hz_10ms_modulation_mae_db": 0.5233816126001063, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9314907467628387, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09019131640706325, "3000–6000 Hz_40ms_envelope_correlation": 0.9936283300245041, "3000–6000 Hz_40ms_modulation_mae_db": 0.37715950714672236, "mr_stft_db": 5.408736307498313, "band_mae_db": 0.1745661361233974, "rms_gain_error_db": -0.08424726312895633, "output_peak": 0.4940049558477471}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.562232056272448, "spectral_convergence": 0.1551330172749364, "spectral_convergence_status": "ok", "amplitude_floor": 1.160899353957536e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.385407896334403, "spectral_convergence": 0.16016142761877905, "spectral_convergence_status": "ok", "amplitude_floor": 1.2404642078999559e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.2822846073208165, "spectral_convergence": 0.16123615118415344, "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": 0.0001295196924728231, "delta_db": 0.25869174475205536, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.002976977856333367, "output_power": 0.0029336423008852652, "delta_db": -0.06368445051305906, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0005003734805512382, "output_power": 0.000509032443324513, "delta_db": 0.07451178774795937, "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": 2.799447769358915e-05, "output_power": 2.6784068901095312e-05, "delta_db": -0.19195815543722713, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.1130460027276325e-05, "output_power": 2.109298445254612e-05, "delta_db": -0.007709195583475661, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 6.414014484484223e-06, "output_power": 6.741323861485889e-06, "delta_db": 0.21615255339312567, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.13042859411034757, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.0429407980749169, "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": 5.4099748533092225}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 123603, "output_samples": 123603, "intelligibility": {"estoi": {"value": 0.9356666565711916, "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"}}, "level": {"reference": {"rms": 0.06526429048136644, "rms_dbfs": -23.706487580888414, "peak": 0.472930908203125, "peak_dbfs": -6.504046038430433, "crest_factor_db": 17.20244154245798, "mean": -4.952813582093477e-07, "zero_energy": false}, "output": {"rms": 0.06494243689849939, "rms_dbfs": -23.74942837896333, "peak": 0.4922653919690344, "peak_dbfs": -6.156013912422189, "crest_factor_db": 17.59341446654114, "mean": -2.972676854880983e-05, "zero_energy": false}, "rms_difference_db": -0.04294079807491613}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 515, "uncovered_tail_samples": 3, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 3.877530492221316e-06, "threshold_dbfs": -54.114447782851144, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 163, "quiet_samples": 39120, "reference_mean_power": 2.965885538280254e-07, "output_mean_power": 7.266954488460359e-07, "output_rms_dbfs": -61.38647559701114, "output_zero_energy": false, "output_peak": 0.02279021570237115, "output_energy_fraction": 5.4533718568940144e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 508, "reference_estimated_voiced_frames": 307, "output_estimated_voiced_frames": 293, "both_estimated_voiced_frames": 291, "reference_voiced_output_unvoiced_frames": 16, "reference_unvoiced_output_voiced_frames": 2, "paired_voiced_fraction": 0.9478827361563518, "absolute_difference_cents_median": 1.346542081901516, "absolute_difference_cents_p95": 7.786509385194629, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 3, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.9391602958669893, "rms_envelope_nrmse": 0.050446435733602066, "envelope_correlation": 0.9974279432805429, "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": 0.0006376842794736029, "reference_active": true, "delta_db": -0.013650820719185617}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00010753471412479324, "output_power": 0.00010372139934322039, "reference_active": true, "delta_db": -0.1568031753286125}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.642399701776048e-05, "output_power": 2.0435284492676358e-05, "reference_active": true, "delta_db": -1.1161782348725853}], "active_band_count": 3, "active_band_mae_db": 0.42887741030679444}}, {"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": 0.6260002844552237, "rms_envelope_nrmse": 0.02617658167970614, "envelope_correlation": 0.9992771723517097, "rms_gain_error_db": -0.04294083701963851, "reference_mean_power": 0.004288676885881949, "output_mean_power": 0.0042464815693882335}, "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": 0.0005593194555879334, "reference_active": true, "delta_db": -0.008157319648368426}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.355233098915975e-05, "output_power": 5.4921036435388504e-05, "reference_active": true, "delta_db": 0.10960345123551347}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6814737983602469e-06, "output_power": 1.381076230620406e-06, "reference_active": true, "delta_db": -0.8547245350028778}], "active_band_count": 3, "active_band_mae_db": 0.32416176862891993}}]}, {"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": 0.00013036665176469105, "log_rms_mae_db": 0.9188609985451879, "rms_envelope_nrmse": 0.08170706998904456, "envelope_correlation": 0.9939911280858044, "rms_gain_error_db": -0.04627558523103585, "reference_mean_power": 0.0015158717741492558, "output_mean_power": 0.001499805382476596}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.187895246183773e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00036232449214344424, "output_power": 0.00034764185244527625, "reference_active": true, "delta_db": -0.1796563670421974}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.27378870003226e-05, "output_power": 4.738095045832684e-05, "reference_active": true, "delta_db": -0.46518956945489237}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1888503336360718e-05, "output_power": 1.4320835376735526e-05, "reference_active": true, "delta_db": 0.8084116839531801}], "active_band_count": 3, "active_band_mae_db": 0.4844192068167566}}, {"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": 0.00011772885872912566, "log_rms_mae_db": 0.6098419277655105, "rms_envelope_nrmse": 0.04775923398827694, "envelope_correlation": 0.9978237702948337, "rms_gain_error_db": -0.04627564730843077, "reference_mean_power": 0.001524762506178652, "output_mean_power": 0.001508601862028097}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.112801089937839e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003193313097067297, "output_power": 0.000304366909758691, "reference_active": true, "delta_db": -0.208440672868293}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4777353739459925e-05, "output_power": 2.3644318248284594e-05, "reference_active": true, "delta_db": -0.20328124937649072}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.078329801445271e-06, "output_power": 1.1250093349179002e-06, "reference_active": true, "delta_db": 0.18404518251048013}], "active_band_count": 3, "active_band_mae_db": 0.19858903491842128}}]}, {"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": 1.119134087493373, "rms_envelope_nrmse": 0.09620255118161417, "envelope_correlation": 0.9934465362390451, "rms_gain_error_db": -0.1683051847877366, "reference_mean_power": 0.00046194923691890866, "output_mean_power": 0.00044438944541375195}, "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": 0.00021745730779534732, "output_power": 0.00021290776235535173, "reference_active": true, "delta_db": -0.09182511427256135}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.26315917085523e-05, "output_power": 5.695518054965887e-05, "reference_active": true, "delta_db": -0.4126021600278165}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.1826956188918756e-06, "output_power": 2.7624638685559658e-06, "reference_active": true, "delta_db": -4.1499085631760675}], "active_band_count": 3, "active_band_mae_db": 1.5514452791588151}}, {"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": 0.6666041696097933, "rms_envelope_nrmse": 0.05348534160985613, "envelope_correlation": 0.9980307304516328, "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": 3.961591197471976e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00020060895095818542, "output_power": 0.00019481608171073757, "reference_active": true, "delta_db": -0.12725502638506647}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.461992258627009e-05, "output_power": 3.179310678193287e-05, "reference_active": true, "delta_db": -0.3699312372055392}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.414804941169707e-07, "output_power": 3.733393665149758e-07, "reference_active": true, "delta_db": -2.9799594444645616}], "active_band_count": 3, "active_band_mae_db": 1.1590485693517225}}]}, {"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": 1.8521534194293836e-05, "log_rms_mae_db": 1.5189547295488528, "rms_envelope_nrmse": 0.13497428981539536, "envelope_correlation": 0.984535025015691, "rms_gain_error_db": -0.215396810590549, "reference_mean_power": 1.684190350930034e-05, "output_mean_power": 1.6026972576134407e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.2347471453358601e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.2528634901423365e-06, "output_power": 5.746033237318569e-06, "reference_active": true, "delta_db": -0.36710813658182495}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0675239180772895e-06, "output_power": 1.7536869777447803e-06, "reference_active": true, "delta_db": -0.7149846529950019}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.652671220760481e-07, "output_power": 2.8246564652489366e-07, "reference_active": true, "delta_db": 0.27282210781215877}], "active_band_count": 3, "active_band_mae_db": 0.4516382991296619}}, {"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": 1.438595762049439e-05, "log_rms_mae_db": 0.9092352522372645, "rms_envelope_nrmse": 0.078063537591977, "envelope_correlation": 0.9946863946190511, "rms_gain_error_db": -0.21539722823837706, "reference_mean_power": 1.694067457344735e-05, "output_mean_power": 1.6120962844244687e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.0973267407020905e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.499482122012408e-06, "output_power": 5.069605767991407e-06, "reference_active": true, "delta_db": -0.3534760631930112}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.267943787177926e-06, "output_power": 1.0916706210870222e-06, "reference_active": true, "delta_db": -0.6500837724818499}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8893101287704844e-08, "output_power": 1.8092931069646308e-08, "reference_active": true, "delta_db": -0.18794324249919475}], "active_band_count": 3, "active_band_mae_db": 0.3971676927246853}}]}], "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"]}}, "output_samples": 123603, "representation_scalars": 1161513, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9933329988091462, "standard_deviation": 0.001707510547420007, "minimum": 0.9903766974979941, "maximum": 0.9955178946968464, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.1000899278334342, "standard_deviation": 0.016832630581305262, "minimum": 1.0667556817334227, "maximum": 1.119134087493373, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.8963057772529761, "standard_deviation": 0.4079851941407643, "minimum": 0.170472382909337, "maximum": 1.5514452791588151, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.0970891881595839, "standard_deviation": 0.011916511676318275, "minimum": 0.08054424978600107, "maximum": 0.1162458742714233, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9978278869794464, "standard_deviation": 0.0005500069345914792, "minimum": 0.9970930032765136, "maximum": 0.99853111538292, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.6800934823299067, "standard_deviation": 0.018010423440900904, "minimum": 0.6456010149161306, "maximum": 0.7028311570849489, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8778094392924117, "standard_deviation": 0.3621892617955699, "minimum": 0.17503139965793793, "maximum": 1.2620947921711456, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05682861688231779, "standard_deviation": 0.007287966508564923, "minimum": 0.049638922224626514, "maximum": 0.0704440840476382, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9844939840515792, "standard_deviation": 0.0008251696936891161, "minimum": 0.9830512137496044, "maximum": 0.9857579716254904, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5160955633919497, "standard_deviation": 0.02293197800142291, "minimum": 1.479362125012706, "maximum": 1.5486052620392268, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5819058114567308, "standard_deviation": 0.1784730613992672, "minimum": 0.3315430793639047, "maximum": 0.8697589138184333, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1388410257356249, "standard_deviation": 0.003599824347725898, "minimum": 0.13320197568780495, "maximum": 0.14344432172208188, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9946690983894724, "standard_deviation": 0.000831302460023311, "minimum": 0.9934576067200767, "maximum": 0.9959443326335354, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9195358469748673, "standard_deviation": 0.019340190378851135, "minimum": 0.8860506546256887, "maximum": 0.9469267186195465, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6541009061498736, "standard_deviation": 0.26944863036790434, "minimum": 0.37715950714672236, "maximum": 1.0070556493672134, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08575084922159848, "standard_deviation": 0.004258933271617987, "minimum": 0.078063537591977, "maximum": 0.0907209027938216, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9947346793968443, "standard_deviation": 0.0006681024860182639, "minimum": 0.9939911280858044, "maximum": 0.9955979506402813, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.9606033066087809, "standard_deviation": 0.03714548663265769, "minimum": 0.9101695454202657, "maximum": 1.00873985723897, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4515556265946259, "standard_deviation": 0.1481920900218596, "minimum": 0.19524740158449228, "maximum": 0.7316624137220359, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07675190345614763, "standard_deviation": 0.005062990663936565, "minimum": 0.07005524737451842, "maximum": 0.081808672805129, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9980673926732444, "standard_deviation": 0.0005387536615738818, "minimum": 0.9971811420725046, "maximum": 0.9987813970035843, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.6660596004766349, "standard_deviation": 0.041975394210254396, "minimum": 0.6098419277655105, "maximum": 0.7198905959298144, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6376689354571449, "standard_deviation": 0.32250208939935704, "minimum": 0.19858903491842128, "maximum": 1.1697263676860303, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04527570674371338, "standard_deviation": 0.006719390730128423, "minimum": 0.03581446364471069, "maximum": 0.055854800954528966, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1998272610777324, "standard_deviation": 0.037651386610365274, "minimum": 0.13042859411034757, "maximum": 0.24557354963724534, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.401813356076324, "standard_deviation": 0.005378278120006235, "minimum": 5.395630665311298, "maximum": 5.4099748533092225, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.47191616779059875, "standard_deviation": 0.021618177578230962, "minimum": 0.4382194775398731, "maximum": 0.49532978733127814, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.0816635442929241, "standard_deviation": 0.027811054255440924, "minimum": -0.1253778539520704, "maximum": -0.0429407980749169, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9972691960405502, "standard_deviation": 0.0003434864888829928, "minimum": 0.9966494163318691, "maximum": 0.9977097980930592, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.929859052540342, "standard_deviation": 0.02115399032849682, "minimum": 0.9047532321453396, "maximum": 0.9710461353247846, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4596585837174053, "standard_deviation": 0.1868421085177811, "minimum": 0.20401383572810097, "maximum": 0.7451902666618765, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.05245560596000224, "standard_deviation": 0.0034888867062409816, "minimum": 0.04782543324840088, "maximum": 0.05838234052457022, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.999125283163535, "standard_deviation": 0.00018548618679672913, "minimum": 0.9987791430843247, "maximum": 0.9992771723517097, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6112431222869662, "standard_deviation": 0.02893785780735912, "minimum": 0.5759483417267605, "maximum": 0.662305692877853, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.6239067864874929, "standard_deviation": 0.17207069623096585, "minimum": 0.32416176862891993, "maximum": 0.8504734549739498, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.029715033612183715, "standard_deviation": 0.0035943322533654393, "minimum": 0.02617658167970614, "maximum": 0.03631474564469855, "valid_count": 8, "planned_count": 8}}, "seconds": 7.304030537998187, "rtf_including_measurement": 1.418223933981833}, {"case": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "normal", "speaker": "jvs_jvs066", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.827402353286743, "predicted_mos": 2.827402353286743, "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": "9ec14646ade1fcfe8ef0c617ccf4922a45503cd380645eacf3b8e18cbee65a83", "internal_samples": 82402, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.287808342000062}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.636200282338792, "全帯域_10ms_rms_envelope_nrmse": 0.21027607828747016, "全帯域_10ms_envelope_correlation": 0.9913479629792203, "全帯域_10ms_modulation_mae_db": 2.0510450848360753, "全帯域_40ms_log_rms_mae_db": 1.4652890004877253, "全帯域_40ms_rms_envelope_nrmse": 0.20256961474345955, "全帯域_40ms_envelope_correlation": 0.9937086925035075, "全帯域_40ms_modulation_mae_db": 1.705510030393081, "300–1000 Hz_10ms_log_rms_mae_db": 1.303304138604526, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.18728630975144755, "300–1000 Hz_10ms_envelope_correlation": 0.9903718726768955, "300–1000 Hz_10ms_modulation_mae_db": 1.768891057173109, "300–1000 Hz_40ms_log_rms_mae_db": 1.140806982827783, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.17683492386790847, "300–1000 Hz_40ms_envelope_correlation": 0.9928718613329143, "300–1000 Hz_40ms_modulation_mae_db": 1.4361921470247072, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3087286431371146, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.28066892248180686, "1000–3000 Hz_10ms_envelope_correlation": 0.9817567712649784, "1000–3000 Hz_10ms_modulation_mae_db": 2.878736378800994, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1135533791934116, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.2645402824949093, "1000–3000 Hz_40ms_envelope_correlation": 0.9859460296831846, "1000–3000 Hz_40ms_modulation_mae_db": 2.902329929171563, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2692050860196211, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.148578335863559, "3000–6000 Hz_10ms_envelope_correlation": 0.9857748503600674, "3000–6000 Hz_10ms_modulation_mae_db": 0.6504090917721744, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8406840779426626, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09933539468281619, "3000–6000 Hz_40ms_envelope_correlation": 0.9950878955156788, "3000–6000 Hz_40ms_modulation_mae_db": 0.4329075638193096, "mr_stft_db": 5.313671584908184, "band_mae_db": 0.9685283289217189, "rms_gain_error_db": 1.4598436212007861, "output_peak": 0.6560195050954105}}], "planned_noise_seeds": [0], "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": 5.576035806586519, "spectral_convergence": 0.366089985140872, "spectral_convergence_status": "ok", "amplitude_floor": 1.160899353957536e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.136175340784531, "spectral_convergence": 0.2532143831319199, "spectral_convergence_status": "ok", "amplitude_floor": 1.2404642078999559e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.228803607353501, "spectral_convergence": 0.2849553206497007, "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": 0.000146090086950743, "delta_db": 0.7815411746848188, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.002976977856333367, "output_power": 0.004230648807493926, "delta_db": 1.526313711465952, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0005003734805512382, "output_power": 0.000616074190539193, "delta_db": 0.9033873076532348, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0006045073176565132, "output_power": 0.0009028327341224589, "delta_db": 1.74205734530152, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.799447769358915e-05, "output_power": 3.373978191548808e-05, "delta_db": 0.8106990203820598, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.1130460027276325e-05, "output_power": 2.4987567765897973e-05, "delta_db": 0.7281503282887203, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 6.414014484484223e-06, "output_power": 6.853065422467116e-06, "delta_db": 0.28754941467572565, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.9685283289217189, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 1.4598436212007861, "pitch": null, "output_rms_dbfs": -22.246643959687628, "output_peak": 0.6560195050954105, "reference_rms_dbfs": -23.706487580888414, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.313671584908184}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 123603, "output_samples": 123603, "intelligibility": {"estoi": {"value": 0.9400623584009449, "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"}}, "level": {"reference": {"rms": 0.06526429048136644, "rms_dbfs": -23.706487580888414, "peak": 0.472930908203125, "peak_dbfs": -6.504046038430433, "crest_factor_db": 17.20244154245798, "mean": -4.952813582093477e-07, "zero_energy": false}, "output": {"rms": 0.07720897767883068, "rms_dbfs": -22.246643959687628, "peak": 0.6560195050954105, "peak_dbfs": -3.6616649554937086, "crest_factor_db": 18.58497900419392, "mean": 4.3651705897336554e-08, "zero_energy": false}, "rms_difference_db": 1.4598436212007861}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 515, "uncovered_tail_samples": 3, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 3.877530492221316e-06, "threshold_dbfs": -54.114447782851144, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 163, "quiet_samples": 39120, "reference_mean_power": 2.965885538280254e-07, "output_mean_power": 8.456376236446027e-07, "output_rms_dbfs": -60.728157028792666, "output_zero_energy": false, "output_peak": 0.026024268060294724, "output_energy_fraction": 4.489712455829275e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 508, "reference_estimated_voiced_frames": 307, "output_estimated_voiced_frames": 317, "both_estimated_voiced_frames": 301, "reference_voiced_output_unvoiced_frames": 6, "reference_unvoiced_output_voiced_frames": 16, "paired_voiced_fraction": 0.9804560260586319, "absolute_difference_cents_median": 3.625083649243061, "absolute_difference_cents_p95": 20.538643995012684, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 3, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.636200282338792, "rms_envelope_nrmse": 0.21027607828747016, "envelope_correlation": 0.9913479629792203, "rms_gain_error_db": 1.459843702357869, "reference_mean_power": 0.004263670396682444, "output_mean_power": 0.005967164279508249}, "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": 0.0009414238916396924, "reference_active": true, "delta_db": 1.6781442298434226}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00010753471412479324, "output_power": 0.00017250678429594156, "reference_active": true, "delta_db": 2.0525749465554983}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.642399701776048e-05, "output_power": 4.615727055108679e-05, "reference_active": true, "delta_db": 2.422416078109305}], "active_band_count": 3, "active_band_mae_db": 2.0510450848360753}}, {"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": 1.4652890004877253, "rms_envelope_nrmse": 0.20256961474345955, "envelope_correlation": 0.9937086925035075, "rms_gain_error_db": 1.4598438552579338, "reference_mean_power": 0.004288676885881949, "output_mean_power": 0.006002161996546213}, "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": 0.0008440683053807867, "reference_active": true, "delta_db": 1.7790193466709336}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.355233098915975e-05, "output_power": 8.230368860644976e-05, "reference_active": true, "delta_db": 1.8664092018313188}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6814737983602469e-06, "output_power": 2.359392847713094e-06, "reference_active": true, "delta_db": 1.47110154267699}], "active_band_count": 3, "active_band_mae_db": 1.705510030393081}}]}, {"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": 0.00013036665176469105, "log_rms_mae_db": 1.303304138604526, "rms_envelope_nrmse": 0.18728630975144755, "envelope_correlation": 0.9903718726768955, "rms_gain_error_db": 1.2146106919150437, "reference_mean_power": 0.0015158717741492558, "output_mean_power": 0.0020050422828645775}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.187895246183773e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00036232449214344424, "output_power": 0.0005292512050136979, "reference_active": true, "delta_db": 1.6456416336172042}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.27378870003226e-05, "output_power": 9.053823260262311e-05, "reference_active": true, "delta_db": 2.347092870423354}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1888503336360718e-05, "output_power": 1.608870359771451e-05, "reference_active": true, "delta_db": 1.313938667478768}], "active_band_count": 3, "active_band_mae_db": 1.768891057173109}}, {"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": 0.00011772885872912566, "log_rms_mae_db": 1.140806982827783, "rms_envelope_nrmse": 0.17683492386790847, "envelope_correlation": 0.9928718613329143, "rms_gain_error_db": 1.2146106971987867, "reference_mean_power": 0.001524762506178652, "output_mean_power": 0.002016802048873843}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.112801089937839e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003193313097067297, "output_power": 0.00047837328731159973, "reference_active": true, "delta_db": 1.7552541814868285}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4777353739459925e-05, "output_power": 4.232476221362814e-05, "reference_active": true, "delta_db": 2.3253960568161727}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.078329801445271e-06, "output_power": 1.136434025053357e-06, "reference_active": true, "delta_db": 0.22792620277112047}], "active_band_count": 3, "active_band_mae_db": 1.4361921470247072}}]}, {"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": 1.3087286431371146, "rms_envelope_nrmse": 0.28066892248180686, "envelope_correlation": 0.9817567712649784, "rms_gain_error_db": 1.7091179274996309, "reference_mean_power": 0.00046194923691890866, "output_mean_power": 0.0006847090164093551}, "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": 0.00021745730779534732, "output_power": 0.00030495052789366586, "reference_active": true, "delta_db": 1.4685538249543946}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.26315917085523e-05, "output_power": 0.00011520342389050236, "reference_active": true, "delta_db": 2.646719377524919}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.1826956188918756e-06, "output_power": 2.034141012245524e-05, "reference_active": true, "delta_db": 4.520935933923668}], "active_band_count": 3, "active_band_mae_db": 2.878736378800994}}, {"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": 1.1135533791934116, "rms_envelope_nrmse": 0.2645402824949093, "envelope_correlation": 0.9859460296831846, "rms_gain_error_db": 1.709117947644795, "reference_mean_power": 0.00046465861059889405, "output_mean_power": 0.0006887248993571833}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 3.961591197471976e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00020060895095818542, "output_power": 0.0002880610437714209, "reference_active": true, "delta_db": 1.5713422311998693}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.461992258627009e-05, "output_power": 6.701873789050904e-05, "reference_active": true, "delta_db": 2.8687015244775473}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.414804941169707e-07, "output_power": 1.980588868501098e-06, "reference_active": true, "delta_db": 4.266946031837273}], "active_band_count": 3, "active_band_mae_db": 2.902329929171563}}]}, {"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": 1.8521534194293836e-05, "log_rms_mae_db": 1.2692050860196211, "rms_envelope_nrmse": 0.148578335863559, "envelope_correlation": 0.9857748503600674, "rms_gain_error_db": 0.549770340205135, "reference_mean_power": 1.684190350930034e-05, "output_mean_power": 1.9114731804373823e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.2347471453358601e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.2528634901423365e-06, "output_power": 7.082043718624669e-06, "reference_active": true, "delta_db": 0.5407965595022821}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0675239180772895e-06, "output_power": 2.3976045887678606e-06, "reference_active": true, "delta_db": 0.6432701875923084}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.652671220760481e-07, "output_power": 3.16518776653308e-07, "reference_active": true, "delta_db": 0.7671605282219327}], "active_band_count": 3, "active_band_mae_db": 0.6504090917721744}}, {"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": 1.438595762049439e-05, "log_rms_mae_db": 0.8406840779426626, "rms_envelope_nrmse": 0.09933539468281619, "envelope_correlation": 0.9950878955156788, "rms_gain_error_db": 0.5497706101119738, "reference_mean_power": 1.694067457344735e-05, "output_mean_power": 1.922683329722573e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.0973267407020905e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.499482122012408e-06, "output_power": 6.339815163060062e-06, "reference_active": true, "delta_db": 0.6175480167673425}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.267943787177926e-06, "output_power": 1.4349590238597055e-06, "reference_active": true, "delta_db": 0.5373949967149781}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8893101287704844e-08, "output_power": 1.8277857414463267e-08, "reference_active": true, "delta_db": -0.14377967797560817}], "active_band_count": 3, "active_band_mae_db": 0.4329075638193096}}]}], "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"]}}, "output_samples": 123603, "representation_scalars": 1059868, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9817567712649784, "standard_deviation": null, "minimum": 0.9817567712649784, "maximum": 0.9817567712649784, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.3087286431371146, "standard_deviation": null, "minimum": 1.3087286431371146, "maximum": 1.3087286431371146, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 2.878736378800994, "standard_deviation": null, "minimum": 2.878736378800994, "maximum": 2.878736378800994, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.28066892248180686, "standard_deviation": null, "minimum": 0.28066892248180686, "maximum": 0.28066892248180686, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9859460296831846, "standard_deviation": null, "minimum": 0.9859460296831846, "maximum": 0.9859460296831846, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.1135533791934116, "standard_deviation": null, "minimum": 1.1135533791934116, "maximum": 1.1135533791934116, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 2.902329929171563, "standard_deviation": null, "minimum": 2.902329929171563, "maximum": 2.902329929171563, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.2645402824949093, "standard_deviation": null, "minimum": 0.2645402824949093, "maximum": 0.2645402824949093, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9857748503600674, "standard_deviation": null, "minimum": 0.9857748503600674, "maximum": 0.9857748503600674, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2692050860196211, "standard_deviation": null, "minimum": 1.2692050860196211, "maximum": 1.2692050860196211, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6504090917721744, "standard_deviation": null, "minimum": 0.6504090917721744, "maximum": 0.6504090917721744, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.148578335863559, "standard_deviation": null, "minimum": 0.148578335863559, "maximum": 0.148578335863559, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9950878955156788, "standard_deviation": null, "minimum": 0.9950878955156788, "maximum": 0.9950878955156788, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8406840779426626, "standard_deviation": null, "minimum": 0.8406840779426626, "maximum": 0.8406840779426626, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.4329075638193096, "standard_deviation": null, "minimum": 0.4329075638193096, "maximum": 0.4329075638193096, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09933539468281619, "standard_deviation": null, "minimum": 0.09933539468281619, "maximum": 0.09933539468281619, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9903718726768955, "standard_deviation": null, "minimum": 0.9903718726768955, "maximum": 0.9903718726768955, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.303304138604526, "standard_deviation": null, "minimum": 1.303304138604526, "maximum": 1.303304138604526, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 1.768891057173109, "standard_deviation": null, "minimum": 1.768891057173109, "maximum": 1.768891057173109, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.18728630975144755, "standard_deviation": null, "minimum": 0.18728630975144755, "maximum": 0.18728630975144755, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9928718613329143, "standard_deviation": null, "minimum": 0.9928718613329143, "maximum": 0.9928718613329143, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.140806982827783, "standard_deviation": null, "minimum": 1.140806982827783, "maximum": 1.140806982827783, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.4361921470247072, "standard_deviation": null, "minimum": 1.4361921470247072, "maximum": 1.4361921470247072, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.17683492386790847, "standard_deviation": null, "minimum": 0.17683492386790847, "maximum": 0.17683492386790847, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 0.9685283289217189, "standard_deviation": null, "minimum": 0.9685283289217189, "maximum": 0.9685283289217189, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 5.313671584908184, "standard_deviation": null, "minimum": 5.313671584908184, "maximum": 5.313671584908184, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.6560195050954105, "standard_deviation": null, "minimum": 0.6560195050954105, "maximum": 0.6560195050954105, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 1.4598436212007861, "standard_deviation": null, "minimum": 1.4598436212007861, "maximum": 1.4598436212007861, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9913479629792203, "standard_deviation": null, "minimum": 0.9913479629792203, "maximum": 0.9913479629792203, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.636200282338792, "standard_deviation": null, "minimum": 1.636200282338792, "maximum": 1.636200282338792, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 2.0510450848360753, "standard_deviation": null, "minimum": 2.0510450848360753, "maximum": 2.0510450848360753, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.21027607828747016, "standard_deviation": null, "minimum": 0.21027607828747016, "maximum": 0.21027607828747016, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9937086925035075, "standard_deviation": null, "minimum": 0.9937086925035075, "maximum": 0.9937086925035075, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 1.4652890004877253, "standard_deviation": null, "minimum": 1.4652890004877253, "maximum": 1.4652890004877253, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 1.705510030393081, "standard_deviation": null, "minimum": 1.705510030393081, "maximum": 1.705510030393081, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.20256961474345955, "standard_deviation": null, "minimum": 0.20256961474345955, "maximum": 0.20256961474345955, "valid_count": 1, "planned_count": 1}}, "seconds": 2.0954155509971315, "rtf_including_measurement": 0.4068669306079234}, {"case": "jvs_jvs066_whisper10_BASIC5000_2372", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "whisper", "speaker": "jvs_jvs066", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.073439359664917, "predicted_mos": 1.073439359664917, "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": "32961e397fd16b1a6ab96ef316e494ab1899c77f3a32f3f431a29fa2fcb615af", "internal_samples": 64140, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.521135052003956}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8480360106083915, "全帯域_10ms_rms_envelope_nrmse": 0.16806685015703715, "全帯域_10ms_envelope_correlation": 0.9736716539422925, "全帯域_10ms_modulation_mae_db": 0.3457950508581849, "全帯域_40ms_log_rms_mae_db": 1.0207764775973698, "全帯域_40ms_rms_envelope_nrmse": 0.09040982681765414, "全帯域_40ms_envelope_correlation": 0.991362463792778, "全帯域_40ms_modulation_mae_db": 0.4135084023003947, "300–1000 Hz_10ms_log_rms_mae_db": 2.760629798280785, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2649626865058365, "300–1000 Hz_10ms_envelope_correlation": 0.9500005272226237, "300–1000 Hz_10ms_modulation_mae_db": 0.4501032830809109, "300–1000 Hz_40ms_log_rms_mae_db": 1.9397364264343084, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16149926162154016, "300–1000 Hz_40ms_envelope_correlation": 0.9799596682896686, "300–1000 Hz_40ms_modulation_mae_db": 0.644367938310542, "1000–3000 Hz_10ms_log_rms_mae_db": 2.085892985780557, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21414434097425655, "1000–3000 Hz_10ms_envelope_correlation": 0.9650849049827432, "1000–3000 Hz_10ms_modulation_mae_db": 0.325993257097615, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2773673018382088, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12369903651795433, "1000–3000 Hz_40ms_envelope_correlation": 0.9872397506424038, "1000–3000 Hz_40ms_modulation_mae_db": 0.5783457495816879, "3000–6000 Hz_10ms_log_rms_mae_db": 1.910271182093993, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1782305925689665, "3000–6000 Hz_10ms_envelope_correlation": 0.9768061434607566, "3000–6000 Hz_10ms_modulation_mae_db": 0.7559714103446548, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1248644829789651, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09414439975661552, "3000–6000 Hz_40ms_envelope_correlation": 0.9934363804115941, "3000–6000 Hz_40ms_modulation_mae_db": 0.8815278298970005, "mr_stft_db": 6.202762560181853, "band_mae_db": 0.20114981564251083, "rms_gain_error_db": 0.005456943175057722, "output_peak": 0.04993784781574376}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.815340195876835, "全帯域_10ms_rms_envelope_nrmse": 0.1559581117799414, "全帯域_10ms_envelope_correlation": 0.9773450152782165, "全帯域_10ms_modulation_mae_db": 0.46657304975462655, "全帯域_40ms_log_rms_mae_db": 0.9136437372845907, "全帯域_40ms_rms_envelope_nrmse": 0.07928413846275635, "全帯域_40ms_envelope_correlation": 0.9933600104167785, "全帯域_40ms_modulation_mae_db": 0.4463125119357189, "300–1000 Hz_10ms_log_rms_mae_db": 2.707428237912111, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24640819041729975, "300–1000 Hz_10ms_envelope_correlation": 0.9570613574965573, "300–1000 Hz_10ms_modulation_mae_db": 0.3696474824691129, "300–1000 Hz_40ms_log_rms_mae_db": 1.8670972057278912, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15365804960675597, "300–1000 Hz_40ms_envelope_correlation": 0.9820928458675116, "300–1000 Hz_40ms_modulation_mae_db": 0.5155944090474492, "1000–3000 Hz_10ms_log_rms_mae_db": 2.091525876567687, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2028748171477622, "1000–3000 Hz_10ms_envelope_correlation": 0.9688672727765355, "1000–3000 Hz_10ms_modulation_mae_db": 0.5488403374742393, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3003508297831226, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10954012948898098, "1000–3000 Hz_40ms_envelope_correlation": 0.9899882615994203, "1000–3000 Hz_40ms_modulation_mae_db": 1.0130001182840385, "3000–6000 Hz_10ms_log_rms_mae_db": 1.835453071474265, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18018360338921544, "3000–6000 Hz_10ms_envelope_correlation": 0.9750315579597159, "3000–6000 Hz_10ms_modulation_mae_db": 0.6650669431901509, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1014429627922513, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08810100091015043, "3000–6000 Hz_40ms_envelope_correlation": 0.9934663685327906, "3000–6000 Hz_40ms_modulation_mae_db": 0.7383839819186226, "mr_stft_db": 6.20324573924347, "band_mae_db": 0.16015750061174033, "rms_gain_error_db": 0.004286868259823797, "output_peak": 0.05880263013236544}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.841325146827229, "全帯域_10ms_rms_envelope_nrmse": 0.16666687987321144, "全帯域_10ms_envelope_correlation": 0.9739652078794074, "全帯域_10ms_modulation_mae_db": 0.5749266667729898, "全帯域_40ms_log_rms_mae_db": 0.8777557552606604, "全帯域_40ms_rms_envelope_nrmse": 0.0801587574848044, "全帯域_40ms_envelope_correlation": 0.9932094966225647, "全帯域_40ms_modulation_mae_db": 0.7623800237718177, "300–1000 Hz_10ms_log_rms_mae_db": 2.700360036445726, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2749707510213983, "300–1000 Hz_10ms_envelope_correlation": 0.9426449452631032, "300–1000 Hz_10ms_modulation_mae_db": 0.8928104712191116, "300–1000 Hz_40ms_log_rms_mae_db": 1.783714490239349, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15785349123184336, "300–1000 Hz_40ms_envelope_correlation": 0.9788362997374788, "300–1000 Hz_40ms_modulation_mae_db": 0.7704391394227493, "1000–3000 Hz_10ms_log_rms_mae_db": 2.133423480682427, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21454238105410317, "1000–3000 Hz_10ms_envelope_correlation": 0.9651273114983479, "1000–3000 Hz_10ms_modulation_mae_db": 0.4278018052364523, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2914767838948282, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10906994920502917, "1000–3000 Hz_40ms_envelope_correlation": 0.9900945065356389, "1000–3000 Hz_40ms_modulation_mae_db": 0.7694052359160336, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8541892888591918, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18123680720257548, "3000–6000 Hz_10ms_envelope_correlation": 0.9743430480114235, "3000–6000 Hz_10ms_modulation_mae_db": 0.804240219307832, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1394607016587237, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09616705913840508, "3000–6000 Hz_40ms_envelope_correlation": 0.9921657690704818, "3000–6000 Hz_40ms_modulation_mae_db": 0.91517834744642, "mr_stft_db": 6.1873181880217105, "band_mae_db": 0.5158323840757926, "rms_gain_error_db": -0.05667619500741586, "output_peak": 0.05213777767432351}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7976558337795085, "全帯域_10ms_rms_envelope_nrmse": 0.13659038525912068, "全帯域_10ms_envelope_correlation": 0.9830724288439233, "全帯域_10ms_modulation_mae_db": 1.0044585086847484, "全帯域_40ms_log_rms_mae_db": 0.944644324375746, "全帯域_40ms_rms_envelope_nrmse": 0.07161912602843366, "全帯域_40ms_envelope_correlation": 0.9954534652564934, "全帯域_40ms_modulation_mae_db": 1.029557843767751, "300–1000 Hz_10ms_log_rms_mae_db": 2.7654486251511536, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24329873086851594, "300–1000 Hz_10ms_envelope_correlation": 0.9555318350835278, "300–1000 Hz_10ms_modulation_mae_db": 0.632299432589063, "300–1000 Hz_40ms_log_rms_mae_db": 1.9434060256636894, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14624380418994443, "300–1000 Hz_40ms_envelope_correlation": 0.9820537657018372, "300–1000 Hz_40ms_modulation_mae_db": 0.8722895779185738, "1000–3000 Hz_10ms_log_rms_mae_db": 2.0589396830789455, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1821126443851332, "1000–3000 Hz_10ms_envelope_correlation": 0.9752324117512255, "1000–3000 Hz_10ms_modulation_mae_db": 0.7414908433363773, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2558118154915243, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10320065223762916, "1000–3000 Hz_40ms_envelope_correlation": 0.9921635065697837, "1000–3000 Hz_40ms_modulation_mae_db": 0.9710708443031053, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8632909881630046, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17414568065569117, "3000–6000 Hz_10ms_envelope_correlation": 0.9763984919336507, "3000–6000 Hz_10ms_modulation_mae_db": 0.8175772040966566, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1177199087950271, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1069104408708965, "3000–6000 Hz_40ms_envelope_correlation": 0.9904501546267968, "3000–6000 Hz_40ms_modulation_mae_db": 1.1102541831256605, "mr_stft_db": 6.177745658782705, "band_mae_db": 0.4372834480029787, "rms_gain_error_db": -0.2401768821463181, "output_peak": 0.05096153866711417}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8788358873051467, "全帯域_10ms_rms_envelope_nrmse": 0.1584126606773273, "全帯域_10ms_envelope_correlation": 0.9766181709638216, "全帯域_10ms_modulation_mae_db": 0.47192974278609134, "全帯域_40ms_log_rms_mae_db": 0.9640133198081541, "全帯域_40ms_rms_envelope_nrmse": 0.08547574528047339, "全帯域_40ms_envelope_correlation": 0.9922739997284645, "全帯域_40ms_modulation_mae_db": 0.7293665740053714, "300–1000 Hz_10ms_log_rms_mae_db": 2.738060742434275, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.26521802143763973, "300–1000 Hz_10ms_envelope_correlation": 0.9493550718778897, "300–1000 Hz_10ms_modulation_mae_db": 0.8215229674085126, "300–1000 Hz_40ms_log_rms_mae_db": 1.9180636883019275, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16077368404780457, "300–1000 Hz_40ms_envelope_correlation": 0.9798255241379932, "300–1000 Hz_40ms_modulation_mae_db": 0.9512322070556299, "1000–3000 Hz_10ms_log_rms_mae_db": 2.0153516141208665, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19859547151194623, "1000–3000 Hz_10ms_envelope_correlation": 0.9701598624333954, "1000–3000 Hz_10ms_modulation_mae_db": 0.4642653170353999, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2332336559284023, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11038758744293478, "1000–3000 Hz_40ms_envelope_correlation": 0.989842063348571, "1000–3000 Hz_40ms_modulation_mae_db": 0.5145665050545253, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8904676007646657, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.19453029646210743, "3000–6000 Hz_10ms_envelope_correlation": 0.9728886646653562, "3000–6000 Hz_10ms_modulation_mae_db": 0.6536704416762086, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1751881759713625, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10860847992197895, "3000–6000 Hz_40ms_envelope_correlation": 0.9915159763621056, "3000–6000 Hz_40ms_modulation_mae_db": 0.35796462167472015, "mr_stft_db": 6.195182507393696, "band_mae_db": 0.5937562836878387, "rms_gain_error_db": 0.002481264456061073, "output_peak": 0.061675946797498285}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.841335683560568, "全帯域_10ms_rms_envelope_nrmse": 0.1654198485881522, "全帯域_10ms_envelope_correlation": 0.9744713632406684, "全帯域_10ms_modulation_mae_db": 0.9004029358895469, "全帯域_40ms_log_rms_mae_db": 1.0031280644738023, "全帯域_40ms_rms_envelope_nrmse": 0.08782969460339944, "全帯域_40ms_envelope_correlation": 0.9924129513129512, "全帯域_40ms_modulation_mae_db": 1.0740000129780711, "300–1000 Hz_10ms_log_rms_mae_db": 2.775509145460419, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2751152171369832, "300–1000 Hz_10ms_envelope_correlation": 0.9443506612352788, "300–1000 Hz_10ms_modulation_mae_db": 0.2943242179305326, "300–1000 Hz_40ms_log_rms_mae_db": 1.993530512801722, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1640177067760921, "300–1000 Hz_40ms_envelope_correlation": 0.9781383681347486, "300–1000 Hz_40ms_modulation_mae_db": 0.5413985028759161, "1000–3000 Hz_10ms_log_rms_mae_db": 2.1432701940171603, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19420625448342935, "1000–3000 Hz_10ms_envelope_correlation": 0.971382371957159, "1000–3000 Hz_10ms_modulation_mae_db": 0.7997512486489481, "1000–3000 Hz_40ms_log_rms_mae_db": 1.3441716529476528, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11249577431684003, "1000–3000 Hz_40ms_envelope_correlation": 0.9900005648163498, "1000–3000 Hz_40ms_modulation_mae_db": 1.150065148605291, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8490670632829416, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1949578566500216, "3000–6000 Hz_10ms_envelope_correlation": 0.9702592374751471, "3000–6000 Hz_10ms_modulation_mae_db": 0.5371416364532194, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0883683887048463, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10637743417383254, "3000–6000 Hz_40ms_envelope_correlation": 0.9904283958482394, "3000–6000 Hz_40ms_modulation_mae_db": 0.7314736257908323, "mr_stft_db": 6.182337983844466, "band_mae_db": 0.3914517732876538, "rms_gain_error_db": -0.21775748136242157, "output_peak": 0.059676446015121544}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8465347828643472, "全帯域_10ms_rms_envelope_nrmse": 0.1464573931174477, "全帯域_10ms_envelope_correlation": 0.979924457272515, "全帯域_10ms_modulation_mae_db": 0.4727734985844781, "全帯域_40ms_log_rms_mae_db": 0.9197849061789477, "全帯域_40ms_rms_envelope_nrmse": 0.0740805027493469, "全帯域_40ms_envelope_correlation": 0.9943163833346507, "全帯域_40ms_modulation_mae_db": 0.8548467312863877, "300–1000 Hz_10ms_log_rms_mae_db": 2.693999367897476, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2438226404587544, "300–1000 Hz_10ms_envelope_correlation": 0.9563473333404306, "300–1000 Hz_10ms_modulation_mae_db": 0.40943167472466974, "300–1000 Hz_40ms_log_rms_mae_db": 1.8358111072488512, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16589093031336244, "300–1000 Hz_40ms_envelope_correlation": 0.9775310995264721, "300–1000 Hz_40ms_modulation_mae_db": 0.6111010297609513, "1000–3000 Hz_10ms_log_rms_mae_db": 2.0755422038534523, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18446135229200097, "1000–3000 Hz_10ms_envelope_correlation": 0.9741940415781923, "1000–3000 Hz_10ms_modulation_mae_db": 0.6194521773303481, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2953675619126703, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09001065397461358, "1000–3000 Hz_40ms_envelope_correlation": 0.9932514433795284, "1000–3000 Hz_40ms_modulation_mae_db": 1.0039924807984413, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8450069882179696, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16249823637897132, "3000–6000 Hz_10ms_envelope_correlation": 0.9795463498020106, "3000–6000 Hz_10ms_modulation_mae_db": 0.6337773027101822, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1351185606159986, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09017265699405312, "3000–6000 Hz_40ms_envelope_correlation": 0.9934752375945112, "3000–6000 Hz_40ms_modulation_mae_db": 1.0166703944099909, "mr_stft_db": 6.199957543045706, "band_mae_db": 0.33803141585247803, "rms_gain_error_db": -0.11684141693614654, "output_peak": 0.05758275631143878}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8482667549634926, "全帯域_10ms_rms_envelope_nrmse": 0.17606793890432426, "全帯域_10ms_envelope_correlation": 0.9715313877666139, "全帯域_10ms_modulation_mae_db": 0.5607613146664464, "全帯域_40ms_log_rms_mae_db": 0.9435346983076577, "全帯域_40ms_rms_envelope_nrmse": 0.09903184062643744, "全帯域_40ms_envelope_correlation": 0.9898699816194241, "全帯域_40ms_modulation_mae_db": 0.772587329560412, "300–1000 Hz_10ms_log_rms_mae_db": 2.8363008295912606, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2397523232341677, "300–1000 Hz_10ms_envelope_correlation": 0.9571721794813323, "300–1000 Hz_10ms_modulation_mae_db": 0.4297454058572778, "300–1000 Hz_40ms_log_rms_mae_db": 1.9743803244713098, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.13848877009339053, "300–1000 Hz_40ms_envelope_correlation": 0.9846517845946858, "300–1000 Hz_40ms_modulation_mae_db": 0.3705210306723894, "1000–3000 Hz_10ms_log_rms_mae_db": 2.062340853025878, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.22345150003383693, "1000–3000 Hz_10ms_envelope_correlation": 0.9636704712624402, "1000–3000 Hz_10ms_modulation_mae_db": 0.7680600165292596, "1000–3000 Hz_40ms_log_rms_mae_db": 1.2497041480759448, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.13176316189753262, "1000–3000 Hz_40ms_envelope_correlation": 0.9863600535150779, "1000–3000 Hz_40ms_modulation_mae_db": 0.9257307197617094, "3000–6000 Hz_10ms_log_rms_mae_db": 1.8428176135167258, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.18122283902837663, "3000–6000 Hz_10ms_envelope_correlation": 0.9758499971639981, "3000–6000 Hz_10ms_modulation_mae_db": 0.3374583803929192, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1021970038695998, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09875303774647994, "3000–6000 Hz_40ms_envelope_correlation": 0.9925895289801729, "3000–6000 Hz_40ms_modulation_mae_db": 0.46217405278493445, "mr_stft_db": 6.189300078531041, "band_mae_db": 0.5986521498595927, "rms_gain_error_db": 0.09791012847644248, "output_peak": 0.061788735331455145}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 6.527798018114332, "spectral_convergence": 0.5951176325401887, "spectral_convergence_status": "ok", "amplitude_floor": 1.776300245720871e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.089420565539452, "spectral_convergence": 0.6074091552206504, "spectral_convergence_status": "ok", "amplitude_floor": 1.1913344769267057e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.991069096891775, "spectral_convergence": 0.6247215372642471, "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": 9.898335469010929e-07, "delta_db": -0.26845088078987217, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.178233710401703e-07, "output_power": 6.928683418955311e-07, "delta_db": 0.49786385496169094, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.652745613182611e-06, "output_power": 5.6673875744041755e-06, "delta_db": 0.011234720305055046, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.2826510059132755e-05, "output_power": 1.2422940324408976e-05, "delta_db": -0.1388410705981991, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2385922939210616e-05, "output_power": 1.2915738222471053e-05, "delta_db": 0.18190860451702634, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.5916906482380547e-06, "output_power": 1.6135536761643102e-06, "delta_db": 0.05924752489819673, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.299457135974266e-06, "output_power": 2.1705765811114616e-06, "delta_db": -0.25050205342753534, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.20114981564251083, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.005456943175057722, "pitch": null, "output_rms_dbfs": -44.38029724717251, "output_peak": 0.04993784781574376, "reference_rms_dbfs": -44.38575419034756, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.202762560181853}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 96209, "output_samples": 96209, "intelligibility": {"estoi": {"value": 0.6109570495702312, "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"}}, "level": {"reference": {"rms": 0.006035486606174957, "rms_dbfs": -44.38575419034756, "peak": 0.051483154296875, "peak_dbfs": -25.766697047411853, "crest_factor_db": 18.619057142935713, "mean": 9.198825116413226e-09, "zero_energy": false}, "output": {"rms": 0.006039279614933936, "rms_dbfs": -44.38029724717251, "peak": 0.04993784781574376, "peak_dbfs": -26.031403569644297, "crest_factor_db": 18.34889367752821, "mean": -4.68659129092988e-06, "zero_energy": false}, "rms_difference_db": 0.005456943175055073}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 400, "uncovered_tail_samples": 209, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 162, "quiet_samples": 38880, "reference_mean_power": 9.41455019293008e-08, "output_mean_power": 2.2525940609324428e-07, "output_rms_dbfs": -66.47317065258544, "output_zero_energy": false, "output_peak": 0.010822008925016158, "output_energy_fraction": 0.0024958772078255446, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 393, "reference_estimated_voiced_frames": 8, "output_estimated_voiced_frames": 2, "both_estimated_voiced_frames": 2, "reference_voiced_output_unvoiced_frames": 6, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 0.25, "absolute_difference_cents_median": 2.3030651735602143, "absolute_difference_cents_p95": 2.9199060470533316, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 209, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.8480360106083915, "rms_envelope_nrmse": 0.16806685015703715, "envelope_correlation": 0.9736716539422925, "rms_gain_error_db": 0.00545519444067544, "reference_mean_power": 3.6506204511776254e-05, "output_mean_power": 3.6552088947398693e-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": 7.741833562680117e-06, "reference_active": true, "delta_db": -0.14215144536066232}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3205374160249087e-06, "output_power": 3.003583693652198e-06, "reference_active": true, "delta_db": -0.43568640366899203}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.233369046941817e-06, "output_power": 1.1095281229476163e-06, "reference_active": true, "delta_db": -0.45954730354490053}], "active_band_count": 3, "active_band_mae_db": 0.3457950508581849}}, {"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": 1.0207764775973698, "rms_envelope_nrmse": 0.09040982681765414, "envelope_correlation": 0.991362463792778, "rms_gain_error_db": 0.0054408703276578145, "reference_mean_power": 3.678163866257165e-05, "output_mean_power": 3.682774782249302e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.647591787295735e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.744366291346525e-06, "output_power": 6.700526363436768e-06, "reference_active": true, "delta_db": -0.028322288239658197}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5635835823033082e-06, "output_power": 1.4474032696490142e-06, "reference_active": true, "delta_db": -0.3353155232101924}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.396664522501234e-08, "output_power": 7.678651945124812e-08, "reference_active": true, "delta_db": -0.8768873954513333}], "active_band_count": 3, "active_band_mae_db": 0.4135084023003947}}]}, {"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": 1.1737971097625874e-05, "log_rms_mae_db": 2.760629798280785, "rms_envelope_nrmse": 0.2649626865058365, "envelope_correlation": 0.9500005272226237, "rms_gain_error_db": 0.3658163107050082, "reference_mean_power": 3.717843862746057e-06, "output_mean_power": 4.04457392751837e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.0069118410394368e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.587317133491619e-06, "output_power": 1.6475232848407273e-06, "reference_active": true, "delta_db": 0.1616785724818089}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.351037742291996e-07, "output_power": 5.69359866916974e-07, "reference_active": true, "delta_db": -0.4745784232095366}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.744514691925593e-07, "output_power": 2.328414389982921e-07, "reference_active": true, "delta_db": -0.7140528535513874}], "active_band_count": 3, "active_band_mae_db": 0.4501032830809109}}, {"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": 7.730313378567769e-06, "log_rms_mae_db": 1.9397364264343084, "rms_envelope_nrmse": 0.16149926162154016, "envelope_correlation": 0.9799596682896686, "rms_gain_error_db": 0.3658040379134076, "reference_mean_power": 3.7459272676951853e-06, "output_mean_power": 4.075113831069128e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.5331447910659277e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.556997418820791e-06, "output_power": 1.6113375145411628e-06, "reference_active": true, "delta_db": 0.14898625691773135}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5335281635338275e-07, "output_power": 3.095652297511808e-07, "reference_active": true, "delta_db": -0.5745638219395015}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.1249603669561334e-08, "output_power": 1.6084051712254663e-08, "reference_active": true, "delta_db": -1.2095537360743929}], "active_band_count": 3, "active_band_mae_db": 0.644367938310542}}]}, {"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": 2.085892985780557, "rms_envelope_nrmse": 0.21414434097425655, "envelope_correlation": 0.9650849049827432, "rms_gain_error_db": -0.07697876737749541, "reference_mean_power": 1.9040046826256083e-05, "output_mean_power": 1.8705535058532895e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 1.3406247189798445e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.3392457188005514e-06, "output_power": 5.969891308504049e-06, "reference_active": true, "delta_db": -0.26071161842407664}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.3917385352512935e-06, "output_power": 2.112163138133383e-06, "reference_active": true, "delta_db": -0.5398624189459121}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.54995852980617e-07, "output_power": 7.247763153218666e-07, "reference_active": true, "delta_db": -0.1774057339228562}], "active_band_count": 3, "active_band_mae_db": 0.325993257097615}}, {"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": 1.2773673018382088, "rms_envelope_nrmse": 0.12369903651795433, "envelope_correlation": 0.9872397506424038, "rms_gain_error_db": -0.07697877067392334, "reference_mean_power": 1.9183917331823965e-05, "output_mean_power": 1.884687791015357e-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": 5.34016408594121e-06, "reference_active": true, "delta_db": -0.2024316408187839}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1687645280234336e-06, "output_power": 1.0294152641271807e-06, "reference_active": true, "delta_db": -0.5513641863610644}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.657756100862396e-08, "output_power": 6.109102161378462e-08, "reference_active": true, "delta_db": -0.9812414215652153}], "active_band_count": 3, "active_band_mae_db": 0.5783457495816879}}]}, {"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": 1.1530093504582301e-05, "log_rms_mae_db": 1.910271182093993, "rms_envelope_nrmse": 0.1782305925689665, "envelope_correlation": 0.9768061434607566, "rms_gain_error_db": 0.2628838935016503, "reference_mean_power": 5.1081468503535174e-06, "output_mean_power": 5.426899304048945e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.2542593631444698e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7396247028720565e-06, "output_power": 1.8332029422464211e-06, "reference_active": true, "delta_db": 0.22754979536480463}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.118165550857852e-07, "output_power": 5.623911191876087e-07, "reference_active": true, "delta_db": 0.40924124693748365}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4689547511366814e-07, "output_power": 1.009011461226538e-07, "reference_active": true, "delta_db": -1.631123188731676}], "active_band_count": 3, "active_band_mae_db": 0.7559714103446548}}, {"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": 9.091353933231888e-06, "log_rms_mae_db": 1.1248644829789651, "rms_envelope_nrmse": 0.09414439975661552, "envelope_correlation": 0.9934363804115941, "rms_gain_error_db": 0.2628837357801428, "reference_mean_power": 5.1467425502402285e-06, "output_mean_power": 5.4679032079369125e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.7984368001248087e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6090100968943604e-06, "output_power": 1.6865138567237483e-06, "reference_active": true, "delta_db": 0.2043114438572077}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.367924284305251e-07, "output_power": 2.5899083087664745e-07, "reference_active": true, "delta_db": 0.38916577441352374}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2506680970493356e-08, "output_power": 7.798865751861448e-09, "reference_active": true, "delta_db": -2.05110627142027}], "active_band_count": 3, "active_band_mae_db": 0.8815278298970005}}]}], "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"]}}, "output_samples": 96209, "representation_scalars": 903888, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9692148310300048, "standard_deviation": 0.004329631467212599, "minimum": 0.9636704712624402, "maximum": 0.9752324117512255, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 2.0832858613908716, "standard_deviation": 0.041219017688698005, "minimum": 2.0153516141208665, "maximum": 2.1432701940171603, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.58695687533608, "standard_deviation": 0.17441941254205934, "minimum": 0.325993257097615, "maximum": 0.7997512486489481, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.20179859523530858, "standard_deviation": 0.014836481812919525, "minimum": 0.1821126443851332, "maximum": 0.22345150003383693, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9898675188008468, "standard_deviation": 0.0022682414551541694, "minimum": 0.9863600535150779, "maximum": 0.9932514433795284, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.2809354687340442, "standard_deviation": 0.035030525422509284, "minimum": 1.2332336559284023, "maximum": 1.3441716529476528, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.865772100288104, "standard_deviation": 0.22409571025597666, "minimum": 0.5145665050545253, "maximum": 1.150065148605291, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.11127086813518933, "standard_deviation": 0.012544996977242043, "minimum": 0.09001065397461358, "maximum": 0.13176316189753262, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9751404363090073, "standard_deviation": 0.0027727524944344464, "minimum": 0.9702592374751471, "maximum": 0.9795463498020106, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.8613204745465945, "standard_deviation": 0.02598960726678272, "minimum": 1.835453071474265, "maximum": 1.910271182093993, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6506129422714779, "standard_deviation": 0.15767146396642776, "minimum": 0.3374583803929192, "maximum": 0.8175772040966566, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1808757390419907, "standard_deviation": 0.010525519769457578, "minimum": 0.16249823637897132, "maximum": 0.1949578566500216, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9921909764283365, "standard_deviation": 0.0012861480878682793, "minimum": 0.9904283958482394, "maximum": 0.9934752375945112, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.1230450231733469, "standard_deviation": 0.027437144705198303, "minimum": 1.0883683887048463, "maximum": 1.1751881759713625, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7767033796310227, "standard_deviation": 0.26098405548270937, "minimum": 0.35796462167472015, "maximum": 1.1102541831256605, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0986543136890515, "standard_deviation": 0.007898843203517945, "minimum": 0.08810100091015043, "maximum": 0.10860847992197895, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9515579888750929, "standard_deviation": 0.0058456568086938014, "minimum": 0.9426449452631032, "maximum": 0.9571721794813323, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.747217097896651, "standard_deviation": 0.04772442253473507, "minimum": 2.693999367897476, "maximum": 2.8363008295912606, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5374856169098989, "standard_deviation": 0.2200198598147079, "minimum": 0.2943242179305326, "maximum": 0.8928104712191116, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.25669357013507443, "standard_deviation": 0.014891677480023891, "minimum": 0.2397523232341677, "maximum": 0.2751152171369832, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9803861694987994, "standard_deviation": 0.002390201777743998, "minimum": 0.9775310995264721, "maximum": 0.9846517845946858, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.906967472611131, "standard_deviation": 0.07211747874653299, "minimum": 1.783714490239349, "maximum": 1.993530512801722, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6596179793830252, "standard_deviation": 0.19399246430955958, "minimum": 0.3705210306723894, "maximum": 0.9512322070556299, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.1560532122350917, "standard_deviation": 0.009455671773091697, "minimum": 0.13848877009339053, "maximum": 0.16589093031336244, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.4045393463775732, "standard_deviation": 0.16588529746989863, "minimum": 0.16015750061174033, "maximum": 0.5986521498595927, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.192231282380581, "standard_deviation": 0.009569833587045906, "minimum": 6.177745658782705, "maximum": 6.20324573924347, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.05657045984313258, "standard_deviation": 0.004841060757844899, "minimum": 0.04993784781574376, "maximum": 0.061788735331455145, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.06516459638561463, "standard_deviation": 0.1181020573318225, "minimum": -0.2401768821463181, "maximum": 0.09791012847644248, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9763249606484323, "standard_deviation": 0.003753737578617602, "minimum": 0.9715313877666139, "maximum": 0.9830724288439233, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.83966628697319, "standard_deviation": 0.0241649975197359, "minimum": 1.7976558337795085, "maximum": 1.8788358873051467, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.599702595999639, "standard_deviation": 0.23021968659661254, "minimum": 0.3457950508581849, "maximum": 1.0044585086847484, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.15920500854457026, "standard_deviation": 0.012774346260814865, "minimum": 0.13659038525912068, "maximum": 0.17606793890432426, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9927823440105131, "standard_deviation": 0.0017278021792144075, "minimum": 0.9898699816194241, "maximum": 0.9954534652564934, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.9484101604108661, "standard_deviation": 0.04710550081175741, "minimum": 0.8777557552606604, "maximum": 1.0207764775973698, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7603199287007406, "standard_deviation": 0.23898933105265263, "minimum": 0.4135084023003947, "maximum": 1.0740000129780711, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0834862040066632, "standard_deviation": 0.009027351825436259, "minimum": 0.07161912602843366, "maximum": 0.09903184062643744, "valid_count": 8, "planned_count": 8}}, "seconds": 3.9738535770011367, "rtf_including_measurement": 0.9913052401337429}, {"case": "jvs_jvs066_whisper10_BASIC5000_2372", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "whisper", "speaker": "jvs_jvs066", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.0858497619628906, "predicted_mos": 1.0858497619628906, "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": 3.3665879260006477}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.712237387762556, "全帯域_10ms_rms_envelope_nrmse": 0.16282017505426685, "全帯域_10ms_envelope_correlation": 0.9753588778592562, "全帯域_10ms_modulation_mae_db": 0.171603465093662, "全帯域_40ms_log_rms_mae_db": 0.9669612777638227, "全帯域_40ms_rms_envelope_nrmse": 0.08968946078840702, "全帯域_40ms_envelope_correlation": 0.9915072717572022, "全帯域_40ms_modulation_mae_db": 0.2430075583118325, "300–1000 Hz_10ms_log_rms_mae_db": 2.6047981493478143, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2607209041496625, "300–1000 Hz_10ms_envelope_correlation": 0.9515420010914674, "300–1000 Hz_10ms_modulation_mae_db": 0.4400996879350822, "300–1000 Hz_40ms_log_rms_mae_db": 1.9083886777915742, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16406691179263105, "300–1000 Hz_40ms_envelope_correlation": 0.9791720513217279, "300–1000 Hz_40ms_modulation_mae_db": 0.605285552816289, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8751267341132212, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21081343655908497, "1000–3000 Hz_10ms_envelope_correlation": 0.966223133048443, "1000–3000 Hz_10ms_modulation_mae_db": 0.20603502434813203, "1000–3000 Hz_40ms_log_rms_mae_db": 1.168216448985258, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.12628314603822788, "1000–3000 Hz_40ms_envelope_correlation": 0.9866439354863928, "1000–3000 Hz_40ms_modulation_mae_db": 0.4316832030729217, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7193343868567696, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17609358546154208, "3000–6000 Hz_10ms_envelope_correlation": 0.9776930390397744, "3000–6000 Hz_10ms_modulation_mae_db": 0.5966851184650513, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0296585872808353, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0947259216111576, "3000–6000 Hz_40ms_envelope_correlation": 0.9935995361063964, "3000–6000 Hz_40ms_modulation_mae_db": 0.680160900270668, "mr_stft_db": 6.1477553286182385, "band_mae_db": 0.19990989778683424, "rms_gain_error_db": 0.013645286793610477, "output_peak": 0.05191181541768}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6420482390890276, "全帯域_10ms_rms_envelope_nrmse": 0.15348708355302199, "全帯域_10ms_envelope_correlation": 0.9781025747350218, "全帯域_10ms_modulation_mae_db": 0.3515165984971773, "全帯域_40ms_log_rms_mae_db": 0.9017933332767003, "全帯域_40ms_rms_envelope_nrmse": 0.0804341443396764, "全帯域_40ms_envelope_correlation": 0.9931678615119099, "全帯域_40ms_modulation_mae_db": 0.2698245138216229, "300–1000 Hz_10ms_log_rms_mae_db": 2.5755372807494954, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.24298420707948898, "300–1000 Hz_10ms_envelope_correlation": 0.9581170742937922, "300–1000 Hz_10ms_modulation_mae_db": 0.273875356369869, "300–1000 Hz_40ms_log_rms_mae_db": 1.8080312961928882, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15123790005200297, "300–1000 Hz_40ms_envelope_correlation": 0.9825610181417538, "300–1000 Hz_40ms_modulation_mae_db": 0.42595392701593643, "1000–3000 Hz_10ms_log_rms_mae_db": 1.848398407312382, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2026866902672892, "1000–3000 Hz_10ms_envelope_correlation": 0.9689068259045523, "1000–3000 Hz_10ms_modulation_mae_db": 0.4595698729077362, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1646367474531492, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11283919600151836, "1000–3000 Hz_40ms_envelope_correlation": 0.9893454078950927, "1000–3000 Hz_40ms_modulation_mae_db": 0.773706789754048, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6796662848926496, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17960838586687272, "3000–6000 Hz_10ms_envelope_correlation": 0.975350862019182, "3000–6000 Hz_10ms_modulation_mae_db": 0.5593186417748276, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0099500959442462, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08953231814710745, "3000–6000 Hz_40ms_envelope_correlation": 0.9933289872471749, "3000–6000 Hz_40ms_modulation_mae_db": 0.5746755416780709, "mr_stft_db": 6.149531788878289, "band_mae_db": 0.1757179853194296, "rms_gain_error_db": 0.0006615772081413661, "output_peak": 0.06018284978241594}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6814525941082112, "全帯域_10ms_rms_envelope_nrmse": 0.16589621025668833, "全帯域_10ms_envelope_correlation": 0.9742273306352053, "全帯域_10ms_modulation_mae_db": 0.37243388451188436, "全帯域_40ms_log_rms_mae_db": 0.8481941570381121, "全帯域_40ms_rms_envelope_nrmse": 0.08426969935090023, "全帯域_40ms_envelope_correlation": 0.9925017006184261, "全帯域_40ms_modulation_mae_db": 0.5415164804000132, "300–1000 Hz_10ms_log_rms_mae_db": 2.5415080699065387, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2735101158276535, "300–1000 Hz_10ms_envelope_correlation": 0.943101680781607, "300–1000 Hz_10ms_modulation_mae_db": 0.8535352985702923, "300–1000 Hz_40ms_log_rms_mae_db": 1.6679253272828825, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15757431293486487, "300–1000 Hz_40ms_envelope_correlation": 0.9788109729913385, "300–1000 Hz_40ms_modulation_mae_db": 0.731696753960783, "1000–3000 Hz_10ms_log_rms_mae_db": 1.907849502862913, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2150001110097766, "1000–3000 Hz_10ms_envelope_correlation": 0.9648828061558236, "1000–3000 Hz_10ms_modulation_mae_db": 0.26060176669073853, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1436168987489903, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11578840253304563, "1000–3000 Hz_40ms_envelope_correlation": 0.9887896773003155, "1000–3000 Hz_40ms_modulation_mae_db": 0.6155163641819245, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6825718388691735, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1817483631477011, "3000–6000 Hz_10ms_envelope_correlation": 0.9742013304484066, "3000–6000 Hz_10ms_modulation_mae_db": 0.6371375532229796, "3000–6000 Hz_40ms_log_rms_mae_db": 1.035815861647281, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10037609363025955, "3000–6000 Hz_40ms_envelope_correlation": 0.9914326006778832, "3000–6000 Hz_40ms_modulation_mae_db": 0.7271664043409137, "mr_stft_db": 6.126476270582139, "band_mae_db": 0.4985849477852144, "rms_gain_error_db": -0.07289360462356875, "output_peak": 0.051704650765629356}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6414429066681624, "全帯域_10ms_rms_envelope_nrmse": 0.13029248056976994, "全帯域_10ms_envelope_correlation": 0.9845147520058167, "全帯域_10ms_modulation_mae_db": 0.7800743835050433, "全帯域_40ms_log_rms_mae_db": 0.8957740112897907, "全帯域_40ms_rms_envelope_nrmse": 0.0701731281109594, "全帯域_40ms_envelope_correlation": 0.9955044293755216, "全帯域_40ms_modulation_mae_db": 0.7575709802263436, "300–1000 Hz_10ms_log_rms_mae_db": 2.582037989829305, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2400985039159044, "300–1000 Hz_10ms_envelope_correlation": 0.9568333417056221, "300–1000 Hz_10ms_modulation_mae_db": 0.4916911320992492, "300–1000 Hz_40ms_log_rms_mae_db": 1.8436132184306238, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1490942645765309, "300–1000 Hz_40ms_envelope_correlation": 0.98139294809839, "300–1000 Hz_40ms_modulation_mae_db": 0.5979583374597416, "1000–3000 Hz_10ms_log_rms_mae_db": 1.797344854304738, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.17496001260003713, "1000–3000 Hz_10ms_envelope_correlation": 0.9770783083151441, "1000–3000 Hz_10ms_modulation_mae_db": 0.6335044539518536, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0957791847501805, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10082745555553103, "1000–3000 Hz_40ms_envelope_correlation": 0.9923794567845412, "1000–3000 Hz_40ms_modulation_mae_db": 0.8087549017031345, "3000–6000 Hz_10ms_log_rms_mae_db": 1.7029616378373895, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17185458432084524, "3000–6000 Hz_10ms_envelope_correlation": 0.977008027008844, "3000–6000 Hz_10ms_modulation_mae_db": 0.7379398947663162, "3000–6000 Hz_40ms_log_rms_mae_db": 1.033753331277011, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10913919870139309, "3000–6000 Hz_40ms_envelope_correlation": 0.9899977068123318, "3000–6000 Hz_40ms_modulation_mae_db": 1.0463696428936766, "mr_stft_db": 6.112935924297279, "band_mae_db": 0.42376891647162174, "rms_gain_error_db": -0.23085055456673403, "output_peak": 0.05193732572467172}}, {"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": 0.3214235832927659, "全帯域_40ms_log_rms_mae_db": 0.8666139494793824, "全帯域_40ms_rms_envelope_nrmse": 0.08274946372701637, "全帯域_40ms_envelope_correlation": 0.9927523296059628, "全帯域_40ms_modulation_mae_db": 0.5213777988758661, "300–1000 Hz_10ms_log_rms_mae_db": 2.6174467854277776, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.25488503991437267, "300–1000 Hz_10ms_envelope_correlation": 0.9530405402938097, "300–1000 Hz_10ms_modulation_mae_db": 0.7862814331153407, "300–1000 Hz_40ms_log_rms_mae_db": 1.856505884267248, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15440804500024893, "300–1000 Hz_40ms_envelope_correlation": 0.9812454501005228, "300–1000 Hz_40ms_modulation_mae_db": 0.8046495501894374, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8026534016414797, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19115304139773964, "1000–3000 Hz_10ms_envelope_correlation": 0.9722740527632647, "1000–3000 Hz_10ms_modulation_mae_db": 0.5374054314980842, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1060502106709467, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10999936520661258, "1000–3000 Hz_40ms_envelope_correlation": 0.9898838694192449, "1000–3000 Hz_40ms_modulation_mae_db": 0.41085440495214604, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6785021552951347, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1892316026350206, "3000–6000 Hz_10ms_envelope_correlation": 0.974514529987796, "3000–6000 Hz_10ms_modulation_mae_db": 0.7599619498144911, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0398536098687847, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1056668060038274, "3000–6000 Hz_40ms_envelope_correlation": 0.9920971030467854, "3000–6000 Hz_40ms_modulation_mae_db": 0.516737685266536, "mr_stft_db": 6.126409834343072, "band_mae_db": 0.6023648683356244, "rms_gain_error_db": -0.020954347018245945, "output_peak": 0.06519807947412244}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6342313936046664, "全帯域_10ms_rms_envelope_nrmse": 0.1564753601949317, "全帯域_10ms_envelope_correlation": 0.9772429161860092, "全帯域_10ms_modulation_mae_db": 0.7208946358928107, "全帯域_40ms_log_rms_mae_db": 0.9084300950027547, "全帯域_40ms_rms_envelope_nrmse": 0.0833534351788267, "全帯域_40ms_envelope_correlation": 0.9932690366053615, "全帯域_40ms_modulation_mae_db": 0.8920886130868088, "300–1000 Hz_10ms_log_rms_mae_db": 2.6389425521523147, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2652157842650239, "300–1000 Hz_10ms_envelope_correlation": 0.94817902333994, "300–1000 Hz_10ms_modulation_mae_db": 0.3401674645833283, "300–1000 Hz_40ms_log_rms_mae_db": 1.9589943764835342, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.16212171533541286, "300–1000 Hz_40ms_envelope_correlation": 0.9785303428443781, "300–1000 Hz_40ms_modulation_mae_db": 0.5644609519948998, "1000–3000 Hz_10ms_log_rms_mae_db": 1.927980029225987, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1875791531502084, "1000–3000 Hz_10ms_envelope_correlation": 0.973403886199849, "1000–3000 Hz_10ms_modulation_mae_db": 0.7127507591250088, "1000–3000 Hz_40ms_log_rms_mae_db": 1.208323475174165, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10971259988427981, "1000–3000 Hz_40ms_envelope_correlation": 0.9906173330638905, "1000–3000 Hz_40ms_modulation_mae_db": 1.0295007498583506, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6782230924145138, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1909790009573043, "3000–6000 Hz_10ms_envelope_correlation": 0.9714891283329533, "3000–6000 Hz_10ms_modulation_mae_db": 0.36838331902898497, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0034807886973436, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10593143350396025, "3000–6000 Hz_40ms_envelope_correlation": 0.9904941272419108, "3000–6000 Hz_40ms_modulation_mae_db": 0.5280852569711256, "mr_stft_db": 6.12391704414345, "band_mae_db": 0.39410665799015593, "rms_gain_error_db": -0.23236491527146383, "output_peak": 0.058713883495660646}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6858953369283012, "全帯域_10ms_rms_envelope_nrmse": 0.13902015534728193, "全帯域_10ms_envelope_correlation": 0.9819413710556547, "全帯域_10ms_modulation_mae_db": 0.2677278846934103, "全帯域_40ms_log_rms_mae_db": 0.8738439597089743, "全帯域_40ms_rms_envelope_nrmse": 0.07248621697589923, "全帯域_40ms_envelope_correlation": 0.9945661901858857, "全帯域_40ms_modulation_mae_db": 0.6101606173017734, "300–1000 Hz_10ms_log_rms_mae_db": 2.563404783962683, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2327959857807296, "300–1000 Hz_10ms_envelope_correlation": 0.9597277710000551, "300–1000 Hz_10ms_modulation_mae_db": 0.381141112015031, "300–1000 Hz_40ms_log_rms_mae_db": 1.7498237507398153, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.15880386088751544, "300–1000 Hz_40ms_envelope_correlation": 0.9790541191601561, "300–1000 Hz_40ms_modulation_mae_db": 0.568917540599775, "1000–3000 Hz_10ms_log_rms_mae_db": 1.82215812492548, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1746666283178428, "1000–3000 Hz_10ms_envelope_correlation": 0.9768882555856554, "1000–3000 Hz_10ms_modulation_mae_db": 0.4378749103526733, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1356991620692103, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08674588618084399, "1000–3000 Hz_40ms_envelope_correlation": 0.9937158131667952, "1000–3000 Hz_40ms_modulation_mae_db": 0.8076856209132056, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6401683600921826, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.154896650512038, "3000–6000 Hz_10ms_envelope_correlation": 0.9814037472594186, "3000–6000 Hz_10ms_modulation_mae_db": 0.5572054791155822, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0119431620928105, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0838283725809241, "3000–6000 Hz_40ms_envelope_correlation": 0.9943311411693082, "3000–6000 Hz_40ms_modulation_mae_db": 0.8873632389062439, "mr_stft_db": 6.139670358835126, "band_mae_db": 0.3640357122106844, "rms_gain_error_db": -0.11836719734935609, "output_peak": 0.05743660011750735}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.6891967830083185, "全帯域_10ms_rms_envelope_nrmse": 0.17211398966599079, "全帯域_10ms_envelope_correlation": 0.9728735593771625, "全帯域_10ms_modulation_mae_db": 0.4338094961570243, "全帯域_40ms_log_rms_mae_db": 0.8989543106800949, "全帯域_40ms_rms_envelope_nrmse": 0.0992522842900571, "全帯域_40ms_envelope_correlation": 0.9898316096785333, "全帯域_40ms_modulation_mae_db": 0.5833552186808577, "300–1000 Hz_10ms_log_rms_mae_db": 2.6871981434456536, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.23951719621629614, "300–1000 Hz_10ms_envelope_correlation": 0.9573595642247299, "300–1000 Hz_10ms_modulation_mae_db": 0.5242715997113726, "300–1000 Hz_40ms_log_rms_mae_db": 1.8759586102149788, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.14306864271769593, "300–1000 Hz_40ms_envelope_correlation": 0.9835115766373906, "300–1000 Hz_40ms_modulation_mae_db": 0.2772300774563301, "1000–3000 Hz_10ms_log_rms_mae_db": 1.8604031846498645, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.2210336872937963, "1000–3000 Hz_10ms_envelope_correlation": 0.9643374546987019, "1000–3000 Hz_10ms_modulation_mae_db": 0.6873728727398004, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1556943106049298, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.13324138666783378, "1000–3000 Hz_40ms_envelope_correlation": 0.9859164657910044, "1000–3000 Hz_40ms_modulation_mae_db": 0.795814748384696, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6805513594778767, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17204022829316834, "3000–6000 Hz_10ms_envelope_correlation": 0.978142511576626, "3000–6000 Hz_10ms_modulation_mae_db": 0.3097836745613682, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0163273304967553, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09390977590741546, "3000–6000 Hz_40ms_envelope_correlation": 0.9932220397620846, "3000–6000 Hz_40ms_modulation_mae_db": 0.4564806569082534, "mr_stft_db": 6.126378765910846, "band_mae_db": 0.6146943487987627, "rms_gain_error_db": 0.09822750933986506, "output_peak": 0.06410355332840681}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 1.1913344769267057e-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": 6.178233710401703e-07, "output_power": 6.849545931575881e-07, "delta_db": 0.4479744952278711, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.652745613182611e-06, "output_power": 5.625251197426526e-06, "delta_db": -0.021175208509368357, "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": 1.2934390569671552e-05, "delta_db": 0.1881759720297404, "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": 2.160978052802255e-06, "delta_db": -0.26974962181641515, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.19990989778683424, "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}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 96209, "output_samples": 96209, "intelligibility": {"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"}}, "level": {"reference": {"rms": 0.006035486606174957, "rms_dbfs": -44.38575419034756, "peak": 0.051483154296875, "peak_dbfs": -25.766697047411853, "crest_factor_db": 18.619057142935713, "mean": 9.198825116413226e-09, "zero_energy": false}, "output": {"rms": 0.006044975636364491, "rms_dbfs": -44.37210890355396, "peak": 0.05191181541768, "peak_dbfs": -25.694675661261574, "crest_factor_db": 18.677433242292384, "mean": -1.1917135279712707e-05, "zero_energy": false}, "rms_difference_db": 0.013645286793604328}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 400, "uncovered_tail_samples": 209, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 162, "quiet_samples": 38880, "reference_mean_power": 9.41455019293008e-08, "output_mean_power": 1.993547020419271e-07, "output_rms_dbfs": -67.0037351647623, "output_zero_energy": false, "output_peak": 0.01167040647642519, "output_energy_fraction": 0.0022046920168779394, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 393, "reference_estimated_voiced_frames": 8, "output_estimated_voiced_frames": 2, "both_estimated_voiced_frames": 2, "reference_voiced_output_unvoiced_frames": 6, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 0.25, "absolute_difference_cents_median": 2.844276579767595, "absolute_difference_cents_p95": 3.504543746101167, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 209, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.16282017505426685, "envelope_correlation": 0.9753588778592562, "rms_gain_error_db": 0.013641861496224643, "reference_mean_power": 3.6506204511776254e-05, "output_mean_power": 3.662105643676843e-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": 3.155352516009927e-06, "reference_active": true, "delta_db": -0.22160492586171154}, {"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": 0.171603465093662}}, {"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": 0.9669612777638227, "rms_envelope_nrmse": 0.08968946078840702, "envelope_correlation": 0.9915072717572022, "rms_gain_error_db": 0.013622789149233996, "reference_mean_power": 3.678163866257165e-05, "output_mean_power": 3.689719509211925e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.647591787295735e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.744366291346525e-06, "output_power": 6.861438157247584e-06, "reference_active": true, "delta_db": 0.07474004258726742}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5635835823033082e-06, "output_power": 1.5161750004719326e-06, "reference_active": true, "delta_db": -0.13371770196807553}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.396664522501234e-08, "output_power": 8.33522310766985e-08, "reference_active": true, "delta_db": -0.5205649303801545}], "active_band_count": 3, "active_band_mae_db": 0.2430075583118325}}]}, {"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": 1.1737971097625874e-05, "log_rms_mae_db": 2.6047981493478143, "rms_envelope_nrmse": 0.2607209041496625, "envelope_correlation": 0.9515420010914674, "rms_gain_error_db": 0.3573464492952885, "reference_mean_power": 3.717843862746057e-06, "output_mean_power": 4.03669365300659e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.0069118410394368e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.587317133491619e-06, "output_power": 1.6712955419857327e-06, "reference_active": true, "delta_db": 0.22389550694356952}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.351037742291996e-07, "output_power": 5.719750170719957e-07, "reference_active": true, "delta_db": -0.4546763368858278}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.744514691925593e-07, "output_power": 2.3675155381706817e-07, "reference_active": true, "delta_db": -0.6417272199758493}], "active_band_count": 3, "active_band_mae_db": 0.4400996879350822}}, {"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": 7.730313378567769e-06, "log_rms_mae_db": 1.9083886777915742, "rms_envelope_nrmse": 0.16406691179263105, "envelope_correlation": 0.9791720513217279, "rms_gain_error_db": 0.35733336660037923, "reference_mean_power": 3.7459272676951853e-06, "output_mean_power": 4.067173295442506e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.5331447910659277e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.556997418820791e-06, "output_power": 1.6312295014664468e-06, "reference_active": true, "delta_db": 0.20227174639674741}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5335281635338275e-07, "output_power": 3.06650260366906e-07, "reference_active": true, "delta_db": -0.6156521938391009}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.1249603669561334e-08, "output_power": 1.6887196719927998e-08, "reference_active": true, "delta_db": -0.9979327182130189}], "active_band_count": 3, "active_band_mae_db": 0.605285552816289}}]}, {"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": 1.8751267341132212, "rms_envelope_nrmse": 0.21081343655908497, "envelope_correlation": 0.966223133048443, "rms_gain_error_db": -0.053991126080559004, "reference_mean_power": 1.9040046826256083e-05, "output_mean_power": 1.8804807825040447e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 1.3406247189798445e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.3392457188005514e-06, "output_power": 6.040442453667433e-06, "reference_active": true, "delta_db": -0.20968834784034593}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.3917385352512935e-06, "output_power": 2.2097170651814363e-06, "reference_active": true, "delta_db": -0.34377031198697106}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.54995852980617e-07, "output_power": 7.4384067824243e-07, "reference_active": true, "delta_db": -0.06464641321707905}], "active_band_count": 3, "active_band_mae_db": 0.20603502434813203}}, {"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": 1.168216448985258, "rms_envelope_nrmse": 0.12628314603822788, "envelope_correlation": 0.9866439354863928, "rms_gain_error_db": -0.05399127592129647, "reference_mean_power": 1.9183917331823965e-05, "output_mean_power": 1.8946900162677702e-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": 5.421984344754513e-06, "reference_active": true, "delta_db": -0.13639506498071752}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1687645280234336e-06, "output_power": 1.0785627747613378e-06, "reference_active": true, "delta_db": -0.34881595216140066}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.657756100862396e-08, "output_power": 6.355030961557035e-08, "reference_active": true, "delta_db": -0.8098385920766469}], "active_band_count": 3, "active_band_mae_db": 0.4316832030729217}}]}, {"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": 1.1530093504582301e-05, "log_rms_mae_db": 1.7193343868567696, "rms_envelope_nrmse": 0.17609358546154208, "envelope_correlation": 0.9776930390397744, "rms_gain_error_db": 0.2983476825141023, "reference_mean_power": 5.1081468503535174e-06, "output_mean_power": 5.471395919926503e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.2542593631444698e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7396247028720565e-06, "output_power": 1.8471449922974665e-06, "reference_active": true, "delta_db": 0.26045420807779934}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.118165550857852e-07, "output_power": 5.612945303368342e-07, "reference_active": true, "delta_db": 0.40076480802962233}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4689547511366814e-07, "output_power": 1.1327257785876495e-07, "reference_active": true, "delta_db": -1.1288363392877323}], "active_band_count": 3, "active_band_mae_db": 0.5966851184650513}}, {"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": 9.091353933231888e-06, "log_rms_mae_db": 1.0296585872808353, "rms_envelope_nrmse": 0.0947259216111576, "envelope_correlation": 0.9935995361063964, "rms_gain_error_db": 0.2983472244160771, "reference_mean_power": 5.1467425502402285e-06, "output_mean_power": 5.512735644633603e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.7984368001248087e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6090100968943604e-06, "output_power": 1.6963787828208851e-06, "reference_active": true, "delta_db": 0.229640625531663}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.367924284305251e-07, "output_power": 2.570559154230391e-07, "reference_active": true, "delta_db": 0.35659790925529905}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2506680970493356e-08, "output_power": 8.947828573274473e-09, "reference_active": true, "delta_db": -1.4542441660250416}], "active_band_count": 3, "active_band_mae_db": 0.680160900270668}}]}], "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"]}}, "output_samples": 96209, "representation_scalars": 903888, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9704993403339293, "standard_deviation": 0.005155072264940729, "minimum": 0.9643374546987019, "maximum": 0.9770783083151441, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.855239279879508, "standard_deviation": 0.047418242992537975, "minimum": 1.797344854304738, "maximum": 1.927980029225987, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.49188938645175334, "standard_deviation": 0.18833438007305947, "minimum": 0.20603502434813203, "maximum": 0.7127507591250088, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1972365950744719, "standard_deviation": 0.017855785756130282, "minimum": 0.1746666283178428, "maximum": 0.2210336872937963, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9896614948634097, "standard_deviation": 0.0026397720464440395, "minimum": 0.9859164657910044, "maximum": 0.9937158131667952, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.1472520548071037, "standard_deviation": 0.03592940584884657, "minimum": 1.0957791847501805, "maximum": 1.208323475174165, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7091895978525533, "standard_deviation": 0.20998935221893614, "minimum": 0.41085440495214604, "maximum": 1.0295007498583506, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.11192967975848662, "standard_deviation": 0.014352959901470898, "minimum": 0.08674588618084399, "maximum": 0.13324138666783378, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9762253969591251, "standard_deviation": 0.0030113614921455302, "minimum": 0.9714891283329533, "maximum": 0.9814037472594186, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.6827473894669613, "standard_deviation": 0.022718890207418293, "minimum": 1.6401683600921826, "maximum": 1.7193343868567696, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5658019538437001, "standard_deviation": 0.15946675504326988, "minimum": 0.3097836745613682, "maximum": 0.7599619498144911, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17705655014931154, "standard_deviation": 0.01143180963452984, "minimum": 0.154896650512038, "maximum": 0.1909790009573043, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9923129052579844, "standard_deviation": 0.001561924058504934, "minimum": 0.9899977068123318, "maximum": 0.9943311411693082, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.0225978459131335, "standard_deviation": 0.013758349977750899, "minimum": 1.0034807886973436, "maximum": 1.0398536098687847, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.677129915904436, "standard_deviation": 0.20360039132294072, "minimum": 0.4564806569082534, "maximum": 1.0463696428936766, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09788874001075562, "standard_deviation": 0.008874540408108426, "minimum": 0.0838283725809241, "maximum": 0.10913919870139309, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9534876245913779, "standard_deviation": 0.0056894813035084, "minimum": 0.943101680781607, "maximum": 0.9597277710000551, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.601359219352698, "standard_deviation": 0.04646695522445235, "minimum": 2.5415080699065387, "maximum": 2.6871981434456536, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5113828855499457, "standard_deviation": 0.20735067946618782, "minimum": 0.273875356369869, "maximum": 0.8535352985702923, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.25121596714364147, "standard_deviation": 0.014463484486589568, "minimum": 0.2327959857807296, "maximum": 0.2735101158276535, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9805348099119573, "standard_deviation": 0.0018991399777031509, "minimum": 0.9785303428443781, "maximum": 0.9835115766373906, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.833655142675443, "standard_deviation": 0.0916956014873917, "minimum": 1.6679253272828825, "maximum": 1.9589943764835342, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.572019086436649, "standard_deviation": 0.16461892283861734, "minimum": 0.2772300774563301, "maximum": 0.8046495501894374, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.15504695666211288, "standard_deviation": 0.00702795772324174, "minimum": 0.14306864271769593, "maximum": 0.16406691179263105, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.4091479168372909, "standard_deviation": 0.16402365430112306, "minimum": 0.1757179853194296, "maximum": 0.6146943487987627, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 6.131634414451055, "standard_deviation": 0.012736293207484622, "minimum": 6.112935924297279, "maximum": 6.149531788878289, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.057648594763261785, "standard_deviation": 0.005439579045301895, "minimum": 0.051704650765629356, "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": 0.9779103631813397, "standard_deviation": 0.003910211596676815, "minimum": 0.9728735593771625, "maximum": 0.9845147520058167, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.6744674878975199, "standard_deviation": 0.031150044650152968, "minimum": 1.6342313936046664, "maximum": 1.712237387762556, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.42743549145547227, "standard_deviation": 0.2143085261594743, "minimum": 0.171603465093662, "maximum": 0.7800743835050433, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.15376406929335978, "standard_deviation": 0.013916909494717538, "minimum": 0.13029248056976994, "maximum": 0.17211398966599079, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9928875536673505, "standard_deviation": 0.0017444237971934544, "minimum": 0.9898316096785333, "maximum": 0.9955044293755216, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.8950706367799541, "standard_deviation": 0.03558745950173787, "minimum": 0.8481941570381121, "maximum": 0.9669612777638227, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5523627225881398, "standard_deviation": 0.2198802936242089, "minimum": 0.2430075583118325, "maximum": 0.8920886130868088, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.0828009790952178, "standard_deviation": 0.009196431514582807, "minimum": 0.0701731281109594, "maximum": 0.0992522842900571, "valid_count": 8, "planned_count": 8}}, "seconds": 5.290789297003357, "rtf_including_measurement": 1.3198239575100101}, {"case": "jvs_jvs066_whisper10_BASIC5000_2372", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "whisper", "speaker": "jvs_jvs066", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.389207363128662, "predicted_mos": 1.389207363128662, "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": "a5ac3fd39161452994b333d45eb7b97fed2d65da46cbbe2d749fc39ab74f7334", "internal_samples": 64140, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.503842073994747}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 2.725441008056497, "全帯域_10ms_rms_envelope_nrmse": 0.25221080267617935, "全帯域_10ms_envelope_correlation": 0.9552297887055254, "全帯域_10ms_modulation_mae_db": 1.0412345624886508, "全帯域_40ms_log_rms_mae_db": 1.9772192300226223, "全帯域_40ms_rms_envelope_nrmse": 0.16841065067695324, "全帯域_40ms_envelope_correlation": 0.9821279850340275, "全帯域_40ms_modulation_mae_db": 1.1826721217072957, "300–1000 Hz_10ms_log_rms_mae_db": 3.794348984296812, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.34852629735990664, "300–1000 Hz_10ms_envelope_correlation": 0.9240479032813134, "300–1000 Hz_10ms_modulation_mae_db": 0.9601135221511953, "300–1000 Hz_40ms_log_rms_mae_db": 3.13488077047881, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.22049003295367198, "300–1000 Hz_40ms_envelope_correlation": 0.9707257687538224, "300–1000 Hz_40ms_modulation_mae_db": 0.9810109760074566, "1000–3000 Hz_10ms_log_rms_mae_db": 2.1105898730414863, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.3210168858915039, "1000–3000 Hz_10ms_envelope_correlation": 0.9453734948489287, "1000–3000 Hz_10ms_modulation_mae_db": 1.3002605863140533, "1000–3000 Hz_40ms_log_rms_mae_db": 1.5438431546268525, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.23012085955338688, "1000–3000 Hz_40ms_envelope_correlation": 0.97572837295806, "1000–3000 Hz_40ms_modulation_mae_db": 1.3257684701586925, "3000–6000 Hz_10ms_log_rms_mae_db": 1.907214628527389, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.21468014580340142, "3000–6000 Hz_10ms_envelope_correlation": 0.9694496756918781, "3000–6000 Hz_10ms_modulation_mae_db": 0.5024827427483899, "3000–6000 Hz_40ms_log_rms_mae_db": 1.2277272913931525, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11794923415567804, "3000–6000 Hz_40ms_envelope_correlation": 0.9921474344801069, "3000–6000 Hz_40ms_modulation_mae_db": 0.7194784641621546, "mr_stft_db": 6.304483379920835, "band_mae_db": 0.8275931844653043, "rms_gain_error_db": 0.7859244301075996, "output_peak": 0.07765222275788844}}], "planned_noise_seeds": [0], "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": 6.50980471138097, "spectral_convergence": 0.6841756739826722, "spectral_convergence_status": "ok", "amplitude_floor": 1.776300245720871e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.227111103213384, "spectral_convergence": 0.7167572126900994, "spectral_convergence_status": "ok", "amplitude_floor": 1.1913344769267057e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.1765343251681495, "spectral_convergence": 0.7485653456404601, "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": 7.461951813823109e-07, "delta_db": -1.495548164553254, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.178233710401703e-07, "output_power": 7.747578293634427e-07, "delta_db": 0.9830164094313536, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.652745613182611e-06, "output_power": 5.532633210314964e-06, "delta_db": -0.09327562308895936, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.2826510059132755e-05, "output_power": 1.7592063597514747e-05, "delta_db": 1.372082803010469, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2385922939210616e-05, "output_power": 1.4611181559381495e-05, "delta_db": 0.7175696369918974, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.5916906482380547e-06, "output_power": 1.9106567976866134e-06, "delta_db": 0.7932401913435977, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.299457135974266e-06, "output_power": 2.4858061870159726e-06, "delta_db": 0.3384194628375989, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.8275931844653043, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.7859244301075996, "pitch": null, "output_rms_dbfs": -43.59982976023997, "output_peak": 0.07765222275788844, "reference_rms_dbfs": -44.38575419034756, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.304483379920835}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 96209, "output_samples": 96209, "intelligibility": {"estoi": {"value": 0.5839582633735814, "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"}}, "level": {"reference": {"rms": 0.006035486606174957, "rms_dbfs": -44.38575419034756, "peak": 0.051483154296875, "peak_dbfs": -25.766697047411853, "crest_factor_db": 18.619057142935713, "mean": 9.198825116413226e-09, "zero_energy": false}, "output": {"rms": 0.006607063974463963, "rms_dbfs": -43.59982976023997, "peak": 0.07765222275788844, "peak_dbfs": -22.19692216569639, "crest_factor_db": 21.402907594543578, "mean": -2.8491286811892254e-10, "zero_energy": false}, "rms_difference_db": 0.7859244301075918}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 400, "uncovered_tail_samples": 209, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 162, "quiet_samples": 38880, "reference_mean_power": 9.41455019293008e-08, "output_mean_power": 1.1562997947814703e-07, "output_rms_dbfs": -69.36929551435031, "output_zero_energy": false, "output_peak": 0.012337177525611876, "output_energy_fraction": 0.001070444069071594, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 393, "reference_estimated_voiced_frames": 8, "output_estimated_voiced_frames": 2, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 8, "reference_unvoiced_output_voiced_frames": 2, "paired_voiced_fraction": 0.0, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 209, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 2.725441008056497, "rms_envelope_nrmse": 0.25221080267617935, "envelope_correlation": 0.9552297887055254, "rms_gain_error_db": 0.7859441202703134, "reference_mean_power": 3.6506204511776254e-05, "output_mean_power": 4.374829122350698e-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": 8.922983602101386e-06, "reference_active": true, "delta_db": 0.4745111991048}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3205374160249087e-06, "output_power": 4.135376134372291e-06, "reference_active": true, "delta_db": 0.9530663880947752}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.233369046941817e-06, "output_power": 1.8226599679784095e-06, "reference_active": true, "delta_db": 1.6961261002663772}], "active_band_count": 3, "active_band_mae_db": 1.0412345624886508}}, {"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": 1.9772192300226223, "rms_envelope_nrmse": 0.16841065067695324, "envelope_correlation": 0.9821279850340275, "rms_gain_error_db": 0.7859648451804335, "reference_mean_power": 3.678163866257165e-05, "output_mean_power": 4.407857624075282e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.647591787295735e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.744366291346525e-06, "output_power": 7.781749956121793e-06, "reference_active": true, "delta_db": 0.6213612280272066}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5635835823033082e-06, "output_power": 2.0401783266967624e-06, "reference_active": true, "delta_db": 1.155470279665205}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.396664522501234e-08, "output_power": 1.4128374812024815e-07, "reference_active": true, "delta_db": 1.771184857429475}], "active_band_count": 3, "active_band_mae_db": 1.1826721217072957}}]}, {"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": 1.1737971097625874e-05, "log_rms_mae_db": 3.794348984296812, "rms_envelope_nrmse": 0.34852629735990664, "envelope_correlation": 0.9240479032813134, "rms_gain_error_db": 0.8720677585029779, "reference_mean_power": 3.717843862746057e-06, "output_mean_power": 4.544623634639236e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.0069118410394368e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.587317133491619e-06, "output_power": 1.893339998322447e-06, "reference_active": true, "delta_db": 0.7656490576073685}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.351037742291996e-07, "output_power": 7.543160412128921e-07, "reference_active": true, "delta_db": 0.7470864985192953}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.744514691925593e-07, "output_power": 3.760330878783793e-07, "reference_active": true, "delta_db": 1.3676050103269222}], "active_band_count": 3, "active_band_mae_db": 0.9601135221511953}}, {"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": 7.730313378567769e-06, "log_rms_mae_db": 3.13488077047881, "rms_envelope_nrmse": 0.22049003295367198, "envelope_correlation": 0.9707257687538224, "rms_gain_error_db": 0.8719907469426849, "reference_mean_power": 3.7459272676951853e-06, "output_mean_power": 4.578871074028826e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.5331447910659277e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.556997418820791e-06, "output_power": 1.92115814173132e-06, "reference_active": true, "delta_db": 0.9127522304643655}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5335281635338275e-07, "output_power": 4.2718114166018823e-07, "reference_active": true, "delta_db": 0.8240351492522908}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.1249603669561334e-08, "output_power": 2.805274662736896e-08, "reference_active": true, "delta_db": 1.206245548305713}], "active_band_count": 3, "active_band_mae_db": 0.9810109760074566}}]}, {"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": 2.1105898730414863, "rms_envelope_nrmse": 0.3210168858915039, "envelope_correlation": 0.9453734948489287, "rms_gain_error_db": 1.1383473103244837, "reference_mean_power": 1.9040046826256083e-05, "output_mean_power": 2.4745870917056823e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 1.3406247189798445e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.3392457188005514e-06, "output_power": 7.0614444959841845e-06, "reference_active": true, "delta_db": 0.46855963830535224}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.3917385352512935e-06, "output_power": 3.0532954172284328e-06, "reference_active": true, "delta_db": 1.0605512501450618}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.54995852980617e-07, "output_power": 1.3035018539794434e-06, "reference_active": true, "delta_db": 2.371670870491746}], "active_band_count": 3, "active_band_mae_db": 1.3002605863140533}}, {"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": 1.5438431546268525, "rms_envelope_nrmse": 0.23012085955338688, "envelope_correlation": 0.97572837295806, "rms_gain_error_db": 1.1383480925379845, "reference_mean_power": 1.9183917331823965e-05, "output_mean_power": 2.493286029239753e-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": 6.5256784663954565e-06, "reference_active": true, "delta_db": 0.6682790561848633}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1687645280234336e-06, "output_power": 1.5821164307998858e-06, "reference_active": true, "delta_db": 1.315114185527546}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.657756100862396e-08, "output_power": 1.211972447463987e-07, "reference_active": true, "delta_db": 1.9939121687636683}], "active_band_count": 3, "active_band_mae_db": 1.3257684701586925}}]}, {"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": 1.1530093504582301e-05, "log_rms_mae_db": 1.907214628527389, "rms_envelope_nrmse": 0.21468014580340142, "envelope_correlation": 0.9694496756918781, "rms_gain_error_db": 0.5412440441750561, "reference_mean_power": 5.1081468503535174e-06, "output_mean_power": 5.786124556981481e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.2542593631444698e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7396247028720565e-06, "output_power": 2.0054352545027637e-06, "reference_active": true, "delta_db": 0.6175307927333274}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.118165550857852e-07, "output_power": 4.952735382360997e-07, "reference_active": true, "delta_db": -0.1426920449219108}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4689547511366814e-07, "output_power": 1.236761277418129e-07, "reference_active": true, "delta_db": -0.7472253905899313}], "active_band_count": 3, "active_band_mae_db": 0.5024827427483899}}, {"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": 9.091353933231888e-06, "log_rms_mae_db": 1.2277272913931525, "rms_envelope_nrmse": 0.11794923415567804, "envelope_correlation": 0.9921474344801069, "rms_gain_error_db": 0.5412452983966415, "reference_mean_power": 5.1467425502402285e-06, "output_mean_power": 5.829844546575452e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.7984368001248087e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6090100968943604e-06, "output_power": 1.8350963686370136e-06, "reference_active": true, "delta_db": 0.5710010641726793}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.367924284305251e-07, "output_power": 2.234257678057675e-07, "reference_active": true, "delta_db": -0.2523455239716526}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2506680970493356e-08, "output_power": 9.196724805732586e-09, "reference_active": true, "delta_db": -1.3350888043421316}], "active_band_count": 3, "active_band_mae_db": 0.7194784641621546}}]}], "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"]}}, "output_samples": 96209, "representation_scalars": 824456, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9453734948489287, "standard_deviation": null, "minimum": 0.9453734948489287, "maximum": 0.9453734948489287, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 2.1105898730414863, "standard_deviation": null, "minimum": 2.1105898730414863, "maximum": 2.1105898730414863, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 1.3002605863140533, "standard_deviation": null, "minimum": 1.3002605863140533, "maximum": 1.3002605863140533, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.3210168858915039, "standard_deviation": null, "minimum": 0.3210168858915039, "maximum": 0.3210168858915039, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.97572837295806, "standard_deviation": null, "minimum": 0.97572837295806, "maximum": 0.97572837295806, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.5438431546268525, "standard_deviation": null, "minimum": 1.5438431546268525, "maximum": 1.5438431546268525, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.3257684701586925, "standard_deviation": null, "minimum": 1.3257684701586925, "maximum": 1.3257684701586925, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.23012085955338688, "standard_deviation": null, "minimum": 0.23012085955338688, "maximum": 0.23012085955338688, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9694496756918781, "standard_deviation": null, "minimum": 0.9694496756918781, "maximum": 0.9694496756918781, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.907214628527389, "standard_deviation": null, "minimum": 1.907214628527389, "maximum": 1.907214628527389, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5024827427483899, "standard_deviation": null, "minimum": 0.5024827427483899, "maximum": 0.5024827427483899, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.21468014580340142, "standard_deviation": null, "minimum": 0.21468014580340142, "maximum": 0.21468014580340142, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9921474344801069, "standard_deviation": null, "minimum": 0.9921474344801069, "maximum": 0.9921474344801069, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.2277272913931525, "standard_deviation": null, "minimum": 1.2277272913931525, "maximum": 1.2277272913931525, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.7194784641621546, "standard_deviation": null, "minimum": 0.7194784641621546, "maximum": 0.7194784641621546, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.11794923415567804, "standard_deviation": null, "minimum": 0.11794923415567804, "maximum": 0.11794923415567804, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9240479032813134, "standard_deviation": null, "minimum": 0.9240479032813134, "maximum": 0.9240479032813134, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 3.794348984296812, "standard_deviation": null, "minimum": 3.794348984296812, "maximum": 3.794348984296812, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.9601135221511953, "standard_deviation": null, "minimum": 0.9601135221511953, "maximum": 0.9601135221511953, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.34852629735990664, "standard_deviation": null, "minimum": 0.34852629735990664, "maximum": 0.34852629735990664, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9707257687538224, "standard_deviation": null, "minimum": 0.9707257687538224, "maximum": 0.9707257687538224, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 3.13488077047881, "standard_deviation": null, "minimum": 3.13488077047881, "maximum": 3.13488077047881, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.9810109760074566, "standard_deviation": null, "minimum": 0.9810109760074566, "maximum": 0.9810109760074566, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.22049003295367198, "standard_deviation": null, "minimum": 0.22049003295367198, "maximum": 0.22049003295367198, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 0.8275931844653043, "standard_deviation": null, "minimum": 0.8275931844653043, "maximum": 0.8275931844653043, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 6.304483379920835, "standard_deviation": null, "minimum": 6.304483379920835, "maximum": 6.304483379920835, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.07765222275788844, "standard_deviation": null, "minimum": 0.07765222275788844, "maximum": 0.07765222275788844, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 0.7859244301075996, "standard_deviation": null, "minimum": 0.7859244301075996, "maximum": 0.7859244301075996, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9552297887055254, "standard_deviation": null, "minimum": 0.9552297887055254, "maximum": 0.9552297887055254, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 2.725441008056497, "standard_deviation": null, "minimum": 2.725441008056497, "maximum": 2.725441008056497, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 1.0412345624886508, "standard_deviation": null, "minimum": 1.0412345624886508, "maximum": 1.0412345624886508, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.25221080267617935, "standard_deviation": null, "minimum": 0.25221080267617935, "maximum": 0.25221080267617935, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9821279850340275, "standard_deviation": null, "minimum": 0.9821279850340275, "maximum": 0.9821279850340275, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 1.9772192300226223, "standard_deviation": null, "minimum": 1.9772192300226223, "maximum": 1.9772192300226223, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 1.1826721217072957, "standard_deviation": null, "minimum": 1.1826721217072957, "maximum": 1.1826721217072957, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.16841065067695324, "standard_deviation": null, "minimum": 0.16841065067695324, "maximum": 0.16841065067695324, "valid_count": 1, "planned_count": 1}}, "seconds": 1.1298509830012335, "rtf_including_measurement": 0.28184913669230116}, {"case": "jvs_jvs082_falset10_BASIC5000_1728", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs082", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.6935651302337646, "predicted_mos": 1.6935651302337646, "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": "b414dc0b3a1ed44f8473b289337f6f66854ca448ba5ffefd341e03736a27e080", "internal_samples": 86710, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.0627763570009847}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3589245783838293, "全帯域_10ms_rms_envelope_nrmse": 0.05664207547113944, "全帯域_10ms_envelope_correlation": 0.9973557426041345, "全帯域_10ms_modulation_mae_db": 0.15124375261200373, "全帯域_40ms_log_rms_mae_db": 0.7069826982704827, "全帯域_40ms_rms_envelope_nrmse": 0.030044970672578494, "全帯域_40ms_envelope_correlation": 0.9992966736886013, "全帯域_40ms_modulation_mae_db": 0.47067934394211797, "300–1000 Hz_10ms_log_rms_mae_db": 0.8458641493191967, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0739653756691801, "300–1000 Hz_10ms_envelope_correlation": 0.9957124382912368, "300–1000 Hz_10ms_modulation_mae_db": 0.3327845614429552, "300–1000 Hz_40ms_log_rms_mae_db": 0.5847888320410558, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043322307837049476, "300–1000 Hz_40ms_envelope_correlation": 0.9985230938400822, "300–1000 Hz_40ms_modulation_mae_db": 0.9544010086648965, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8412367370226836, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.059457190710790454, "1000–3000 Hz_10ms_envelope_correlation": 0.9978176754897934, "1000–3000 Hz_10ms_modulation_mae_db": 0.6649847223620973, "1000–3000 Hz_40ms_log_rms_mae_db": 0.537105335738172, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03262666821456376, "1000–3000 Hz_40ms_envelope_correlation": 0.9993919423410826, "1000–3000 Hz_40ms_modulation_mae_db": 0.5849847705758877, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1776705157012162, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12913868491157685, "3000–6000 Hz_10ms_envelope_correlation": 0.9893266292978504, "3000–6000 Hz_10ms_modulation_mae_db": 0.5031388403937933, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8092263389033908, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.061771874552941496, "3000–6000 Hz_40ms_envelope_correlation": 0.9976841594799826, "3000–6000 Hz_40ms_modulation_mae_db": 0.6083878464359177, "mr_stft_db": 5.4211883081033045, "band_mae_db": 1.0413133935429444, "rms_gain_error_db": -0.09516918009905721, "output_peak": 0.21482982742763837}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3466611005369287, "全帯域_10ms_rms_envelope_nrmse": 0.06175396773433907, "全帯域_10ms_envelope_correlation": 0.9968325987580958, "全帯域_10ms_modulation_mae_db": 0.5815971710632317, "全帯域_40ms_log_rms_mae_db": 0.769352241445854, "全帯域_40ms_rms_envelope_nrmse": 0.033633792441397706, "全帯域_40ms_envelope_correlation": 0.9990815789572737, "全帯域_40ms_modulation_mae_db": 0.688964471066695, "300–1000 Hz_10ms_log_rms_mae_db": 0.8401256646917896, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08179694487400041, "300–1000 Hz_10ms_envelope_correlation": 0.9947033381259298, "300–1000 Hz_10ms_modulation_mae_db": 0.4774268721158283, "300–1000 Hz_40ms_log_rms_mae_db": 0.5776608595053763, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04984840177817084, "300–1000 Hz_40ms_envelope_correlation": 0.9979559530462117, "300–1000 Hz_40ms_modulation_mae_db": 0.9694833690025518, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8351505567122385, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.061345562008514404, "1000–3000 Hz_10ms_envelope_correlation": 0.9977048279941585, "1000–3000 Hz_10ms_modulation_mae_db": 0.7035403103748865, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5186160511842478, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03711521875258476, "1000–3000 Hz_40ms_envelope_correlation": 0.9992180809217975, "1000–3000 Hz_40ms_modulation_mae_db": 0.8150565775343231, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1907032931619752, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11478717676614614, "3000–6000 Hz_10ms_envelope_correlation": 0.991812613152397, "3000–6000 Hz_10ms_modulation_mae_db": 0.3175300029028862, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8379960224391151, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06742547392463308, "3000–6000 Hz_40ms_envelope_correlation": 0.9974314935935106, "3000–6000 Hz_40ms_modulation_mae_db": 0.6763153151892741, "mr_stft_db": 5.421103635015615, "band_mae_db": 1.2474571138339312, "rms_gain_error_db": -0.09155481915365013, "output_peak": 0.20945345123425269}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3290583762535102, "全帯域_10ms_rms_envelope_nrmse": 0.06654826402429134, "全帯域_10ms_envelope_correlation": 0.9963322503443951, "全帯域_10ms_modulation_mae_db": 0.5074967965210079, "全帯域_40ms_log_rms_mae_db": 0.717017947376702, "全帯域_40ms_rms_envelope_nrmse": 0.03612951987397551, "全帯域_40ms_envelope_correlation": 0.9989567878645976, "全帯域_40ms_modulation_mae_db": 0.6699658758329213, "300–1000 Hz_10ms_log_rms_mae_db": 0.8188509510849997, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07309948557288576, "300–1000 Hz_10ms_envelope_correlation": 0.9958080531533084, "300–1000 Hz_10ms_modulation_mae_db": 0.5187377073084413, "300–1000 Hz_40ms_log_rms_mae_db": 0.5542674749476756, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04145223048328492, "300–1000 Hz_40ms_envelope_correlation": 0.9986028921219631, "300–1000 Hz_40ms_modulation_mae_db": 0.9773223202296671, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8551130288952004, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06631397277455768, "1000–3000 Hz_10ms_envelope_correlation": 0.9972801449374017, "1000–3000 Hz_10ms_modulation_mae_db": 0.4244293522027283, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5150052866963617, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03951878105841918, "1000–3000 Hz_40ms_envelope_correlation": 0.9990821552753942, "1000–3000 Hz_40ms_modulation_mae_db": 0.8168604791572515, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2211702852393325, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13401863742503456, "3000–6000 Hz_10ms_envelope_correlation": 0.9907361136752791, "3000–6000 Hz_10ms_modulation_mae_db": 0.8347105730843208, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8419130946676898, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09980760727889045, "3000–6000 Hz_40ms_envelope_correlation": 0.9961008564160481, "3000–6000 Hz_40ms_modulation_mae_db": 1.422889983701505, "mr_stft_db": 5.416424649600234, "band_mae_db": 1.2510291249067063, "rms_gain_error_db": -0.10502878529035534, "output_peak": 0.22604660259534762}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2809189375169956, "全帯域_10ms_rms_envelope_nrmse": 0.07456187352081706, "全帯域_10ms_envelope_correlation": 0.9953811465238397, "全帯域_10ms_modulation_mae_db": 0.4384201328768773, "全帯域_40ms_log_rms_mae_db": 0.666009928447425, "全帯域_40ms_rms_envelope_nrmse": 0.03927586807866401, "全帯域_40ms_envelope_correlation": 0.9987726347111285, "全帯域_40ms_modulation_mae_db": 0.7571625786837023, "300–1000 Hz_10ms_log_rms_mae_db": 0.8409174342303379, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07814723110762369, "300–1000 Hz_10ms_envelope_correlation": 0.995220832838502, "300–1000 Hz_10ms_modulation_mae_db": 0.2914056308692094, "300–1000 Hz_40ms_log_rms_mae_db": 0.5807403110403712, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04392384248864982, "300–1000 Hz_40ms_envelope_correlation": 0.9984454481423408, "300–1000 Hz_40ms_modulation_mae_db": 0.664492139891332, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8275057166166879, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06678268734217863, "1000–3000 Hz_10ms_envelope_correlation": 0.9973609772032822, "1000–3000 Hz_10ms_modulation_mae_db": 0.544742728253056, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5487021893255015, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04027468212192892, "1000–3000 Hz_40ms_envelope_correlation": 0.9991824499287933, "1000–3000 Hz_40ms_modulation_mae_db": 0.8521136411142102, "3000–6000 Hz_10ms_log_rms_mae_db": 1.208761864052675, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1185016575542201, "3000–6000 Hz_10ms_envelope_correlation": 0.9912611776008268, "3000–6000 Hz_10ms_modulation_mae_db": 0.9718540854027786, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8329946628848406, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.059854701959114805, "3000–6000 Hz_40ms_envelope_correlation": 0.9981169947506496, "3000–6000 Hz_40ms_modulation_mae_db": 0.425082468969419, "mr_stft_db": 5.427535752053082, "band_mae_db": 1.2608207749447267, "rms_gain_error_db": -0.11476301538829478, "output_peak": 0.21309651108712716}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.294549815297281, "全帯域_10ms_rms_envelope_nrmse": 0.05804811512465609, "全帯域_10ms_envelope_correlation": 0.9972669977420217, "全帯域_10ms_modulation_mae_db": 0.23245625084752786, "全帯域_40ms_log_rms_mae_db": 0.7025490617743458, "全帯域_40ms_rms_envelope_nrmse": 0.03323559992735995, "全帯域_40ms_envelope_correlation": 0.9991675175368079, "全帯域_40ms_modulation_mae_db": 0.2207321700790048, "300–1000 Hz_10ms_log_rms_mae_db": 0.9088788683573124, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06816122345638975, "300–1000 Hz_10ms_envelope_correlation": 0.9963538752378541, "300–1000 Hz_10ms_modulation_mae_db": 0.7862278578901741, "300–1000 Hz_40ms_log_rms_mae_db": 0.6808591627019824, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.041409649656427634, "300–1000 Hz_40ms_envelope_correlation": 0.9986029465045138, "300–1000 Hz_40ms_modulation_mae_db": 0.9617814342467043, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8530266470891533, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06654274653651808, "1000–3000 Hz_10ms_envelope_correlation": 0.997263833027381, "1000–3000 Hz_10ms_modulation_mae_db": 0.7909243725017494, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5377393340634198, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03795590407420055, "1000–3000 Hz_40ms_envelope_correlation": 0.9991600622320523, "1000–3000 Hz_40ms_modulation_mae_db": 0.5768303990313687, "3000–6000 Hz_10ms_log_rms_mae_db": 1.163508587798957, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13670856336861698, "3000–6000 Hz_10ms_envelope_correlation": 0.9881630632664309, "3000–6000 Hz_10ms_modulation_mae_db": 1.4141015408617215, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7951106661180548, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06559390009103236, "3000–6000 Hz_40ms_envelope_correlation": 0.9976024949741471, "3000–6000 Hz_40ms_modulation_mae_db": 0.8304072739147533, "mr_stft_db": 5.420353430212173, "band_mae_db": 1.2483066279090256, "rms_gain_error_db": -0.11242122931405654, "output_peak": 0.22628264003436244}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3201993446703222, "全帯域_10ms_rms_envelope_nrmse": 0.05858610722147373, "全帯域_10ms_envelope_correlation": 0.9971061552591378, "全帯域_10ms_modulation_mae_db": 0.5268856538954131, "全帯域_40ms_log_rms_mae_db": 0.6535244977549104, "全帯域_40ms_rms_envelope_nrmse": 0.028916385506164325, "全帯域_40ms_envelope_correlation": 0.9992768321736953, "全帯域_40ms_modulation_mae_db": 0.7026431427444395, "300–1000 Hz_10ms_log_rms_mae_db": 0.8229275783346911, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07841875002781461, "300–1000 Hz_10ms_envelope_correlation": 0.995180880068054, "300–1000 Hz_10ms_modulation_mae_db": 0.8222812050810678, "300–1000 Hz_40ms_log_rms_mae_db": 0.551493380054629, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04327573960578109, "300–1000 Hz_40ms_envelope_correlation": 0.9984808593630715, "300–1000 Hz_40ms_modulation_mae_db": 1.274762662949926, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8467382826446727, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06289050485491299, "1000–3000 Hz_10ms_envelope_correlation": 0.9975502227990016, "1000–3000 Hz_10ms_modulation_mae_db": 0.6676026864389549, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5254248159097952, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.036122375408788356, "1000–3000 Hz_40ms_envelope_correlation": 0.9992341474936348, "1000–3000 Hz_40ms_modulation_mae_db": 1.1607486904321862, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1911087580169117, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13847011417142135, "3000–6000 Hz_10ms_envelope_correlation": 0.9876912868980051, "3000–6000 Hz_10ms_modulation_mae_db": 0.6040848861486542, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8205422357378807, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08953528173230624, "3000–6000 Hz_40ms_envelope_correlation": 0.9947132299477658, "3000–6000 Hz_40ms_modulation_mae_db": 0.48881038577778374, "mr_stft_db": 5.415328292872232, "band_mae_db": 1.1202655378008906, "rms_gain_error_db": -0.04137521925224167, "output_peak": 0.23026795025124003}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.3326505167376035, "全帯域_10ms_rms_envelope_nrmse": 0.07528026356815286, "全帯域_10ms_envelope_correlation": 0.9953670945832532, "全帯域_10ms_modulation_mae_db": 0.0642901182684836, "全帯域_40ms_log_rms_mae_db": 0.6826948043866832, "全帯域_40ms_rms_envelope_nrmse": 0.05256839243171472, "全帯域_40ms_envelope_correlation": 0.9977589094740146, "全帯域_40ms_modulation_mae_db": 0.2825090535559409, "300–1000 Hz_10ms_log_rms_mae_db": 0.8011616196561766, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07187572456141429, "300–1000 Hz_10ms_envelope_correlation": 0.9959549695290797, "300–1000 Hz_10ms_modulation_mae_db": 0.5027244670241038, "300–1000 Hz_40ms_log_rms_mae_db": 0.5752634275695726, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03986621987594534, "300–1000 Hz_40ms_envelope_correlation": 0.9987249679614121, "300–1000 Hz_40ms_modulation_mae_db": 0.5863231512833695, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8384240846991398, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.055896309769165875, "1000–3000 Hz_10ms_envelope_correlation": 0.9981102116215625, "1000–3000 Hz_10ms_modulation_mae_db": 0.3323285708025217, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5103679786538264, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03304830662430342, "1000–3000 Hz_40ms_envelope_correlation": 0.9994055163055586, "1000–3000 Hz_40ms_modulation_mae_db": 0.6222339279210466, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1591751323374482, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12497052850916164, "3000–6000 Hz_10ms_envelope_correlation": 0.990600981689628, "3000–6000 Hz_10ms_modulation_mae_db": 0.7078615217715711, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7813108129075639, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0783608820193915, "3000–6000 Hz_40ms_envelope_correlation": 0.9968299639044566, "3000–6000 Hz_40ms_modulation_mae_db": 0.4160590587014296, "mr_stft_db": 5.4218768596749145, "band_mae_db": 1.2780314840081561, "rms_gain_error_db": -0.14834684792386543, "output_peak": 0.24489077926530967}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2955448477616258, "全帯域_10ms_rms_envelope_nrmse": 0.06700052588026313, "全帯域_10ms_envelope_correlation": 0.9962951083279727, "全帯域_10ms_modulation_mae_db": 0.6282117004874286, "全帯域_40ms_log_rms_mae_db": 0.6856952233598107, "全帯域_40ms_rms_envelope_nrmse": 0.03383778651084421, "全帯域_40ms_envelope_correlation": 0.9991195275282968, "全帯域_40ms_modulation_mae_db": 0.8478996502830868, "300–1000 Hz_10ms_log_rms_mae_db": 0.8669706198930667, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07072862655027783, "300–1000 Hz_10ms_envelope_correlation": 0.9960359432437016, "300–1000 Hz_10ms_modulation_mae_db": 0.301077290104201, "300–1000 Hz_40ms_log_rms_mae_db": 0.5736904122543426, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.039005711878129075, "300–1000 Hz_40ms_envelope_correlation": 0.9987417756906738, "300–1000 Hz_40ms_modulation_mae_db": 0.964972211313818, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8384789146804958, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05887606345775105, "1000–3000 Hz_10ms_envelope_correlation": 0.9980282811880857, "1000–3000 Hz_10ms_modulation_mae_db": 0.5979475967580472, "1000–3000 Hz_40ms_log_rms_mae_db": 0.523888042144616, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.037116413227076775, "1000–3000 Hz_40ms_envelope_correlation": 0.9993642489237334, "1000–3000 Hz_40ms_modulation_mae_db": 0.7147416749431285, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1911120443002876, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1255258158546958, "3000–6000 Hz_10ms_envelope_correlation": 0.9908473905568425, "3000–6000 Hz_10ms_modulation_mae_db": 0.4660826173050969, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8245588013325432, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07668397065886401, "3000–6000 Hz_40ms_envelope_correlation": 0.9974150638958256, "3000–6000 Hz_40ms_modulation_mae_db": 0.8706768535390284, "mr_stft_db": 5.4214965524025684, "band_mae_db": 1.3389405709992845, "rms_gain_error_db": -0.11123036202914202, "output_peak": 0.22354845378084173}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.5817310403470515, "spectral_convergence": 0.1638863991456749, "spectral_convergence_status": "ok", "amplitude_floor": 8.628776010687778e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.494613692473973, "spectral_convergence": 0.178102861705369, "spectral_convergence_status": "ok", "amplitude_floor": 8.696913128358987e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.187220191488891, "spectral_convergence": 0.1739563475084712, "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": 6.4311390607191555e-06, "delta_db": 6.318452322177169, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008569985031977355, "output_power": 0.0008291017858945077, "delta_db": -0.1437221277983643, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0002039561579698118, "output_power": 0.0002072270666251555, "delta_db": 0.06909657105814376, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00031755380447674584, "output_power": 0.0003103678461615452, "delta_db": -0.09940597816655908, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 8.391217397004902e-05, "output_power": 7.960459187348633e-05, "delta_db": -0.22886852703998536, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2641952404694477e-05, "output_power": 1.1854761471959969e-05, "delta_db": -0.27921330910586245, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.274471551779886e-06, "output_power": 2.1970352111310536e-06, "delta_db": -0.1504349194545273, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.0413133935429444, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.09516918009905721, "pitch": null, "output_rms_dbfs": -28.3959623482116, "output_peak": 0.21482982742763837, "reference_rms_dbfs": -28.300793168112545, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.4211883081033045}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 130065, "output_samples": 130065, "intelligibility": {"estoi": {"value": 0.8728173997501023, "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"}}, "level": {"reference": {"rms": 0.038455666393735516, "rms_dbfs": -28.300793168112545, "peak": 0.220855712890625, "peak_dbfs": -13.117827246673288, "crest_factor_db": 15.182965921439258, "mean": 1.9380709284780687e-07, "zero_energy": false}, "output": {"rms": 0.03803661691447473, "rms_dbfs": -28.3959623482116, "peak": 0.21482982742763837, "peak_dbfs": -13.358108408433015, "crest_factor_db": 15.037853939778588, "mean": -2.6929202006280238e-06, "zero_energy": false}, "rms_difference_db": -0.09516918009905595}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 541, "uncovered_tail_samples": 225, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.6147675896839552e-06, "threshold_dbfs": -57.918899759837146, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 245, "quiet_samples": 58800, "reference_mean_power": 9.664815856891424e-08, "output_mean_power": 2.407183902319633e-07, "output_rms_dbfs": -66.18490729537305, "output_zero_energy": false, "output_peak": 0.011229449739761081, "output_energy_fraction": 7.52181046904017e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 534, "reference_estimated_voiced_frames": 280, "output_estimated_voiced_frames": 250, "both_estimated_voiced_frames": 249, "reference_voiced_output_unvoiced_frames": 31, "reference_unvoiced_output_voiced_frames": 1, "paired_voiced_fraction": 0.8892857142857142, "absolute_difference_cents_median": 1.3949425114976637, "absolute_difference_cents_p95": 11.822603070234795, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 225, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.3589245783838293, "rms_envelope_nrmse": 0.05664207547113944, "envelope_correlation": 0.9973557426041345, "rms_gain_error_db": -0.09516938056402027, "reference_mean_power": 0.0014814008893508253, "output_mean_power": 0.0014492912259581922}, "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": 0.00028420617055412194, "reference_active": true, "delta_db": -0.12066459388350054}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.043814645706353e-05, "output_power": 2.996543102565663e-05, "reference_active": true, "delta_db": -0.06797673358688926}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.705913608511969e-06, "output_power": 5.368045630056418e-06, "reference_active": true, "delta_db": -0.2650899303656214}], "active_band_count": 3, "active_band_mae_db": 0.15124375261200373}}, {"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": 0.7069826982704827, "rms_envelope_nrmse": 0.030044970672578494, "envelope_correlation": 0.9992966736886013, "rms_gain_error_db": -0.09516969132630634, "reference_mean_power": 0.001489661173505724, "output_mean_power": 0.0014573723625029185}, "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": 0.0002532933075068463, "reference_active": true, "delta_db": -0.1048380260280478}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3907004138768798e-05, "output_power": 1.3445937301129119e-05, "reference_active": true, "delta_db": -0.14642502107382427}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.4011744172060643e-07, "output_power": 3.36892297297939e-07, "reference_active": true, "delta_db": -1.1607749847244817}], "active_band_count": 3, "active_band_mae_db": 0.47067934394211797}}]}, {"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": 8.480086855572361e-05, "log_rms_mae_db": 0.8458641493191967, "rms_envelope_nrmse": 0.0739653756691801, "envelope_correlation": 0.9957124382912368, "rms_gain_error_db": -0.06939340208927813, "reference_mean_power": 0.0005471873658289664, "output_mean_power": 0.0005385136561897015}, "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": 0.00011550738621428663, "output_power": 0.00011086582352463252, "reference_active": true, "delta_db": -0.17812069094298652}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3854221447460656e-05, "output_power": 1.1803874203111375e-05, "reference_active": true, "delta_db": -0.6955755270311794}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9357817767829538e-06, "output_power": 1.8810080341491593e-06, "reference_active": true, "delta_db": -0.1246574663546997}], "active_band_count": 3, "active_band_mae_db": 0.3327845614429552}}, {"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": 7.444752199710231e-05, "log_rms_mae_db": 0.5847888320410558, "rms_envelope_nrmse": 0.043322307837049476, "envelope_correlation": 0.9985230938400822, "rms_gain_error_db": -0.06939350037965056, "reference_mean_power": 0.000550238587629155, "output_mean_power": 0.000541516499464067}, "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": 9.910211940271507e-05, "output_power": 9.553866815593851e-05, "reference_active": true, "delta_db": -0.1590375966214057}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.2312084488175375e-06, "output_power": 5.391459937471715e-06, "reference_active": true, "delta_db": -0.628658972574877}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.5189682275535194e-07, "output_power": 1.5619676825088e-07, "reference_active": true, "delta_db": -2.0755064567984065}], "active_band_count": 3, "active_band_mae_db": 0.9544010086648965}}]}, {"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": 0.8412367370226836, "rms_envelope_nrmse": 0.059457190710790454, "envelope_correlation": 0.9978176754897934, "rms_gain_error_db": -0.10715353358136714, "reference_mean_power": 0.0003517587960046477, "output_mean_power": 0.00034318603944650785}, "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": 3.408664178054299e-05, "output_power": 3.2211618192416617e-05, "reference_active": true, "delta_db": -0.24571673885091463}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.90892498484566e-06, "output_power": 7.634743700761151e-06, "reference_active": true, "delta_db": -0.6703083977277937}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.006695723935486e-07, "output_power": 4.6853574562197037e-07, "reference_active": true, "delta_db": -1.0789290305075836}], "active_band_count": 3, "active_band_mae_db": 0.6649847223620973}}, {"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": 0.537105335738172, "rms_envelope_nrmse": 0.03262666821456376, "envelope_correlation": 0.9993919423410826, "rms_gain_error_db": -0.10715354807828294, "reference_mean_power": 0.0003537202709185465, "output_mean_power": 0.0003450997098638783}, "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": 2.87650208801992e-05, "reference_active": true, "delta_db": -0.23850200356489162}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.277692934034563e-06, "output_power": 3.6285418059460757e-06, "reference_active": true, "delta_db": -0.7147747522516443}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.6389202390485585e-08, "output_power": 4.688438202995474e-08, "reference_active": true, "delta_db": -0.8016775559111272}], "active_band_count": 3, "active_band_mae_db": 0.5849847705758877}}]}, {"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": 1.1776705157012162, "rms_envelope_nrmse": 0.12913868491157685, "envelope_correlation": 0.9893266292978504, "rms_gain_error_db": -0.17835206305852794, "reference_mean_power": 4.415064676151012e-05, "output_mean_power": 4.2374234301539465e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 2.2237128168975065e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.193805277966024e-06, "output_power": 8.313251401918815e-06, "reference_active": true, "delta_db": -0.4372438703898245}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0890347422283219e-06, "output_power": 1.0801658475935218e-06, "reference_active": true, "delta_db": -0.035512930255119375}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8576888047519527e-07, "output_power": 2.3585165924685414e-07, "reference_active": true, "delta_db": 1.036659720536436}], "active_band_count": 3, "active_band_mae_db": 0.5031388403937933}}, {"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": 0.8092263389033908, "rms_envelope_nrmse": 0.061771874552941496, "envelope_correlation": 0.9976841594799826, "rms_gain_error_db": -0.1783520760062843, "reference_mean_power": 4.439683700027619e-05, "output_mean_power": 4.261051888662952e-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": 8.24746849682131e-06, "output_power": 7.5237611887795635e-06, "reference_active": true, "delta_db": -0.398856631450282}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.957219370502519e-07, "output_power": 4.4175230252654044e-07, "reference_active": true, "delta_db": -0.5005931620875415}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6536836687109697e-08, "output_power": 1.3362295228252445e-08, "reference_active": true, "delta_db": -0.9257137457699298}], "active_band_count": 3, "active_band_mae_db": 0.6083878464359177}}]}], "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"]}}, "output_samples": 130065, "representation_scalars": 1221138, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9976395217825833, "standard_deviation": 0.0003304848371954707, "minimum": 0.997263833027381, "maximum": 0.9981102116215625, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.841959246045034, "standard_deviation": 0.009248501150872656, "minimum": 0.8275057166166879, "maximum": 0.8551130288952004, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5908125424617552, "standard_deviation": 0.15157327273367452, "minimum": 0.3323285708025217, "maximum": 0.7909243725017494, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.062263129681798646, "standard_deviation": 0.004075506779859264, "minimum": 0.055896309769165875, "maximum": 0.06678268734217863, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9992548254277559, "standard_deviation": 0.00011909976811146042, "minimum": 0.9990821552753942, "maximum": 0.9994055163055586, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.5271061292144926, "standard_deviation": 0.01304552132451369, "minimum": 0.5103679786538264, "maximum": 0.5487021893255015, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7679462700886753, "standard_deviation": 0.19274441654615967, "minimum": 0.5768303990313687, "maximum": 1.1607486904321862, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03672229368523322, "standard_deviation": 0.0027491180665138704, "minimum": 0.03262666821456376, "maximum": 0.04027468212192892, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9900549070171575, "standard_deviation": 0.0014943250306124031, "minimum": 0.9876912868980051, "maximum": 0.991812613152397, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.1879013100761004, "standard_deviation": 0.021028220519407757, "minimum": 1.1591751323374482, "maximum": 1.2211702852393325, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7274205084838528, "standard_deviation": 0.34743837850049025, "minimum": 0.3175300029028862, "maximum": 1.4141015408617215, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12776514732010918, "standard_deviation": 0.008473810173239912, "minimum": 0.11478717676614614, "maximum": 0.13847011417142135, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9969867821202982, "standard_deviation": 0.0011021088519712898, "minimum": 0.9947132299477658, "maximum": 0.9981169947506496, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8179565793738849, "standard_deviation": 0.0213574271583285, "minimum": 0.7813108129075639, "maximum": 0.8419130946676898, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.717328648278639, "standard_deviation": 0.3329652982121483, "minimum": 0.4160590587014296, "maximum": 1.422889983701505, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07487921152714674, "standard_deviation": 0.014096189336038992, "minimum": 0.059854701959114805, "maximum": 0.09980760727889045, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9956212913109583, "standard_deviation": 0.0005424957468216205, "minimum": 0.9947033381259298, "maximum": 0.9963538752378541, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.8432121106959463, "standard_deviation": 0.0331049995496891, "minimum": 0.8011616196561766, "maximum": 0.9088788683573124, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5040831989794976, "standard_deviation": 0.20617922522652007, "minimum": 0.2914056308692094, "maximum": 0.8222812050810678, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07452417022744831, "standard_deviation": 0.00455814903862574, "minimum": 0.06816122345638975, "maximum": 0.08179694487400041, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9985097420837836, "standard_deviation": 0.0002476617095893407, "minimum": 0.9979559530462117, "maximum": 0.9987417756906738, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.5848454825143757, "standard_deviation": 0.040621475473945845, "minimum": 0.551493380054629, "maximum": 0.6808591627019824, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.9191922871977831, "standard_deviation": 0.21151220951249786, "minimum": 0.5863231512833695, "maximum": 1.274762662949926, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04276301295042978, "standard_deviation": 0.0033420358166074346, "minimum": 0.039005711878129075, "maximum": 0.04984840177817084, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.2232705784932083, "standard_deviation": 0.09523587703089073, "minimum": 1.0413133935429444, "maximum": 1.3389405709992845, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.4206634349917655, "standard_deviation": 0.003710826625502765, "minimum": 5.415328292872232, "maximum": 5.427535752053082, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.22355202695951498, "standard_deviation": 0.01132815429472701, "minimum": 0.20945345123425269, "maximum": 0.24489077926530967, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.10248618230633288, "standard_deviation": 0.030102527128099868, "minimum": -0.14834684792386543, "maximum": -0.04137521925224167, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9964921367678563, "standard_deviation": 0.0007931457043352711, "minimum": 0.9953670945832532, "maximum": 0.9973557426041345, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.319813439644762, "standard_deviation": 0.027362341053903973, "minimum": 1.2809189375169956, "maximum": 1.3589245783838293, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3913251970714967, "standard_deviation": 0.2125489642259204, "minimum": 0.0642901182684836, "maximum": 0.6282117004874286, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.0648026490681416, "standard_deviation": 0.007300286121762385, "minimum": 0.05664207547113944, "maximum": 0.07528026356815286, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9989288077418019, "standard_deviation": 0.0005024193847533732, "minimum": 0.9977589094740146, "maximum": 0.9992966736886013, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6979783003520267, "standard_deviation": 0.03573972432709396, "minimum": 0.6535244977549104, "maximum": 0.769352241445854, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5800695357734885, "standard_deviation": 0.2291881513799088, "minimum": 0.2207321700790048, "maximum": 0.8478996502830868, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.035955289430337364, "standard_deviation": 0.0074527052067397915, "minimum": 0.028916385506164325, "maximum": 0.05256839243171472, "valid_count": 8, "planned_count": 8}}, "seconds": 7.469571654997708, "rtf_including_measurement": 1.3783086896547496}, {"case": "jvs_jvs082_falset10_BASIC5000_1728", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs082", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.6691093444824219, "predicted_mos": 1.6691093444824219, "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": 3.4286446510013775}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.274883390161223, "全帯域_10ms_rms_envelope_nrmse": 0.05300869794327403, "全帯域_10ms_envelope_correlation": 0.9977129803276675, "全帯域_10ms_modulation_mae_db": 0.22669309080401093, "全帯域_40ms_log_rms_mae_db": 0.7023181666967468, "全帯域_40ms_rms_envelope_nrmse": 0.028396435193587612, "全帯域_40ms_envelope_correlation": 0.9994020226936223, "全帯域_40ms_modulation_mae_db": 0.4883624402845064, "300–1000 Hz_10ms_log_rms_mae_db": 0.7627626877913188, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07143809238849673, "300–1000 Hz_10ms_envelope_correlation": 0.9960090240838532, "300–1000 Hz_10ms_modulation_mae_db": 0.37888561125824577, "300–1000 Hz_40ms_log_rms_mae_db": 0.5374293616790191, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04199188707797649, "300–1000 Hz_40ms_envelope_correlation": 0.9986240656182779, "300–1000 Hz_40ms_modulation_mae_db": 0.942194336923316, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8019837953155563, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05924398720634125, "1000–3000 Hz_10ms_envelope_correlation": 0.9978488286082511, "1000–3000 Hz_10ms_modulation_mae_db": 0.665293680987541, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5234844173311514, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03312000903594599, "1000–3000 Hz_40ms_envelope_correlation": 0.9993872579002268, "1000–3000 Hz_40ms_modulation_mae_db": 0.5784975033608236, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1079161343381583, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12871521232890742, "3000–6000 Hz_10ms_envelope_correlation": 0.9893595608915978, "3000–6000 Hz_10ms_modulation_mae_db": 0.5024341406974856, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7679531589521342, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.061093259242149416, "3000–6000 Hz_40ms_envelope_correlation": 0.9976782961895735, "3000–6000 Hz_40ms_modulation_mae_db": 0.5879702119559241, "mr_stft_db": 5.410515843269717, "band_mae_db": 1.000949404181786, "rms_gain_error_db": -0.10335498557354507, "output_peak": 0.21619555418188252}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2637285384295904, "全帯域_10ms_rms_envelope_nrmse": 0.06141800287538496, "全帯域_10ms_envelope_correlation": 0.9968707193046918, "全帯域_10ms_modulation_mae_db": 0.6544525026957179, "全帯域_40ms_log_rms_mae_db": 0.7519415650540441, "全帯域_40ms_rms_envelope_nrmse": 0.03333369715538534, "全帯域_40ms_envelope_correlation": 0.9991038603675172, "全帯域_40ms_modulation_mae_db": 0.7954699991450389, "300–1000 Hz_10ms_log_rms_mae_db": 0.8015208616461257, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08061206579381651, "300–1000 Hz_10ms_envelope_correlation": 0.9948494041467084, "300–1000 Hz_10ms_modulation_mae_db": 0.5182386894194296, "300–1000 Hz_40ms_log_rms_mae_db": 0.5478114666996494, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.048742368125265, "300–1000 Hz_40ms_envelope_correlation": 0.9980415738828234, "300–1000 Hz_40ms_modulation_mae_db": 1.0407026814232, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7974341123499591, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06189560823581846, "1000–3000 Hz_10ms_envelope_correlation": 0.997691643210373, "1000–3000 Hz_10ms_modulation_mae_db": 0.6891046277671831, "1000–3000 Hz_40ms_log_rms_mae_db": 0.48878768525272864, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03743979976865312, "1000–3000 Hz_40ms_envelope_correlation": 0.9992360609260351, "1000–3000 Hz_40ms_modulation_mae_db": 0.7781169458423807, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1170490372772888, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11447606513567822, "3000–6000 Hz_10ms_envelope_correlation": 0.9917711778091313, "3000–6000 Hz_10ms_modulation_mae_db": 0.3662767843334847, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7773494322053442, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06639098541264139, "3000–6000 Hz_40ms_envelope_correlation": 0.9974140020284661, "3000–6000 Hz_40ms_modulation_mae_db": 0.6446503072263373, "mr_stft_db": 5.398753750158218, "band_mae_db": 1.2306233953748233, "rms_gain_error_db": -0.0939483030791685, "output_peak": 0.21119314319962074}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2571003818285555, "全帯域_10ms_rms_envelope_nrmse": 0.06521411302270311, "全帯域_10ms_envelope_correlation": 0.9964832415686989, "全帯域_10ms_modulation_mae_db": 0.44049599891103436, "全帯域_40ms_log_rms_mae_db": 0.7434569816872775, "全帯域_40ms_rms_envelope_nrmse": 0.03569806611179268, "全帯域_40ms_envelope_correlation": 0.9989863649671812, "全帯域_40ms_modulation_mae_db": 0.6013855918919289, "300–1000 Hz_10ms_log_rms_mae_db": 0.7819029717164845, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0721125508778329, "300–1000 Hz_10ms_envelope_correlation": 0.9959231057368241, "300–1000 Hz_10ms_modulation_mae_db": 0.4581870402314235, "300–1000 Hz_40ms_log_rms_mae_db": 0.5310248642568726, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04060940593101274, "300–1000 Hz_40ms_envelope_correlation": 0.9986630067887227, "300–1000 Hz_40ms_modulation_mae_db": 0.8833986280993907, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8073615160740532, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0658513846635466, "1000–3000 Hz_10ms_envelope_correlation": 0.9973261893921669, "1000–3000 Hz_10ms_modulation_mae_db": 0.4302831468522819, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4793152385189854, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.039008885570241375, "1000–3000 Hz_40ms_envelope_correlation": 0.9991164612063762, "1000–3000 Hz_40ms_modulation_mae_db": 0.7256262722027044, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1535612507017499, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1363514031816353, "3000–6000 Hz_10ms_envelope_correlation": 0.9902636893802478, "3000–6000 Hz_10ms_modulation_mae_db": 0.8271492238154852, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7944964691474591, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10174725728575029, "3000–6000 Hz_40ms_envelope_correlation": 0.9957815132631004, "3000–6000 Hz_40ms_modulation_mae_db": 1.361508342800695, "mr_stft_db": 5.401225816439077, "band_mae_db": 1.222465631654974, "rms_gain_error_db": -0.10612896735519076, "output_peak": 0.2268518028268997}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2291898594217097, "全帯域_10ms_rms_envelope_nrmse": 0.07274402694343654, "全帯域_10ms_envelope_correlation": 0.995609564776062, "全帯域_10ms_modulation_mae_db": 0.4066871181811056, "全帯域_40ms_log_rms_mae_db": 0.707919521688837, "全帯域_40ms_rms_envelope_nrmse": 0.03833727970899075, "全帯域_40ms_envelope_correlation": 0.9988366867855001, "全帯域_40ms_modulation_mae_db": 0.6907489970747721, "300–1000 Hz_10ms_log_rms_mae_db": 0.7943567850581901, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07758660779808879, "300–1000 Hz_10ms_envelope_correlation": 0.9952814292151774, "300–1000 Hz_10ms_modulation_mae_db": 0.24384857008119534, "300–1000 Hz_40ms_log_rms_mae_db": 0.548962849689049, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043715162684594376, "300–1000 Hz_40ms_envelope_correlation": 0.9984544430945024, "300–1000 Hz_40ms_modulation_mae_db": 0.578958297901744, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7718310826830741, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06474384053186327, "1000–3000 Hz_10ms_envelope_correlation": 0.9975324648929803, "1000–3000 Hz_10ms_modulation_mae_db": 0.5455736923791742, "1000–3000 Hz_40ms_log_rms_mae_db": 0.5035599363913105, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03909571662708278, "1000–3000 Hz_40ms_envelope_correlation": 0.9992420418867914, "1000–3000 Hz_40ms_modulation_mae_db": 0.7775857397650691, "3000–6000 Hz_10ms_log_rms_mae_db": 1.1148425274181415, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.11759258793524367, "3000–6000 Hz_10ms_envelope_correlation": 0.9913575611104047, "3000–6000 Hz_10ms_modulation_mae_db": 0.9303582096731362, "3000–6000 Hz_40ms_log_rms_mae_db": 0.783476698213938, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.05923498176409333, "3000–6000 Hz_40ms_envelope_correlation": 0.9981092254516334, "3000–6000 Hz_40ms_modulation_mae_db": 0.4299559102228064, "mr_stft_db": 5.4041719628193645, "band_mae_db": 1.2601105725859771, "rms_gain_error_db": -0.11515782853337327, "output_peak": 0.21098262277196497}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2095175428119411, "全帯域_10ms_rms_envelope_nrmse": 0.05753113248445883, "全帯域_10ms_envelope_correlation": 0.9973043801837018, "全帯域_10ms_modulation_mae_db": 0.2206683626492644, "全帯域_40ms_log_rms_mae_db": 0.6663819794241127, "全帯域_40ms_rms_envelope_nrmse": 0.03280076317303502, "全帯域_40ms_envelope_correlation": 0.9991799551504458, "全帯域_40ms_modulation_mae_db": 0.15712505151200123, "300–1000 Hz_10ms_log_rms_mae_db": 0.8653320919825919, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06928700697924532, "300–1000 Hz_10ms_envelope_correlation": 0.9962209727552482, "300–1000 Hz_10ms_modulation_mae_db": 0.6159638848218569, "300–1000 Hz_40ms_log_rms_mae_db": 0.6452887012071566, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04232659865358514, "300–1000 Hz_40ms_envelope_correlation": 0.9985330824353371, "300–1000 Hz_40ms_modulation_mae_db": 0.7208750332144186, "1000–3000 Hz_10ms_log_rms_mae_db": 0.8022597635371276, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06596958756731802, "1000–3000 Hz_10ms_envelope_correlation": 0.9973122514868753, "1000–3000 Hz_10ms_modulation_mae_db": 0.7288760236889725, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4950946304981875, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03707309094120679, "1000–3000 Hz_40ms_envelope_correlation": 0.9992022417828422, "1000–3000 Hz_40ms_modulation_mae_db": 0.5269520498861681, "3000–6000 Hz_10ms_log_rms_mae_db": 1.099775947775409, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13607426975038445, "3000–6000 Hz_10ms_envelope_correlation": 0.9881830687467456, "3000–6000 Hz_10ms_modulation_mae_db": 1.4652544616121783, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7543580858948391, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.06325147408744973, "3000–6000 Hz_40ms_envelope_correlation": 0.9976702609481048, "3000–6000 Hz_40ms_modulation_mae_db": 0.8958022229098659, "mr_stft_db": 5.403385851659528, "band_mae_db": 1.2290662681512161, "rms_gain_error_db": -0.10869018309368589, "output_peak": 0.23035431247435434}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.207597105664091, "全帯域_10ms_rms_envelope_nrmse": 0.057329722388404065, "全帯域_10ms_envelope_correlation": 0.9972239958751159, "全帯域_10ms_modulation_mae_db": 0.5853370008977934, "全帯域_40ms_log_rms_mae_db": 0.6241758969186152, "全帯域_40ms_rms_envelope_nrmse": 0.028601270652279347, "全帯域_40ms_envelope_correlation": 0.9992851890394239, "全帯域_40ms_modulation_mae_db": 0.7529555558266545, "300–1000 Hz_10ms_log_rms_mae_db": 0.7537767817382467, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07755654675556485, "300–1000 Hz_10ms_envelope_correlation": 0.9952825910413016, "300–1000 Hz_10ms_modulation_mae_db": 0.709692413532469, "300–1000 Hz_40ms_log_rms_mae_db": 0.4964233045031956, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04291387370188716, "300–1000 Hz_40ms_envelope_correlation": 0.9985053031872434, "300–1000 Hz_40ms_modulation_mae_db": 1.196141687382559, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7954396691805854, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.06220107831945549, "1000–3000 Hz_10ms_envelope_correlation": 0.9975832217265527, "1000–3000 Hz_10ms_modulation_mae_db": 0.6312916741784177, "1000–3000 Hz_40ms_log_rms_mae_db": 0.49576752691496506, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.035185190149318805, "1000–3000 Hz_40ms_envelope_correlation": 0.9992525979847424, "1000–3000 Hz_40ms_modulation_mae_db": 1.101346233150612, "3000–6000 Hz_10ms_log_rms_mae_db": 1.115005489307435, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.13966112951657117, "3000–6000 Hz_10ms_envelope_correlation": 0.9874545931715759, "3000–6000 Hz_10ms_modulation_mae_db": 0.6897489085770411, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7652846868854202, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0894688525242531, "3000–6000 Hz_40ms_envelope_correlation": 0.9946979872791091, "3000–6000 Hz_40ms_modulation_mae_db": 0.4564622599164669, "mr_stft_db": 5.397882024585126, "band_mae_db": 1.0945818257427922, "rms_gain_error_db": -0.03391296496903806, "output_peak": 0.22605474662626543}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2656786139734466, "全帯域_10ms_rms_envelope_nrmse": 0.07422596784247297, "全帯域_10ms_envelope_correlation": 0.9954985677701392, "全帯域_10ms_modulation_mae_db": 0.06743252628580068, "全帯域_40ms_log_rms_mae_db": 0.6980033318902901, "全帯域_40ms_rms_envelope_nrmse": 0.05229140778914262, "全帯域_40ms_envelope_correlation": 0.9977801057986694, "全帯域_40ms_modulation_mae_db": 0.26287800003757195, "300–1000 Hz_10ms_log_rms_mae_db": 0.7815560233065169, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07035112593917164, "300–1000 Hz_10ms_envelope_correlation": 0.9961237266111632, "300–1000 Hz_10ms_modulation_mae_db": 0.5236337660356166, "300–1000 Hz_40ms_log_rms_mae_db": 0.5459287561154845, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03872131248604764, "300–1000 Hz_40ms_envelope_correlation": 0.9987973724759514, "300–1000 Hz_40ms_modulation_mae_db": 0.47785076081209477, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7902761190387042, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.0561720690871678, "1000–3000 Hz_10ms_envelope_correlation": 0.9980910424060794, "1000–3000 Hz_10ms_modulation_mae_db": 0.34386132325259716, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4923475679425008, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03369869519217913, "1000–3000 Hz_40ms_envelope_correlation": 0.9993773598268908, "1000–3000 Hz_40ms_modulation_mae_db": 0.6865145240812298, "3000–6000 Hz_10ms_log_rms_mae_db": 1.087756676545472, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12289080499184574, "3000–6000 Hz_10ms_envelope_correlation": 0.9908752307454071, "3000–6000 Hz_10ms_modulation_mae_db": 0.6585029869588975, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7257623589055424, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0753226068123338, "3000–6000 Hz_40ms_envelope_correlation": 0.9970680815035976, "3000–6000 Hz_40ms_modulation_mae_db": 0.33560398484632953, "mr_stft_db": 5.405067055448796, "band_mae_db": 1.2604680974902152, "rms_gain_error_db": -0.14681219301136372, "output_peak": 0.2387609470572053}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2156728826448557, "全帯域_10ms_rms_envelope_nrmse": 0.06556812378813309, "全帯域_10ms_envelope_correlation": 0.9964540627446977, "全帯域_10ms_modulation_mae_db": 0.5673923295974734, "全帯域_40ms_log_rms_mae_db": 0.6597721356111342, "全帯域_40ms_rms_envelope_nrmse": 0.03320144944588637, "全帯域_40ms_envelope_correlation": 0.9991542814224896, "全帯域_40ms_modulation_mae_db": 0.744917575496928, "300–1000 Hz_10ms_log_rms_mae_db": 0.8182501160236554, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06738259473991678, "300–1000 Hz_10ms_envelope_correlation": 0.9964000569898948, "300–1000 Hz_10ms_modulation_mae_db": 0.2204932880621693, "300–1000 Hz_40ms_log_rms_mae_db": 0.5388503277607327, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03691238994374578, "300–1000 Hz_40ms_envelope_correlation": 0.9988726819157783, "300–1000 Hz_40ms_modulation_mae_db": 0.7703913293630172, "1000–3000 Hz_10ms_log_rms_mae_db": 0.7758516440915992, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.05817679321061172, "1000–3000 Hz_10ms_envelope_correlation": 0.998083704222405, "1000–3000 Hz_10ms_modulation_mae_db": 0.5848164561904146, "1000–3000 Hz_40ms_log_rms_mae_db": 0.4887453946182904, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.03661588042240585, "1000–3000 Hz_40ms_envelope_correlation": 0.9993909949197495, "1000–3000 Hz_40ms_modulation_mae_db": 0.7141929748933152, "3000–6000 Hz_10ms_log_rms_mae_db": 1.109580243785995, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.12291248952163403, "3000–6000 Hz_10ms_envelope_correlation": 0.9910397181553691, "3000–6000 Hz_10ms_modulation_mae_db": 0.46152942622592846, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7594523014497677, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07277785378281751, "3000–6000 Hz_40ms_envelope_correlation": 0.9975332608256497, "3000–6000 Hz_40ms_modulation_mae_db": 0.7780755542600062, "mr_stft_db": 5.403647866419607, "band_mae_db": 1.3054892273066099, "rms_gain_error_db": -0.1100365521093635, "output_peak": 0.22605407237275424}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.547973902984727, "spectral_convergence": 0.1624484298206989, "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": 5.212916784115049, "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": 6.263820716588638e-06, "delta_db": 6.203966505982827, "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": 0.00020707489446818595, "delta_db": 0.06590626363750399, "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": 1.1964817179188718e-05, "delta_db": -0.23908083894245374, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.274471551779886e-06, "output_power": 2.2806206180268042e-06, "delta_db": 0.011725370475560798, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.000949404181786, "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": 0.21619555418188252, "reference_rms_dbfs": -28.300793168112545, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.410515843269717}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 130065, "output_samples": 130065, "intelligibility": {"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"}}, "level": {"reference": {"rms": 0.038455666393735516, "rms_dbfs": -28.300793168112545, "peak": 0.220855712890625, "peak_dbfs": -13.117827246673288, "crest_factor_db": 15.182965921439258, "mean": 1.9380709284780687e-07, "zero_energy": false}, "output": {"rms": 0.038000787115913745, "rms_dbfs": -28.40414815368609, "peak": 0.21619555418188252, "peak_dbfs": -13.303064821357049, "crest_factor_db": 15.101083332329042, "mean": -1.271548445930281e-05, "zero_energy": false}, "rms_difference_db": -0.10335498557354583}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 541, "uncovered_tail_samples": 225, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.6147675896839552e-06, "threshold_dbfs": -57.918899759837146, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 245, "quiet_samples": 58800, "reference_mean_power": 9.664815856891424e-08, "output_mean_power": 2.318009161453205e-07, "output_rms_dbfs": -66.34884851909649, "output_zero_energy": false, "output_peak": 0.01503751128486857, "output_energy_fraction": 7.25682824429711e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 534, "reference_estimated_voiced_frames": 280, "output_estimated_voiced_frames": 251, "both_estimated_voiced_frames": 250, "reference_voiced_output_unvoiced_frames": 30, "reference_unvoiced_output_voiced_frames": 1, "paired_voiced_fraction": 0.8928571428571429, "absolute_difference_cents_median": 1.365981015060751, "absolute_difference_cents_p95": 12.898048395786589, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 225, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.274883390161223, "rms_envelope_nrmse": 0.05300869794327403, "envelope_correlation": 0.9977129803276675, "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": 0.00028386320893672125, "reference_active": true, "delta_db": -0.1259085433522019}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.043814645706353e-05, "output_power": 3.0021597235435395e-05, "reference_active": true, "delta_db": -0.05984408130804213}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.705913608511969e-06, "output_power": 5.0920484480601666e-06, "reference_active": true, "delta_db": -0.49432664775178886}], "active_band_count": 3, "active_band_mae_db": 0.22669309080401093}}, {"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": 0.7023181666967468, "rms_envelope_nrmse": 0.028396435193587612, "envelope_correlation": 0.9994020226936223, "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": 0.00025283050831234887, "reference_active": true, "delta_db": -0.11278039847271054}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3907004138768798e-05, "output_power": 1.3500096171287264e-05, "reference_active": true, "delta_db": -0.12896721590005936}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.4011744172060643e-07, "output_power": 3.320737979236015e-07, "reference_active": true, "delta_db": -1.2233397064807494}], "active_band_count": 3, "active_band_mae_db": 0.4883624402845064}}]}, {"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": 8.480086855572361e-05, "log_rms_mae_db": 0.7627626877913188, "rms_envelope_nrmse": 0.07143809238849673, "envelope_correlation": 0.9960090240838532, "rms_gain_error_db": -0.07531659055902608, "reference_mean_power": 0.0005471873658289664, "output_mean_power": 0.0005377796971299058}, "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": 0.00011550738621428663, "output_power": 0.00011135645973591086, "reference_active": true, "delta_db": -0.1589434111233174}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3854221447460656e-05, "output_power": 1.182972665034668e-05, "reference_active": true, "delta_db": -0.6860741567356774}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9357817767829538e-06, "output_power": 1.8100579136804416e-06, "reference_active": true, "delta_db": -0.2916392659157425}], "active_band_count": 3, "active_band_mae_db": 0.37888561125824577}}, {"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": 7.444752199710231e-05, "log_rms_mae_db": 0.5374293616790191, "rms_envelope_nrmse": 0.04199188707797649, "envelope_correlation": 0.9986240656182779, "rms_gain_error_db": -0.07531668236256972, "reference_mean_power": 0.000550238587629155, "output_mean_power": 0.0005407784485320855}, "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": 9.910211940271507e-05, "output_power": 9.58706692698999e-05, "reference_active": true, "delta_db": -0.14397183250412388}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.2312084488175375e-06, "output_power": 5.387848599397774e-06, "reference_active": true, "delta_db": -0.631568963046185}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.5189682275535194e-07, "output_power": 1.570791230976454e-07, "reference_active": true, "delta_db": -2.051042215219639}], "active_band_count": 3, "active_band_mae_db": 0.942194336923316}}]}, {"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": 0.8019837953155563, "rms_envelope_nrmse": 0.05924398720634125, "envelope_correlation": 0.9978488286082511, "rms_gain_error_db": -0.11619595643298909, "reference_mean_power": 0.0003517587960046477, "output_mean_power": 0.0003424722369363099}, "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": 3.408664178054299e-05, "output_power": 3.209046211803511e-05, "reference_active": true, "delta_db": -0.26208245410140174}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.90892498484566e-06, "output_power": 7.685636039781082e-06, "reference_active": true, "delta_db": -0.6414548788456076}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.006695723935486e-07, "output_power": 4.6709074458589717e-07, "reference_active": true, "delta_db": -1.0923437100156137}], "active_band_count": 3, "active_band_mae_db": 0.665293680987541}}, {"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": 0.5234844173311514, "rms_envelope_nrmse": 0.03312000903594599, "envelope_correlation": 0.9993872579002268, "rms_gain_error_db": -0.11619597212323277, "reference_mean_power": 0.0003537202709185465, "output_mean_power": 0.00034438192696093325}, "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": 2.8653104646306335e-05, "reference_active": true, "delta_db": -0.25543208058214645}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.277692934034563e-06, "output_power": 3.6468715152653605e-06, "reference_active": true, "delta_db": -0.6928914362016342}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.6389202390485585e-08, "output_power": 4.704127153870032e-08, "reference_active": true, "delta_db": -0.7871689932986901}], "active_band_count": 3, "active_band_mae_db": 0.5784975033608236}}]}, {"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": 1.1079161343381583, "rms_envelope_nrmse": 0.12871521232890742, "envelope_correlation": 0.9893595608915978, "rms_gain_error_db": -0.15356994191196688, "reference_mean_power": 4.415064676151012e-05, "output_mean_power": 4.261672535669988e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 2.2237128168975065e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.193805277966024e-06, "output_power": 8.35758911834917e-06, "reference_active": true, "delta_db": -0.4141428504215164}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0890347422283219e-06, "output_power": 1.0777195553638828e-06, "reference_active": true, "delta_db": -0.04535971516895253}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8576888047519527e-07, "output_power": 2.3645742154778722e-07, "reference_active": true, "delta_db": 1.047799856501988}], "active_band_count": 3, "active_band_mae_db": 0.5024341406974856}}, {"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": 0.7679531589521342, "rms_envelope_nrmse": 0.061093259242149416, "envelope_correlation": 0.9976782961895735, "rms_gain_error_db": -0.15356995601580195, "reference_mean_power": 4.439683700027619e-05, "output_mean_power": 4.285436209400952e-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": 8.24746849682131e-06, "output_power": 7.556237356226658e-06, "reference_active": true, "delta_db": -0.3801507382387678}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.957219370502519e-07, "output_power": 4.4011575527376974e-07, "reference_active": true, "delta_db": -0.5167122232299828}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6536836687109697e-08, "output_power": 1.354402260744963e-08, "reference_active": true, "delta_db": -0.8670476743990219}], "active_band_count": 3, "active_band_mae_db": 0.5879702119559241}}]}], "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"]}}, "output_samples": 130065, "representation_scalars": 1221138, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9976836682432104, "standard_deviation": 0.00030519725030692384, "minimum": 0.9973122514868753, "maximum": 0.9980910424060794, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.7928047127838325, "standard_deviation": 0.012804139299864402, "minimum": 0.7718310826830741, "maximum": 0.8073615160740532, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5773875781620728, "standard_deviation": 0.13272103923122683, "minimum": 0.34386132325259716, "maximum": 0.7288760236889725, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.061781793602765325, "standard_deviation": 0.0036638614177651224, "minimum": 0.0561720690871678, "maximum": 0.06596958756731802, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9992756270542067, "standard_deviation": 0.00010004548422669198, "minimum": 0.9991164612063762, "maximum": 0.9993909949197495, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.49588779968351493, "standard_deviation": 0.013145815029487584, "minimum": 0.4793152385189854, "maximum": 0.5234844173311514, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.7361040303977879, "standard_deviation": 0.17259409407680135, "minimum": 0.5269520498861681, "maximum": 1.101346233150612, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03640465846337923, "standard_deviation": 0.0022419694510166666, "minimum": 0.03312000903594599, "maximum": 0.03909571662708278, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9900380750013098, "standard_deviation": 0.0015618449482501426, "minimum": 0.9874545931715759, "maximum": 0.9917711778091313, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.113185913393706, "standard_deviation": 0.018967609626457393, "minimum": 1.087756676545472, "maximum": 1.1535612507017499, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.7376567677367046, "standard_deviation": 0.34899871440749697, "minimum": 0.3662767843334847, "maximum": 1.4652544616121783, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1273342452952375, "standard_deviation": 0.009343332835812838, "minimum": 0.11447606513567822, "maximum": 0.13966112951657117, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9969940784361544, "standard_deviation": 0.001157818664346963, "minimum": 0.9946979872791091, "maximum": 0.9981092254516334, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7660166489568057, "standard_deviation": 0.02086723991654309, "minimum": 0.7257623589055424, "maximum": 0.7944964691474591, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6862535992673039, "standard_deviation": 0.32975078057469487, "minimum": 0.33560398484632953, "maximum": 1.361508342800695, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07366090886393607, "standard_deviation": 0.014973960187352295, "minimum": 0.05923498176409333, "maximum": 0.10174725728575029, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9957612888225214, "standard_deviation": 0.0005515177997699442, "minimum": 0.9948494041467084, "maximum": 0.9964000569898948, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 0.7949322899078912, "standard_deviation": 0.03509363072872372, "minimum": 0.7537767817382467, "maximum": 0.8653320919825919, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.45861790793030077, "standard_deviation": 0.17103236579453784, "minimum": 0.2204932880621693, "maximum": 0.709692413532469, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07329082390901669, "standard_deviation": 0.004700322494402495, "minimum": 0.06738259473991678, "maximum": 0.08061206579381651, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9985614411748296, "standard_deviation": 0.0002542321927365165, "minimum": 0.9980415738828234, "maximum": 0.9988726819157783, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.548964953988895, "standard_deviation": 0.04243761912164187, "minimum": 0.4964233045031956, "maximum": 0.6452887012071566, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8263140943899676, "standard_deviation": 0.2379310000704219, "minimum": 0.47785076081209477, "maximum": 1.196141687382559, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04199162482551429, "standard_deviation": 0.0035438068157039857, "minimum": 0.03691238994374578, "maximum": 0.048742368125265, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 1.2004693028110491, "standard_deviation": 0.101007328532499, "minimum": 1.000949404181786, "maximum": 1.3054892273066099, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.403081271349929, "standard_deviation": 0.003964519870939468, "minimum": 5.397882024585126, "maximum": 5.410515843269717, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.22330590018886842, "standard_deviation": 0.00974942995087655, "minimum": 0.21098262277196497, "maximum": 0.2387609470572053, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.1022552472155911, "standard_deviation": 0.03164455070363277, "minimum": -0.14681219301136372, "maximum": -0.03391296496903806, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.996644689068847, "standard_deviation": 0.0007937798046259664, "minimum": 0.9954985677701392, "maximum": 0.9977129803276675, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.2404210393669266, "standard_deviation": 0.027821076445066432, "minimum": 1.207597105664091, "maximum": 1.274883390161223, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.39614486625277506, "standard_deviation": 0.20752902191820166, "minimum": 0.06743252628580068, "maximum": 0.6544525026957179, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.06337997341103345, "standard_deviation": 0.00751855157768843, "minimum": 0.05300869794327403, "maximum": 0.07422596784247297, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9989660582781061, "standard_deviation": 0.0005093008208097576, "minimum": 0.9977801057986694, "maximum": 0.9994020226936223, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.6942461973713823, "standard_deviation": 0.04291421987623279, "minimum": 0.6241758969186152, "maximum": 0.7519415650540441, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5617304014086753, "standard_deviation": 0.2394571947528393, "minimum": 0.15712505151200123, "maximum": 0.7954699991450389, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03533254615376247, "standard_deviation": 0.007607624157312389, "minimum": 0.028396435193587612, "maximum": 0.05229140778914262, "valid_count": 8, "planned_count": 8}}, "seconds": 6.783245578000788, "rtf_including_measurement": 1.2516656584939754}, {"case": "jvs_jvs082_falset10_BASIC5000_1728", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "falsetto", "speaker": "jvs_jvs082", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.149235725402832, "predicted_mos": 2.149235725402832, "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": "059de3c044860ccda01a6ef818fae6c42871abf9358b380087bd4157336a1756", "internal_samples": 86710, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.350645942002302}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 2.464699119688431, "全帯域_10ms_rms_envelope_nrmse": 0.23993315031950266, "全帯域_10ms_envelope_correlation": 0.9918319368912478, "全帯域_10ms_modulation_mae_db": 1.428083025027884, "全帯域_40ms_log_rms_mae_db": 2.528460357980337, "全帯域_40ms_rms_envelope_nrmse": 0.23301146552479468, "全帯域_40ms_envelope_correlation": 0.9938287716253291, "全帯域_40ms_modulation_mae_db": 1.2895746784424815, "300–1000 Hz_10ms_log_rms_mae_db": 1.2301498026168007, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.23753621744616005, "300–1000 Hz_10ms_envelope_correlation": 0.9883805004213922, "300–1000 Hz_10ms_modulation_mae_db": 1.6853303122036232, "300–1000 Hz_40ms_log_rms_mae_db": 1.2125857023847852, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.23059248485839223, "300–1000 Hz_40ms_envelope_correlation": 0.9900700952001241, "300–1000 Hz_40ms_modulation_mae_db": 1.4714087599737284, "1000–3000 Hz_10ms_log_rms_mae_db": 0.9704927431217494, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.22120643393910483, "1000–3000 Hz_10ms_envelope_correlation": 0.994665140679267, "1000–3000 Hz_10ms_modulation_mae_db": 1.661059140368063, "1000–3000 Hz_40ms_log_rms_mae_db": 0.883382691369791, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.21166145577671633, "1000–3000 Hz_40ms_envelope_correlation": 0.9967570756227544, "1000–3000 Hz_40ms_modulation_mae_db": 1.607794945651741, "3000–6000 Hz_10ms_log_rms_mae_db": 1.0376107441616191, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.21661999701562046, "3000–6000 Hz_10ms_envelope_correlation": 0.9927741800873574, "3000–6000 Hz_10ms_modulation_mae_db": 0.9633647315164883, "3000–6000 Hz_40ms_log_rms_mae_db": 0.898751611327274, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.2038991055810547, "3000–6000 Hz_40ms_envelope_correlation": 0.9955411912081717, "3000–6000 Hz_40ms_modulation_mae_db": 0.9573226723677563, "mr_stft_db": 5.291917517580227, "band_mae_db": 1.6667669961907918, "rms_gain_error_db": 1.6815006683325895, "output_peak": 0.30236255732116113}}], "planned_noise_seeds": [0], "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": 5.521868933570904, "spectral_convergence": 0.332242062342157, "spectral_convergence_status": "ok", "amplitude_floor": 8.628776010687778e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.277923768677469, "spectral_convergence": 0.27316507469098955, "spectral_convergence_status": "ok", "amplitude_floor": 8.696913128358987e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.0759598504923105, "spectral_convergence": 0.2968396132096722, "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": 3.708830780582278e-06, "delta_db": 3.927943503953318, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008569985031977355, "output_power": 0.0013192047864080542, "delta_db": 1.8733215496836644, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0002039561579698118, "output_power": 0.00025702028294619024, "delta_db": 1.0043057501745063, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00031755380447674584, "output_power": 0.00045672073433874067, "delta_db": 1.5783340807657096, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 8.391217397004902e-05, "output_power": 0.00012168915024167932, "delta_db": 1.614268856244999, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2641952404694477e-05, "output_power": 1.7276454281434327e-05, "delta_db": 1.3564046429270693, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.274471551779886e-06, "output_power": 2.444328481155937e-06, "delta_db": 0.31279058958627565, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.6667669961907918, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 1.6815006683325895, "pitch": null, "output_rms_dbfs": -26.619292499779952, "output_peak": 0.30236255732116113, "reference_rms_dbfs": -28.300793168112545, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.291917517580227}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 130065, "output_samples": 130065, "intelligibility": {"estoi": {"value": 0.9246467872300507, "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"}}, "level": {"reference": {"rms": 0.038455666393735516, "rms_dbfs": -28.300793168112545, "peak": 0.220855712890625, "peak_dbfs": -13.117827246673288, "crest_factor_db": 15.182965921439258, "mean": 1.9380709284780687e-07, "zero_energy": false}, "output": {"rms": 0.04666973931229782, "rms_dbfs": -26.619292499779952, "peak": 0.30236255732116113, "peak_dbfs": -10.389439802808491, "crest_factor_db": 16.229852696971466, "mean": 4.7653337625400396e-09, "zero_energy": false}, "rms_difference_db": 1.6815006683325926}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 541, "uncovered_tail_samples": 225, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.6147675896839552e-06, "threshold_dbfs": -57.918899759837146, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 245, "quiet_samples": 58800, "reference_mean_power": 9.664815856891424e-08, "output_mean_power": 1.707112394113124e-07, "output_rms_dbfs": -67.67737884546527, "output_zero_energy": false, "output_peak": 0.008841599692611534, "output_energy_fraction": 3.543302627110121e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 534, "reference_estimated_voiced_frames": 280, "output_estimated_voiced_frames": 286, "both_estimated_voiced_frames": 274, "reference_voiced_output_unvoiced_frames": 6, "reference_unvoiced_output_voiced_frames": 12, "paired_voiced_fraction": 0.9785714285714285, "absolute_difference_cents_median": 3.541562127425083, "absolute_difference_cents_p95": 19.907279412247153, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 225, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 2.464699119688431, "rms_envelope_nrmse": 0.23993315031950266, "envelope_correlation": 0.9918319368912478, "rms_gain_error_db": 1.681500786438241, "reference_mean_power": 0.0014814008893508253, "output_mean_power": 0.0021818388957997857}, "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": 0.00044359140157497034, "reference_active": true, "delta_db": 1.8128315705709674}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.043814645706353e-05, "output_power": 4.623103975750282e-05, "reference_active": true, "delta_db": 1.8151545866209382}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.705913608511969e-06, "output_power": 6.6366892578311644e-06, "reference_active": true, "delta_db": 0.656262917891747}], "active_band_count": 3, "active_band_mae_db": 1.428083025027884}}, {"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": 2.528460357980337, "rms_envelope_nrmse": 0.23301146552479468, "envelope_correlation": 0.9938287716253291, "rms_gain_error_db": 1.681501311322949, "reference_mean_power": 0.001489661173505724, "output_mean_power": 0.002194005084038}, "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": 0.00039822705310804977, "reference_active": true, "delta_db": 1.8602324234700842}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3907004138768798e-05, "output_power": 2.125492996890542e-05, "reference_active": true, "delta_db": 1.84226094484249}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.4011744172060643e-07, "output_power": 4.235898188899159e-07, "reference_active": true, "delta_db": -0.16623066701487005}], "active_band_count": 3, "active_band_mae_db": 1.2895746784424815}}]}, {"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": 8.480086855572361e-05, "log_rms_mae_db": 1.2301498026168007, "rms_envelope_nrmse": 0.23753621744616005, "envelope_correlation": 0.9883805004213922, "rms_gain_error_db": 1.556981188836556, "reference_mean_power": 0.0005471873658289664, "output_mean_power": 0.0007831305752255878}, "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": 0.00011550738621428663, "output_power": 0.00017934338881473144, "reference_active": true, "delta_db": 1.9107561535668016}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3854221447460656e-05, "output_power": 2.1522743405676903e-05, "reference_active": true, "delta_db": 1.9131550288530046}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9357817767829538e-06, "output_power": 2.5707768035714536e-06, "reference_active": true, "delta_db": 1.232079754191063}], "active_band_count": 3, "active_band_mae_db": 1.6853303122036232}}, {"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": 7.444752199710231e-05, "log_rms_mae_db": 1.2125857023847852, "rms_envelope_nrmse": 0.23059248485839223, "envelope_correlation": 0.9900700952001241, "rms_gain_error_db": 1.5569809281783504, "reference_mean_power": 0.000550238587629155, "output_mean_power": 0.0007874974143928182}, "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": 9.910211940271507e-05, "output_power": 0.0001563573077089509, "reference_active": true, "delta_db": 1.9803524135117592}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.2312084488175375e-06, "output_power": 9.696743718020614e-06, "reference_active": true, "delta_db": 1.9205363780480424}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.5189682275535194e-07, "output_power": 2.8350220332234296e-07, "reference_active": true, "delta_db": 0.513337488361383}], "active_band_count": 3, "active_band_mae_db": 1.4714087599737284}}]}, {"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": 0.9704927431217494, "rms_envelope_nrmse": 0.22120643393910483, "envelope_correlation": 0.994665140679267, "rms_gain_error_db": 1.5613604552006426, "reference_mean_power": 0.0003517587960046477, "output_mean_power": 0.000503942529593447}, "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": 3.408664178054299e-05, "output_power": 4.7441518098985225e-05, "reference_active": true, "delta_db": 1.4357436113170243}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.90892498484566e-06, "output_power": 1.3603669576985342e-05, "reference_active": true, "delta_db": 1.838307726055015}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.006695723935486e-07, "output_power": 8.903243292550326e-07, "reference_active": true, "delta_db": 1.70912608373215}], "active_band_count": 3, "active_band_mae_db": 1.661059140368063}}, {"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": 0.883382691369791, "rms_envelope_nrmse": 0.21166145577671633, "envelope_correlation": 0.9967570756227544, "rms_gain_error_db": 1.5613604835749781, "reference_mean_power": 0.0003537202709185465, "output_mean_power": 0.0005067526136785827}, "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": 4.255623312104107e-05, "reference_active": true, "delta_db": 1.4624828530194287}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.277692934034563e-06, "output_power": 6.539117801872503e-06, "reference_active": true, "delta_db": 1.8430955486638465}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.6389202390485585e-08, "output_power": 7.997911518380177e-08, "reference_active": true, "delta_db": 1.5178064352719478}], "active_band_count": 3, "active_band_mae_db": 1.607794945651741}}]}, {"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": 1.0376107441616191, "rms_envelope_nrmse": 0.21661999701562046, "envelope_correlation": 0.9927741800873574, "rms_gain_error_db": 1.4572457522236792, "reference_mean_power": 4.415064676151012e-05, "output_mean_power": 6.175350967391141e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 2.2237128168975065e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.193805277966024e-06, "output_power": 1.2039127221866882e-05, "reference_active": true, "delta_db": 1.1709970254157558}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0890347422283219e-06, "output_power": 1.5314779850469175e-06, "reference_active": true, "delta_db": 1.480690234401456}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8576888047519527e-07, "output_power": 1.7584590954172854e-07, "reference_active": true, "delta_db": -0.238406934732253}], "active_band_count": 3, "active_band_mae_db": 0.9633647315164883}}, {"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": 0.898751611327274, "rms_envelope_nrmse": 0.2038991055810547, "envelope_correlation": 0.9955411912081717, "rms_gain_error_db": 1.4572458960020793, "reference_mean_power": 4.439683700027619e-05, "output_mean_power": 6.209785801696852e-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": 8.24746849682131e-06, "output_power": 1.0749579537632063e-05, "reference_active": true, "delta_db": 1.150708121266907}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.957219370502519e-07, "output_power": 7.297043672083793e-07, "reference_active": true, "delta_db": 1.6790880742199623}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6536836687109697e-08, "output_power": 1.6377034175004117e-08, "reference_active": true, "delta_db": -0.04217182161639953}], "active_band_count": 3, "active_band_mae_db": 0.9573226723677563}}]}], "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"]}}, "output_samples": 130065, "representation_scalars": 1114352, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.994665140679267, "standard_deviation": null, "minimum": 0.994665140679267, "maximum": 0.994665140679267, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 0.9704927431217494, "standard_deviation": null, "minimum": 0.9704927431217494, "maximum": 0.9704927431217494, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 1.661059140368063, "standard_deviation": null, "minimum": 1.661059140368063, "maximum": 1.661059140368063, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.22120643393910483, "standard_deviation": null, "minimum": 0.22120643393910483, "maximum": 0.22120643393910483, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9967570756227544, "standard_deviation": null, "minimum": 0.9967570756227544, "maximum": 0.9967570756227544, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.883382691369791, "standard_deviation": null, "minimum": 0.883382691369791, "maximum": 0.883382691369791, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.607794945651741, "standard_deviation": null, "minimum": 1.607794945651741, "maximum": 1.607794945651741, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.21166145577671633, "standard_deviation": null, "minimum": 0.21166145577671633, "maximum": 0.21166145577671633, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9927741800873574, "standard_deviation": null, "minimum": 0.9927741800873574, "maximum": 0.9927741800873574, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.0376107441616191, "standard_deviation": null, "minimum": 1.0376107441616191, "maximum": 1.0376107441616191, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.9633647315164883, "standard_deviation": null, "minimum": 0.9633647315164883, "maximum": 0.9633647315164883, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.21661999701562046, "standard_deviation": null, "minimum": 0.21661999701562046, "maximum": 0.21661999701562046, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9955411912081717, "standard_deviation": null, "minimum": 0.9955411912081717, "maximum": 0.9955411912081717, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.898751611327274, "standard_deviation": null, "minimum": 0.898751611327274, "maximum": 0.898751611327274, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.9573226723677563, "standard_deviation": null, "minimum": 0.9573226723677563, "maximum": 0.9573226723677563, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.2038991055810547, "standard_deviation": null, "minimum": 0.2038991055810547, "maximum": 0.2038991055810547, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9883805004213922, "standard_deviation": null, "minimum": 0.9883805004213922, "maximum": 0.9883805004213922, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.2301498026168007, "standard_deviation": null, "minimum": 1.2301498026168007, "maximum": 1.2301498026168007, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 1.6853303122036232, "standard_deviation": null, "minimum": 1.6853303122036232, "maximum": 1.6853303122036232, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.23753621744616005, "standard_deviation": null, "minimum": 0.23753621744616005, "maximum": 0.23753621744616005, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9900700952001241, "standard_deviation": null, "minimum": 0.9900700952001241, "maximum": 0.9900700952001241, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.2125857023847852, "standard_deviation": null, "minimum": 1.2125857023847852, "maximum": 1.2125857023847852, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.4714087599737284, "standard_deviation": null, "minimum": 1.4714087599737284, "maximum": 1.4714087599737284, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.23059248485839223, "standard_deviation": null, "minimum": 0.23059248485839223, "maximum": 0.23059248485839223, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 1.6667669961907918, "standard_deviation": null, "minimum": 1.6667669961907918, "maximum": 1.6667669961907918, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 5.291917517580227, "standard_deviation": null, "minimum": 5.291917517580227, "maximum": 5.291917517580227, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.30236255732116113, "standard_deviation": null, "minimum": 0.30236255732116113, "maximum": 0.30236255732116113, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 1.6815006683325895, "standard_deviation": null, "minimum": 1.6815006683325895, "maximum": 1.6815006683325895, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9918319368912478, "standard_deviation": null, "minimum": 0.9918319368912478, "maximum": 0.9918319368912478, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 2.464699119688431, "standard_deviation": null, "minimum": 2.464699119688431, "maximum": 2.464699119688431, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 1.428083025027884, "standard_deviation": null, "minimum": 1.428083025027884, "maximum": 1.428083025027884, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.23993315031950266, "standard_deviation": null, "minimum": 0.23993315031950266, "maximum": 0.23993315031950266, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9938287716253291, "standard_deviation": null, "minimum": 0.9938287716253291, "maximum": 0.9938287716253291, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 2.528460357980337, "standard_deviation": null, "minimum": 2.528460357980337, "maximum": 2.528460357980337, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 1.2895746784424815, "standard_deviation": null, "minimum": 1.2895746784424815, "maximum": 1.2895746784424815, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.23301146552479468, "standard_deviation": null, "minimum": 0.23301146552479468, "maximum": 0.23301146552479468, "valid_count": 1, "planned_count": 1}}, "seconds": 2.4294783690056647, "rtf_including_measurement": 0.4482949360407178}, {"case": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "normal", "speaker": "jvs_jvs082", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.2728936672210693, "predicted_mos": 2.2728936672210693, "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": "84b8983400e47b814b59d674284d057f55d7d409cd1f8dd5fc4dea80104752c2", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.411594053002773}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1469914583030258, "全帯域_10ms_rms_envelope_nrmse": 0.03862946665133215, "全帯域_10ms_envelope_correlation": 0.9985545552489183, "全帯域_10ms_modulation_mae_db": 0.2230930907922444, "全帯域_40ms_log_rms_mae_db": 0.605907368393408, "全帯域_40ms_rms_envelope_nrmse": 0.021821835759189206, "全帯域_40ms_envelope_correlation": 0.9995762865803942, "全帯域_40ms_modulation_mae_db": 0.37589775876689524, "300–1000 Hz_10ms_log_rms_mae_db": 1.532619527052877, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06643564868739796, "300–1000 Hz_10ms_envelope_correlation": 0.9960768688539159, "300–1000 Hz_10ms_modulation_mae_db": 0.24743196773538775, "300–1000 Hz_40ms_log_rms_mae_db": 1.2124518262109683, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037878840964841745, "300–1000 Hz_40ms_envelope_correlation": 0.9987062070767231, "300–1000 Hz_40ms_modulation_mae_db": 0.8108027766425896, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2957278537090104, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10981423499355186, "1000–3000 Hz_10ms_envelope_correlation": 0.9919414440141195, "1000–3000 Hz_10ms_modulation_mae_db": 1.2079167869159964, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9276445181358552, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06792900064273373, "1000–3000 Hz_40ms_envelope_correlation": 0.9974810297373207, "1000–3000 Hz_40ms_modulation_mae_db": 1.092041564186314, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5837337959204623, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14819833912935176, "3000–6000 Hz_10ms_envelope_correlation": 0.9844480809588482, "3000–6000 Hz_10ms_modulation_mae_db": 0.4874974681355404, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9819639915126831, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08943403236892981, "3000–6000 Hz_40ms_envelope_correlation": 0.9954933147546137, "3000–6000 Hz_40ms_modulation_mae_db": 0.8439033068967131, "mr_stft_db": 5.481281434104429, "band_mae_db": 0.18104729378922205, "rms_gain_error_db": -0.07861024680452176, "output_peak": 0.1590551267669874}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1351652586098404, "全帯域_10ms_rms_envelope_nrmse": 0.04184493265304771, "全帯域_10ms_envelope_correlation": 0.9983153153958718, "全帯域_10ms_modulation_mae_db": 0.5004652133401261, "全帯域_40ms_log_rms_mae_db": 0.5955138974325047, "全帯域_40ms_rms_envelope_nrmse": 0.024454317282172164, "全帯域_40ms_envelope_correlation": 0.9994803545538046, "全帯域_40ms_modulation_mae_db": 0.5721286223983336, "300–1000 Hz_10ms_log_rms_mae_db": 1.497321925005351, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06158097696253506, "300–1000 Hz_10ms_envelope_correlation": 0.996642247525945, "300–1000 Hz_10ms_modulation_mae_db": 0.8353691935566623, "300–1000 Hz_40ms_log_rms_mae_db": 1.1384850920440472, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03562978331925064, "300–1000 Hz_40ms_envelope_correlation": 0.9988516491864957, "300–1000 Hz_40ms_modulation_mae_db": 1.2582629545531763, "1000–3000 Hz_10ms_log_rms_mae_db": 1.340073197661549, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.14190830567114376, "1000–3000 Hz_10ms_envelope_correlation": 0.9864241640063509, "1000–3000 Hz_10ms_modulation_mae_db": 1.1487874227837298, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9118119578501573, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08622346390176172, "1000–3000 Hz_40ms_envelope_correlation": 0.9960176837263809, "1000–3000 Hz_40ms_modulation_mae_db": 0.8592293858858384, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5987282432230951, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1658216704595979, "3000–6000 Hz_10ms_envelope_correlation": 0.9792316054015036, "3000–6000 Hz_10ms_modulation_mae_db": 0.4762956730916164, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9996997018801448, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08910877643320868, "3000–6000 Hz_40ms_envelope_correlation": 0.9944761353653534, "3000–6000 Hz_40ms_modulation_mae_db": 0.2242201845820014, "mr_stft_db": 5.473542400639121, "band_mae_db": 0.17748950065977337, "rms_gain_error_db": -0.0983805764922213, "output_peak": 0.15022058427439094}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1741762142938672, "全帯域_10ms_rms_envelope_nrmse": 0.04139521451176931, "全帯域_10ms_envelope_correlation": 0.998319167981312, "全帯域_10ms_modulation_mae_db": 0.6960115281606978, "全帯域_40ms_log_rms_mae_db": 0.5705611365655492, "全帯域_40ms_rms_envelope_nrmse": 0.021127049232363453, "全帯域_40ms_envelope_correlation": 0.9995926087498538, "全帯域_40ms_modulation_mae_db": 0.8589045165635785, "300–1000 Hz_10ms_log_rms_mae_db": 1.440142457108297, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06066761907209514, "300–1000 Hz_10ms_envelope_correlation": 0.996782266755747, "300–1000 Hz_10ms_modulation_mae_db": 0.8379720215559293, "300–1000 Hz_40ms_log_rms_mae_db": 1.0675804384649685, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037445134618007164, "300–1000 Hz_40ms_envelope_correlation": 0.9987595162967908, "300–1000 Hz_40ms_modulation_mae_db": 1.0490439171980264, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3480650660856113, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1287513749956826, "1000–3000 Hz_10ms_envelope_correlation": 0.9888379094695214, "1000–3000 Hz_10ms_modulation_mae_db": 0.172583718706161, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9074259623522059, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08354664341788892, "1000–3000 Hz_40ms_envelope_correlation": 0.9959489415657538, "1000–3000 Hz_40ms_modulation_mae_db": 0.40199106009708824, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6041376158964757, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15565101762019667, "3000–6000 Hz_10ms_envelope_correlation": 0.9825143229890061, "3000–6000 Hz_10ms_modulation_mae_db": 0.36217977958615427, "3000–6000 Hz_40ms_log_rms_mae_db": 1.052010657695939, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10328299782008407, "3000–6000 Hz_40ms_envelope_correlation": 0.9930620109371986, "3000–6000 Hz_40ms_modulation_mae_db": 0.3929765271410453, "mr_stft_db": 5.488296786238737, "band_mae_db": 0.2161063456399869, "rms_gain_error_db": -0.0733123587573219, "output_peak": 0.1605894099629893}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.176667050638142, "全帯域_10ms_rms_envelope_nrmse": 0.045731218777732605, "全帯域_10ms_envelope_correlation": 0.9978962619376438, "全帯域_10ms_modulation_mae_db": 0.2562575475070883, "全帯域_40ms_log_rms_mae_db": 0.6225423998253368, "全帯域_40ms_rms_envelope_nrmse": 0.02271136165070261, "全帯域_40ms_envelope_correlation": 0.999484993816256, "全帯域_40ms_modulation_mae_db": 0.28589897066666065, "300–1000 Hz_10ms_log_rms_mae_db": 1.4117892941950951, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0656287413945099, "300–1000 Hz_10ms_envelope_correlation": 0.996163229878024, "300–1000 Hz_10ms_modulation_mae_db": 0.27914004671310166, "300–1000 Hz_40ms_log_rms_mae_db": 1.073703377058788, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03641757412582954, "300–1000 Hz_40ms_envelope_correlation": 0.9988008686805793, "300–1000 Hz_40ms_modulation_mae_db": 0.4168854834981673, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2929834715419137, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12751999840003098, "1000–3000 Hz_10ms_envelope_correlation": 0.9886937352263294, "1000–3000 Hz_10ms_modulation_mae_db": 1.0368845179586754, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8796786171163216, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06869073732340686, "1000–3000 Hz_40ms_envelope_correlation": 0.9973065496783479, "1000–3000 Hz_40ms_modulation_mae_db": 0.8737088297487295, "3000–6000 Hz_10ms_log_rms_mae_db": 1.630357549492661, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17868401183864507, "3000–6000 Hz_10ms_envelope_correlation": 0.9773173789676458, "3000–6000 Hz_10ms_modulation_mae_db": 0.9488716069440266, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0479991545498784, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12426468334519011, "3000–6000 Hz_40ms_envelope_correlation": 0.9903418735299309, "3000–6000 Hz_40ms_modulation_mae_db": 1.0490861725819507, "mr_stft_db": 5.467512458014788, "band_mae_db": 0.24612539169724254, "rms_gain_error_db": -0.0590950155546906, "output_peak": 0.15245068339365156}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.2104327349712396, "全帯域_10ms_rms_envelope_nrmse": 0.04089381749837626, "全帯域_10ms_envelope_correlation": 0.9983373622492225, "全帯域_10ms_modulation_mae_db": 0.37150559775882214, "全帯域_40ms_log_rms_mae_db": 0.6343118908174666, "全帯域_40ms_rms_envelope_nrmse": 0.02161142222960086, "全帯域_40ms_envelope_correlation": 0.9995516616599731, "全帯域_40ms_modulation_mae_db": 0.5039025826902189, "300–1000 Hz_10ms_log_rms_mae_db": 1.4877424015411507, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0644551504441588, "300–1000 Hz_10ms_envelope_correlation": 0.9963297741473105, "300–1000 Hz_10ms_modulation_mae_db": 0.5833751290579956, "300–1000 Hz_40ms_log_rms_mae_db": 1.1204694284990193, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03715855193129593, "300–1000 Hz_40ms_envelope_correlation": 0.9987506033693152, "300–1000 Hz_40ms_modulation_mae_db": 0.862079454101568, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3254186507598484, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12712357769515154, "1000–3000 Hz_10ms_envelope_correlation": 0.9885304148611692, "1000–3000 Hz_10ms_modulation_mae_db": 0.47183509468049006, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9011933885513161, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07459882372818046, "1000–3000 Hz_40ms_envelope_correlation": 0.9963594827583782, "1000–3000 Hz_40ms_modulation_mae_db": 0.35904262489491484, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5977129151016782, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15836574347915477, "3000–6000 Hz_10ms_envelope_correlation": 0.9810211549911826, "3000–6000 Hz_10ms_modulation_mae_db": 0.5789705989017812, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9845069442933976, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08828364498339082, "3000–6000 Hz_40ms_envelope_correlation": 0.9943420919088062, "3000–6000 Hz_40ms_modulation_mae_db": 0.4021566591254282, "mr_stft_db": 5.46702505169493, "band_mae_db": 0.19437555132600548, "rms_gain_error_db": -0.06219100760763659, "output_peak": 0.15424691179089525}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1255693156646966, "全帯域_10ms_rms_envelope_nrmse": 0.04188159829567338, "全帯域_10ms_envelope_correlation": 0.9982533978522491, "全帯域_10ms_modulation_mae_db": 0.1720991884679635, "全帯域_40ms_log_rms_mae_db": 0.5678947544783085, "全帯域_40ms_rms_envelope_nrmse": 0.022790462564423197, "全帯域_40ms_envelope_correlation": 0.999501236004051, "全帯域_40ms_modulation_mae_db": 0.5529270490786004, "300–1000 Hz_10ms_log_rms_mae_db": 1.4681811484146816, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05898717182980252, "300–1000 Hz_10ms_envelope_correlation": 0.9968923738852731, "300–1000 Hz_10ms_modulation_mae_db": 0.3481707015057103, "300–1000 Hz_40ms_log_rms_mae_db": 1.1424815569207547, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03273896855710506, "300–1000 Hz_40ms_envelope_correlation": 0.9990042140733512, "300–1000 Hz_40ms_modulation_mae_db": 0.814486388443369, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3582522126317338, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13379690951420217, "1000–3000 Hz_10ms_envelope_correlation": 0.9870128418923603, "1000–3000 Hz_10ms_modulation_mae_db": 0.9907952271522719, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9333601958620846, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.069418711024127, "1000–3000 Hz_40ms_envelope_correlation": 0.9965845347086902, "1000–3000 Hz_40ms_modulation_mae_db": 0.6564567650686829, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6116718770964829, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16346476751327407, "3000–6000 Hz_10ms_envelope_correlation": 0.9811739656526184, "3000–6000 Hz_10ms_modulation_mae_db": 0.7941380085612533, "3000–6000 Hz_40ms_log_rms_mae_db": 1.036549168236163, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10021034552325513, "3000–6000 Hz_40ms_envelope_correlation": 0.9944541885446296, "3000–6000 Hz_40ms_modulation_mae_db": 0.4711004977341631, "mr_stft_db": 5.478034198297404, "band_mae_db": 0.16153321483522984, "rms_gain_error_db": -0.06769656794935132, "output_peak": 0.15607874699197244}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1428497950852585, "全帯域_10ms_rms_envelope_nrmse": 0.04378394910240106, "全帯域_10ms_envelope_correlation": 0.9981331493876335, "全帯域_10ms_modulation_mae_db": 0.3609572267506877, "全帯域_40ms_log_rms_mae_db": 0.5979076779295084, "全帯域_40ms_rms_envelope_nrmse": 0.02575561785807461, "全帯域_40ms_envelope_correlation": 0.99939034138242, "全帯域_40ms_modulation_mae_db": 0.4454560052965239, "300–1000 Hz_10ms_log_rms_mae_db": 1.4818392622718075, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.0707643673615312, "300–1000 Hz_10ms_envelope_correlation": 0.9955650505598597, "300–1000 Hz_10ms_modulation_mae_db": 0.49846672831690125, "300–1000 Hz_40ms_log_rms_mae_db": 1.09183802667731, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04407741841028764, "300–1000 Hz_40ms_envelope_correlation": 0.9982383799950497, "300–1000 Hz_40ms_modulation_mae_db": 0.9470782987581915, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3831897083244664, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1211666805986551, "1000–3000 Hz_10ms_envelope_correlation": 0.9898796127711574, "1000–3000 Hz_10ms_modulation_mae_db": 0.40992566139302583, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9657483817640163, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06965093348670262, "1000–3000 Hz_40ms_envelope_correlation": 0.997169932803584, "1000–3000 Hz_40ms_modulation_mae_db": 0.3659538988421058, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5992703760805136, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16878989081874926, "3000–6000 Hz_10ms_envelope_correlation": 0.9787473738721822, "3000–6000 Hz_10ms_modulation_mae_db": 0.5664812335668918, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0203119794053386, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10378885431059152, "3000–6000 Hz_40ms_envelope_correlation": 0.9924815132440473, "3000–6000 Hz_40ms_modulation_mae_db": 0.51931132892338, "mr_stft_db": 5.4814807311373075, "band_mae_db": 0.17964972816805774, "rms_gain_error_db": -0.0887421721466189, "output_peak": 0.15895313940899275}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1032563503360806, "全帯域_10ms_rms_envelope_nrmse": 0.04164135268374198, "全帯域_10ms_envelope_correlation": 0.9982698355880185, "全帯域_10ms_modulation_mae_db": 0.607988539971585, "全帯域_40ms_log_rms_mae_db": 0.5427290306418301, "全帯域_40ms_rms_envelope_nrmse": 0.021554527556737393, "全帯域_40ms_envelope_correlation": 0.9995497380467746, "全帯域_40ms_modulation_mae_db": 0.6379067499252433, "300–1000 Hz_10ms_log_rms_mae_db": 1.481857209188639, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06883093964082547, "300–1000 Hz_10ms_envelope_correlation": 0.9957990925272222, "300–1000 Hz_10ms_modulation_mae_db": 0.4975581082622667, "300–1000 Hz_40ms_log_rms_mae_db": 1.1312410458409563, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.040455975888397076, "300–1000 Hz_40ms_envelope_correlation": 0.9985173908395302, "300–1000 Hz_40ms_modulation_mae_db": 0.5409416132353784, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3166749492451744, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12015256450809994, "1000–3000 Hz_10ms_envelope_correlation": 0.9894905943073781, "1000–3000 Hz_10ms_modulation_mae_db": 0.2178096879836705, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9067266422989353, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07222450081220035, "1000–3000 Hz_40ms_envelope_correlation": 0.996043794581354, "1000–3000 Hz_40ms_modulation_mae_db": 0.3695911148457916, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6679919529997238, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15748528242502272, "3000–6000 Hz_10ms_envelope_correlation": 0.9817064942072615, "3000–6000 Hz_10ms_modulation_mae_db": 0.15109907868470043, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0700492361666591, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09507292663243216, "3000–6000 Hz_40ms_envelope_correlation": 0.9939977983252538, "3000–6000 Hz_40ms_modulation_mae_db": 0.38450972562222313, "mr_stft_db": 5.485340957510291, "band_mae_db": 0.1922302180358691, "rms_gain_error_db": -0.06293637488717155, "output_peak": 0.15890994614952553}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.559673940646955, "spectral_convergence": 0.12730646099196719, "spectral_convergence_status": "ok", "amplitude_floor": 5.237444731722431e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.490416524663498, "spectral_convergence": 0.13288923352538332, "spectral_convergence_status": "ok", "amplitude_floor": 5.437369948912744e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.393753837002833, "spectral_convergence": 0.13242715299410807, "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": 6.611225535505043e-05, "delta_db": 0.11870430863429379, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008444430165469724, "output_power": 0.0008257970914115565, "delta_db": -0.09696999591477107, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 6.039141474549642e-05, "output_power": 6.226913864188052e-05, "delta_db": 0.1329765461660726, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 3.556975687019485e-05, "output_power": 3.2555481037061274e-05, "delta_db": -0.38456779835516103, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.090392882810899e-05, "output_power": 1.0532139412239008e-05, "delta_db": -0.15066408959784333, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2355857763199668e-06, "output_power": 1.342698932196282e-06, "delta_db": 0.36105743342234664, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.0422411240430348e-06, "output_power": 1.0476284737496633e-06, "delta_db": 0.022390884434065998, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.18104729378922205, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.07861024680452176, "pitch": null, "output_rms_dbfs": -30.001492347752468, "output_peak": 0.1590551267669874, "reference_rms_dbfs": -29.922882100947945, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.481281434104429}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.9318590056398346, "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"}}, "level": {"reference": {"rms": 0.03190479033407081, "rms_dbfs": -29.922882100947945, "peak": 0.15533447265625, "peak_dbfs": -16.17464305245918, "crest_factor_db": 13.74823904848876, "mean": -8.231268988715278e-07, "zero_energy": false}, "output": {"rms": 0.031617343867942696, "rms_dbfs": -30.001492347752464, "peak": 0.1590551267669874, "peak_dbfs": -15.969046557447498, "crest_factor_db": 14.032445790304966, "mean": -1.4797322126990684e-05, "zero_energy": false}, "rms_difference_db": -0.07861024680451933}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 204, "quiet_samples": 48960, "reference_mean_power": 9.005820816930603e-08, "output_mean_power": 2.0108735149560957e-07, "output_rms_dbfs": -66.96615245904597, "output_zero_energy": false, "output_peak": 0.01204159818149046, "output_energy_fraction": 6.83931971360301e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 314, "output_estimated_voiced_frames": 297, "both_estimated_voiced_frames": 293, "reference_voiced_output_unvoiced_frames": 21, "reference_unvoiced_output_voiced_frames": 4, "paired_voiced_fraction": 0.9331210191082803, "absolute_difference_cents_median": 1.380076881044419, "absolute_difference_cents_p95": 14.681316177672677, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.1469914583030258, "rms_envelope_nrmse": 0.03862946665133215, "envelope_correlation": 0.9985545552489183, "rms_gain_error_db": -0.07781034684527752, "reference_mean_power": 0.0010176842474405314, "output_mean_power": 0.00099961328082998}, "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": 0.00012769490764673875, "reference_active": true, "delta_db": -0.18578460497482807}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5932863269435214e-05, "output_power": 1.6001339035049592e-05, "reference_active": true, "delta_db": 0.018624979228016345}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.591650627521311e-06, "output_power": 4.1255501139340085e-06, "reference_active": true, "delta_db": -0.46486968817388885}], "active_band_count": 3, "active_band_mae_db": 0.2230930907922444}}, {"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": 0.605907368393408, "rms_envelope_nrmse": 0.021821835759189206, "envelope_correlation": 0.9995762865803942, "rms_gain_error_db": -0.07684175937221337, "reference_mean_power": 0.0010161096570352637, "output_mean_power": 0.0009982892694905357}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.9042638692252314e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00011759425242544186, "output_power": 0.00011280917049972416, "reference_active": true, "delta_db": -0.18041689728394877}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 7.519272755909202e-06, "output_power": 7.923733091547662e-06, "reference_active": true, "delta_db": 0.2275399922622316}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.598733053895234e-07, "output_power": 3.0491303735698103e-07, "reference_active": true, "delta_db": -0.7197363867545055}], "active_band_count": 3, "active_band_mae_db": 0.37589775876689524}}]}, {"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": 4.667982083652564e-05, "log_rms_mae_db": 1.532619527052877, "rms_envelope_nrmse": 0.06643564868739796, "envelope_correlation": 0.9960768688539159, "rms_gain_error_db": -0.017027541392982973, "reference_mean_power": 0.0002794511004585033, "output_mean_power": 0.00027835759146636803}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.938593634377073e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.2950751511150254e-05, "output_power": 3.0886960145139104e-05, "reference_active": true, "delta_db": -0.2809015634077062}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.807348843301906e-06, "output_power": 3.5792747090377847e-06, "reference_active": true, "delta_db": -0.2682763856014341}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5906604704508287e-06, "output_power": 1.5214780564688918e-06, "reference_active": true, "delta_db": -0.1931179541970229}], "active_band_count": 3, "active_band_mae_db": 0.24743196773538775}}, {"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": 4.25438813129898e-05, "log_rms_mae_db": 1.2124518262109683, "rms_envelope_nrmse": 0.037878840964841745, "envelope_correlation": 0.9987062070767231, "rms_gain_error_db": -0.013793783844874773, "reference_mean_power": 0.0002774218749538236, "output_mean_power": 0.0002765421431338143}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 9.236914065861679e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.9257092980847747e-05, "output_power": 2.7153019828051194e-05, "reference_active": true, "delta_db": -0.3241303517179063}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8979287936807771e-06, "output_power": 1.9463146302293645e-06, "reference_active": true, "delta_db": 0.10933132624101367}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.435917808710527e-08, "output_power": 5.955105833519671e-08, "reference_active": true, "delta_db": -1.998946651968849}], "active_band_count": 3, "active_band_mae_db": 0.8108027766425896}}]}, {"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": 1.2957278537090104, "rms_envelope_nrmse": 0.10981423499355186, "envelope_correlation": 0.9919414440141195, "rms_gain_error_db": -0.3343944873774505, "reference_mean_power": 3.509769240032237e-05, "output_mean_power": 3.2496689043083396e-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": 9.271294612633019e-06, "reference_active": true, "delta_db": -0.417888102187906}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.594184871691995e-06, "output_power": 2.4369400251927887e-06, "reference_active": true, "delta_db": -0.27156081339124755}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.354712471534306e-07, "output_power": 1.7069671317907682e-07, "reference_active": true, "delta_db": -2.9343014451688356}], "active_band_count": 3, "active_band_mae_db": 1.2079167869159964}}, {"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": 0.9276445181358552, "rms_envelope_nrmse": 0.06792900064273373, "envelope_correlation": 0.9974810297373207, "rms_gain_error_db": -0.33740960237137624, "reference_mean_power": 3.5141167460930974e-05, "output_mean_power": 3.251436115008268e-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": 8.699169836872868e-06, "reference_active": true, "delta_db": -0.38207414407882473}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.126122979707458e-06, "output_power": 1.0720309965379126e-06, "reference_active": true, "delta_db": -0.21378478130769418}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.795751713818223e-08, "output_power": 1.508245447384845e-08, "reference_active": true, "delta_db": -2.680265767172423}], "active_band_count": 3, "active_band_mae_db": 1.092041564186314}}]}, {"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": 1.0101884937381447e-05, "log_rms_mae_db": 1.5837337959204623, "rms_envelope_nrmse": 0.14819833912935176, "envelope_correlation": 0.9844480809588482, "rms_gain_error_db": -0.46751241965834844, "reference_mean_power": 6.452617383104311e-06, "output_mean_power": 5.794082461654045e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.152733675321415e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.1017382665662714e-06, "output_power": 1.9005557902085406e-06, "reference_active": true, "delta_db": -0.43698008845742176}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.306147609644791e-07, "output_power": 3.5894885386222686e-07, "reference_active": true, "delta_db": -0.7905634189157622}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.161739165108224e-08, "output_power": 8.615442753955933e-08, "reference_active": true, "delta_db": 0.2349488970334373}], "active_band_count": 3, "active_band_mae_db": 0.4874974681355404}}, {"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": 8.618352616189348e-06, "log_rms_mae_db": 0.9819639915126831, "rms_envelope_nrmse": 0.08943403236892981, "envelope_correlation": 0.9954933147546137, "rms_gain_error_db": -0.4687210847752764, "reference_mean_power": 6.45826084166141e-06, "output_mean_power": 5.7975362552796935e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.765522812781555e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.8830611185238986e-06, "output_power": 1.699589598431562e-06, "reference_active": true, "delta_db": -0.4452035162062617}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.7697767264084277e-07, "output_power": 1.4996410916390882e-07, "reference_active": true, "delta_db": -0.7193114757126273}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.816205310457988e-09, "output_power": 7.165131089083575e-09, "reference_active": true, "delta_db": -1.3671949287712504}], "active_band_count": 3, "active_band_mae_db": 0.8439033068967131}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9888513395685483, "standard_deviation": 0.0017077138002098006, "minimum": 0.9864241640063509, "maximum": 0.9919414440141195, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.3325481387449134, "standard_deviation": 0.03104502158039015, "minimum": 1.2929834715419137, "maximum": 1.3831897083244664, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.7070672646967526, "standard_deviation": 0.4315951910771303, "minimum": 0.172583718706161, "maximum": 1.2079167869159964, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12627920579706475, "standard_deviation": 0.009591050096936365, "minimum": 0.10981423499355186, "maximum": 0.14190830567114376, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9966139936949762, "standard_deviation": 0.0006243973291370038, "minimum": 0.9959489415657538, "maximum": 0.9974810297373207, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.9166987079913615, "standard_deviation": 0.025700179896892848, "minimum": 0.8796786171163216, "maximum": 0.9657483817640163, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6222519054461833, "standard_deviation": 0.2899707659044368, "minimum": 0.35904262489491484, "maximum": 1.092041564186314, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0740353517921252, "standard_deviation": 0.007060962612624669, "minimum": 0.06792900064273373, "maximum": 0.08622346390176172, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.980770047130031, "standard_deviation": 0.002269439738193454, "minimum": 0.9773173789676458, "maximum": 0.9844480809588482, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.6117005407263867, "standard_deviation": 0.026388817184320238, "minimum": 1.5837337959204623, "maximum": 1.6679919529997238, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.5456916809339956, "standard_deviation": 0.2459389106269421, "minimum": 0.15109907868470043, "maximum": 0.9488716069440266, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16205759041049905, "standard_deviation": 0.009301067215093344, "minimum": 0.14819833912935176, "maximum": 0.17868401183864507, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9935811158262291, "standard_deviation": 0.0016010628599543405, "minimum": 0.9903418735299309, "maximum": 0.9954933147546137, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.0241363542175255, "standard_deviation": 0.03288346271749514, "minimum": 0.9819639915126831, "maximum": 1.0700492361666591, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.5359080503258631, "standard_deviation": 0.27283641530350894, "minimum": 0.2242201845820014, "maximum": 1.0490861725819507, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09918078267713529, "standard_deviation": 0.011954623183316896, "minimum": 0.08828364498339082, "maximum": 0.12426468334519011, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9962813630166621, "standard_deviation": 0.0004718174231927428, "minimum": 0.9955650505598597, "maximum": 0.9968923738852731, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.4751866530972375, "standard_deviation": 0.036510866295961564, "minimum": 1.4117892941950951, "maximum": 1.532619527052877, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.5159354870879943, "standard_deviation": 0.22905010587939117, "minimum": 0.24743196773538775, "maximum": 0.8379720215559293, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06466882692410701, "standard_deviation": 0.004077696028984486, "minimum": 0.05898717182980252, "maximum": 0.0707643673615312, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9987036036897294, "standard_deviation": 0.00023243887955551987, "minimum": 0.9982383799950497, "maximum": 0.9990042140733512, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.1222813489646017, "standard_deviation": 0.046542896830838565, "minimum": 1.0675804384649685, "maximum": 1.2124518262109683, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.8374476108038083, "standard_deviation": 0.26739741432071573, "minimum": 0.4168854834981673, "maximum": 1.2582629545531763, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03772528097687685, "standard_deviation": 0.0033635463496796115, "minimum": 0.03273896855710506, "maximum": 0.04407741841028764, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.19356965551892338, "standard_deviation": 0.02647891398398177, "minimum": 0.16153321483522984, "maximum": 0.24612539169724254, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.477814252204626, "standard_deviation": 0.007863388345221857, "minimum": 5.46702505169493, "maximum": 5.488296786238737, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.15631306859242566, "standard_deviation": 0.0037009655235104456, "minimum": 0.15022058427439094, "maximum": 0.1605894099629893, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.07387054002494174, "standard_deviation": 0.013923696223047056, "minimum": -0.0983805764922213, "maximum": -0.0590950155546906, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9982598807051087, "standard_deviation": 0.0001881659694691774, "minimum": 0.9978962619376438, "maximum": 0.9985545552489183, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.1518885222377688, "standard_deviation": 0.033766588896753574, "minimum": 1.1032563503360806, "maximum": 1.2104327349712396, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.39854724159365185, "standard_deviation": 0.1879176980839829, "minimum": 0.1720991884679635, "maximum": 0.6960115281606978, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.0419751937717593, "standard_deviation": 0.0020776407700933345, "minimum": 0.03862946665133215, "maximum": 0.045731218777732605, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9995159025991909, "standard_deviation": 6.563247371318696e-05, "minimum": 0.99939034138242, "maximum": 0.9995926087498538, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.592171019510489, "standard_deviation": 0.03031237250479676, "minimum": 0.5427290306418301, "maximum": 0.6343118908174666, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5291277819232568, "standard_deviation": 0.1745516736795485, "minimum": 0.28589897066666065, "maximum": 0.8589045165635785, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.022728324266657936, "standard_deviation": 0.0016106245152050177, "minimum": 0.021127049232363453, "maximum": 0.02575561785807461, "valid_count": 8, "planned_count": 8}}, "seconds": 8.240763278998202, "rtf_including_measurement": 1.3734605464997003}, {"case": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "normal", "speaker": "jvs_jvs082", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.39521861076355, "predicted_mos": 2.39521861076355, "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": 3.526251762996253}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0596337429393852, "全帯域_10ms_rms_envelope_nrmse": 0.03735336577168146, "全帯域_10ms_envelope_correlation": 0.9986446705753732, "全帯域_10ms_modulation_mae_db": 0.1594411854381563, "全帯域_40ms_log_rms_mae_db": 0.5838044260693729, "全帯域_40ms_rms_envelope_nrmse": 0.020845462739975867, "全帯域_40ms_envelope_correlation": 0.9996132204229141, "全帯域_40ms_modulation_mae_db": 0.31495302079662174, "300–1000 Hz_10ms_log_rms_mae_db": 1.4637321478362615, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06543493317213046, "300–1000 Hz_10ms_envelope_correlation": 0.9961916675214424, "300–1000 Hz_10ms_modulation_mae_db": 0.21101333404622016, "300–1000 Hz_40ms_log_rms_mae_db": 1.163989728141257, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03781464204115897, "300–1000 Hz_40ms_envelope_correlation": 0.9987099330966713, "300–1000 Hz_40ms_modulation_mae_db": 0.6737841858297956, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2139682874979922, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10856237078305837, "1000–3000 Hz_10ms_envelope_correlation": 0.9918915699977683, "1000–3000 Hz_10ms_modulation_mae_db": 0.8209002419257051, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8806826469411875, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06747679354986996, "1000–3000 Hz_40ms_envelope_correlation": 0.9972316673714313, "1000–3000 Hz_40ms_modulation_mae_db": 0.6658088488599656, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5080991521454592, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1460819822115779, "3000–6000 Hz_10ms_envelope_correlation": 0.9846128058796253, "3000–6000 Hz_10ms_modulation_mae_db": 0.5857575952399746, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9264193354546827, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08732802261063069, "3000–6000 Hz_40ms_envelope_correlation": 0.995402441613222, "3000–6000 Hz_40ms_modulation_mae_db": 0.5610704960812779, "mr_stft_db": 5.472557851182216, "band_mae_db": 0.20236346418005444, "rms_gain_error_db": -0.07556268034266686, "output_peak": 0.15894095453272641}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1010362104975984, "全帯域_10ms_rms_envelope_nrmse": 0.041772561043870955, "全帯域_10ms_envelope_correlation": 0.9983282796215751, "全帯域_10ms_modulation_mae_db": 0.49226805962813597, "全帯域_40ms_log_rms_mae_db": 0.5807670637671863, "全帯域_40ms_rms_envelope_nrmse": 0.024288340390558036, "全帯域_40ms_envelope_correlation": 0.9994948417025155, "全帯域_40ms_modulation_mae_db": 0.5524673487514183, "300–1000 Hz_10ms_log_rms_mae_db": 1.4344961083388, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06224323648715693, "300–1000 Hz_10ms_envelope_correlation": 0.9965671128731907, "300–1000 Hz_10ms_modulation_mae_db": 0.7488333628788011, "300–1000 Hz_40ms_log_rms_mae_db": 1.081894675942441, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03606744985045319, "300–1000 Hz_40ms_envelope_correlation": 0.998823273119658, "300–1000 Hz_40ms_modulation_mae_db": 1.0472464248207374, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2877011918174217, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.14534470013348566, "1000–3000 Hz_10ms_envelope_correlation": 0.9859788182798458, "1000–3000 Hz_10ms_modulation_mae_db": 1.381349048201266, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8806036899939415, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09059825311319979, "1000–3000 Hz_40ms_envelope_correlation": 0.9957960936398637, "1000–3000 Hz_40ms_modulation_mae_db": 1.1004403187751517, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5322314908863433, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17061530110656067, "3000–6000 Hz_10ms_envelope_correlation": 0.9777388129152533, "3000–6000 Hz_10ms_modulation_mae_db": 0.642297083547306, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9576240171069798, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09038509274000357, "3000–6000 Hz_40ms_envelope_correlation": 0.9939138663443862, "3000–6000 Hz_40ms_modulation_mae_db": 0.43335123029010236, "mr_stft_db": 5.46491821740419, "band_mae_db": 0.17973462630984613, "rms_gain_error_db": -0.10123564175290584, "output_peak": 0.15089476584165476}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1260396828022683, "全帯域_10ms_rms_envelope_nrmse": 0.04041079463161024, "全帯域_10ms_envelope_correlation": 0.9983934741262959, "全帯域_10ms_modulation_mae_db": 0.6817179816531894, "全帯域_40ms_log_rms_mae_db": 0.5765066782339656, "全帯域_40ms_rms_envelope_nrmse": 0.020884358038444847, "全帯域_40ms_envelope_correlation": 0.9995973783646234, "全帯域_40ms_modulation_mae_db": 0.7437503065358974, "300–1000 Hz_10ms_log_rms_mae_db": 1.3739482329560755, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06140017841032432, "300–1000 Hz_10ms_envelope_correlation": 0.9966907409799732, "300–1000 Hz_10ms_modulation_mae_db": 0.7136370118188383, "300–1000 Hz_40ms_log_rms_mae_db": 1.010819045935476, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038330259082402944, "300–1000 Hz_40ms_envelope_correlation": 0.9986912584680995, "300–1000 Hz_40ms_modulation_mae_db": 0.8137881560031769, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2812690378183933, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13083934507177863, "1000–3000 Hz_10ms_envelope_correlation": 0.988518161835201, "1000–3000 Hz_10ms_modulation_mae_db": 0.3006052198708553, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8735433803011607, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.08536106431261255, "1000–3000 Hz_40ms_envelope_correlation": 0.9958252077684951, "1000–3000 Hz_40ms_modulation_mae_db": 0.2592568301026654, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5488040622321884, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15925475437857378, "3000–6000 Hz_10ms_envelope_correlation": 0.9812097784624949, "3000–6000 Hz_10ms_modulation_mae_db": 0.45464419936101486, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0196261067376426, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10760516425822673, "3000–6000 Hz_40ms_envelope_correlation": 0.9917525744440282, "3000–6000 Hz_40ms_modulation_mae_db": 0.22223840629247849, "mr_stft_db": 5.477669787642, "band_mae_db": 0.20249912525328798, "rms_gain_error_db": -0.07119675790066991, "output_peak": 0.1604994963414295}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.1459237335028456, "全帯域_10ms_rms_envelope_nrmse": 0.046074078833691995, "全帯域_10ms_envelope_correlation": 0.997858642225498, "全帯域_10ms_modulation_mae_db": 0.18940911861512388, "全帯域_40ms_log_rms_mae_db": 0.6323843122898506, "全帯域_40ms_rms_envelope_nrmse": 0.023567752671451437, "全帯域_40ms_envelope_correlation": 0.9994385765033923, "全帯域_40ms_modulation_mae_db": 0.17860376755364857, "300–1000 Hz_10ms_log_rms_mae_db": 1.3539206787049336, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06689137927490035, "300–1000 Hz_10ms_envelope_correlation": 0.9960100482825965, "300–1000 Hz_10ms_modulation_mae_db": 0.3188794364608776, "300–1000 Hz_40ms_log_rms_mae_db": 1.0566689177160593, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03758446622367625, "300–1000 Hz_40ms_envelope_correlation": 0.9987223812193782, "300–1000 Hz_40ms_modulation_mae_db": 0.36963631219288656, "1000–3000 Hz_10ms_log_rms_mae_db": 1.214426054690925, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12382068816206027, "1000–3000 Hz_10ms_envelope_correlation": 0.9891235928753485, "1000–3000 Hz_10ms_modulation_mae_db": 0.7357336344269879, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8290171789445488, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0657360718738849, "1000–3000 Hz_40ms_envelope_correlation": 0.9972702432972916, "1000–3000 Hz_40ms_modulation_mae_db": 0.6014376677270958, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5570456498712268, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17615686054033405, "3000–6000 Hz_10ms_envelope_correlation": 0.9778368629297901, "3000–6000 Hz_10ms_modulation_mae_db": 0.974251507302449, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0090197862871675, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12342655417610032, "3000–6000 Hz_40ms_envelope_correlation": 0.9902545969293807, "3000–6000 Hz_40ms_modulation_mae_db": 0.702662142379839, "mr_stft_db": 5.461610619271014, "band_mae_db": 0.23633352735435426, "rms_gain_error_db": -0.05704754129267276, "output_peak": 0.15270838106517115}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0997043364629562, "全帯域_10ms_rms_envelope_nrmse": 0.039805347911196824, "全帯域_10ms_envelope_correlation": 0.9984286785147243, "全帯域_10ms_modulation_mae_db": 0.35757108418640665, "全帯域_40ms_log_rms_mae_db": 0.5744783626203244, "全帯域_40ms_rms_envelope_nrmse": 0.021561038357910924, "全帯域_40ms_envelope_correlation": 0.9995569373958924, "全帯域_40ms_modulation_mae_db": 0.4431026100913648, "300–1000 Hz_10ms_log_rms_mae_db": 1.403933314101873, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05988676775656933, "300–1000 Hz_10ms_envelope_correlation": 0.9968361874933791, "300–1000 Hz_10ms_modulation_mae_db": 0.62666176796411, "300–1000 Hz_40ms_log_rms_mae_db": 1.0506079500274919, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03418684559068391, "300–1000 Hz_40ms_envelope_correlation": 0.9989448211160756, "300–1000 Hz_40ms_modulation_mae_db": 0.8517358457932875, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2619808471561067, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.13060391678631927, "1000–3000 Hz_10ms_envelope_correlation": 0.9877764314171366, "1000–3000 Hz_10ms_modulation_mae_db": 0.5842580524853375, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8748497299939259, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07698066418372836, "1000–3000 Hz_40ms_envelope_correlation": 0.9960090020664928, "1000–3000 Hz_40ms_modulation_mae_db": 0.49291393032152014, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5117684334103687, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16758307330326938, "3000–6000 Hz_10ms_envelope_correlation": 0.9784414798568836, "3000–6000 Hz_10ms_modulation_mae_db": 0.9347860012680579, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9291908053740094, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09128604259058444, "3000–6000 Hz_40ms_envelope_correlation": 0.9934173583599387, "3000–6000 Hz_40ms_modulation_mae_db": 0.5733068191840903, "mr_stft_db": 5.455272797867539, "band_mae_db": 0.1953916166127411, "rms_gain_error_db": -0.06549931515705808, "output_peak": 0.15581677547320405}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0342330578518653, "全帯域_10ms_rms_envelope_nrmse": 0.04112340809917491, "全帯域_10ms_envelope_correlation": 0.9983203912209959, "全帯域_10ms_modulation_mae_db": 0.17985754171110338, "全帯域_40ms_log_rms_mae_db": 0.542105384276488, "全帯域_40ms_rms_envelope_nrmse": 0.02291209020235531, "全帯域_40ms_envelope_correlation": 0.9994969884607912, "全帯域_40ms_modulation_mae_db": 0.6019776880270338, "300–1000 Hz_10ms_log_rms_mae_db": 1.382676777458927, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.05888032538076265, "300–1000 Hz_10ms_envelope_correlation": 0.9968996001678085, "300–1000 Hz_10ms_modulation_mae_db": 0.2869210776926632, "300–1000 Hz_40ms_log_rms_mae_db": 1.068599542231732, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03342107376377327, "300–1000 Hz_40ms_envelope_correlation": 0.9989617354211573, "300–1000 Hz_40ms_modulation_mae_db": 0.635743155838842, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2832326961008216, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11586747406605438, "1000–3000 Hz_10ms_envelope_correlation": 0.9903280276262081, "1000–3000 Hz_10ms_modulation_mae_db": 0.5088454120818361, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8825556590982431, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06273207213303333, "1000–3000 Hz_40ms_envelope_correlation": 0.997261014334681, "1000–3000 Hz_40ms_modulation_mae_db": 0.17624583375650574, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5251090048712008, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16054758887167236, "3000–6000 Hz_10ms_envelope_correlation": 0.9814745801114515, "3000–6000 Hz_10ms_modulation_mae_db": 0.8324512604206923, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9774876959391509, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09643905476719648, "3000–6000 Hz_40ms_envelope_correlation": 0.9945306919489331, "3000–6000 Hz_40ms_modulation_mae_db": 0.4018037937109064, "mr_stft_db": 5.4658688444848, "band_mae_db": 0.16134362216573533, "rms_gain_error_db": -0.06856593842256391, "output_peak": 0.15408956256567413}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0711888602661308, "全帯域_10ms_rms_envelope_nrmse": 0.04110198665954453, "全帯域_10ms_envelope_correlation": 0.9983761054645477, "全帯域_10ms_modulation_mae_db": 0.3745150280790192, "全帯域_40ms_log_rms_mae_db": 0.5747252210220661, "全帯域_40ms_rms_envelope_nrmse": 0.024026097563866748, "全帯域_40ms_envelope_correlation": 0.9994941113141271, "全帯域_40ms_modulation_mae_db": 0.4310283293233132, "300–1000 Hz_10ms_log_rms_mae_db": 1.4349682130794141, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06944632023983455, "300–1000 Hz_10ms_envelope_correlation": 0.9957324158539295, "300–1000 Hz_10ms_modulation_mae_db": 0.5354036946630285, "300–1000 Hz_40ms_log_rms_mae_db": 1.0611312833154263, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04345393743471164, "300–1000 Hz_40ms_envelope_correlation": 0.998292673900844, "300–1000 Hz_40ms_modulation_mae_db": 0.8988742854807802, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2982484675558843, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12293855852091283, "1000–3000 Hz_10ms_envelope_correlation": 0.9897712899699875, "1000–3000 Hz_10ms_modulation_mae_db": 0.6163706999539564, "1000–3000 Hz_40ms_log_rms_mae_db": 0.916968160081318, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07194383718079174, "1000–3000 Hz_40ms_envelope_correlation": 0.9972120291276246, "1000–3000 Hz_40ms_modulation_mae_db": 0.6569515091383088, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5252486027043046, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16983215775264007, "3000–6000 Hz_10ms_envelope_correlation": 0.978245167744885, "3000–6000 Hz_10ms_modulation_mae_db": 0.5773023480620973, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9768590340963557, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10125727954608893, "3000–6000 Hz_40ms_envelope_correlation": 0.9926417857047326, "3000–6000 Hz_40ms_modulation_mae_db": 0.3237247964259579, "mr_stft_db": 5.4702882353935705, "band_mae_db": 0.18820917777302745, "rms_gain_error_db": -0.09330438699512814, "output_peak": 0.15835383209369042}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.0424283933598528, "全帯域_10ms_rms_envelope_nrmse": 0.04203760356204209, "全帯域_10ms_envelope_correlation": 0.9982355785894973, "全帯域_10ms_modulation_mae_db": 0.6110111061777447, "全帯域_40ms_log_rms_mae_db": 0.5404499745457138, "全帯域_40ms_rms_envelope_nrmse": 0.02189401038172776, "全帯域_40ms_envelope_correlation": 0.999534860728853, "全帯域_40ms_modulation_mae_db": 0.6065957915112767, "300–1000 Hz_10ms_log_rms_mae_db": 1.4102097558520048, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.06848779605847952, "300–1000 Hz_10ms_envelope_correlation": 0.9958388664270748, "300–1000 Hz_10ms_modulation_mae_db": 0.5157378468374713, "300–1000 Hz_40ms_log_rms_mae_db": 1.0874877032733818, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04033377609836621, "300–1000 Hz_40ms_envelope_correlation": 0.9985251305103885, "300–1000 Hz_40ms_modulation_mae_db": 0.5182287184827546, "1000–3000 Hz_10ms_log_rms_mae_db": 1.255899157918026, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12145786720718367, "1000–3000 Hz_10ms_envelope_correlation": 0.989304011225278, "1000–3000 Hz_10ms_modulation_mae_db": 0.4051466336903376, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8807308938879408, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07486255167382053, "1000–3000 Hz_40ms_envelope_correlation": 0.995761844444861, "1000–3000 Hz_40ms_modulation_mae_db": 0.43407967592385416, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6252442464822987, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15993516850013234, "3000–6000 Hz_10ms_envelope_correlation": 0.9807697854536502, "3000–6000 Hz_10ms_modulation_mae_db": 0.17609024654308594, "3000–6000 Hz_40ms_log_rms_mae_db": 1.0382958080361513, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09385425678253609, "3000–6000 Hz_40ms_envelope_correlation": 0.9937668115649394, "3000–6000 Hz_40ms_modulation_mae_db": 0.26130960712911455, "mr_stft_db": 5.4742416522986685, "band_mae_db": 0.20209253073558295, "rms_gain_error_db": -0.06357134326885613, "output_peak": 0.15908783290803988}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 0.12677310730005925, "spectral_convergence_status": "ok", "amplitude_floor": 5.237444731722431e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.479432388083743, "spectral_convergence": 0.13244263715404628, "spectral_convergence_status": "ok", "amplitude_floor": 5.437369948912744e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.414597819404401, "spectral_convergence": 0.13205806203745135, "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": 6.224424190501186e-05, "delta_db": 0.13123978252893262, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 3.556975687019485e-05, "output_power": 3.308776623468403e-05, "delta_db": -0.3141344786982877, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.090392882810899e-05, "output_power": 1.0561203868242562e-05, "delta_db": -0.13869582009934758, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2355857763199668e-06, "output_power": 1.376793423228381e-06, "delta_db": 0.4699588255863876, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.0422411240430348e-06, "output_power": 1.0759199263035809e-06, "delta_db": 0.13811745564090785, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.20236346418005444, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.07556268034266686, "pitch": null, "output_rms_dbfs": -29.998444781290612, "output_peak": 0.15894095453272641, "reference_rms_dbfs": -29.922882100947945, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.472557851182216}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"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"}}, "level": {"reference": {"rms": 0.03190479033407081, "rms_dbfs": -29.922882100947945, "peak": 0.15533447265625, "peak_dbfs": -16.17464305245918, "crest_factor_db": 13.74823904848876, "mean": -8.231268988715278e-07, "zero_energy": false}, "output": {"rms": 0.03162843920379184, "rms_dbfs": -29.998444781290612, "peak": 0.15894095453272641, "peak_dbfs": -15.975283662414837, "crest_factor_db": 14.023161118875773, "mean": -2.400376817440226e-05, "zero_energy": false}, "rms_difference_db": -0.07556268034266722}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 204, "quiet_samples": 48960, "reference_mean_power": 9.005820816930603e-08, "output_mean_power": 1.684137804190361e-07, "output_rms_dbfs": -67.73622375335846, "output_zero_energy": false, "output_peak": 0.009851808098504678, "output_energy_fraction": 5.724018382800541e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 314, "output_estimated_voiced_frames": 299, "both_estimated_voiced_frames": 296, "reference_voiced_output_unvoiced_frames": 18, "reference_unvoiced_output_voiced_frames": 3, "paired_voiced_fraction": 0.9426751592356688, "absolute_difference_cents_median": 1.2364001429130864, "absolute_difference_cents_p95": 14.48197929978114, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.0596337429393852, "rms_envelope_nrmse": 0.03735336577168146, "envelope_correlation": 0.9986446705753732, "rms_gain_error_db": -0.0751044735964718, "reference_mean_power": 0.0010176842474405314, "output_mean_power": 0.0010002362842861966}, "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": 0.00012852814089853154, "reference_active": true, "delta_db": -0.15753813135821798}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5932863269435214e-05, "output_power": 1.597181564869786e-05, "reference_active": true, "delta_db": 0.010604596159419343}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.591650627521311e-06, "output_power": 4.27514405122477e-06, "reference_active": true, "delta_db": -0.31018082879683156}], "active_band_count": 3, "active_band_mae_db": 0.1594411854381563}}, {"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": 0.5838044260693729, "rms_envelope_nrmse": 0.020845462739975867, "envelope_correlation": 0.9996132204229141, "rms_gain_error_db": -0.0743237349959107, "reference_mean_power": 0.0010161096570352637, "output_mean_power": 0.0009988682419810777}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.9042638692252314e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00011759425242544186, "output_power": 0.00011347317882932699, "reference_active": true, "delta_db": -0.15492874214843666}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 7.519272755909202e-06, "output_power": 7.920532636913188e-06, "reference_active": true, "delta_db": 0.22578549024862213}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.598733053895234e-07, "output_power": 3.1603497645684283e-07, "reference_active": true, "delta_db": -0.5641448299928064}], "active_band_count": 3, "active_band_mae_db": 0.31495302079662174}}]}, {"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": 4.667982083652564e-05, "log_rms_mae_db": 1.4637321478362615, "rms_envelope_nrmse": 0.06543493317213046, "envelope_correlation": 0.9961916675214424, "rms_gain_error_db": -0.019688148306864047, "reference_mean_power": 0.0002794511004585033, "output_mean_power": 0.0002781871142087476}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.938593634377073e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.2950751511150254e-05, "output_power": 3.095613396145935e-05, "reference_active": true, "delta_db": -0.27118606657406}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.807348843301906e-06, "output_power": 3.510544445659412e-06, "reference_active": true, "delta_db": -0.3524819445319319}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5906604704508287e-06, "output_power": 1.5940967914450409e-06, "reference_active": true, "delta_db": 0.009371991032668564}], "active_band_count": 3, "active_band_mae_db": 0.21101333404622016}}, {"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": 4.25438813129898e-05, "log_rms_mae_db": 1.163989728141257, "rms_envelope_nrmse": 0.03781464204115897, "envelope_correlation": 0.9987099330966713, "rms_gain_error_db": -0.016287245527359554, "reference_mean_power": 0.0002774218749538236, "output_mean_power": 0.00027638341458544264}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 9.236914065861679e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.9257092980847747e-05, "output_power": 2.7213268321281628e-05, "reference_active": true, "delta_db": -0.3145046811948788}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8979287936807771e-06, "output_power": 1.9164489698484103e-06, "reference_active": true, "delta_db": 0.04217345012973731}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.435917808710527e-08, "output_power": 6.431565644970966e-08, "reference_active": true, "delta_db": -1.6646744261647708}], "active_band_count": 3, "active_band_mae_db": 0.6737841858297956}}]}, {"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": 1.2139682874979922, "rms_envelope_nrmse": 0.10856237078305837, "envelope_correlation": 0.9918915699977683, "rms_gain_error_db": -0.28140238079222973, "reference_mean_power": 3.509769240032237e-05, "output_mean_power": 3.289563887570872e-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": 9.430240235566084e-06, "reference_active": true, "delta_db": -0.34406435490313825}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.594184871691995e-06, "output_power": 2.568933485868729e-06, "reference_active": true, "delta_db": -0.042480625862503986}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.354712471534306e-07, "output_power": 2.079886943919696e-07, "reference_active": true, "delta_db": -2.076155745011473}], "active_band_count": 3, "active_band_mae_db": 0.8209002419257051}}, {"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": 0.8806826469411875, "rms_envelope_nrmse": 0.06747679354986996, "envelope_correlation": 0.9972316673714313, "rms_gain_error_db": -0.28626237130726795, "reference_mean_power": 3.5141167460930974e-05, "output_mean_power": 3.289954929559366e-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": 8.864781734349154e-06, "reference_active": true, "delta_db": -0.30017177197071404}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.126122979707458e-06, "output_power": 1.1444263318790285e-06, "reference_active": true, "delta_db": 0.07002021051655957}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.795751713818223e-08, "output_power": 1.9220963030267788e-08, "reference_active": true, "delta_db": -1.6272345640926231}], "active_band_count": 3, "active_band_mae_db": 0.6658088488599656}}]}, {"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": 1.0101884937381447e-05, "log_rms_mae_db": 1.5080991521454592, "rms_envelope_nrmse": 0.1460819822115779, "envelope_correlation": 0.9846128058796253, "rms_gain_error_db": -0.4187982781828225, "reference_mean_power": 6.452617383104311e-06, "output_mean_power": 5.859439655528634e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.152733675321415e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.1017382665662714e-06, "output_power": 1.910118814655012e-06, "reference_active": true, "delta_db": -0.41518249146129993}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.306147609644791e-07, "output_power": 3.629418925529736e-07, "reference_active": true, "delta_db": -0.7425181332711903}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.161739165108224e-08, "output_power": 9.370007261766084e-08, "reference_active": true, "delta_db": 0.5995721609874333}], "active_band_count": 3, "active_band_mae_db": 0.5857575952399746}}, {"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": 8.618352616189348e-06, "log_rms_mae_db": 0.9264193354546827, "rms_envelope_nrmse": 0.08732802261063069, "envelope_correlation": 0.995402441613222, "rms_gain_error_db": -0.42130972114775767, "reference_mean_power": 6.45826084166141e-06, "output_mean_power": 5.86117393450912e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.765522812781555e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.8830611185238986e-06, "output_power": 1.7074765583137343e-06, "reference_active": true, "delta_db": -0.4250966611200534}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.7697767264084277e-07, "output_power": 1.5453271194541327e-07, "reference_active": true, "delta_db": -0.5889805333535765}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.816205310457988e-09, "output_power": 8.41453660241898e-09, "reference_active": true, "delta_db": -0.669134293770204}], "active_band_count": 3, "active_band_mae_db": 0.5610704960812779}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9890864879033467, "standard_deviation": 0.0017576122801167178, "minimum": 0.9859788182798458, "maximum": 0.9918915699977683, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.2620907175694462, "standard_deviation": 0.032522753232622006, "minimum": 1.2139682874979922, "maximum": 1.2982484675558843, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6691511178295353, "standard_deviation": 0.3329311149480535, "minimum": 0.3006052198708553, "maximum": 1.381349048201266, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.12492936509135665, "standard_deviation": 0.01102694394735516, "minimum": 0.10856237078305837, "maximum": 0.14534470013348566, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9965458877563427, "standard_deviation": 0.0007497309993771048, "minimum": 0.995761844444861, "maximum": 0.9972702432972916, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8773689174052832, "standard_deviation": 0.023864562503655623, "minimum": 0.8290171789445488, "maximum": 0.916968160081318, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5483918268256334, "standard_deviation": 0.2857021705301896, "minimum": 0.17624583375650574, "maximum": 1.1004403187751517, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.07446141350261765, "standard_deviation": 0.009669832751892617, "minimum": 0.06273207213303333, "maximum": 0.09059825311319979, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9800411591692542, "standard_deviation": 0.00241411018331468, "minimum": 0.9777388129152533, "maximum": 0.9846128058796253, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.541693830325424, "standard_deviation": 0.0376564837865723, "minimum": 1.5080991521454592, "maximum": 1.6252442464822987, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6471975302180848, "standard_deviation": 0.26503192573015366, "minimum": 0.17609024654308594, "maximum": 0.974251507302449, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.16375086083309506, "standard_deviation": 0.009334437758530654, "minimum": 0.1460819822115779, "maximum": 0.17615686054033405, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9932100158636952, "standard_deviation": 0.001629235400634702, "minimum": 0.9902545969293807, "maximum": 0.995402441613222, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9793153236290174, "standard_deviation": 0.04101628793653675, "minimum": 0.9264193354546827, "maximum": 1.0382958080361513, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.4349334114367209, "standard_deviation": 0.1671561541205738, "minimum": 0.22223840629247849, "maximum": 0.702662142379839, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09894768343392091, "standard_deviation": 0.011824748571954547, "minimum": 0.08732802261063069, "maximum": 0.12342655417610032, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9963458299499244, "standard_deviation": 0.00046056579715317004, "minimum": 0.9957324158539295, "maximum": 0.9968996001678085, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.4072356535410362, "standard_deviation": 0.03640547281796927, "minimum": 1.3539206787049336, "maximum": 1.4637321478362615, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.49463594154525126, "standard_deviation": 0.20234112425934206, "minimum": 0.21101333404622016, "maximum": 0.7488333628788011, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.06408386709751976, "standard_deviation": 0.0040203161469542885, "minimum": 0.05888032538076265, "maximum": 0.06944632023983455, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9987089008565341, "standard_deviation": 0.00022044602800418823, "minimum": 0.998292673900844, "maximum": 0.9989617354211573, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.0726498558229083, "standard_deviation": 0.043690417859460776, "minimum": 1.010819045935476, "maximum": 1.163989728141257, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.7261296355552826, "standard_deviation": 0.21962230091928375, "minimum": 0.36963631219288656, "maximum": 1.0472464248207374, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.03764905626065329, "standard_deviation": 0.0032461892254908036, "minimum": 0.03342107376377327, "maximum": 0.04345393743471164, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.1959959612980787, "standard_deviation": 0.021624518101115042, "minimum": 0.16134362216573533, "maximum": 0.23633352735435426, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.467803500693, "standard_deviation": 0.007319340497920763, "minimum": 5.455272797867539, "maximum": 5.477669787642, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.15629895010269879, "standard_deviation": 0.0034607278882067883, "minimum": 0.15089476584165476, "maximum": 0.1604994963414295, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.0744979506415652, "standard_deviation": 0.015216013377856188, "minimum": -0.10123564175290584, "maximum": -0.05704754129267276, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9983232275423135, "standard_deviation": 0.00022223912863007683, "minimum": 0.997858642225498, "maximum": 0.9986446705753732, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.0850235022103627, "standard_deviation": 0.03980873682381375, "minimum": 1.0342330578518653, "maximum": 1.1459237335028456, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3807238881861099, "standard_deviation": 0.20091256672266242, "minimum": 0.1594411854381563, "maximum": 0.6817179816531894, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.04120989331410163, "standard_deviation": 0.002454303355181509, "minimum": 0.03735336577168146, "maximum": 0.046074078833691995, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9995283643616386, "standard_deviation": 5.87554877650745e-05, "minimum": 0.9994385765033923, "maximum": 0.9996132204229141, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.575652677853121, "standard_deviation": 0.0284823404527837, "minimum": 0.5404499745457138, "maximum": 0.6323843122898506, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.48405985782382177, "standard_deviation": 0.18024933852114827, "minimum": 0.17860376755364857, "maximum": 0.7437503065358974, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.022497393793286365, "standard_deviation": 0.0013853137739576256, "minimum": 0.020845462739975867, "maximum": 0.024288340390558036, "valid_count": 8, "planned_count": 8}}, "seconds": 7.827637841997785, "rtf_including_measurement": 1.3046063069996308}, {"case": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "normal", "speaker": "jvs_jvs082", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.21260666847229, "predicted_mos": 2.21260666847229, "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": "88c72e687618556836dcfa6c8c5d058a9e37f1aae94ffb9ae28aaf181936c4cd", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.106955060000473}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 2.4323987832622347, "全帯域_10ms_rms_envelope_nrmse": 0.24364689443837056, "全帯域_10ms_envelope_correlation": 0.9882222994921743, "全帯域_10ms_modulation_mae_db": 1.8834592517949584, "全帯域_40ms_log_rms_mae_db": 2.0871033902694833, "全帯域_40ms_rms_envelope_nrmse": 0.2382142363570763, "全帯域_40ms_envelope_correlation": 0.9898357444277714, "全帯域_40ms_modulation_mae_db": 1.835025309916648, "300–1000 Hz_10ms_log_rms_mae_db": 2.3154157225602376, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2659407796821359, "300–1000 Hz_10ms_envelope_correlation": 0.9904353067917785, "300–1000 Hz_10ms_modulation_mae_db": 1.5354487513914055, "300–1000 Hz_40ms_log_rms_mae_db": 2.3244712728070813, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.26008770738998793, "300–1000 Hz_40ms_envelope_correlation": 0.9922009028163238, "300–1000 Hz_40ms_modulation_mae_db": 1.2338634622430245, "1000–3000 Hz_10ms_log_rms_mae_db": 1.2496509916302359, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21620514463810056, "1000–3000 Hz_10ms_envelope_correlation": 0.9855300258097814, "1000–3000 Hz_10ms_modulation_mae_db": 1.149574537597126, "1000–3000 Hz_40ms_log_rms_mae_db": 1.1565139304381322, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.20358664367675594, "1000–3000 Hz_40ms_envelope_correlation": 0.9883313151285046, "1000–3000 Hz_40ms_modulation_mae_db": 1.0448102159546448, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5323582685207842, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.21180481383367586, "3000–6000 Hz_10ms_envelope_correlation": 0.9813312891636793, "3000–6000 Hz_10ms_modulation_mae_db": 1.3492180578770665, "3000–6000 Hz_40ms_log_rms_mae_db": 1.1928562490544101, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.17271890897019643, "3000–6000 Hz_40ms_envelope_correlation": 0.9907801004751736, "3000–6000 Hz_40ms_modulation_mae_db": 1.281106059243474, "mr_stft_db": 5.477013209027429, "band_mae_db": 1.0333239748400784, "rms_gain_error_db": 1.6670047074544851, "output_peak": 0.17967242471874667}}], "planned_noise_seeds": [0], "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": 5.705988597064638, "spectral_convergence": 0.3844558562076913, "spectral_convergence_status": "ok", "amplitude_floor": 5.237444731722431e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.322457233753826, "spectral_convergence": 0.2647813976619999, "spectral_convergence_status": "ok", "amplitude_floor": 5.437369948912744e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.4025937962638215, "spectral_convergence": 0.2875953080136151, "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": 6.775759827344745e-05, "delta_db": 0.22546461570191256, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008444430165469724, "output_power": 0.0012747242125648603, "delta_db": 1.788458865525544, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 6.039141474549642e-05, "output_power": 8.572988609035198e-05, "delta_db": 1.5215704305165012, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 3.556975687019485e-05, "output_power": 4.9302346028280665e-05, "delta_db": 1.417866887969821, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.090392882810899e-05, "output_power": 1.408124945309703e-05, "delta_db": 1.110581840820864, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2355857763199668e-06, "output_power": 1.4705934093303063e-06, "delta_db": 0.7561971509384203, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.0422411240430348e-06, "output_power": 1.1462543808569708e-06, "delta_db": 0.41312803240748475, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.0333239748400784, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 1.6670047074544851, "pitch": null, "output_rms_dbfs": -28.255877393493456, "output_peak": 0.17967242471874667, "reference_rms_dbfs": -29.922882100947945, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.477013209027429}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.9544995595841991, "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"}}, "level": {"reference": {"rms": 0.03190479033407081, "rms_dbfs": -29.922882100947945, "peak": 0.15533447265625, "peak_dbfs": -16.17464305245918, "crest_factor_db": 13.74823904848876, "mean": -8.231268988715278e-07, "zero_energy": false}, "output": {"rms": 0.038655040294898475, "rms_dbfs": -28.255877393493456, "peak": 0.17967242471874667, "peak_dbfs": -14.910371425147455, "crest_factor_db": 13.345505968346005, "mean": 1.3323878401347417e-05, "zero_energy": false}, "rms_difference_db": 1.6670047074544883}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 204, "quiet_samples": 48960, "reference_mean_power": 9.005820816930603e-08, "output_mean_power": 1.5573165377147847e-07, "output_rms_dbfs": -68.07623104444808, "output_zero_energy": false, "output_peak": 0.005290960524131558, "output_energy_fraction": 3.543590689552792e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 314, "output_estimated_voiced_frames": 327, "both_estimated_voiced_frames": 308, "reference_voiced_output_unvoiced_frames": 6, "reference_unvoiced_output_voiced_frames": 19, "paired_voiced_fraction": 0.9808917197452229, "absolute_difference_cents_median": 5.4514012562718674, "absolute_difference_cents_p95": 28.960911491757514, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 2.4323987832622347, "rms_envelope_nrmse": 0.24364689443837056, "envelope_correlation": 0.9882222994921743, "rms_gain_error_db": 1.667137462171766, "reference_mean_power": 0.0010176842474405314, "output_mean_power": 0.0014939181319899842}, "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": 0.0002156662345326274, "reference_active": true, "delta_db": 2.090301168975552}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5932863269435214e-05, "output_power": 2.6676134894993372e-05, "reference_active": true, "delta_db": 2.2382907569495094}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.591650627521311e-06, "output_power": 6.225115572055356e-06, "reference_active": true, "delta_db": 1.321785829459814}], "active_band_count": 3, "active_band_mae_db": 1.8834592517949584}}, {"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": 2.0871033902694833, "rms_envelope_nrmse": 0.2382142363570763, "envelope_correlation": 0.9898357444277714, "rms_gain_error_db": 1.6640567502604944, "reference_mean_power": 0.0010161096570352637, "output_mean_power": 0.0014905489876580105}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.9042638692252314e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00011759425242544186, "output_power": 0.00019573270090566318, "reference_active": true, "delta_db": 2.212772934093069}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 7.519272755909202e-06, "output_power": 1.265921631182529e-05, "reference_active": true, "delta_db": 2.2623098203453464}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.598733053895234e-07, "output_power": 4.5619335016723494e-07, "reference_active": true, "delta_db": 1.0299931753115295}], "active_band_count": 3, "active_band_mae_db": 1.835025309916648}}]}, {"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": 4.667982083652564e-05, "log_rms_mae_db": 2.3154157225602376, "rms_envelope_nrmse": 0.2659407796821359, "envelope_correlation": 0.9904353067917785, "rms_gain_error_db": 1.8596956745084992, "reference_mean_power": 0.0002794511004585033, "output_mean_power": 0.0004288203546150225}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.938593634377073e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.2950751511150254e-05, "output_power": 4.766882284785547e-05, "reference_active": true, "delta_db": 1.6036910338388342}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.807348843301906e-06, "output_power": 5.1124533858633345e-06, "reference_active": true, "delta_db": 1.2800669094454855}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5906604704508287e-06, "output_power": 2.3650281788125872e-06, "reference_active": true, "delta_db": 1.7225883108898965}], "active_band_count": 3, "active_band_mae_db": 1.5354487513914055}}, {"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": 4.25438813129898e-05, "log_rms_mae_db": 2.3244712728070813, "rms_envelope_nrmse": 0.26008770738998793, "envelope_correlation": 0.9922009028163238, "rms_gain_error_db": 1.8566044813395384, "reference_mean_power": 0.0002774218749538236, "output_mean_power": 0.0004254035901005019}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 9.236914065861679e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.9257092980847747e-05, "output_power": 4.2882927830276355e-05, "reference_active": true, "delta_db": 1.6605325721361484}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8979287936807771e-06, "output_power": 2.3586390045249544e-06, "reference_active": true, "delta_db": 0.9438156156169071}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.435917808710527e-08, "output_power": 1.2148100306515352e-07, "reference_active": true, "delta_db": 1.0972421989760173}], "active_band_count": 3, "active_band_mae_db": 1.2338634622430245}}]}, {"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": 1.2496509916302359, "rms_envelope_nrmse": 0.21620514463810056, "envelope_correlation": 0.9855300258097814, "rms_gain_error_db": 1.2459003593079505, "reference_mean_power": 3.509769240032237e-05, "output_mean_power": 4.675936442350991e-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": 1.1733951326113206e-05, "reference_active": true, "delta_db": 0.6051509034709865}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.594184871691995e-06, "output_power": 3.254033258707026e-06, "reference_active": true, "delta_db": 0.9842106508221167}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.354712471534306e-07, "output_power": 5.147442560340102e-07, "reference_active": true, "delta_db": 1.8593620584982749}], "active_band_count": 3, "active_band_mae_db": 1.149574537597126}}, {"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": 1.1565139304381322, "rms_envelope_nrmse": 0.20358664367675594, "envelope_correlation": 0.9883313151285046, "rms_gain_error_db": 1.2474241915272692, "reference_mean_power": 3.5141167460930974e-05, "output_mean_power": 4.683371456011648e-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": 1.1047437729055879e-05, "reference_active": true, "delta_db": 0.6557633804521562}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.126122979707458e-06, "output_power": 1.4495706913597825e-06, "reference_active": true, "delta_db": 1.0965357869783094}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.795751713818223e-08, "output_power": 3.843366035096362e-08, "reference_active": true, "delta_db": 1.3821314804334688}], "active_band_count": 3, "active_band_mae_db": 1.0448102159546448}}]}, {"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": 1.0101884937381447e-05, "log_rms_mae_db": 1.5323582685207842, "rms_envelope_nrmse": 0.21180481383367586, "envelope_correlation": 0.9813312891636793, "rms_gain_error_db": 1.0720381121863056, "reference_mean_power": 6.452617383104311e-06, "output_mean_power": 8.259233131078776e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.152733675321415e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.1017382665662714e-06, "output_power": 2.531839615311475e-06, "reference_active": true, "delta_db": 0.808575593743231}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.306147609644791e-07, "output_power": 5.481198333914967e-07, "reference_active": true, "delta_db": 1.047866042015079}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.161739165108224e-08, "output_power": 1.351773614603043e-07, "reference_active": true, "delta_db": 2.1912125378728895}], "active_band_count": 3, "active_band_mae_db": 1.3492180578770665}}, {"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": 8.618352616189348e-06, "log_rms_mae_db": 1.1928562490544101, "rms_envelope_nrmse": 0.17271890897019643, "envelope_correlation": 0.9907801004751736, "rms_gain_error_db": 1.0677211247897784, "reference_mean_power": 6.45826084166141e-06, "output_mean_power": 8.258243689487658e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.765522812781555e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.8830611185238986e-06, "output_power": 2.2863474930977872e-06, "reference_active": true, "delta_db": 0.8427782166806084}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.7697767264084277e-07, "output_power": 2.3291195526730143e-07, "reference_active": true, "delta_db": 1.1927330167059593}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.816205310457988e-09, "output_power": 1.4884159925116195e-08, "reference_active": true, "delta_db": 1.8078069443438545}], "active_band_count": 3, "active_band_mae_db": 1.281106059243474}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1234628, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9855300258097814, "standard_deviation": null, "minimum": 0.9855300258097814, "maximum": 0.9855300258097814, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.2496509916302359, "standard_deviation": null, "minimum": 1.2496509916302359, "maximum": 1.2496509916302359, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 1.149574537597126, "standard_deviation": null, "minimum": 1.149574537597126, "maximum": 1.149574537597126, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.21620514463810056, "standard_deviation": null, "minimum": 0.21620514463810056, "maximum": 0.21620514463810056, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9883313151285046, "standard_deviation": null, "minimum": 0.9883313151285046, "maximum": 0.9883313151285046, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 1.1565139304381322, "standard_deviation": null, "minimum": 1.1565139304381322, "maximum": 1.1565139304381322, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.0448102159546448, "standard_deviation": null, "minimum": 1.0448102159546448, "maximum": 1.0448102159546448, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.20358664367675594, "standard_deviation": null, "minimum": 0.20358664367675594, "maximum": 0.20358664367675594, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9813312891636793, "standard_deviation": null, "minimum": 0.9813312891636793, "maximum": 0.9813312891636793, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.5323582685207842, "standard_deviation": null, "minimum": 1.5323582685207842, "maximum": 1.5323582685207842, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.3492180578770665, "standard_deviation": null, "minimum": 1.3492180578770665, "maximum": 1.3492180578770665, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.21180481383367586, "standard_deviation": null, "minimum": 0.21180481383367586, "maximum": 0.21180481383367586, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9907801004751736, "standard_deviation": null, "minimum": 0.9907801004751736, "maximum": 0.9907801004751736, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 1.1928562490544101, "standard_deviation": null, "minimum": 1.1928562490544101, "maximum": 1.1928562490544101, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.281106059243474, "standard_deviation": null, "minimum": 1.281106059243474, "maximum": 1.281106059243474, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.17271890897019643, "standard_deviation": null, "minimum": 0.17271890897019643, "maximum": 0.17271890897019643, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9904353067917785, "standard_deviation": null, "minimum": 0.9904353067917785, "maximum": 0.9904353067917785, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.3154157225602376, "standard_deviation": null, "minimum": 2.3154157225602376, "maximum": 2.3154157225602376, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 1.5354487513914055, "standard_deviation": null, "minimum": 1.5354487513914055, "maximum": 1.5354487513914055, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2659407796821359, "standard_deviation": null, "minimum": 0.2659407796821359, "maximum": 0.2659407796821359, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9922009028163238, "standard_deviation": null, "minimum": 0.9922009028163238, "maximum": 0.9922009028163238, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 2.3244712728070813, "standard_deviation": null, "minimum": 2.3244712728070813, "maximum": 2.3244712728070813, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.2338634622430245, "standard_deviation": null, "minimum": 1.2338634622430245, "maximum": 1.2338634622430245, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.26008770738998793, "standard_deviation": null, "minimum": 0.26008770738998793, "maximum": 0.26008770738998793, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 1.0333239748400784, "standard_deviation": null, "minimum": 1.0333239748400784, "maximum": 1.0333239748400784, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 5.477013209027429, "standard_deviation": null, "minimum": 5.477013209027429, "maximum": 5.477013209027429, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.17967242471874667, "standard_deviation": null, "minimum": 0.17967242471874667, "maximum": 0.17967242471874667, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 1.6670047074544851, "standard_deviation": null, "minimum": 1.6670047074544851, "maximum": 1.6670047074544851, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9882222994921743, "standard_deviation": null, "minimum": 0.9882222994921743, "maximum": 0.9882222994921743, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 2.4323987832622347, "standard_deviation": null, "minimum": 2.4323987832622347, "maximum": 2.4323987832622347, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 1.8834592517949584, "standard_deviation": null, "minimum": 1.8834592517949584, "maximum": 1.8834592517949584, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.24364689443837056, "standard_deviation": null, "minimum": 0.24364689443837056, "maximum": 0.24364689443837056, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9898357444277714, "standard_deviation": null, "minimum": 0.9898357444277714, "maximum": 0.9898357444277714, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 2.0871033902694833, "standard_deviation": null, "minimum": 2.0871033902694833, "maximum": 2.0871033902694833, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 1.835025309916648, "standard_deviation": null, "minimum": 1.835025309916648, "maximum": 1.835025309916648, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.2382142363570763, "standard_deviation": null, "minimum": 0.2382142363570763, "maximum": 0.2382142363570763, "valid_count": 1, "planned_count": 1}}, "seconds": 2.391893603002245, "rtf_including_measurement": 0.39864893383370753}, {"case": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "kind": "natural_speech", "method": "hnm", "language": "ja", "style": "whisper", "speaker": "jvs_jvs082", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 3.0797231197357178, "predicted_mos": 3.0797231197357178, "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": "f92d7b6bf4f3dfb7e80146662304b6c8b10724878737d0c040efb925611df4c5", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.2539003109995974}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8727038124540587, "全帯域_10ms_rms_envelope_nrmse": 0.218567587149457, "全帯域_10ms_envelope_correlation": 0.9596901555165053, "全帯域_10ms_modulation_mae_db": 0.6777190395151772, "全帯域_40ms_log_rms_mae_db": 1.0509797291634742, "全帯域_40ms_rms_envelope_nrmse": 0.1203018459450852, "全帯域_40ms_envelope_correlation": 0.9869938475722854, "全帯域_40ms_modulation_mae_db": 0.834984442779482, "300–1000 Hz_10ms_log_rms_mae_db": 2.427969194032196, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.33821941745673134, "300–1000 Hz_10ms_envelope_correlation": 0.9255378209728565, "300–1000 Hz_10ms_modulation_mae_db": 0.9522473202029239, "300–1000 Hz_40ms_log_rms_mae_db": 1.8611856070936952, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2511406913865113, "300–1000 Hz_40ms_envelope_correlation": 0.95850876344338, "300–1000 Hz_40ms_modulation_mae_db": 1.3831692730597942, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5011853722167015, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19284560582725294, "1000–3000 Hz_10ms_envelope_correlation": 0.9781495762935931, "1000–3000 Hz_10ms_modulation_mae_db": 0.2682307420911653, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8939766759080705, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10123603823917823, "1000–3000 Hz_40ms_envelope_correlation": 0.994431639625526, "1000–3000 Hz_40ms_modulation_mae_db": 0.5734198232176705, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3699109306054198, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.26541193829363074, "3000–6000 Hz_10ms_envelope_correlation": 0.9559090202917998, "3000–6000 Hz_10ms_modulation_mae_db": 1.2146036604338215, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8163121910897911, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14339606241908143, "3000–6000 Hz_40ms_envelope_correlation": 0.9874302568968637, "3000–6000 Hz_40ms_modulation_mae_db": 1.6140893731953672, "mr_stft_db": 5.990131325381857, "band_mae_db": 0.5427338854765323, "rms_gain_error_db": 0.241180029341401, "output_peak": 0.0142128428209864}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.895952694172566, "全帯域_10ms_rms_envelope_nrmse": 0.218819299144047, "全帯域_10ms_envelope_correlation": 0.9577824613661486, "全帯域_10ms_modulation_mae_db": 0.7664186937180689, "全帯域_40ms_log_rms_mae_db": 0.9053766377354249, "全帯域_40ms_rms_envelope_nrmse": 0.10003533077969357, "全帯域_40ms_envelope_correlation": 0.990238021004777, "全帯域_40ms_modulation_mae_db": 0.753724767786269, "300–1000 Hz_10ms_log_rms_mae_db": 2.4093583570792516, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3233981930733027, "300–1000 Hz_10ms_envelope_correlation": 0.9298133680580605, "300–1000 Hz_10ms_modulation_mae_db": 0.9248065132088406, "300–1000 Hz_40ms_log_rms_mae_db": 1.766868697017354, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.22924512006622125, "300–1000 Hz_40ms_envelope_correlation": 0.9642182121284791, "300–1000 Hz_40ms_modulation_mae_db": 0.7412635895544466, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4807929806576154, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.22046722891420586, "1000–3000 Hz_10ms_envelope_correlation": 0.969627899884248, "1000–3000 Hz_10ms_modulation_mae_db": 0.8354139836432414, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9210853452399581, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10191780205500858, "1000–3000 Hz_40ms_envelope_correlation": 0.9933744085192169, "1000–3000 Hz_40ms_modulation_mae_db": 0.881443163431856, "3000–6000 Hz_10ms_log_rms_mae_db": 1.378952863903743, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.25790593474967305, "3000–6000 Hz_10ms_envelope_correlation": 0.9609034190762524, "3000–6000 Hz_10ms_modulation_mae_db": 1.1795657389455598, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7645909846494843, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12600899938637714, "3000–6000 Hz_40ms_envelope_correlation": 0.9906304719426007, "3000–6000 Hz_40ms_modulation_mae_db": 1.2048026474410463, "mr_stft_db": 5.986977955452932, "band_mae_db": 0.6820402354510249, "rms_gain_error_db": 0.015699850602223266, "output_peak": 0.0130321291132412}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8278690311936976, "全帯域_10ms_rms_envelope_nrmse": 0.21758303647561975, "全帯域_10ms_envelope_correlation": 0.9579221899047187, "全帯域_10ms_modulation_mae_db": 0.36952332748042904, "全帯域_40ms_log_rms_mae_db": 0.9616923511686065, "全帯域_40ms_rms_envelope_nrmse": 0.11086384258222903, "全帯域_40ms_envelope_correlation": 0.9880072662229914, "全帯域_40ms_modulation_mae_db": 0.7062497741007095, "300–1000 Hz_10ms_log_rms_mae_db": 2.3597774327900933, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.31180610578203505, "300–1000 Hz_10ms_envelope_correlation": 0.9246368311519164, "300–1000 Hz_10ms_modulation_mae_db": 1.1061743231263634, "300–1000 Hz_40ms_log_rms_mae_db": 1.6705810945659505, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1950062439503206, "300–1000 Hz_40ms_envelope_correlation": 0.9690110891100848, "300–1000 Hz_40ms_modulation_mae_db": 2.1351884898051705, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4802667045084215, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21304991090176545, "1000–3000 Hz_10ms_envelope_correlation": 0.9717679006204448, "1000–3000 Hz_10ms_modulation_mae_db": 0.3139616892272825, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8768585171715101, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09264547941912461, "1000–3000 Hz_40ms_envelope_correlation": 0.9946237052461109, "1000–3000 Hz_40ms_modulation_mae_db": 0.5938080689784887, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3387674384048498, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.27312337509223045, "3000–6000 Hz_10ms_envelope_correlation": 0.9530046008093077, "3000–6000 Hz_10ms_modulation_mae_db": 1.0791125139728375, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8151060043441363, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13392527722581496, "3000–6000 Hz_40ms_envelope_correlation": 0.9883637833587894, "3000–6000 Hz_40ms_modulation_mae_db": 1.7758917007837198, "mr_stft_db": 6.001171849823078, "band_mae_db": 0.4150022937873804, "rms_gain_error_db": -0.03830718713800139, "output_peak": 0.014584935221625716}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7862802296273974, "全帯域_10ms_rms_envelope_nrmse": 0.2071672116236183, "全帯域_10ms_envelope_correlation": 0.9617497497809273, "全帯域_10ms_modulation_mae_db": 0.5521932708402564, "全帯域_40ms_log_rms_mae_db": 0.8972583289591894, "全帯域_40ms_rms_envelope_nrmse": 0.09600520577306562, "全帯域_40ms_envelope_correlation": 0.991134142061362, "全帯域_40ms_modulation_mae_db": 0.7193272628541201, "300–1000 Hz_10ms_log_rms_mae_db": 2.5235489211699975, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.32065468922653284, "300–1000 Hz_10ms_envelope_correlation": 0.9297269024049477, "300–1000 Hz_10ms_modulation_mae_db": 0.808562304360153, "300–1000 Hz_40ms_log_rms_mae_db": 1.9421242419328588, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.21212038552832907, "300–1000 Hz_40ms_envelope_correlation": 0.9697893316385087, "300–1000 Hz_40ms_modulation_mae_db": 1.1940413454384282, "1000–3000 Hz_10ms_log_rms_mae_db": 1.487701944925784, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20467346440227702, "1000–3000 Hz_10ms_envelope_correlation": 0.973077406874812, "1000–3000 Hz_10ms_modulation_mae_db": 0.5168558724520526, "1000–3000 Hz_40ms_log_rms_mae_db": 0.836875982672147, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09310492146733335, "1000–3000 Hz_40ms_envelope_correlation": 0.9943819001412287, "1000–3000 Hz_40ms_modulation_mae_db": 0.44887933253755086, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3448687723358868, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2614717811195044, "3000–6000 Hz_10ms_envelope_correlation": 0.9570796000483116, "3000–6000 Hz_10ms_modulation_mae_db": 1.2447154017905864, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8052622022603275, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13016107069241137, "3000–6000 Hz_40ms_envelope_correlation": 0.9889381925818705, "3000–6000 Hz_40ms_modulation_mae_db": 1.7304899730925811, "mr_stft_db": 5.977090204084906, "band_mae_db": 0.44822341914917513, "rms_gain_error_db": -0.09176628713818644, "output_peak": 0.013886249421811752}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7784930466920528, "全帯域_10ms_rms_envelope_nrmse": 0.18951381283030028, "全帯域_10ms_envelope_correlation": 0.9685761730541468, "全帯域_10ms_modulation_mae_db": 0.6292149524353307, "全帯域_40ms_log_rms_mae_db": 0.8838863174209466, "全帯域_40ms_rms_envelope_nrmse": 0.09565131168917182, "全帯域_40ms_envelope_correlation": 0.9914822225840643, "全帯域_40ms_modulation_mae_db": 0.9812922098658277, "300–1000 Hz_10ms_log_rms_mae_db": 2.498243987999531, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3026339304770349, "300–1000 Hz_10ms_envelope_correlation": 0.9313227994033415, "300–1000 Hz_10ms_modulation_mae_db": 0.8865226068456007, "300–1000 Hz_40ms_log_rms_mae_db": 1.8498033624287333, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.18210531392407303, "300–1000 Hz_40ms_envelope_correlation": 0.9752098540334523, "300–1000 Hz_40ms_modulation_mae_db": 1.1023961821248063, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4721063749629117, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.16394884484230557, "1000–3000 Hz_10ms_envelope_correlation": 0.9829127111638959, "1000–3000 Hz_10ms_modulation_mae_db": 0.4516794277407374, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8647097873961174, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07830446247656635, "1000–3000 Hz_40ms_envelope_correlation": 0.9960227145685524, "1000–3000 Hz_40ms_modulation_mae_db": 0.8987936229871162, "3000–6000 Hz_10ms_log_rms_mae_db": 1.348629504600642, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2900566168913495, "3000–6000 Hz_10ms_envelope_correlation": 0.9470619067314209, "3000–6000 Hz_10ms_modulation_mae_db": 1.0245432304061544, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8081639690104239, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.16171715154384905, "3000–6000 Hz_40ms_envelope_correlation": 0.984343493414105, "3000–6000 Hz_40ms_modulation_mae_db": 1.6967838130964044, "mr_stft_db": 5.987718653782454, "band_mae_db": 0.41110344320650594, "rms_gain_error_db": 0.04309889891056988, "output_peak": 0.014561388374899615}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8682399078013427, "全帯域_10ms_rms_envelope_nrmse": 0.2109418219837846, "全帯域_10ms_envelope_correlation": 0.9620583555708101, "全帯域_10ms_modulation_mae_db": 0.6129892388331157, "全帯域_40ms_log_rms_mae_db": 0.9148788740682018, "全帯域_40ms_rms_envelope_nrmse": 0.09878327490424811, "全帯域_40ms_envelope_correlation": 0.9912288995335615, "全帯域_40ms_modulation_mae_db": 0.6891112933999805, "300–1000 Hz_10ms_log_rms_mae_db": 2.475053683619952, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.36375424353165, "300–1000 Hz_10ms_envelope_correlation": 0.894959971715011, "300–1000 Hz_10ms_modulation_mae_db": 0.8664646481191468, "300–1000 Hz_40ms_log_rms_mae_db": 1.871249892506632, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.21589820829971332, "300–1000 Hz_40ms_envelope_correlation": 0.9608476991709761, "300–1000 Hz_40ms_modulation_mae_db": 1.328181367832227, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4970904673959353, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.22002675415551431, "1000–3000 Hz_10ms_envelope_correlation": 0.9720022088307112, "1000–3000 Hz_10ms_modulation_mae_db": 0.5187075572428099, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9191000938597589, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.11523449808262785, "1000–3000 Hz_40ms_envelope_correlation": 0.9930699151710395, "1000–3000 Hz_40ms_modulation_mae_db": 0.7809804884139947, "3000–6000 Hz_10ms_log_rms_mae_db": 1.32357534786438, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2859955998783874, "3000–6000 Hz_10ms_envelope_correlation": 0.9483531050521922, "3000–6000 Hz_10ms_modulation_mae_db": 1.0936465924890608, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7833107068718406, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1547904917437345, "3000–6000 Hz_40ms_envelope_correlation": 0.9852299509482348, "3000–6000 Hz_40ms_modulation_mae_db": 1.7596453287041094, "mr_stft_db": 5.982482146765448, "band_mae_db": 0.46967595663156364, "rms_gain_error_db": 0.20269368104115104, "output_peak": 0.013931117578737582}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8464762100484335, "全帯域_10ms_rms_envelope_nrmse": 0.21770733016107416, "全帯域_10ms_envelope_correlation": 0.9596242660981784, "全帯域_10ms_modulation_mae_db": 0.4597265465311507, "全帯域_40ms_log_rms_mae_db": 0.9427099108102183, "全帯域_40ms_rms_envelope_nrmse": 0.10152653018089786, "全帯域_40ms_envelope_correlation": 0.9907052613001511, "全帯域_40ms_modulation_mae_db": 0.5733700815508178, "300–1000 Hz_10ms_log_rms_mae_db": 2.4849906890948468, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3288492368293042, "300–1000 Hz_10ms_envelope_correlation": 0.9189517915411228, "300–1000 Hz_10ms_modulation_mae_db": 1.0654615426894631, "300–1000 Hz_40ms_log_rms_mae_db": 1.8004180638839165, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.2040936783722721, "300–1000 Hz_40ms_envelope_correlation": 0.9675692244779022, "300–1000 Hz_40ms_modulation_mae_db": 1.2093367017124732, "1000–3000 Hz_10ms_log_rms_mae_db": 1.464429992967691, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20158186272280101, "1000–3000 Hz_10ms_envelope_correlation": 0.9741699124540125, "1000–3000 Hz_10ms_modulation_mae_db": 0.6251385526989509, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8591665393587595, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10011461102718862, "1000–3000 Hz_40ms_envelope_correlation": 0.993469648534473, "1000–3000 Hz_40ms_modulation_mae_db": 0.2542250063033099, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3273328035422567, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2568946209691946, "3000–6000 Hz_10ms_envelope_correlation": 0.9591514877489064, "3000–6000 Hz_10ms_modulation_mae_db": 1.000767453864128, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7790102106886764, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13550932765994708, "3000–6000 Hz_40ms_envelope_correlation": 0.987823767970959, "3000–6000 Hz_40ms_modulation_mae_db": 1.4441636221107446, "mr_stft_db": 5.997713017393511, "band_mae_db": 0.4014157853507307, "rms_gain_error_db": 0.20524183622209263, "output_peak": 0.014722188679734773}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.8307136737141962, "全帯域_10ms_rms_envelope_nrmse": 0.2057308912939898, "全帯域_10ms_envelope_correlation": 0.9628682238126497, "全帯域_10ms_modulation_mae_db": 0.6253237033242578, "全帯域_40ms_log_rms_mae_db": 0.9108097967358347, "全帯域_40ms_rms_envelope_nrmse": 0.09838558013210602, "全帯域_40ms_envelope_correlation": 0.9907430234199279, "全帯域_40ms_modulation_mae_db": 0.7612252032502536, "300–1000 Hz_10ms_log_rms_mae_db": 2.506745294141674, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.2919075546178638, "300–1000 Hz_10ms_envelope_correlation": 0.9402012129072197, "300–1000 Hz_10ms_modulation_mae_db": 0.7686345312028634, "300–1000 Hz_40ms_log_rms_mae_db": 1.9343993755761573, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.18514231291528135, "300–1000 Hz_40ms_envelope_correlation": 0.9766774494584365, "300–1000 Hz_40ms_modulation_mae_db": 0.7728562617699071, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5138112812389388, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20527726351960143, "1000–3000 Hz_10ms_envelope_correlation": 0.9730399883165152, "1000–3000 Hz_10ms_modulation_mae_db": 0.6481265065363041, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9392022168192011, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10135746378762875, "1000–3000 Hz_40ms_envelope_correlation": 0.9933312799763878, "1000–3000 Hz_40ms_modulation_mae_db": 0.8278678049400207, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3433906864515086, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.27634711598134315, "3000–6000 Hz_10ms_envelope_correlation": 0.9559837250182567, "3000–6000 Hz_10ms_modulation_mae_db": 1.2904726901597294, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8050058773317503, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1434185034650455, "3000–6000 Hz_40ms_envelope_correlation": 0.9883496754864, "3000–6000 Hz_40ms_modulation_mae_db": 1.7287440738264994, "mr_stft_db": 5.98821185994683, "band_mae_db": 0.5963330214051021, "rms_gain_error_db": 0.05844640451323976, "output_peak": 0.012678975085482384}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 6.210105750152133, "spectral_convergence": 0.6994016274588687, "spectral_convergence_status": "ok", "amplitude_floor": 3.772168230462137e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 5.851742132957514, "spectral_convergence": 0.6431565377918914, "spectral_convergence_status": "ok", "amplitude_floor": 1.9872090073495523e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 5.908546093035926, "spectral_convergence": 0.6780904674780273, "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": 1.0873924052055522e-07, "delta_db": 0.2656343958306697, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 3.789702976182104e-08, "output_power": 5.212650518821403e-08, "delta_db": 1.3845343590896366, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.1288069701978556e-08, "output_power": 5.5449732103272173e-08, "delta_db": 0.3388309816931915, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.8766557699122943e-07, "output_power": 2.9964724257604113e-07, "delta_db": 0.17722389677732076, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 6.379889954922647e-08, "output_power": 7.43427499485035e-08, "delta_db": 0.6642543391701017, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 5.958002892412794e-08, "output_power": 5.078865069123087e-08, "delta_db": -0.6933403469145705, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.518375636706213e-08, "output_power": 3.302252798018779e-08, "delta_db": -0.27531887886023554, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.5427338854765323, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.241180029341401, "pitch": null, "output_rms_dbfs": -61.71264946733014, "output_peak": 0.0142128428209864, "reference_rms_dbfs": -61.95382949667153, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.990131325381857}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.4667161659974341, "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"}}, "level": {"reference": {"rms": 0.0007985617884541367, "rms_dbfs": -61.95382949667153, "peak": 0.0279541015625, "peak_dbfs": -31.071089225837348, "crest_factor_db": 30.882740270834184, "mean": -4.7323438856336806e-07, "zero_energy": false}, "output": {"rms": 0.0008210460699668472, "rms_dbfs": -61.71264946733014, "peak": 0.0142128428209864, "peak_dbfs": -36.94638093548848, "crest_factor_db": 24.76626853184165, "mean": -1.2964320251931726e-05, "zero_energy": false}, "rms_difference_db": 0.24118002934139326}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 530, "quiet_samples": 127200, "reference_mean_power": 1.6852030852727545e-07, "output_mean_power": 1.963633553416923e-07, "output_rms_dbfs": -67.06939555539718, "output_zero_energy": false, "output_peak": 0.004334894507333303, "output_energy_fraction": 0.25730605745124563, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 0, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 1.8727038124540587, "rms_envelope_nrmse": 0.218567587149457, "envelope_correlation": 0.9596901555165053, "rms_gain_error_db": 0.24117713239291133, "reference_mean_power": 6.381840334285008e-07, "output_mean_power": 6.746268899260045e-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": 4.664860525585169e-08, "reference_active": true, "delta_db": -0.6119363239411134}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8108171988414046e-08, "output_power": 2.0041435323693542e-08, "reference_active": true, "delta_db": 0.4405421082866934}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5077869163047108e-08, "output_power": 1.2030179344705618e-08, "reference_active": true, "delta_db": -0.9806786863177253}], "active_band_count": 3, "active_band_mae_db": 0.6777190395151772}}, {"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": 1.0509797291634742, "rms_envelope_nrmse": 0.1203018459450852, "envelope_correlation": 0.9869938475722854, "rms_gain_error_db": 0.24113673472922365, "reference_mean_power": 6.411560082425094e-07, "output_mean_power": 6.777622718584724e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.6310662622414218e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.1382633554527724e-08, "output_power": 4.3071857506904016e-08, "reference_active": true, "delta_db": -0.7662275828818095}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.770301277631505e-09, "output_power": 1.0174224106491508e-08, "reference_active": true, "delta_db": 0.17593343698945768}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.622703760150781e-10, "output_power": 6.714565043717791e-10, "reference_active": true, "delta_db": -1.562792308467179}], "active_band_count": 3, "active_band_mae_db": 0.834984442779482}}]}, {"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": 2.2104964131872056e-06, "log_rms_mae_db": 2.427969194032196, "rms_envelope_nrmse": 0.33821941745673134, "envelope_correlation": 0.9255378209728565, "rms_gain_error_db": 0.9299521664321222, "reference_mean_power": 5.8846313595735504e-08, "output_mean_power": 7.289780950512557e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.019969626272196e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.669218221395936e-09, "output_power": 6.716388818031537e-09, "reference_active": true, "delta_db": 0.7361265559010366}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.997554044063298e-09, "output_power": 4.932495236156731e-09, "reference_active": true, "delta_db": -0.05690824841377595}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.156278331683378e-09, "output_power": 3.2060156391919294e-09, "reference_active": true, "delta_db": -2.063707156293959}], "active_band_count": 3, "active_band_mae_db": 0.9522473202029239}}, {"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": 1.1954716835574719e-06, "log_rms_mae_db": 1.8611856070936952, "rms_envelope_nrmse": 0.2511406913865113, "envelope_correlation": 0.95850876344338, "rms_gain_error_db": 0.9294974514260164, "reference_mean_power": 5.9130565750138855e-08, "output_mean_power": 7.324226721204327e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.6907038028137213e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.9716031414726236e-09, "output_power": 7.07480835583678e-09, "reference_active": true, "delta_db": 0.06382023151988453}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1694216774888575e-09, "output_power": 2.483072865629676e-09, "reference_active": true, "delta_db": -1.0599055989986588}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5180140726512645e-10, "output_power": 2.2509683078065516e-10, "reference_active": true, "delta_db": -3.0257819886608397}], "active_band_count": 3, "active_band_mae_db": 1.3831692730597942}}]}, {"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": 1.5011853722167015, "rms_envelope_nrmse": 0.19284560582725294, "envelope_correlation": 0.9781495762935931, "rms_gain_error_db": 0.33610146576431266, "reference_mean_power": 3.0019112356646434e-07, "output_mean_power": 3.2434558665921074e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.170424846915179e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.917571308133626e-08, "output_power": 4.3347746182901595e-08, "reference_active": true, "delta_db": -0.5478414445462978}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.373644839895842e-09, "output_power": 6.2916981774320735e-09, "reference_active": true, "delta_db": -0.056199788510671596}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.9583662339560916e-09, "output_power": 3.779643807482835e-09, "reference_active": true, "delta_db": -0.2006509932165265}], "active_band_count": 3, "active_band_mae_db": 0.2682307420911653}}, {"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": 0.8939766759080705, "rms_envelope_nrmse": 0.10123603823917823, "envelope_correlation": 0.994431639625526, "rms_gain_error_db": 0.3360940134873785, "reference_mean_power": 3.016958800523271e-07, "output_mean_power": 3.2597086194188195e-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": 3.9910009155520514e-08, "reference_active": true, "delta_db": -0.561512733798275}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.58988056021656e-09, "output_power": 3.6701484952211825e-09, "reference_active": true, "delta_db": 0.09603636980134955}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0107624253076597e-10, "output_power": 2.357248948814489e-10, "reference_active": true, "delta_db": -1.0627103660533868}], "active_band_count": 3, "active_band_mae_db": 0.5734198232176705}}]}, {"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": 2.0353597876361005e-06, "log_rms_mae_db": 1.3699109306054198, "rms_envelope_nrmse": 0.26541193829363074, "envelope_correlation": 0.9559090202917998, "rms_gain_error_db": -0.39303919597930453, "reference_mean_power": 5.358047115055495e-08, "output_mean_power": 4.8944354880048384e-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": 5.2466604070258305e-09, "output_power": 5.695483639016939e-09, "reference_active": true, "delta_db": 0.3564765347317618}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.042126892400445e-09, "output_power": 3.236766835635868e-09, "reference_active": true, "delta_db": 0.26934090335213545}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.4881774270193605e-09, "output_power": 1.2418867441997822e-09, "reference_active": true, "delta_db": -3.017993543217567}], "active_band_count": 3, "active_band_mae_db": 1.2146036604338215}}, {"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": 1.4732086031870809e-06, "log_rms_mae_db": 0.8163121910897911, "rms_envelope_nrmse": 0.14339606241908143, "envelope_correlation": 0.9874302568968637, "rms_gain_error_db": -0.3930701520341076, "reference_mean_power": 5.38474224114617e-08, "output_mean_power": 4.9187857247122896e-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": 6.316794721929926e-09, "output_power": 6.291275573290571e-09, "reference_active": true, "delta_db": -0.01758055009504415}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0867827772247913e-09, "output_power": 1.7407532627389142e-09, "reference_active": true, "delta_db": -0.787400258590857}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.2900642849732045e-10, "output_power": 9.03896995052109e-11, "reference_active": true, "delta_db": -4.037287310900201}], "active_band_count": 3, "active_band_mae_db": 1.6140893731953672}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.974343450554779, "standard_deviation": 0.004235936476090487, "minimum": 0.969627899884248, "maximum": 0.9829127111638959, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4871731398592498, "standard_deviation": 0.01620065989721992, "minimum": 1.464429992967691, "maximum": 1.5138112812389388, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.522264291454068, "standard_deviation": 0.18417161374513352, "minimum": 0.2682307420911653, "maximum": 0.8354139836432414, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.20273386691071546, "standard_deviation": 0.01825826819875447, "minimum": 0.16394884484230557, "maximum": 0.22046722891420586, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9940881514728168, "standard_deviation": 0.0009809076790426856, "minimum": 0.9930699151710395, "maximum": 0.9960227145685524, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8888718948031904, "standard_deviation": 0.03550606026441351, "minimum": 0.836875982672147, "maximum": 0.9392022168192011, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.6574271638512509, "standard_deviation": 0.22988356435342858, "minimum": 0.2542250063033099, "maximum": 0.8987936229871162, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09798940956933205, "standard_deviation": 0.010550146708800537, "minimum": 0.07830446247656635, "maximum": 0.11523449808262785, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.954680858097056, "standard_deviation": 0.00490721508403578, "minimum": 0.9470619067314209, "maximum": 0.9609034190762524, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.3469285434635858, "standard_deviation": 0.019158616040294663, "minimum": 1.32357534786438, "maximum": 1.378952863903743, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.1409284102577346, "standard_deviation": 0.10643810812644451, "minimum": 1.000767453864128, "maximum": 1.2904726901597294, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2709008728719141, "standard_deviation": 0.01261220540195515, "minimum": 0.2568946209691946, "maximum": 0.2900566168913495, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9876386990749779, "standard_deviation": 0.002014546012861129, "minimum": 0.984343493414105, "maximum": 0.9906304719426007, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7970952682808038, "standard_deviation": 0.018970207143788168, "minimum": 0.7645909846494843, "maximum": 0.8163121910897911, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.619326316531309, "standard_deviation": 0.19895106360868836, "minimum": 1.2048026474410463, "maximum": 1.7758917007837198, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.14111586051703262, "standard_deviation": 0.01226651998901348, "minimum": 0.12600899938637714, "maximum": 0.16171715154384905, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9243938372693096, "standard_deviation": 0.013379262132340633, "minimum": 0.894959971715011, "maximum": 0.9402012129072197, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.460710944990943, "standard_deviation": 0.05627535164692842, "minimum": 2.3597774327900933, "maximum": 2.5235489211699975, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.9223592237194194, "standard_deviation": 0.11720253449069978, "minimum": 0.7686345312028634, "maximum": 1.1061743231263634, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.32265292137430684, "standard_deviation": 0.022162607351223062, "minimum": 0.2919075546178638, "maximum": 0.36375424353165, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9677289529326525, "standard_deviation": 0.0063991390789806726, "minimum": 0.95850876344338, "maximum": 0.9766774494584365, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.8370787918756624, "standard_deviation": 0.08977074734320767, "minimum": 1.6705810945659505, "maximum": 1.9421242419328588, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.2333041514121565, "standard_deviation": 0.4339561658757243, "minimum": 0.7412635895544466, "maximum": 2.1351884898051705, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.20934399430534023, "standard_deviation": 0.023159350954424278, "minimum": 0.18210531392407303, "maximum": 0.2511406913865113, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.4958160050572519, "standard_deviation": 0.10180601580214488, "minimum": 0.4014157853507307, "maximum": 0.6820402354510249, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.988937126578877, "standard_deviation": 0.007708957677806275, "minimum": 5.977090204084906, "maximum": 6.001171849823078, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.013951228287064927, "standard_deviation": 0.0007468696670485962, "minimum": 0.012678975085482384, "maximum": 0.014722188679734773, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": 0.07953590329431123, "standard_deviation": 0.1231593286058614, "minimum": -0.09176628713818644, "maximum": 0.241180029341401, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9612839468880106, "standard_deviation": 0.003492025591249987, "minimum": 0.9577824613661486, "maximum": 0.9685761730541468, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.8383410757129681, "standard_deviation": 0.041265648251429456, "minimum": 1.7784930466920528, "maximum": 1.895952694172566, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.5866385965847233, "standard_deviation": 0.1248154977272027, "minimum": 0.36952332748042904, "maximum": 0.7664186937180689, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.21075387383273636, "standard_deviation": 0.0100737511373643, "minimum": 0.18951381283030028, "maximum": 0.218819299144047, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.99006658546239, "standard_deviation": 0.0016506301266350858, "minimum": 0.9869938475722854, "maximum": 0.9914822225840643, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.9334489932577371, "standard_deviation": 0.05359715937496041, "minimum": 0.8838863174209466, "maximum": 1.0509797291634742, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.7524106294484325, "standard_deviation": 0.11866657588179837, "minimum": 0.5733700815508178, "maximum": 0.9812922098658277, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.10269411524831215, "standard_deviation": 0.008564125789143184, "minimum": 0.09565131168917182, "maximum": 0.1203018459450852, "valid_count": 8, "planned_count": 8}}, "seconds": 7.050257950999367, "rtf_including_measurement": 1.1750429918332277}, {"case": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "kind": "natural_speech", "method": "candidate", "language": "ja", "style": "whisper", "speaker": "jvs_jvs082", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 2.8367221355438232, "predicted_mos": 2.8367221355438232, "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": 3.214749839004071}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7970231990323762, "全帯域_10ms_rms_envelope_nrmse": 0.20203205345195271, "全帯域_10ms_envelope_correlation": 0.9650210066990967, "全帯域_10ms_modulation_mae_db": 0.5626225600262263, "全帯域_40ms_log_rms_mae_db": 1.0083383783659432, "全帯域_40ms_rms_envelope_nrmse": 0.11169244568299765, "全帯域_40ms_envelope_correlation": 0.9883433382975486, "全帯域_40ms_modulation_mae_db": 0.6701611298690265, "300–1000 Hz_10ms_log_rms_mae_db": 2.3899944005262266, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3255071927799192, "300–1000 Hz_10ms_envelope_correlation": 0.9296447488305785, "300–1000 Hz_10ms_modulation_mae_db": 0.8950807648885863, "300–1000 Hz_40ms_log_rms_mae_db": 1.820134694839936, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.240638392936322, "300–1000 Hz_40ms_envelope_correlation": 0.9608508619850852, "300–1000 Hz_40ms_modulation_mae_db": 1.3071922667898954, "1000–3000 Hz_10ms_log_rms_mae_db": 1.459132751226194, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18489945932562282, "1000–3000 Hz_10ms_envelope_correlation": 0.9793769110817069, "1000–3000 Hz_10ms_modulation_mae_db": 0.270059465713836, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8912879165395872, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09908270449144034, "1000–3000 Hz_40ms_envelope_correlation": 0.9942122579172197, "1000–3000 Hz_40ms_modulation_mae_db": 0.4419674388308277, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3108086877845293, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24225837447838078, "3000–6000 Hz_10ms_envelope_correlation": 0.9635461780038665, "3000–6000 Hz_10ms_modulation_mae_db": 0.928251567677291, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7929704718053812, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14415254716305007, "3000–6000 Hz_40ms_envelope_correlation": 0.9872872226748816, "3000–6000 Hz_40ms_modulation_mae_db": 1.3877276470028599, "mr_stft_db": 5.965629876950996, "band_mae_db": 0.48332929181552603, "rms_gain_error_db": 0.13159276812373974, "output_peak": 0.01424913917589817}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.85296740140075, "全帯域_10ms_rms_envelope_nrmse": 0.20632950460507882, "全帯域_10ms_envelope_correlation": 0.9624997350676024, "全帯域_10ms_modulation_mae_db": 0.6065641760711912, "全帯域_40ms_log_rms_mae_db": 0.8891890031780247, "全帯域_40ms_rms_envelope_nrmse": 0.09738529013095301, "全帯域_40ms_envelope_correlation": 0.9908292968264364, "全帯域_40ms_modulation_mae_db": 0.49236016438521374, "300–1000 Hz_10ms_log_rms_mae_db": 2.307366665882433, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.29138167688771116, "300–1000 Hz_10ms_envelope_correlation": 0.9420215675743435, "300–1000 Hz_10ms_modulation_mae_db": 0.7197455596841005, "300–1000 Hz_40ms_log_rms_mae_db": 1.6519831468693602, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20366401067321926, "300–1000 Hz_40ms_envelope_correlation": 0.9712423611231146, "300–1000 Hz_40ms_modulation_mae_db": 0.5929926864180687, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4154636281717057, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.21496823822642064, "1000–3000 Hz_10ms_envelope_correlation": 0.9710730440019586, "1000–3000 Hz_10ms_modulation_mae_db": 0.7579256620895537, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8994334567795252, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10018179748496574, "1000–3000 Hz_40ms_envelope_correlation": 0.9935519681247977, "1000–3000 Hz_40ms_modulation_mae_db": 0.7390324975822763, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3106705885746222, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.22376536461869617, "3000–6000 Hz_10ms_envelope_correlation": 0.9698550772489889, "3000–6000 Hz_10ms_modulation_mae_db": 0.8394857716648579, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7437572571033766, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12017942462562843, "3000–6000 Hz_40ms_envelope_correlation": 0.9908771637667658, "3000–6000 Hz_40ms_modulation_mae_db": 0.8855054893576222, "mr_stft_db": 5.960646826848451, "band_mae_db": 0.6914160210900953, "rms_gain_error_db": -0.06483002293665008, "output_peak": 0.01348450375585317}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7709324491263179, "全帯域_10ms_rms_envelope_nrmse": 0.19660415863665304, "全帯域_10ms_envelope_correlation": 0.965718275336261, "全帯域_10ms_modulation_mae_db": 0.31732536176250803, "全帯域_40ms_log_rms_mae_db": 0.9604347382338796, "全帯域_40ms_rms_envelope_nrmse": 0.10486163948666374, "全帯域_40ms_envelope_correlation": 0.9892452189321969, "全帯域_40ms_modulation_mae_db": 0.5528710619790972, "300–1000 Hz_10ms_log_rms_mae_db": 2.3215207062832355, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3022534569608876, "300–1000 Hz_10ms_envelope_correlation": 0.9284168432012067, "300–1000 Hz_10ms_modulation_mae_db": 1.0193027503042131, "300–1000 Hz_40ms_log_rms_mae_db": 1.6547428258932044, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20872624650748017, "300–1000 Hz_40ms_envelope_correlation": 0.9629468987471241, "300–1000 Hz_40ms_modulation_mae_db": 2.030153464710023, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4134457517960082, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20272946788496785, "1000–3000 Hz_10ms_envelope_correlation": 0.9745099748585235, "1000–3000 Hz_10ms_modulation_mae_db": 0.39175333156123443, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8608670379040028, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09191364797955297, "1000–3000 Hz_40ms_envelope_correlation": 0.9947223070788261, "1000–3000 Hz_40ms_modulation_mae_db": 0.4750227890559735, "3000–6000 Hz_10ms_log_rms_mae_db": 1.28241870098686, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.24896287811702755, "3000–6000 Hz_10ms_envelope_correlation": 0.9610518562723368, "3000–6000 Hz_10ms_modulation_mae_db": 0.8679560189509791, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7787987947315376, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.12843457356085794, "3000–6000 Hz_40ms_envelope_correlation": 0.9896110833834716, "3000–6000 Hz_40ms_modulation_mae_db": 1.5215315932653988, "mr_stft_db": 5.977113707851582, "band_mae_db": 0.40083112038916674, "rms_gain_error_db": -0.07065686202382933, "output_peak": 0.018040455796409963}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7181081536087883, "全帯域_10ms_rms_envelope_nrmse": 0.20181056226576488, "全帯域_10ms_envelope_correlation": 0.9637496037695265, "全帯域_10ms_modulation_mae_db": 0.441406630678582, "全帯域_40ms_log_rms_mae_db": 0.8949479583446649, "全帯域_40ms_rms_envelope_nrmse": 0.10239920241217738, "全帯域_40ms_envelope_correlation": 0.9898101044050167, "全帯域_40ms_modulation_mae_db": 0.5397343923389569, "300–1000 Hz_10ms_log_rms_mae_db": 2.4329304041188724, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3040234141859958, "300–1000 Hz_10ms_envelope_correlation": 0.9372048239889764, "300–1000 Hz_10ms_modulation_mae_db": 0.6449818185138719, "300–1000 Hz_40ms_log_rms_mae_db": 1.8637973750019563, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.21328701912099926, "300–1000 Hz_40ms_envelope_correlation": 0.9688845255806187, "300–1000 Hz_40ms_modulation_mae_db": 1.0421689188171153, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4416733986102626, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.19834814253914226, "1000–3000 Hz_10ms_envelope_correlation": 0.9747062219943702, "1000–3000 Hz_10ms_modulation_mae_db": 0.5978418892507812, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7969513928583369, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10255909202497095, "1000–3000 Hz_40ms_envelope_correlation": 0.9933507145316492, "1000–3000 Hz_40ms_modulation_mae_db": 0.3296915278163413, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3060068773553644, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.22798526164229554, "3000–6000 Hz_10ms_envelope_correlation": 0.9674809546963294, "3000–6000 Hz_10ms_modulation_mae_db": 0.963676496101087, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7902806097259925, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11740356171207847, "3000–6000 Hz_40ms_envelope_correlation": 0.9910602627209578, "3000–6000 Hz_40ms_modulation_mae_db": 1.3901227217730305, "mr_stft_db": 5.951465727676973, "band_mae_db": 0.40589609798609316, "rms_gain_error_db": -0.12683282439523674, "output_peak": 0.013869141401446837}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7097152039616834, "全帯域_10ms_rms_envelope_nrmse": 0.17589030376840983, "全帯域_10ms_envelope_correlation": 0.972721111828769, "全帯域_10ms_modulation_mae_db": 0.43635618384802005, "全帯域_40ms_log_rms_mae_db": 0.8451025657909458, "全帯域_40ms_rms_envelope_nrmse": 0.08691488900252033, "全帯域_40ms_envelope_correlation": 0.9926558103853329, "全帯域_40ms_modulation_mae_db": 0.7231712505493763, "300–1000 Hz_10ms_log_rms_mae_db": 2.4371731475887985, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.29838683584554704, "300–1000 Hz_10ms_envelope_correlation": 0.9321532527674017, "300–1000 Hz_10ms_modulation_mae_db": 0.742667741181442, "300–1000 Hz_40ms_log_rms_mae_db": 1.8119075844235586, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.19218337462504634, "300–1000 Hz_40ms_envelope_correlation": 0.9709456953179346, "300–1000 Hz_40ms_modulation_mae_db": 0.9014527685758624, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4075095256595063, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.15280941617605856, "1000–3000 Hz_10ms_envelope_correlation": 0.9850938120595825, "1000–3000 Hz_10ms_modulation_mae_db": 0.3704364444216624, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8335780621729164, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07591198995495646, "1000–3000 Hz_40ms_envelope_correlation": 0.9962580378478231, "1000–3000 Hz_40ms_modulation_mae_db": 0.7625384440800499, "3000–6000 Hz_10ms_log_rms_mae_db": 1.280761760565417, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.2616864530069785, "3000–6000 Hz_10ms_envelope_correlation": 0.9575121004270206, "3000–6000 Hz_10ms_modulation_mae_db": 0.7166507942959456, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7887902399045856, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.15281590944459397, "3000–6000 Hz_40ms_envelope_correlation": 0.9864470419703879, "3000–6000 Hz_40ms_modulation_mae_db": 1.1917399400018633, "mr_stft_db": 5.959428539021984, "band_mae_db": 0.3821189843102312, "rms_gain_error_db": 0.004208480930748683, "output_peak": 0.016047006625443474}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7846090322179253, "全帯域_10ms_rms_envelope_nrmse": 0.19395183165955296, "全帯域_10ms_envelope_correlation": 0.9677587361993443, "全帯域_10ms_modulation_mae_db": 0.5247309499458582, "全帯域_40ms_log_rms_mae_db": 0.8463295452754228, "全帯域_40ms_rms_envelope_nrmse": 0.09041662238153639, "全帯域_40ms_envelope_correlation": 0.9924633720609799, "全帯域_40ms_modulation_mae_db": 0.5489835983882072, "300–1000 Hz_10ms_log_rms_mae_db": 2.3638939179547274, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3335981024591802, "300–1000 Hz_10ms_envelope_correlation": 0.9102058298475005, "300–1000 Hz_10ms_modulation_mae_db": 0.6295085032383749, "300–1000 Hz_40ms_log_rms_mae_db": 1.7827233234962228, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.21058892297308965, "300–1000 Hz_40ms_envelope_correlation": 0.9617509682027002, "300–1000 Hz_40ms_modulation_mae_db": 1.2656203499173921, "1000–3000 Hz_10ms_log_rms_mae_db": 1.432728636059608, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.20276818562735402, "1000–3000 Hz_10ms_envelope_correlation": 0.9760575378082916, "1000–3000 Hz_10ms_modulation_mae_db": 0.5719332252581938, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8765667160681406, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.10655068023102571, "1000–3000 Hz_40ms_envelope_correlation": 0.9939720135581456, "1000–3000 Hz_40ms_modulation_mae_db": 0.6019030604869114, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2752809494301511, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.25256504193301765, "3000–6000 Hz_10ms_envelope_correlation": 0.9600733954797837, "3000–6000 Hz_10ms_modulation_mae_db": 0.9312817556369332, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7521034908391607, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.14086029441825035, "3000–6000 Hz_40ms_envelope_correlation": 0.9878716352444338, "3000–6000 Hz_40ms_modulation_mae_db": 1.4453608656279542, "mr_stft_db": 5.95946942514043, "band_mae_db": 0.4586645044629231, "rms_gain_error_db": 0.13209400414303235, "output_peak": 0.014013863210890293}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7754095378208221, "全帯域_10ms_rms_envelope_nrmse": 0.1949884465273732, "全帯域_10ms_envelope_correlation": 0.9672637528989125, "全帯域_10ms_modulation_mae_db": 0.5093234792116008, "全帯域_40ms_log_rms_mae_db": 0.9030949790426079, "全帯域_40ms_rms_envelope_nrmse": 0.09134795416810985, "全帯域_40ms_envelope_correlation": 0.99217455959075, "全帯域_40ms_modulation_mae_db": 0.4583257178337125, "300–1000 Hz_10ms_log_rms_mae_db": 2.3959581445803217, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.3132850108636561, "300–1000 Hz_10ms_envelope_correlation": 0.9256516091772661, "300–1000 Hz_10ms_modulation_mae_db": 0.8212376225755801, "300–1000 Hz_40ms_log_rms_mae_db": 1.7614599997440303, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.20834056050069527, "300–1000 Hz_40ms_envelope_correlation": 0.9650234391107949, "300–1000 Hz_40ms_modulation_mae_db": 1.0044804294038039, "1000–3000 Hz_10ms_log_rms_mae_db": 1.408056400265842, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.18992763791944295, "1000–3000 Hz_10ms_envelope_correlation": 0.9769733293655162, "1000–3000 Hz_10ms_modulation_mae_db": 0.7863520990682193, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8359025084270543, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.09471509366216092, "1000–3000 Hz_40ms_envelope_correlation": 0.9941554143755498, "1000–3000 Hz_40ms_modulation_mae_db": 0.31876190387034775, "3000–6000 Hz_10ms_log_rms_mae_db": 1.2845472755580165, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.23434489765566735, "3000–6000 Hz_10ms_envelope_correlation": 0.965752302464555, "3000–6000 Hz_10ms_modulation_mae_db": 0.7659388129377209, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7556426465418379, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.13402721155398764, "3000–6000 Hz_40ms_envelope_correlation": 0.9879882720435585, "3000–6000 Hz_40ms_modulation_mae_db": 1.374458480130011, "mr_stft_db": 5.969027501912194, "band_mae_db": 0.30209574677798795, "rms_gain_error_db": 0.10815620896395814, "output_peak": 0.01415685928341888}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 1.7118681943338485, "全帯域_10ms_rms_envelope_nrmse": 0.19434457330750018, "全帯域_10ms_envelope_correlation": 0.9670977505080147, "全帯域_10ms_modulation_mae_db": 0.4928388225802128, "全帯域_40ms_log_rms_mae_db": 0.8815484334326618, "全帯域_40ms_rms_envelope_nrmse": 0.09401633877256904, "全帯域_40ms_envelope_correlation": 0.9915064664756514, "全帯域_40ms_modulation_mae_db": 0.566188106068174, "300–1000 Hz_10ms_log_rms_mae_db": 2.4278004794964034, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.28975419885618076, "300–1000 Hz_10ms_envelope_correlation": 0.9418421762071191, "300–1000 Hz_10ms_modulation_mae_db": 0.6061027313414308, "300–1000 Hz_40ms_log_rms_mae_db": 1.8743680475764397, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.1991997496427266, "300–1000 Hz_40ms_envelope_correlation": 0.9723371410167213, "300–1000 Hz_40ms_modulation_mae_db": 0.6420839771230622, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4458862110358157, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1941934445453807, "1000–3000 Hz_10ms_envelope_correlation": 0.9758299569150207, "1000–3000 Hz_10ms_modulation_mae_db": 0.5283920736903638, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8977085105689913, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0963516191344449, "1000–3000 Hz_40ms_envelope_correlation": 0.9939393071685018, "1000–3000 Hz_40ms_modulation_mae_db": 0.6470132728585344, "3000–6000 Hz_10ms_log_rms_mae_db": 1.284653424232367, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.25340865169576604, "3000–6000 Hz_10ms_envelope_correlation": 0.9639490706210478, "3000–6000 Hz_10ms_modulation_mae_db": 0.9379161340675535, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7688899705623554, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.15060666368156947, "3000–6000 Hz_40ms_envelope_correlation": 0.9876538116344568, "3000–6000 Hz_40ms_modulation_mae_db": 1.162337705338838, "mr_stft_db": 5.961067451220234, "band_mae_db": 0.6226393894425539, "rms_gain_error_db": 0.0666814897411296, "output_peak": 0.01372595733754324}}], "planned_noise_seeds": [0, 1, 2, 3, 4, 5, 6, 7], "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": 5.821915924633524, "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": 2.9654222866142496e-07, "delta_db": 0.13198651279484175, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 6.379889954922647e-08, "output_power": 6.982018537912355e-08, "delta_db": 0.39167809819974286, "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": 0.48332929181552603, "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}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"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"}}, "level": {"reference": {"rms": 0.0007985617884541367, "rms_dbfs": -61.95382949667153, "peak": 0.0279541015625, "peak_dbfs": -31.071089225837348, "crest_factor_db": 30.882740270834184, "mean": -4.7323438856336806e-07, "zero_energy": false}, "output": {"rms": 0.0008107522518139773, "rms_dbfs": -61.82223672854779, "peak": 0.01424913917589817, "peak_dbfs": -36.92422743233707, "crest_factor_db": 24.898009296210727, "mean": -1.045880274014597e-05, "zero_energy": false}, "rms_difference_db": 0.13159276812373832}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 530, "quiet_samples": 127200, "reference_mean_power": 1.6852030852727545e-07, "output_mean_power": 1.8408592843772897e-07, "output_rms_dbfs": -67.34979407777413, "output_zero_energy": false, "output_peak": 0.003981176746615284, "output_energy_fraction": 0.24738244884293686, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 0, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.20203205345195271, "envelope_correlation": 0.9650210066990967, "rms_gain_error_db": 0.13161239905085387, "reference_mean_power": 6.381840334285008e-07, "output_mean_power": 6.578201529691563e-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": 4.660366531203103e-08, "reference_active": true, "delta_db": -0.6161222104638587}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8108171988414046e-08, "output_power": 2.0771050381036233e-08, "reference_active": true, "delta_db": 0.5958384843300458}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5077869163047108e-08, "output_power": 1.3512922062074575e-08, "reference_active": true, "delta_db": -0.47590698528477426}], "active_band_count": 3, "active_band_mae_db": 0.5626225600262263}}, {"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": 1.0083383783659432, "rms_envelope_nrmse": 0.11169244568299765, "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": 1.6310662622414218e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.1382633554527724e-08, "output_power": 4.310178964038481e-08, "reference_active": true, "delta_db": -0.7632105675052019}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.770301277631505e-09, "output_power": 1.0668939483444857e-08, "reference_active": true, "delta_db": 0.3821329586514737}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.622703760150781e-10, "output_power": 7.884662888990273e-10, "reference_active": true, "delta_db": -0.865139863450404}], "active_band_count": 3, "active_band_mae_db": 0.6701611298690265}}]}, {"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": 2.2104964131872056e-06, "log_rms_mae_db": 2.3899944005262266, "rms_envelope_nrmse": 0.3255071927799192, "envelope_correlation": 0.9296447488305785, "rms_gain_error_db": 0.8531743357937169, "reference_mean_power": 5.8846313595735504e-08, "output_mean_power": 7.162039227972625e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.019969626272196e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.669218221395936e-09, "output_power": 6.581256803685467e-09, "reference_active": true, "delta_db": 0.6478566318476011}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.997554044063298e-09, "output_power": 4.802420908767241e-09, "reference_active": true, "delta_db": -0.1729727813865064}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.156278331683378e-09, "output_power": 3.3565650177852395e-09, "reference_active": true, "delta_db": -1.8644128814316514}], "active_band_count": 3, "active_band_mae_db": 0.8950807648885863}}, {"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": 1.1954716835574719e-06, "log_rms_mae_db": 1.820134694839936, "rms_envelope_nrmse": 0.240638392936322, "envelope_correlation": 0.9608508619850852, "rms_gain_error_db": 0.8527113438489248, "reference_mean_power": 5.9130565750138855e-08, "output_mean_power": 7.195867677610636e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.6907038028137213e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.9716031414726236e-09, "output_power": 6.9484351076819975e-09, "reference_active": true, "delta_db": -0.014456509878011663}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1694216774888575e-09, "output_power": 2.4210260202079908e-09, "reference_active": true, "delta_db": -1.1698056689971743}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5180140726512645e-10, "output_power": 2.405559576436712e-10, "reference_active": true, "delta_db": -2.7373146214945003}], "active_band_count": 3, "active_band_mae_db": 1.3071922667898954}}]}, {"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": 1.459132751226194, "rms_envelope_nrmse": 0.18489945932562282, "envelope_correlation": 0.9793769110817069, "rms_gain_error_db": 0.2517764018173956, "reference_mean_power": 3.0019112356646434e-07, "output_mean_power": 3.181086557990732e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.170424846915179e-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": 6.360756186530917e-09, "reference_active": true, "delta_db": -0.008791105188591237}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.9583662339560916e-09, "output_power": 4.1278117379307725e-09, "reference_active": true, "delta_db": 0.18203908377178551}], "active_band_count": 3, "active_band_mae_db": 0.270059465713836}}, {"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": 0.8912879165395872, "rms_envelope_nrmse": 0.09908270449144034, "envelope_correlation": 0.9942122579172197, "rms_gain_error_db": 0.25177142913726674, "reference_mean_power": 3.016958800523271e-07, "output_mean_power": 3.1970286074822415e-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": 3.924853949927186e-08, "reference_active": true, "delta_db": -0.6340960020091811}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.58988056021656e-09, "output_power": 3.7243914857407424e-09, "reference_active": true, "delta_db": 0.15975325843147123}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0107624253076597e-10, "output_power": 2.663613342862941e-10, "reference_active": true, "delta_db": -0.5320530560518306}], "active_band_count": 3, "active_band_mae_db": 0.4419674388308277}}]}, {"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": 2.0353597876361005e-06, "log_rms_mae_db": 1.3108086877845293, "rms_envelope_nrmse": 0.24225837447838078, "envelope_correlation": 0.9635461780038665, "rms_gain_error_db": -0.41868726887623553, "reference_mean_power": 5.358047115055495e-08, "output_mean_power": 4.865615667997409e-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": 5.2466604070258305e-09, "output_power": 5.581178406930758e-09, "reference_active": true, "delta_db": 0.2684295015739033}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.042126892400445e-09, "output_power": 3.0573281512826214e-09, "reference_active": true, "delta_db": 0.02164729954313568}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.4881774270193605e-09, "output_power": 1.4009207101452147e-09, "reference_active": true, "delta_db": -2.494677901914834}], "active_band_count": 3, "active_band_mae_db": 0.928251567677291}}, {"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": 1.4732086031870809e-06, "log_rms_mae_db": 0.7929704718053812, "rms_envelope_nrmse": 0.14415254716305007, "envelope_correlation": 0.9872872226748816, "rms_gain_error_db": -0.418708397013552, "reference_mean_power": 5.38474224114617e-08, "output_mean_power": 4.8898335891196024e-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": 6.316794721929926e-09, "output_power": 6.194366683206884e-09, "reference_active": true, "delta_db": -0.08499853392545684}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0867827772247913e-09, "output_power": 1.7152241032739751e-09, "reference_active": true, "delta_db": -0.8515637271599957}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.2900642849732045e-10, "output_power": 1.0893955720464712e-10, "reference_active": true, "delta_db": -3.226620679923127}], "active_band_count": 3, "active_band_mae_db": 1.3877276470028599}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1351638, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9767025985106212, "standard_deviation": 0.004128305014554526, "minimum": 0.9710730440019586, "maximum": 0.9850938120595825, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4279870378531179, "standard_deviation": 0.019585266681821794, "minimum": 1.4075095256595063, "maximum": 1.459132751226194, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.5343367738817306, "standard_deviation": 0.18362278841881877, "minimum": 0.270059465713836, "maximum": 0.7863520990682193, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.19258049903054872, "standard_deviation": 0.01848413904105471, "minimum": 0.15280941617605856, "maximum": 0.21496823822642064, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9942702525753141, "standard_deviation": 0.0009049190094378698, "minimum": 0.9933507145316492, "maximum": 0.9962580378478231, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8615369501648193, "standard_deviation": 0.036773647153885064, "minimum": 0.7969513928583369, "maximum": 0.8994334567795252, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5394913668226577, "standard_deviation": 0.17379274341008558, "minimum": 0.31876190387034775, "maximum": 0.7625384440800499, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.09590832812043974, "standard_deviation": 0.009283340297587608, "minimum": 0.07591198995495646, "maximum": 0.10655068023102571, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9636526169017411, "standard_deviation": 0.004051724545587043, "minimum": 0.9575121004270206, "maximum": 0.9698550772489889, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.2918935330609158, "standard_deviation": 0.01466580469234022, "minimum": 1.2752809494301511, "maximum": 1.3108086877845293, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.868894668916546, "standard_deviation": 0.08928831100679756, "minimum": 0.7166507942959456, "maximum": 0.963676496101087, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.2431221153934787, "standard_deviation": 0.013391492889023252, "minimum": 0.22376536461869617, "maximum": 0.2616864530069785, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9885995616798642, "standard_deviation": 0.0017079338755889779, "minimum": 0.9864470419703879, "maximum": 0.9910602627209578, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.7714041851517784, "standard_deviation": 0.01916095763060532, "minimum": 0.7437572571033766, "maximum": 0.7929704718053812, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.2948480553121973, "standard_deviation": 0.20488074768537726, "minimum": 0.8855054893576222, "maximum": 1.5215315932653988, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.13606002327000205, "standard_deviation": 0.013327912668643945, "minimum": 0.11740356171207847, "maximum": 0.15281590944459397, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.930892606449299, "standard_deviation": 0.01033909020511859, "minimum": 0.9102058298475005, "maximum": 0.9420215675743435, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 2.3845797333038776, "standard_deviation": 0.0499955369239902, "minimum": 2.307366665882433, "maximum": 2.4371731475887985, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.75982843646595, "standard_deviation": 0.1439726906472627, "minimum": 0.6061027313414308, "maximum": 1.0193027503042131, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.30727373610488473, "standard_deviation": 0.01574712288257001, "minimum": 0.28975419885618076, "maximum": 0.3335981024591802, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9667477363855117, "standard_deviation": 0.004641308478344016, "minimum": 0.9608508619850852, "maximum": 0.9723371410167213, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 1.7776396247305886, "standard_deviation": 0.08530656281402112, "minimum": 1.6519831468693602, "maximum": 1.8743680475764397, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 1.0982681077194028, "standard_deviation": 0.45578082663337743, "minimum": 0.5929926864180687, "maximum": 2.030153464710023, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.20957853462244733, "standard_deviation": 0.01427805447864746, "minimum": 0.19218337462504634, "maximum": 0.240638392936322, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.46837389453432215, "standard_deviation": 0.12951414851611998, "minimum": 0.30209574677798795, "maximum": 0.6914160210900953, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.962981132077855, "standard_deviation": 0.0076529437142693005, "minimum": 5.951465727676973, "maximum": 5.977113707851582, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.014698365823363004, "standard_deviation": 0.0015610723267398018, "minimum": 0.01348450375585317, "maximum": 0.018040455796409963, "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": 0.0031073409228787644, "minimum": 0.9624997350676024, "maximum": 0.972721111828769, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 1.765079146437814, "standard_deviation": 0.04981395121753824, "minimum": 1.7097152039616834, "maximum": 1.85296740140075, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4863960205155249, "standard_deviation": 0.08896269997938226, "minimum": 0.31732536176250803, "maximum": 0.6065641760711912, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.19574392927778572, "standard_deviation": 0.009173299391306388, "minimum": 0.17589030376840983, "maximum": 0.20632950460507882, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9908785208717391, "standard_deviation": 0.0016028236696979353, "minimum": 0.9883433382975486, "maximum": 0.9926558103853329, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.9036232002080189, "standard_deviation": 0.05564071883675549, "minimum": 0.8451025657909458, "maximum": 1.0083383783659432, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5689744276764706, "standard_deviation": 0.08754589499333795, "minimum": 0.4583257178337125, "maximum": 0.7231712505493763, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.09737929775469092, "standard_deviation": 0.008381275197466797, "minimum": 0.08691488900252033, "maximum": 0.11169244568299765, "valid_count": 8, "planned_count": 8}}, "seconds": 7.095166594997863, "rtf_including_measurement": 1.1825277658329771}, {"case": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "kind": "natural_speech", "method": "world_harvest", "language": "ja", "style": "whisper", "speaker": "jvs_jvs082", "speaker_group": null, "status": "measured", "mos": {"status": "measured", "value": 1.395681381225586, "predicted_mos": 1.395681381225586, "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": "2d6c914261a62fe7283b03c64934502a05f102295c936d2b187ade5caf3c179a", "internal_samples": 96000, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.247731019000639}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 3.21766867247639, "全帯域_10ms_rms_envelope_nrmse": 0.33646530825029686, "全帯域_10ms_envelope_correlation": 0.9201734636847784, "全帯域_10ms_modulation_mae_db": 0.8712647853217003, "全帯域_40ms_log_rms_mae_db": 2.579661776583072, "全帯域_40ms_rms_envelope_nrmse": 0.24954279362370277, "全帯域_40ms_envelope_correlation": 0.9558855614753771, "全帯域_40ms_modulation_mae_db": 0.9596860685389155, "300–1000 Hz_10ms_log_rms_mae_db": 3.4923782605273983, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.6294592569261637, "300–1000 Hz_10ms_envelope_correlation": 0.8007860485498659, "300–1000 Hz_10ms_modulation_mae_db": 0.9087062207555231, "300–1000 Hz_40ms_log_rms_mae_db": 3.1663723381425646, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.5182918871861049, "300–1000 Hz_40ms_envelope_correlation": 0.8650889233298354, "300–1000 Hz_40ms_modulation_mae_db": 0.6937868384608, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5654171473829206, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.30147386880199206, "1000–3000 Hz_10ms_envelope_correlation": 0.9600519655792678, "1000–3000 Hz_10ms_modulation_mae_db": 1.9523552515749223, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9580326460500003, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.20658191515198698, "1000–3000 Hz_40ms_envelope_correlation": 0.98618355769199, "1000–3000 Hz_40ms_modulation_mae_db": 1.7831936211705173, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4591257978371466, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.3019076754340191, "3000–6000 Hz_10ms_envelope_correlation": 0.9477481941307703, "3000–6000 Hz_10ms_modulation_mae_db": 0.704186680967814, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8611063004988678, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.17677661491714364, "3000–6000 Hz_40ms_envelope_correlation": 0.981920283508591, "3000–6000 Hz_40ms_modulation_mae_db": 0.99088882153946, "mr_stft_db": 6.171591842799916, "band_mae_db": 1.6029015330416085, "rms_gain_error_db": 0.48808718589845923, "output_peak": 0.014450510041459131}}], "planned_noise_seeds": [0], "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": 6.426374326373883, "spectral_convergence": 0.7912794987491407, "spectral_convergence_status": "ok", "amplitude_floor": 3.772168230462137e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 6.020186594626651, "spectral_convergence": 0.735803611343242, "spectral_convergence_status": "ok", "amplitude_floor": 1.9872090073495523e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 6.068214607399216, "spectral_convergence": 0.7312675363416365, "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": 4.148718947561414e-08, "delta_db": -3.919088409921863, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 3.789702976182104e-08, "output_power": 7.543260215268825e-08, "delta_db": 2.9895391676565737, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.1288069701978556e-08, "output_power": 5.998965661927568e-08, "delta_db": 0.6806002194855334, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.8766557699122943e-07, "output_power": 3.485747793535157e-07, "delta_db": 0.8340806523974893, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 6.379889954922647e-08, "output_power": 1.0169001414555593e-07, "delta_db": 2.024651199944471, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 5.958002892412794e-08, "output_power": 5.3704192577779144e-08, "delta_db": -0.4509251819909126, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.518375636706213e-08, "output_power": 3.267379762069406e-08, "delta_db": -0.3214258998944173, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 1.6029015330416085, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.48808718589845923, "pitch": null, "output_rms_dbfs": -61.46574231077308, "output_peak": 0.014450510041459131, "reference_rms_dbfs": -61.95382949667153, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 6.171591842799916}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 0.47871071331150333, "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"}}, "level": {"reference": {"rms": 0.0007985617884541367, "rms_dbfs": -61.95382949667153, "peak": 0.0279541015625, "peak_dbfs": -31.071089225837348, "crest_factor_db": 30.882740270834184, "mean": -4.7323438856336806e-07, "zero_energy": false}, "output": {"rms": 0.0008447202092676148, "rms_dbfs": -61.46574231077308, "peak": 0.014450510041459131, "peak_dbfs": -36.80233647782749, "crest_factor_db": 24.663405832945585, "mean": 1.0210439459755896e-09, "zero_energy": false}, "rms_difference_db": 0.48808718589845057}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 530, "quiet_samples": 127200, "reference_mean_power": 1.6852030852727545e-07, "output_mean_power": 1.8430653597486622e-07, "output_rms_dbfs": -67.3445926332956, "output_zero_energy": false, "output_peak": 0.010080251583709395, "output_energy_fraction": 0.228160041394586, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 21, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 21, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 3.21766867247639, "rms_envelope_nrmse": 0.33646530825029686, "envelope_correlation": 0.9201734636847784, "rms_gain_error_db": 0.4883764037768812, "reference_mean_power": 6.381840334285008e-07, "output_mean_power": 7.141403546136587e-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": 6.872717597028556e-08, "reference_active": true, "delta_db": 1.070962032022049}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8108171988414046e-08, "output_power": 2.3801852042284556e-08, "reference_active": true, "delta_db": 1.1873614049333976}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5077869163047108e-08, "output_power": 1.6363909249661e-08, "reference_active": true, "delta_db": 0.35547091900965394}], "active_band_count": 3, "active_band_mae_db": 0.8712647853217003}}, {"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": 2.579661776583072, "rms_envelope_nrmse": 0.24954279362370277, "envelope_correlation": 0.9558855614753771, "rms_gain_error_db": 0.48943904259736626, "reference_mean_power": 6.411560082425094e-07, "output_mean_power": 7.176416245175958e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.6310662622414218e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.1382633554527724e-08, "output_power": 6.53055264597441e-08, "reference_active": true, "delta_db": 1.0413357512746082}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.770301277631505e-09, "output_power": 1.2728578554080038e-08, "reference_active": true, "delta_db": 1.1487195128493846}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.622703760150781e-10, "output_power": 1.1277099444388846e-09, "reference_active": true, "delta_db": 0.6890029414927535}], "active_band_count": 3, "active_band_mae_db": 0.9596860685389155}}]}, {"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": 2.2104964131872056e-06, "log_rms_mae_db": 3.4923782605273983, "rms_envelope_nrmse": 0.6294592569261637, "envelope_correlation": 0.8007860485498659, "rms_gain_error_db": 2.1608791475941267, "reference_mean_power": 5.8846313595735504e-08, "output_mean_power": 9.67848043748492e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.019969626272196e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.669218221395936e-09, "output_power": 7.873250170588019e-09, "reference_active": true, "delta_db": 1.4263087694413323}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.997554044063298e-09, "output_power": 6.10203650439643e-09, "reference_active": true, "delta_db": 0.8671730208636325}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.156278331683378e-09, "output_power": 5.696394249817282e-09, "reference_active": true, "delta_db": 0.4326368719616041}], "active_band_count": 3, "active_band_mae_db": 0.9087062207555231}}, {"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": 1.1954716835574719e-06, "log_rms_mae_db": 3.1663723381425646, "rms_envelope_nrmse": 0.5182918871861049, "envelope_correlation": 0.8650889233298354, "rms_gain_error_db": 2.1598168382650678, "reference_mean_power": 5.9130565750138855e-08, "output_mean_power": 9.722852964146378e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.6907038028137213e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.9716031414726236e-09, "output_power": 9.298641644179493e-09, "reference_active": true, "delta_db": 1.2508685404368782}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1694216774888575e-09, "output_power": 3.4818943630361336e-09, "reference_active": true, "delta_db": 0.4083556696159854}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5180140726512645e-10, "output_power": 4.09952886630936e-10, "reference_active": true, "delta_db": -0.4221363053295365}], "active_band_count": 3, "active_band_mae_db": 0.6937868384608}}]}, {"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": 1.5654171473829206, "rms_envelope_nrmse": 0.30147386880199206, "envelope_correlation": 0.9600519655792678, "rms_gain_error_db": 1.117733916489469, "reference_mean_power": 3.0019112356646434e-07, "output_mean_power": 3.883034399763213e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.170424846915179e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.917571308133626e-08, "output_power": 6.031887020394636e-08, "reference_active": true, "delta_db": 0.8870253222938008}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.373644839895842e-09, "output_power": 1.1256012361267436e-08, "reference_active": true, "delta_db": 2.4699670184703977}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.9583662339560916e-09, "output_power": 7.039200162202515e-09, "reference_active": true, "delta_db": 2.5000734139605676}], "active_band_count": 3, "active_band_mae_db": 1.9523552515749223}}, {"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": 0.9580326460500003, "rms_envelope_nrmse": 0.20658191515198698, "envelope_correlation": 0.98618355769199, "rms_gain_error_db": 1.1177621165246898, "reference_mean_power": 3.016958800523271e-07, "output_mean_power": 3.9025240769475504e-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": 5.7461550832533984e-08, "reference_active": true, "delta_db": 1.0214424221576819}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.58988056021656e-09, "output_power": 6.3367957081360395e-09, "reference_active": true, "delta_db": 2.4678970683543344}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0107624253076597e-10, "output_power": 4.6206239478169527e-10, "reference_active": true, "delta_db": 1.8602413729995355}], "active_band_count": 3, "active_band_mae_db": 1.7831936211705173}}]}, {"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": 2.0353597876361005e-06, "log_rms_mae_db": 1.4591257978371466, "rms_envelope_nrmse": 0.3019076754340191, "envelope_correlation": 0.9477481941307703, "rms_gain_error_db": 0.42105370841627254, "reference_mean_power": 5.358047115055495e-08, "output_mean_power": 5.903531692180968e-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": 5.2466604070258305e-09, "output_power": 5.59071832976863e-09, "reference_active": true, "delta_db": 0.27584657129975265}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.042126892400445e-09, "output_power": 2.9456253840942214e-09, "reference_active": true, "delta_db": -0.13999811539064808}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.4881774270193605e-09, "output_power": 1.6834871670633173e-09, "reference_active": true, "delta_db": -1.6967153562130413}], "active_band_count": 3, "active_band_mae_db": 0.704186680967814}}, {"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": 1.4732086031870809e-06, "log_rms_mae_db": 0.8611063004988678, "rms_envelope_nrmse": 0.17677661491714364, "envelope_correlation": 0.981920283508591, "rms_gain_error_db": 0.42111195524694134, "reference_mean_power": 5.38474224114617e-08, "output_mean_power": 5.9330241305516343e-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": 6.316794721929926e-09, "output_power": 6.379062551000967e-09, "reference_active": true, "delta_db": 0.04260096947029696}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0867827772247913e-09, "output_power": 1.7562155880704711e-09, "reference_active": true, "delta_db": -0.7489941610899826}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.2900642849732045e-10, "output_power": 1.3859275894750736e-10, "reference_active": true, "delta_db": -2.1810713340581005}], "active_band_count": 3, "active_band_mae_db": 0.99088882153946}}]}], "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"]}}, "output_samples": 144000, "representation_scalars": 1234628, "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9600519655792678, "standard_deviation": null, "minimum": 0.9600519655792678, "maximum": 0.9600519655792678, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.5654171473829206, "standard_deviation": null, "minimum": 1.5654171473829206, "maximum": 1.5654171473829206, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 1.9523552515749223, "standard_deviation": null, "minimum": 1.9523552515749223, "maximum": 1.9523552515749223, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.30147386880199206, "standard_deviation": null, "minimum": 0.30147386880199206, "maximum": 0.30147386880199206, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.98618355769199, "standard_deviation": null, "minimum": 0.98618355769199, "maximum": 0.98618355769199, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.9580326460500003, "standard_deviation": null, "minimum": 0.9580326460500003, "maximum": 0.9580326460500003, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 1.7831936211705173, "standard_deviation": null, "minimum": 1.7831936211705173, "maximum": 1.7831936211705173, "valid_count": 1, "planned_count": 1}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.20658191515198698, "standard_deviation": null, "minimum": 0.20658191515198698, "maximum": 0.20658191515198698, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9477481941307703, "standard_deviation": null, "minimum": 0.9477481941307703, "maximum": 0.9477481941307703, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.4591257978371466, "standard_deviation": null, "minimum": 1.4591257978371466, "maximum": 1.4591257978371466, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.704186680967814, "standard_deviation": null, "minimum": 0.704186680967814, "maximum": 0.704186680967814, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.3019076754340191, "standard_deviation": null, "minimum": 0.3019076754340191, "maximum": 0.3019076754340191, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.981920283508591, "standard_deviation": null, "minimum": 0.981920283508591, "maximum": 0.981920283508591, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8611063004988678, "standard_deviation": null, "minimum": 0.8611063004988678, "maximum": 0.8611063004988678, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.99088882153946, "standard_deviation": null, "minimum": 0.99088882153946, "maximum": 0.99088882153946, "valid_count": 1, "planned_count": 1}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.17677661491714364, "standard_deviation": null, "minimum": 0.17677661491714364, "maximum": 0.17677661491714364, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.8007860485498659, "standard_deviation": null, "minimum": 0.8007860485498659, "maximum": 0.8007860485498659, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 3.4923782605273983, "standard_deviation": null, "minimum": 3.4923782605273983, "maximum": 3.4923782605273983, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.9087062207555231, "standard_deviation": null, "minimum": 0.9087062207555231, "maximum": 0.9087062207555231, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.6294592569261637, "standard_deviation": null, "minimum": 0.6294592569261637, "maximum": 0.6294592569261637, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.8650889233298354, "standard_deviation": null, "minimum": 0.8650889233298354, "maximum": 0.8650889233298354, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 3.1663723381425646, "standard_deviation": null, "minimum": 3.1663723381425646, "maximum": 3.1663723381425646, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.6937868384608, "standard_deviation": null, "minimum": 0.6937868384608, "maximum": 0.6937868384608, "valid_count": 1, "planned_count": 1}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.5182918871861049, "standard_deviation": null, "minimum": 0.5182918871861049, "maximum": 0.5182918871861049, "valid_count": 1, "planned_count": 1}, "band_mae_db": {"mean": 1.6029015330416085, "standard_deviation": null, "minimum": 1.6029015330416085, "maximum": 1.6029015330416085, "valid_count": 1, "planned_count": 1}, "mr_stft_db": {"mean": 6.171591842799916, "standard_deviation": null, "minimum": 6.171591842799916, "maximum": 6.171591842799916, "valid_count": 1, "planned_count": 1}, "output_peak": {"mean": 0.014450510041459131, "standard_deviation": null, "minimum": 0.014450510041459131, "maximum": 0.014450510041459131, "valid_count": 1, "planned_count": 1}, "rms_gain_error_db": {"mean": 0.48808718589845923, "standard_deviation": null, "minimum": 0.48808718589845923, "maximum": 0.48808718589845923, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_envelope_correlation": {"mean": 0.9201734636847784, "standard_deviation": null, "minimum": 0.9201734636847784, "maximum": 0.9201734636847784, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_log_rms_mae_db": {"mean": 3.21766867247639, "standard_deviation": null, "minimum": 3.21766867247639, "maximum": 3.21766867247639, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_modulation_mae_db": {"mean": 0.8712647853217003, "standard_deviation": null, "minimum": 0.8712647853217003, "maximum": 0.8712647853217003, "valid_count": 1, "planned_count": 1}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.33646530825029686, "standard_deviation": null, "minimum": 0.33646530825029686, "maximum": 0.33646530825029686, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_envelope_correlation": {"mean": 0.9558855614753771, "standard_deviation": null, "minimum": 0.9558855614753771, "maximum": 0.9558855614753771, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_log_rms_mae_db": {"mean": 2.579661776583072, "standard_deviation": null, "minimum": 2.579661776583072, "maximum": 2.579661776583072, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_modulation_mae_db": {"mean": 0.9596860685389155, "standard_deviation": null, "minimum": 0.9596860685389155, "maximum": 0.9596860685389155, "valid_count": 1, "planned_count": 1}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.24954279362370277, "standard_deviation": null, "minimum": 0.24954279362370277, "maximum": 0.24954279362370277, "valid_count": 1, "planned_count": 1}}, "seconds": 2.02453001899994, "rtf_including_measurement": 0.3374216698333233}], "calibration": [{"case": "jvs_jvs004_falset10_BASIC5000_2951", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 1.3518293902907786e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 1.2606433835114825e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 1.1242940814223918e-07, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0005754412253654517, "output_power": 0.0005754412253654517, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0015091092814657461, "output_power": 0.0015091092814657461, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00043576714857085195, "output_power": 0.00043576714857085195, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 9.403622080703858e-05, "output_power": 9.403622080703858e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.140246786176929e-05, "output_power": 3.140246786176929e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2121205040710494e-05, "output_power": 1.2121205040710494e-05, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -25.754466608205988, "output_peak": 0.359771728515625, "reference_rms_dbfs": -25.754466608205988, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 108438, "output_samples": 108438, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.05155569782788039, "rms_dbfs": -25.754466608205988, "peak": 0.359771728515625, "peak_dbfs": -8.879459345216006, "crest_factor_db": 16.875007262989982, "mean": -3.1914027918026893e-07, "zero_energy": false}, "output": {"rms": 0.05155569782788039, "rms_dbfs": -25.754466608205988, "peak": 0.359771728515625, "peak_dbfs": -8.879459345216006, "crest_factor_db": 16.875007262989982, "mean": -3.1914027918026893e-07, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 451, "uncovered_tail_samples": 198, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 3.559632289689034e-06, "threshold_dbfs": -54.48594862366153, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 182, "quiet_samples": 43680, "reference_mean_power": 2.0628618059386482e-07, "output_mean_power": 2.0628618059386482e-07, "output_rms_dbfs": -66.85529865060558, "output_zero_energy": false, "output_peak": 0.01068115234375, "output_energy_fraction": 3.1262084057314745e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 444, "reference_estimated_voiced_frames": 263, "output_estimated_voiced_frames": 263, "both_estimated_voiced_frames": 263, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 1.0, "absolute_difference_cents_median": 0.0, "absolute_difference_cents_p95": 0.0, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 198, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.002662852134818696, "output_mean_power": 0.002662852134818696}, "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": 0.00040104774940998337, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0004799671480036486, "output_power": 0.0004799671480036486, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.6992126812237875e-05, "output_power": 4.6992126812237875e-05, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999998, "rms_gain_error_db": 0.0, "reference_mean_power": 0.002680683564334513, "output_mean_power": 0.002680683564334513}, "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": 0.0003898422445000547, "output_power": 0.0003898422445000547, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0002615577546182838, "output_power": 0.0002615577546182838, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.9711216791425515e-06, "output_power": 4.9711216791425515e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.00018970614972877836, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0020637883836989693, "output_mean_power": 0.0020637883836989693}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 1.5811898835528856e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00043243433753203383, "output_power": 0.00043243433753203383, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00038978360738039326, "output_power": 0.00038978360738039326, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.805770696622082e-05, "output_power": 3.805770696622082e-05, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.00016763715453010973, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 0.00207760838531689, "output_mean_power": 0.00207760838531689}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 1.3894681028634637e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0004594859732757339, "output_power": 0.0004594859732757339, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019541576327050035, "output_power": 0.00019541576327050035, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.9559112605266995e-06, "output_power": 4.9559112605266995e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0003994594973118105, "output_mean_power": 0.0003994594973118105}, "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": 0.00010755692941582863, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.796860879459569e-05, "output_power": 8.796860879459569e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.822952666689089e-06, "output_power": 4.822952666689089e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.00040213443933265886, "output_mean_power": 0.00040213443933265886}, "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": 0.000106294645864879, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.178329128126849e-05, "output_power": 5.178329128126849e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.031671442188497e-07, "output_power": 4.031671442188497e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 2.8330015424642847e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 5.860864109462448e-05, "output_mean_power": 5.860864109462448e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 902, "frequency_resolution_hz": 0.22172949002217296, "power_floor": 4.400349500158723e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.626242950468033e-05, "output_power": 1.626242950468033e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.53282953817687e-06, "output_power": 9.53282953817687e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.75992153022225e-06, "output_power": 1.75992153022225e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 2.5104708341377374e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 5.9001105225872584e-05, "output_mean_power": 5.9001105225872584e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 896, "frequency_resolution_hz": 0.2232142857142857, "power_floor": 3.767766826204734e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3755010045242993e-05, "output_power": 1.3755010045242993e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.79209512684818e-06, "output_power": 5.79209512684818e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0124260162334762e-07, "output_power": 1.0124260162334762e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 3.196427345275879, "predicted_mos": 3.196427345275879, "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": 4.413647228997434}}, {"case": "jvs_jvs004_parallel100_VOICEACTRESS100_058", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 9.829298518478812e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 9.065329093063253e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 0.0001149513766055836, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0017363654374162414, "output_power": 0.0017363654374162414, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0004421876194377549, "output_power": 0.0004421876194377549, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.7408011480563064e-05, "output_power": 2.7408011480563064e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.7412343207141002e-05, "output_power": 2.7412343207141002e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.428426915438781e-05, "output_power": 3.428426915438781e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.433275239990599e-05, "output_power": 1.433275239990599e-05, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -26.20342509158779, "output_peak": 0.274444580078125, "reference_rms_dbfs": -26.20342509158779, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.04895857238218429, "rms_dbfs": -26.20342509158779, "peak": 0.274444580078125, "peak_dbfs": -11.230906830925164, "crest_factor_db": 14.972518260662627, "mean": 2.86102294921875e-08, "zero_energy": false}, "output": {"rms": 0.04895857238218429, "rms_dbfs": -26.20342509158779, "peak": 0.274444580078125, "peak_dbfs": -11.230906830925164, "crest_factor_db": 14.972518260662627, "mean": 2.86102294921875e-08, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.9656674889847638e-06, "threshold_dbfs": -57.06489945258896, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 169, "quiet_samples": 40560, "reference_mean_power": 1.257790860589557e-07, "output_mean_power": 1.257790860589557e-07, "output_rms_dbfs": -69.00391565284005, "output_zero_energy": false, "output_peak": 0.00848388671875, "output_energy_fraction": 1.4780407168506377e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 349, "output_estimated_voiced_frames": 349, "both_estimated_voiced_frames": 349, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 1.0, "absolute_difference_cents_median": 0.0, "absolute_difference_cents_p95": 0.0, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.002398940884341968, "output_mean_power": 0.002398940884341968}, "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": 0.0003971876344997112, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.277425400163653e-05, "output_power": 5.277425400163653e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.46569016072901e-05, "output_power": 1.46569016072901e-05, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0024110057038516162, "output_mean_power": 0.0024110057038516162}, "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": 0.00035367674920645624, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.2909806376051565e-05, "output_power": 2.2909806376051565e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.181144761591818e-07, "output_power": 8.181144761591818e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0001330045450117286, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0013111812883454673, "output_mean_power": 0.0013111812883454673}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.210472671322612e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00029715337433814054, "output_power": 0.00029715337433814054, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.93632000258319e-05, "output_power": 4.93632000258319e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.447186660847196e-06, "output_power": 9.447186660847196e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.00012063998479701062, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.001317775623677917, "output_mean_power": 0.001317775623677917}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.775720236374232e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00027184637186405784, "output_power": 0.00027184637186405784, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0948015125222872e-05, "output_power": 2.0948015125222872e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.002499595181279e-07, "output_power": 7.002499595181279e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 3.621970358575803e-05, "output_mean_power": 3.621970358575803e-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": 1.6016299479105344e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.217328435986185e-06, "output_power": 5.217328435986185e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.162268250073546e-07, "output_power": 6.162268250073546e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 3.640185858193717e-05, "output_mean_power": 3.640185858193717e-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": 1.5750584190620256e-05, "output_power": 1.5750584190620256e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.575523670498514e-06, "output_power": 2.575523670498514e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.671987913674405e-08, "output_power": 6.671987913674405e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 5.2682733202745264e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 3.423479078027134e-05, "output_mean_power": 3.423479078027134e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.0114400042064674e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3904345626991899e-05, "output_power": 1.3904345626991899e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.3366002483256705e-06, "output_power": 5.3366002483256705e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0373079000270227e-06, "output_power": 2.0373079000270227e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 3.282155756745638e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 3.440696652445241e-05, "output_mean_power": 3.440696652445241e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.861052719142989e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.506769965034781e-05, "output_power": 1.506769965034781e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.789058518393087e-06, "output_power": 2.789058518393087e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4153621023540904e-07, "output_power": 1.4153621023540904e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 4.027534008026123, "predicted_mos": 4.027534008026123, "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": 6.7267371009947965}}, {"case": "jvs_jvs004_whisper10_BASIC5000_0074", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 7.347807435362163e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 3.5954742817466214e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 1.2516812561146785e-07, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 8.469209703610173e-08, "output_power": 8.469209703610173e-08, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 4.7196494133004234e-07, "output_power": 4.7196494133004234e-07, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.5661034348838578e-06, "output_power": 1.5661034348838578e-06, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2294550474819316e-06, "output_power": 1.2294550474819316e-06, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 3.3429464378207576e-06, "output_power": 3.3429464378207576e-06, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.563896615059082e-07, "output_power": 9.563896615059082e-07, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -51.09203551694498, "output_peak": 0.031829833984375, "reference_rms_dbfs": -51.09203551694498, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 109060, "output_samples": 109060, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.002788677060125476, "rms_dbfs": -51.09203551694498, "peak": 0.031829833984375, "peak_dbfs": -29.94331253066374, "crest_factor_db": 21.148722986281236, "mean": 3.343893807021364e-07, "zero_energy": false}, "output": {"rms": 0.002788677060125476, "rms_dbfs": -51.09203551694498, "peak": 0.031829833984375, "peak_dbfs": -29.94331253066374, "crest_factor_db": 21.148722986281236, "mean": 3.343893807021364e-07, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 454, "uncovered_tail_samples": 100, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 216, "quiet_samples": 51840, "reference_mean_power": 1.3537558706845214e-07, "output_mean_power": 1.3537558706845214e-07, "output_rms_dbfs": -68.68459647005321, "output_zero_energy": false, "output_peak": 0.004302978515625, "output_energy_fraction": 0.008274531320943003, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 447, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 0, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 100, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999998, "rms_gain_error_db": 0.0, "reference_mean_power": 7.792370026271951e-06, "output_mean_power": 7.792370026271951e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 4.121961515330989e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.794158794213974e-06, "output_power": 1.794158794213974e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.126361226638654e-07, "output_power": 3.126361226638654e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9590349245364566e-07, "output_power": 1.9590349245364566e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 7.844041250222317e-06, "output_mean_power": 7.844041250222317e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 3.76922807220892e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6572550629104971e-06, "output_power": 1.6572550629104971e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5392861690297655e-07, "output_power": 1.5392861690297655e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6336932951152273e-08, "output_power": 1.6336932951152273e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 2.930731002663351e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 4.2741366364654733e-07, "output_mean_power": 4.2741366364654733e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 2.439886077983056e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.61585037342205e-08, "output_power": 9.61585037342205e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8718875021930907e-08, "output_power": 1.8718875021930907e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.0143942568188063e-08, "output_power": 2.0143942568188063e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 1.7360896811833872e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 4.3025101883138414e-07, "output_mean_power": 4.3025101883138414e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 2.1733905138014219e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.047483464267475e-08, "output_power": 9.047483464267475e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.338915747949231e-09, "output_power": 9.338915747949231e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4382767429380366e-09, "output_power": 1.4382767429380366e-09, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 1.7870157226185334e-06, "output_mean_power": 1.7870157226185334e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.838724239404774e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.063249741710561e-07, "output_power": 7.063249741710561e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.6547376644024293e-07, "output_power": 1.6547376644024293e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2023841152792086e-07, "output_power": 1.2023841152792086e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 1.7989086732437154e-06, "output_mean_power": 1.7989086732437154e-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": 6.664518497859096e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.184085944051964e-08, "output_power": 8.184085944051964e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1933830695482323e-08, "output_power": 1.1933830695482323e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 1.7907615060268865e-06, "output_mean_power": 1.7907615060268865e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 907, "frequency_resolution_hz": 0.2205071664829107, "power_floor": 1.0367232303591375e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.7413558674441084e-07, "output_power": 4.7413558674441084e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0977135221440411e-07, "output_power": 1.0977135221440411e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.057533835167398e-08, "output_power": 3.057533835167398e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 1.8026836617488883e-06, "output_mean_power": 1.8026836617488883e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 901, "frequency_resolution_hz": 0.22197558268590456, "power_floor": 9.630136220520236e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.5232190822756626e-07, "output_power": 4.5232190822756626e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.528340255264922e-08, "output_power": 5.528340255264922e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.335569867441393e-09, "output_power": 2.335569867441393e-09, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 3.780768871307373, "predicted_mos": 3.780768871307373, "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": 5.807421322999289}}, {"case": "jvs_jvs018_falset10_VOICEACTRESS100_004", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 9.086732072822267e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 8.520258431312163e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 3.131933551513939e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0004897019472039064, "output_power": 0.0004897019472039064, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.00038033005135275084, "output_power": 0.00038033005135275084, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0002067238728943134, "output_power": 0.0002067238728943134, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.323291799953591e-05, "output_power": 1.323291799953591e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.500515826026349e-05, "output_power": 2.500515826026349e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.8390290595099542e-05, "output_power": 2.8390290595099542e-05, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -29.30071709983901, "output_peak": 0.37799072265625, "reference_rms_dbfs": -29.30071709983901, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.03427394890906224, "rms_dbfs": -29.30071709983901, "peak": 0.37799072265625, "peak_dbfs": -8.450377185723308, "crest_factor_db": 20.8503399141157, "mean": -4.2978922526041666e-07, "zero_energy": false}, "output": {"rms": 0.03427394890906224, "rms_dbfs": -29.30071709983901, "peak": 0.37799072265625, "peak_dbfs": -8.450377185723308, "crest_factor_db": 20.8503399141157, "mean": -4.2978922526041666e-07, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 2.1519445744343104e-06, "threshold_dbfs": -56.67168918566671, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 230, "quiet_samples": 55200, "reference_mean_power": 7.20824607634458e-08, "output_mean_power": 7.20824607634458e-08, "output_rms_dbfs": -71.42170395756187, "output_zero_energy": false, "output_peak": 0.0079345703125, "output_energy_fraction": 2.3522197918784192e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 317, "output_estimated_voiced_frames": 317, "both_estimated_voiced_frames": 317, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 1.0, "absolute_difference_cents_median": 0.0, "absolute_difference_cents_p95": 0.0, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0011756832947918806, "output_mean_power": 0.0011756832947918806}, "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": 0.00015071015783187623, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2413420104691182e-05, "output_power": 1.2413420104691182e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0999366671117794e-06, "output_power": 3.0999366671117794e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0011815960953402045, "output_mean_power": 0.0011815960953402045}, "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": 0.00013630386160039194, "output_power": 0.00013630386160039194, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.09070162469366e-06, "output_power": 5.09070162469366e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.569083691066088e-07, "output_power": 1.569083691066088e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 9.549209054072811e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0006895778722497405, "output_mean_power": 0.0006895778722497405}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.48267581801043e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.030686777059307e-05, "output_power": 7.030686777059307e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.045775397952225e-06, "output_power": 6.045775397952225e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.002295743692013e-06, "output_power": 1.002295743692013e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 8.872309512115069e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0006930459912916038, "output_mean_power": 0.0006930459912916038}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.440447414854182e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.43293436790663e-05, "output_power": 6.43293436790663e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6389748271852193e-06, "output_power": 2.6389748271852193e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.49082443996622e-08, "output_power": 7.49082443996622e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0001528560580614903, "output_mean_power": 0.0001528560580614903}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 2.6939080235935487e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.743995800608424e-06, "output_power": 8.743995800608424e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.018682293764139e-06, "output_power": 2.018682293764139e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.212055898483429e-07, "output_power": 4.212055898483429e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.00015362482187073777, "output_mean_power": 0.00015362482187073777}, "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": 8.417995641253307e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.917412489595775e-07, "output_power": 9.917412489595775e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.978602825033769e-08, "output_power": 1.978602825033769e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 1.1577512969913926e-05, "output_mean_power": 1.1577512969913926e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.302605621158198e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.645490651287569e-07, "output_power": 8.645490651287569e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.59009391584252e-07, "output_power": 4.59009391584252e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.3044874644069092e-07, "output_power": 2.3044874644069092e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 1.1635739617517738e-05, "output_mean_power": 1.1635739617517738e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 4.177196911262555e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 8.600495243066517e-07, "output_power": 8.600495243066517e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.5501826725164145e-07, "output_power": 2.5501826725164145e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.780810925112428e-08, "output_power": 1.780810925112428e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 3.6278302669525146, "predicted_mos": 3.6278302669525146, "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": 5.362742261997482}}, {"case": "jvs_jvs018_parallel100_VOICEACTRESS100_053", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 8.606911899432486e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 7.696353352907002e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 0.00011977037496359504, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0009579981539513103, "output_power": 0.0009579981539513103, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0008712676276581917, "output_power": 0.0008712676276581917, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00010621716934048885, "output_power": 0.00010621716934048885, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.322826988453831e-05, "output_power": 5.322826988453831e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 7.685697629736477e-05, "output_power": 7.685697629736477e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.3518932532436965e-05, "output_power": 3.3518932532436965e-05, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -26.53870587331253, "output_peak": 0.300323486328125, "reference_rms_dbfs": -26.53870587331253, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.04710475034036298, "rms_dbfs": -26.53870587331253, "peak": 0.300323486328125, "peak_dbfs": -10.448214063056167, "crest_factor_db": 16.09049181025636, "mean": -1.2700610690646702e-05, "zero_energy": false}, "output": {"rms": 0.04710475034036298, "rms_dbfs": -26.53870587331253, "peak": 0.300323486328125, "peak_dbfs": -10.448214063056167, "crest_factor_db": 16.09049181025636, "mean": -1.2700610690646702e-05, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.984813836558412e-06, "threshold_dbfs": -57.022802211663084, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 222, "quiet_samples": 53280, "reference_mean_power": 8.965192877270795e-08, "output_mean_power": 8.965192877270795e-08, "output_rms_dbfs": -70.47440362584418, "output_zero_energy": false, "output_peak": 0.007171630859375, "output_energy_fraction": 1.494968179647225e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 312, "output_estimated_voiced_frames": 312, "both_estimated_voiced_frames": 312, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 1.0, "absolute_difference_cents_median": 0.0, "absolute_difference_cents_p95": 0.0, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.002217082801939853, "output_mean_power": 0.002217082801939853}, "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": 0.0003498826441717729, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.422870023578459e-05, "output_power": 8.422870023578459e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2432690798089742e-05, "output_power": 1.2432690798089742e-05, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 0.002205255256660357, "output_mean_power": 0.002205255256660357}, "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": 0.00029633227983582444, "output_power": 0.00029633227983582444, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.2550897730277714e-05, "output_power": 4.2550897730277714e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.293923839625808e-07, "output_power": 9.293923839625808e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0001225394829970324, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0009458112547504992, "output_mean_power": 0.0009458112547504992}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 7.572635748614322e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021454762051170177, "output_power": 0.00021454762051170177, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.152647446601543e-05, "output_power": 6.152647446601543e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.926247906815996e-06, "output_power": 6.926247906815996e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.00011593520090475494, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0009490323754435319, "output_mean_power": 0.0009490323754435319}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 7.167599035150244e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00018822421406971727, "output_power": 0.00018822421406971727, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.6896254802287652e-05, "output_power": 2.6896254802287652e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.519942395248385e-07, "output_power": 7.519942395248385e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 0.00014098678071692043, "output_mean_power": 0.00014098678071692043}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.160899550412932e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.7499181258859675e-05, "output_power": 3.7499181258859675e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.267009960974534e-06, "output_power": 8.267009960974534e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.898653312592319e-07, "output_power": 7.898653312592319e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 0.00014167955800585476, "output_mean_power": 0.00014167955800585476}, "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": 3.3910555465812715e-05, "output_power": 3.3910555465812715e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.965549503856846e-06, "output_power": 3.965549503856846e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.243578010746913e-08, "output_power": 6.243578010746913e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 4.041281383552759e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 5.063950126149288e-05, "output_mean_power": 5.063950126149288e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.808534933602363e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.3975319757086051e-05, "output_power": 1.3975319757086051e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.037166885946861e-06, "output_power": 4.037166885946861e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.222770754615436e-07, "output_power": 8.222770754615436e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 3.6032760748614396e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 5.078542798446868e-05, "output_mean_power": 5.078542798446868e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.512050765202737e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.2965326164159417e-05, "output_power": 1.2965326164159417e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.904625885804089e-06, "output_power": 1.904625885804089e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.69464596815875e-08, "output_power": 5.69464596815875e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 4.155929088592529, "predicted_mos": 4.155929088592529, "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": 5.800608683995961}}, {"case": "jvs_jvs018_whisper10_VOICEACTRESS100_005", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 9.167242110941195e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 5.84028801806317e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 1.3843123087683508e-07, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.81286342317638e-08, "output_power": 6.81286342317638e-08, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 9.335883160942139e-07, "output_power": 9.335883160942139e-07, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.7505166473017637e-06, "output_power": 1.7505166473017637e-06, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 5.470519881244434e-07, "output_power": 5.470519881244434e-07, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.7292398267785066e-06, "output_power": 2.7292398267785066e-06, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 9.57439203602588e-07, "output_power": 9.57439203602588e-07, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -51.47251958187441, "output_peak": 0.036651611328125, "reference_rms_dbfs": -51.47251958187441, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.0026691563923850765, "rms_dbfs": -51.47251958187441, "peak": 0.036651611328125, "peak_dbfs": -28.71813855113624, "crest_factor_db": 22.754381030738173, "mean": -1.292758517795139e-07, "zero_energy": false}, "output": {"rms": 0.0026691563923850765, "rms_dbfs": -51.47251958187441, "peak": 0.036651611328125, "peak_dbfs": -28.71813855113624, "crest_factor_db": 22.754381030738173, "mean": -1.292758517795139e-07, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 361, "quiet_samples": 86640, "reference_mean_power": 1.2447742146757172e-07, "output_mean_power": 1.2447742146757172e-07, "output_rms_dbfs": -69.04909416610842, "output_zero_energy": false, "output_peak": 0.006591796875, "output_energy_fraction": 0.010512318076919639, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 0, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 7.130327548553108e-06, "output_mean_power": 7.130327548553108e-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": 1.2770281801289633e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.124025700263392e-07, "output_power": 2.124025700263392e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.509706557401959e-07, "output_power": 1.509706557401959e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 7.166117032249278e-06, "output_mean_power": 7.166117032249278e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.171922661595566e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.0939532041259814e-06, "output_power": 1.0939532041259814e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.164609293708589e-07, "output_power": 1.164609293708589e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.0690330771826296e-08, "output_power": 1.0690330771826296e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 6.5560927718001166e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 7.945163829144028e-07, "output_mean_power": 7.945163829144028e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.079115524536589e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.4868570435085094e-07, "output_power": 1.4868570435085094e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.530749650867309e-08, "output_power": 3.530749650867309e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.491869757314003e-08, "output_power": 2.491869757314003e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 4.158309417730709e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999998, "rms_gain_error_db": 0.0, "reference_mean_power": 7.985041710031804e-07, "output_mean_power": 7.985041710031804e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.703673751837486e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.314092622690957e-07, "output_power": 1.314092622690957e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9292191287469542e-08, "output_power": 1.9292191287469542e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4692549483461508e-09, "output_power": 1.4692549483461508e-09, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 1.4849128654353035e-06, "output_mean_power": 1.4849128654353035e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 6.418114993045289e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.69138926350769e-07, "output_power": 2.69138926350769e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.5217312260061476e-08, "output_power": 4.5217312260061476e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6338303134826183e-08, "output_power": 2.6338303134826183e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 1.4923708236731126e-06, "output_mean_power": 1.4923708236731126e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 5.994698288619124e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.5519066781428626e-07, "output_power": 2.5519066781428626e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4359212852663977e-08, "output_power": 2.4359212852663977e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5357702928828264e-09, "output_power": 1.5357702928828264e-09, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 1.0774952268311021e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 1.9952232017025357e-06, "output_mean_power": 1.9952232017025357e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.5794872115033738e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.151593028482198e-07, "output_power": 7.151593028482198e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.2474197679576507e-07, "output_power": 1.2474197679576507e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.137663053230785e-08, "output_power": 8.137663053230785e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 7.143885674653837e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 2.0052568878051227e-06, "output_mean_power": 2.0052568878051227e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.5118360803946562e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.45069205976456e-07, "output_power": 6.45069205976456e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.385509447185756e-08, "output_power": 8.385509447185756e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.7337556623287715e-09, "output_power": 5.7337556623287715e-09, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 3.3819596767425537, "predicted_mos": 3.3819596767425537, "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": 6.986588511994341}}, {"case": "jvs_jvs066_falset10_BASIC5000_1205", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 1.7496801023785185e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 1.6784480256181157e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 5.01876573628214e-07, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0014282687361772438, "output_power": 0.0014282687361772438, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.002893798215697645, "output_power": 0.002893798215697645, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0011796153749935407, "output_power": 0.0011796153749935407, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.624359886340766e-05, "output_power": 1.624359886340766e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.5152799044228294e-05, "output_power": 2.5152799044228294e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.2062863831028078e-05, "output_power": 1.2062863831028078e-05, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -22.552656329931906, "output_peak": 0.618865966796875, "reference_rms_dbfs": -22.552656329931906, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 97768, "output_samples": 97768, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.07453618896376232, "rms_dbfs": -22.552656329931906, "peak": 0.618865966796875, "peak_dbfs": -4.1680679948339865, "crest_factor_db": 18.38458833509792, "mean": -4.1983207775678136e-07, "zero_energy": false}, "output": {"rms": 0.07453618896376232, "rms_dbfs": -22.552656329931906, "peak": 0.618865966796875, "peak_dbfs": -4.1680679948339865, "crest_factor_db": 18.38458833509792, "mean": -4.1983207775678136e-07, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 407, "uncovered_tail_samples": 88, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.062095803557895e-05, "threshold_dbfs": -49.73836307096394, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 176, "quiet_samples": 42240, "reference_mean_power": 5.006247330598082e-07, "output_mean_power": 5.006247330598082e-07, "output_rms_dbfs": -63.004876981435885, "output_zero_energy": false, "output_peak": 0.01177978515625, "output_energy_fraction": 3.893185644226924e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 400, "reference_estimated_voiced_frames": 224, "output_estimated_voiced_frames": 224, "both_estimated_voiced_frames": 224, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 1.0, "absolute_difference_cents_median": 0.0, "absolute_difference_cents_p95": 0.0, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 88, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 0.005567487969490699, "output_mean_power": 0.005567487969490699}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 4.765376195527078e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0029556164553593994, "output_power": 0.0029556164553593994, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00036953756834478597, "output_power": 0.00036953756834478597, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 0.00011202447087610656, "output_power": 0.00011202447087610656, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.005608881493358216, "output_mean_power": 0.005608881493358216}, "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": 0.0027064910584040595, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.0001811755718908924, "output_power": 0.0001811755718908924, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.701057462757455e-06, "output_power": 9.701057462757455e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.000250633951078475, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0041004048785232994, "output_mean_power": 0.0041004048785232994}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 3.4168869077487372e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0021098794264420902, "output_power": 0.0021098794264420902, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00027960522877585665, "output_power": 0.00027960522877585665, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.021566680060555e-05, "output_power": 9.021566680060555e-05, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.00024415679244648494, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.004130891145990155, "output_mean_power": 0.004130891145990155}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 807, "frequency_resolution_hz": 0.24783147459727384, "power_floor": 3.1086003931775325e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0019093077513610537, "output_power": 0.0019093077513610537, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00014045819894614964, "output_power": 0.00014045819894614964, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.796438388581158e-06, "output_power": 7.796438388581158e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0008784725402011367, "output_mean_power": 0.0008784725402011367}, "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": 0.0007015897284632315, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.449911857407873e-05, "output_power": 8.449911857407873e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6127775103534608e-05, "output_power": 2.6127775103534608e-05, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0008850039267330396, "output_mean_power": 0.0008850039267330396}, "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": 0.0006783838060260436, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3933140159486266e-05, "output_power": 3.3933140159486266e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.944075796645493e-06, "output_power": 1.944075796645493e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 2.2340226127796087e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 1.7310253593278313e-05, "output_mean_power": 1.7310253593278313e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 813, "frequency_resolution_hz": 0.24600246002460022, "power_floor": 1.3633964732936542e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 7.958677073783262e-06, "output_power": 7.958677073783262e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3383871013961868e-06, "output_power": 1.3383871013961868e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5351180848670046e-07, "output_power": 4.5351180848670046e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 1.65910250564749e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 1.743895029874837e-05, "output_mean_power": 1.743895029874837e-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": 7.384237970170298e-06, "output_power": 7.384237970170298e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.219739967436263e-07, "output_power": 4.219739967436263e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.2063085962498154e-08, "output_power": 3.2063085962498154e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 3.9487907886505127, "predicted_mos": 3.9487907886505127, "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": 3.8798921039997367}}, {"case": "jvs_jvs066_parallel100_VOICEACTRESS100_025", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 1.160899353957536e-06}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 1.2404642078999559e-06}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 0.00012203000528970826, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.002976977856333367, "output_power": 0.002976977856333367, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0005003734805512382, "output_power": 0.0005003734805512382, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0006045073176565132, "output_power": 0.0006045073176565132, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 2.799447769358915e-05, "output_power": 2.799447769358915e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 2.1130460027276325e-05, "output_power": 2.1130460027276325e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 6.414014484484223e-06, "output_power": 6.414014484484223e-06, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -23.706487580888414, "output_peak": 0.472930908203125, "reference_rms_dbfs": -23.706487580888414, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 123603, "output_samples": 123603, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.06526429048136644, "rms_dbfs": -23.706487580888414, "peak": 0.472930908203125, "peak_dbfs": -6.504046038430433, "crest_factor_db": 17.20244154245798, "mean": -4.952813582093477e-07, "zero_energy": false}, "output": {"rms": 0.06526429048136644, "rms_dbfs": -23.706487580888414, "peak": 0.472930908203125, "peak_dbfs": -6.504046038430433, "crest_factor_db": 17.20244154245798, "mean": -4.952813582093477e-07, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 515, "uncovered_tail_samples": 3, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 3.877530492221316e-06, "threshold_dbfs": -54.114447782851144, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 163, "quiet_samples": 39120, "reference_mean_power": 2.965885538280254e-07, "output_mean_power": 2.965885538280254e-07, "output_rms_dbfs": -65.27845613608542, "output_zero_energy": false, "output_peak": 0.0123291015625, "output_energy_fraction": 2.2038040601310906e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 508, "reference_estimated_voiced_frames": 307, "output_estimated_voiced_frames": 307, "both_estimated_voiced_frames": 307, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 1.0, "absolute_difference_cents_median": 0.0, "absolute_difference_cents_p95": 0.0, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 3, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.004263670396682444, "output_mean_power": 0.004263670396682444}, "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": 0.000639691813348002, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00010753471412479324, "output_power": 0.00010753471412479324, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.642399701776048e-05, "output_power": 2.642399701776048e-05, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.004288676885881949, "output_mean_power": 0.004288676885881949}, "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": 0.0005603710082458684, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.355233098915975e-05, "output_power": 5.355233098915975e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6814737983602469e-06, "output_power": 1.6814737983602469e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.00013036665176469105, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0015158717741492558, "output_mean_power": 0.0015158717741492558}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.187895246183773e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00036232449214344424, "output_power": 0.00036232449214344424, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.27378870003226e-05, "output_power": 5.27378870003226e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.1888503336360718e-05, "output_power": 1.1888503336360718e-05, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.00011772885872912566, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 0.001524762506178652, "output_mean_power": 0.001524762506178652}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.112801089937839e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0003193313097067297, "output_power": 0.0003193313097067297, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.4777353739459925e-05, "output_power": 2.4777353739459925e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.078329801445271e-06, "output_power": 1.078329801445271e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.00046194923691890866, "output_mean_power": 0.00046194923691890866}, "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": 0.00021745730779534732, "output_power": 0.00021745730779534732, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.26315917085523e-05, "output_power": 6.26315917085523e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.1826956188918756e-06, "output_power": 7.1826956188918756e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.00046465861059889405, "output_mean_power": 0.00046465861059889405}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 3.961591197471976e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00020060895095818542, "output_power": 0.00020060895095818542, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.461992258627009e-05, "output_power": 3.461992258627009e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.414804941169707e-07, "output_power": 7.414804941169707e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 1.8521534194293836e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 1.684190350930034e-05, "output_mean_power": 1.684190350930034e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1029, "frequency_resolution_hz": 0.1943634596695821, "power_floor": 1.2347471453358601e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.2528634901423365e-06, "output_power": 6.2528634901423365e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0675239180772895e-06, "output_power": 2.0675239180772895e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.652671220760481e-07, "output_power": 2.652671220760481e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 1.438595762049439e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 1.694067457344735e-05, "output_mean_power": 1.694067457344735e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1023, "frequency_resolution_hz": 0.19550342130987292, "power_floor": 1.0973267407020905e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.499482122012408e-06, "output_power": 5.499482122012408e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.267943787177926e-06, "output_power": 1.267943787177926e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8893101287704844e-08, "output_power": 1.8893101287704844e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 4.037966251373291, "predicted_mos": 4.037966251373291, "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": 3.1097026169954916}}, {"case": "jvs_jvs066_whisper10_BASIC5000_2372", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 1.776300245720871e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 1.1913344769267057e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 1.0529488065388325e-06, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 6.178233710401703e-07, "output_power": 6.178233710401703e-07, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.652745613182611e-06, "output_power": 5.652745613182611e-06, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 1.2826510059132755e-05, "output_power": 1.2826510059132755e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.2385922939210616e-05, "output_power": 1.2385922939210616e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.5916906482380547e-06, "output_power": 1.5916906482380547e-06, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.299457135974266e-06, "output_power": 2.299457135974266e-06, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -44.38575419034756, "output_peak": 0.051483154296875, "reference_rms_dbfs": -44.38575419034756, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 96209, "output_samples": 96209, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.006035486606174957, "rms_dbfs": -44.38575419034756, "peak": 0.051483154296875, "peak_dbfs": -25.766697047411853, "crest_factor_db": 18.619057142935713, "mean": 9.198825116413226e-09, "zero_energy": false}, "output": {"rms": 0.006035486606174957, "rms_dbfs": -44.38575419034756, "peak": 0.051483154296875, "peak_dbfs": -25.766697047411853, "crest_factor_db": 18.619057142935713, "mean": 9.198825116413226e-09, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 400, "uncovered_tail_samples": 209, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 162, "quiet_samples": 38880, "reference_mean_power": 9.41455019293008e-08, "output_mean_power": 9.41455019293008e-08, "output_rms_dbfs": -70.26200424813008, "output_zero_energy": false, "output_peak": 0.00311279296875, "output_energy_fraction": 0.001044444939178879, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 393, "reference_estimated_voiced_frames": 8, "output_estimated_voiced_frames": 8, "both_estimated_voiced_frames": 8, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 1.0, "absolute_difference_cents_median": 0.0, "absolute_difference_cents_p95": 0.0, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 209, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 3.6506204511776254e-05, "output_mean_power": 3.6506204511776254e-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": 7.999428757782778e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.3205374160249087e-06, "output_power": 3.3205374160249087e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.233369046941817e-06, "output_power": 1.233369046941817e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 3.678163866257165e-05, "output_mean_power": 3.678163866257165e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 1.647591787295735e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.744366291346525e-06, "output_power": 6.744366291346525e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5635835823033082e-06, "output_power": 1.5635835823033082e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.396664522501234e-08, "output_power": 9.396664522501234e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 1.1737971097625874e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 3.717843862746057e-06, "output_mean_power": 3.717843862746057e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.0069118410394368e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.587317133491619e-06, "output_power": 1.587317133491619e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.351037742291996e-07, "output_power": 6.351037742291996e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.744514691925593e-07, "output_power": 2.744514691925593e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 7.730313378567769e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 3.7459272676951853e-06, "output_mean_power": 3.7459272676951853e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.5331447910659277e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.556997418820791e-06, "output_power": 1.556997418820791e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.5335281635338275e-07, "output_power": 3.5335281635338275e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.1249603669561334e-08, "output_power": 2.1249603669561334e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 1.9040046826256083e-05, "output_mean_power": 1.9040046826256083e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 1.3406247189798445e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.3392457188005514e-06, "output_power": 6.3392457188005514e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.3917385352512935e-06, "output_power": 2.3917385352512935e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.54995852980617e-07, "output_power": 7.54995852980617e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999998, "rms_gain_error_db": 0.0, "reference_mean_power": 1.9183917331823965e-05, "output_mean_power": 1.9183917331823965e-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": 5.5949700460751985e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.1687645280234336e-06, "output_power": 1.1687645280234336e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 7.657756100862396e-08, "output_power": 7.657756100862396e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 1.1530093504582301e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 5.1081468503535174e-06, "output_mean_power": 5.1081468503535174e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 800, "frequency_resolution_hz": 0.25, "power_floor": 3.2542593631444698e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.7396247028720565e-06, "output_power": 1.7396247028720565e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 5.118165550857852e-07, "output_power": 5.118165550857852e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.4689547511366814e-07, "output_power": 1.4689547511366814e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 9.091353933231888e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 5.1467425502402285e-06, "output_mean_power": 5.1467425502402285e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 794, "frequency_resolution_hz": 0.2518891687657431, "power_floor": 2.7984368001248087e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.6090100968943604e-06, "output_power": 1.6090100968943604e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.367924284305251e-07, "output_power": 2.367924284305251e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.2506680970493356e-08, "output_power": 1.2506680970493356e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 1.9535834789276123, "predicted_mos": 1.9535834789276123, "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": 4.191345307997835}}, {"case": "jvs_jvs082_falset10_BASIC5000_1728", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 8.628776010687778e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 8.696913128358987e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 1.5012142154628568e-06, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008569985031977355, "output_power": 0.0008569985031977355, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0002039561579698118, "output_power": 0.0002039561579698118, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.00031755380447674584, "output_power": 0.00031755380447674584, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 8.391217397004902e-05, "output_power": 8.391217397004902e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2641952404694477e-05, "output_power": 1.2641952404694477e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 2.274471551779886e-06, "output_power": 2.274471551779886e-06, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -28.300793168112545, "output_peak": 0.220855712890625, "reference_rms_dbfs": -28.300793168112545, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 130065, "output_samples": 130065, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.038455666393735516, "rms_dbfs": -28.300793168112545, "peak": 0.220855712890625, "peak_dbfs": -13.117827246673288, "crest_factor_db": 15.182965921439258, "mean": 1.9380709284780687e-07, "zero_energy": false}, "output": {"rms": 0.038455666393735516, "rms_dbfs": -28.300793168112545, "peak": 0.220855712890625, "peak_dbfs": -13.117827246673288, "crest_factor_db": 15.182965921439258, "mean": 1.9380709284780687e-07, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"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"}, "output": {"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"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 541, "uncovered_tail_samples": 225, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1.6147675896839552e-06, "threshold_dbfs": -57.918899759837146, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 245, "quiet_samples": 58800, "reference_mean_power": 9.664815856891424e-08, "output_mean_power": 9.664815856891424e-08, "output_rms_dbfs": -70.14806416141148, "output_zero_energy": false, "output_peak": 0.007781982421875, "output_energy_fraction": 2.954539370182486e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 534, "reference_estimated_voiced_frames": 280, "output_estimated_voiced_frames": 280, "both_estimated_voiced_frames": 280, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 1.0, "absolute_difference_cents_median": 0.0, "absolute_difference_cents_p95": 0.0, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 225, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0014814008893508253, "output_mean_power": 0.0014814008893508253}, "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": 0.0002922132888675935, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.043814645706353e-05, "output_power": 3.043814645706353e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.705913608511969e-06, "output_power": 5.705913608511969e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 0.001489661173505724, "output_mean_power": 0.001489661173505724}, "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": 0.000259482167884596, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3907004138768798e-05, "output_power": 1.3907004138768798e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.4011744172060643e-07, "output_power": 4.4011744172060643e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 8.480086855572361e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0005471873658289664, "output_mean_power": 0.0005471873658289664}, "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": 0.00011550738621428663, "output_power": 0.00011550738621428663, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.3854221447460656e-05, "output_power": 1.3854221447460656e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.9357817767829538e-06, "output_power": 1.9357817767829538e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 7.444752199710231e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.000550238587629155, "output_mean_power": 0.000550238587629155}, "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": 9.910211940271507e-05, "output_power": 9.910211940271507e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.2312084488175375e-06, "output_power": 6.2312084488175375e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.5189682275535194e-07, "output_power": 2.5189682275535194e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0003517587960046477, "output_mean_power": 0.0003517587960046477}, "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": 3.408664178054299e-05, "output_power": 3.408664178054299e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 8.90892498484566e-06, "output_power": 8.90892498484566e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 6.006695723935486e-07, "output_power": 6.006695723935486e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999998, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0003537202709185465, "output_mean_power": 0.0003537202709185465}, "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": 3.0388893978542697e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.277692934034563e-06, "output_power": 4.277692934034563e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.6389202390485585e-08, "output_power": 5.6389202390485585e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 4.415064676151012e-05, "output_mean_power": 4.415064676151012e-05}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1082, "frequency_resolution_hz": 0.18484288354898337, "power_floor": 2.2237128168975065e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 9.193805277966024e-06, "output_power": 9.193805277966024e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.0890347422283219e-06, "output_power": 1.0890347422283219e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.8576888047519527e-07, "output_power": 1.8576888047519527e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 4.439683700027619e-05, "output_mean_power": 4.439683700027619e-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": 8.24746849682131e-06, "output_power": 8.24746849682131e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.957219370502519e-07, "output_power": 4.957219370502519e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.6536836687109697e-08, "output_power": 1.6536836687109697e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 2.99242901802063, "predicted_mos": 2.99242901802063, "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": 3.159427225997206}}, {"case": "jvs_jvs082_parallel100_VOICEACTRESS100_079", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 5.237444731722431e-07}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 5.437369948912744e-07}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 6.432970236988243e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0008444430165469724, "output_power": 0.0008444430165469724, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 6.039141474549642e-05, "output_power": 6.039141474549642e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 3.556975687019485e-05, "output_power": 3.556975687019485e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 1.090392882810899e-05, "output_power": 1.090392882810899e-05, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 1.2355857763199668e-06, "output_power": 1.2355857763199668e-06, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 1.0422411240430348e-06, "output_power": 1.0422411240430348e-06, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -29.922882100947945, "output_peak": 0.15533447265625, "reference_rms_dbfs": -29.922882100947945, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.03190479033407081, "rms_dbfs": -29.922882100947945, "peak": 0.15533447265625, "peak_dbfs": -16.17464305245918, "crest_factor_db": 13.74823904848876, "mean": -8.231268988715278e-07, "zero_energy": false}, "output": {"rms": 0.03190479033407081, "rms_dbfs": -29.922882100947945, "peak": 0.15533447265625, "peak_dbfs": -16.17464305245918, "crest_factor_db": 13.74823904848876, "mean": -8.231268988715278e-07, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 204, "quiet_samples": 48960, "reference_mean_power": 9.005820816930603e-08, "output_mean_power": 9.005820816930603e-08, "output_rms_dbfs": -70.45476698167272, "output_zero_energy": false, "output_peak": 0.00274658203125, "output_energy_fraction": 3.0080872506514547e-05, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 314, "output_estimated_voiced_frames": 314, "both_estimated_voiced_frames": 314, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": 1.0, "absolute_difference_cents_median": 0.0, "absolute_difference_cents_p95": 0.0, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0010176842474405314, "output_mean_power": 0.0010176842474405314}, "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": 0.00013327602732153044, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.5932863269435214e-05, "output_power": 1.5932863269435214e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.591650627521311e-06, "output_power": 4.591650627521311e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0010161096570352637, "output_mean_power": 0.0010161096570352637}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.9042638692252314e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00011759425242544186, "output_power": 0.00011759425242544186, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 7.519272755909202e-06, "output_power": 7.519272755909202e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.598733053895234e-07, "output_power": 3.598733053895234e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 4.667982083652564e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0002794511004585033, "output_mean_power": 0.0002794511004585033}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 9.938593634377073e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 3.2950751511150254e-05, "output_power": 3.2950751511150254e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.807348843301906e-06, "output_power": 3.807348843301906e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5906604704508287e-06, "output_power": 1.5906604704508287e-06, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 4.25438813129898e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 0.0002774218749538236, "output_mean_power": 0.0002774218749538236}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 9.236914065861679e-11, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.9257092980847747e-05, "output_power": 2.9257092980847747e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8979287936807771e-06, "output_power": 1.8979287936807771e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.435917808710527e-08, "output_power": 9.435917808710527e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 3.509769240032237e-05, "output_mean_power": 3.509769240032237e-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": 1.0207730418969553e-05, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.594184871691995e-06, "output_power": 2.594184871691995e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.354712471534306e-07, "output_power": 3.354712471534306e-07, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 3.5141167460930974e-05, "output_mean_power": 3.5141167460930974e-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": 9.499160468037956e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.126122979707458e-06, "output_power": 1.126122979707458e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.795751713818223e-08, "output_power": 2.795751713818223e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 1.0101884937381447e-05, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 6.452617383104311e-06, "output_mean_power": 6.452617383104311e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 4.152733675321415e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 2.1017382665662714e-06, "output_power": 2.1017382665662714e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.306147609644791e-07, "output_power": 4.306147609644791e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.161739165108224e-08, "output_power": 8.161739165108224e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 8.618352616189348e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 6.45826084166141e-06, "output_mean_power": 6.45826084166141e-06}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 3.765522812781555e-12, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 1.8830611185238986e-06, "output_power": 1.8830611185238986e-06, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.7697767264084277e-07, "output_power": 1.7697767264084277e-07, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.816205310457988e-09, "output_power": 9.816205310457988e-09, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 4.198392391204834, "predicted_mos": 4.198392391204834, "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": 3.4178994680041797}}, {"case": "jvs_jvs082_whisper10_VOICEACTRESS100_001", "method": "identity", "status": "measured", "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": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 3.772168230462137e-08}, {"window_ms": 20, "window_samples": 480, "hop_samples": 120, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "spectral_convergence_status": "ok", "amplitude_floor": 1.9872090073495523e-08}, {"window_ms": 80, "window_samples": 1920, "hop_samples": 480, "log_magnitude_mae_db": 0.0, "spectral_convergence": 0.0, "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": 1.0228756868362371e-07, "delta_db": 0.0, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 3.789702976182104e-08, "output_power": 3.789702976182104e-08, "delta_db": 0.0, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 5.1288069701978556e-08, "output_power": 5.1288069701978556e-08, "delta_db": 0.0, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 2.8766557699122943e-07, "output_power": 2.8766557699122943e-07, "delta_db": 0.0, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 6.379889954922647e-08, "output_power": 6.379889954922647e-08, "delta_db": 0.0, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 5.958002892412794e-08, "output_power": 5.958002892412794e-08, "delta_db": 0.0, "reference_active": true}, {"low_hz": 8000.0, "high_hz": 12000.0, "reference_power": 3.518375636706213e-08, "output_power": 3.518375636706213e-08, "delta_db": 0.0, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 7, "band_count": 7, "active_band_mae_db": 0.0, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": 0.0, "pitch": null, "output_rms_dbfs": -61.95382949667153, "output_peak": 0.0279541015625, "reference_rms_dbfs": -61.95382949667153, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 0.0}, "extended": {"schema": "extended-diagnostics-v1", "status": "measured", "alignment": "none", "gain_normalization": "none", "sample_rate": 24000, "reference_samples": 144000, "output_samples": 144000, "intelligibility": {"estoi": {"value": 1.0, "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"}}, "level": {"reference": {"rms": 0.0007985617884541367, "rms_dbfs": -61.95382949667153, "peak": 0.0279541015625, "peak_dbfs": -31.071089225837348, "crest_factor_db": 30.882740270834184, "mean": -4.7323438856336806e-07, "zero_energy": false}, "output": {"rms": 0.0007985617884541367, "rms_dbfs": -61.95382949667153, "peak": 0.0279541015625, "peak_dbfs": -31.071089225837348, "crest_factor_db": 30.882740270834184, "mean": -4.7323438856336806e-07, "zero_energy": false}, "rms_difference_db": 0.0}, "full_scale": {"reference": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}, "output": {"sample_count": 144000, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, "quiet_regions": {"block_ms": 10.0, "block_samples": 240, "total_blocks": 600, "uncovered_tail_samples": 0, "meaning": "参照低エネルギー区間。人が付けた無音・無声ラベルではない", "status": "measured", "threshold_power": 1e-06, "threshold_dbfs": -60.0, "threshold_policy": "max(-60 dBFS, 最大参照ブロック電力より40 dB下)", "quiet_blocks": 530, "quiet_samples": 127200, "reference_mean_power": 1.6852030852727545e-07, "output_mean_power": 1.6852030852727545e-07, "output_rms_dbfs": -67.73347754437366, "output_zero_energy": false, "output_peak": 0.00384521484375, "output_energy_fraction": 0.23343169010376988, "energy_fraction_denominator": "出力波形全体のエネルギー"}, "pitch_consistency": {"status": "estimated_consistency_not_ground_truth", "estimator": "independent-yin-difference-v2-prefiltered", "fmin_hz": 65.0, "fmax_hz": 700.0, "frame_ms": 80.0, "hop_ms": 10.0, "prefilter": {"kind": "butterworth-forward-backward", "order_per_pass": 6, "cutoff_hz": 2000.0, "pad_type": "even", "max_pad_samples": 1920}, "total_frames": 593, "reference_estimated_voiced_frames": 0, "output_estimated_voiced_frames": 0, "both_estimated_voiced_frames": 0, "reference_voiced_output_unvoiced_frames": 0, "reference_unvoiced_output_voiced_frames": 0, "paired_voiced_fraction": null, "absolute_difference_cents_median": null, "absolute_difference_cents_p95": null, "difference_over_600_cents_frames": 0, "uncovered_tail_samples": 0, "scope": "自然音声の参照F0は未知。同じ独立測定器の入出力推定値の整合性のみ"}, "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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 6.381840334285008e-07, "output_mean_power": 6.381840334285008e-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": 5.3707173350027986e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.8108171988414046e-08, "output_power": 1.8108171988414046e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.5077869163047108e-08, "output_power": 1.5077869163047108e-08, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 6.411560082425094e-07, "output_mean_power": 6.411560082425094e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 1.6310662622414218e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.1382633554527724e-08, "output_power": 5.1382633554527724e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.770301277631505e-09, "output_power": 9.770301277631505e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 9.622703760150781e-10, "output_power": 9.622703760150781e-10, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 2.2104964131872056e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 5.8846313595735504e-08, "output_mean_power": 5.8846313595735504e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 3.019969626272196e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.669218221395936e-09, "output_power": 5.669218221395936e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 4.997554044063298e-09, "output_power": 4.997554044063298e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.156278331683378e-09, "output_power": 5.156278331683378e-09, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 1.1954716835574719e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 5.9130565750138855e-08, "output_mean_power": 5.9130565750138855e-08}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1193, "frequency_resolution_hz": 0.16764459346186086, "power_floor": 2.6907038028137213e-14, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 6.9716031414726236e-09, "output_power": 6.9716031414726236e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.1694216774888575e-09, "output_power": 3.1694216774888575e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.5180140726512645e-10, "output_power": 4.5180140726512645e-10, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999998, "rms_gain_error_db": 0.0, "reference_mean_power": 3.0019112356646434e-07, "output_mean_power": 3.0019112356646434e-07}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1199, "frequency_resolution_hz": 0.16680567139282734, "power_floor": 1.170424846915179e-13, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 4.917571308133626e-08, "output_power": 4.917571308133626e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 6.373644839895842e-09, "output_power": 6.373644839895842e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.9583662339560916e-09, "output_power": 3.9583662339560916e-09, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0000000000000002, "rms_gain_error_db": 0.0, "reference_mean_power": 3.016958800523271e-07, "output_mean_power": 3.016958800523271e-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": 4.541853281346178e-08, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.58988056021656e-09, "output_power": 3.58988056021656e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.0107624253076597e-10, "output_power": 3.0107624253076597e-10, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}, {"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": 2.0353597876361005e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 1.0, "rms_gain_error_db": 0.0, "reference_mean_power": 5.358047115055495e-08, "output_mean_power": 5.358047115055495e-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": 5.2466604070258305e-09, "output_power": 5.2466604070258305e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.042126892400445e-09, "output_power": 3.042126892400445e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.4881774270193605e-09, "output_power": 2.4881774270193605e-09, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}, {"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": 1.4732086031870809e-06, "log_rms_mae_db": 0.0, "rms_envelope_nrmse": 0.0, "envelope_correlation": 0.9999999999999999, "rms_gain_error_db": 0.0, "reference_mean_power": 5.38474224114617e-08, "output_mean_power": 5.38474224114617e-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": 6.316794721929926e-09, "output_power": 6.316794721929926e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 2.0867827772247913e-09, "output_power": 2.0867827772247913e-09, "reference_active": true, "delta_db": 0.0}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.2900642849732045e-10, "output_power": 2.2900642849732045e-10, "reference_active": true, "delta_db": 0.0}], "active_band_count": 3, "active_band_mae_db": 0.0}}]}], "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"]}}, "mos": {"status": "measured", "value": 3.9916884899139404, "predicted_mos": 3.9916884899139404, "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": 3.4233674529968994}}], "data_manifest": "data/jvs_available_v1.json", "corpus_counts": {"recordings": 12, "speakers": 4}, "alignment": "none", "normalization": "none", "public_audio": false, "mos_provenance": {"name": "UTMOSv2", "quantity": "predicted_mos_not_human_rating", "source_repository": "https://github.com/sarulab-speech/UTMOSv2", "source_commit": "cc2700db57bb83ee13dc31ebe1b868c254e15d09", "checkpoint_revision": "506474f2b33dc77c234d668cc419be1861899cad", "checkpoint_sha256": "c8149d988e4bbf3f347e6966b5d769de347a5f8c59ffca1dc4bd4bf5b8585e57", "fold": 0, "device": "cpu", "configuration": "fusion_stage3", "predict_dataset": "bvcc", "repetitions": 1, "extraction_seed": 20261012, "cpu_threads": 4, "remove_silent_section": false, "nnpack_enabled": false, "internal_sample_rate": 16000, "ssl_crop_seconds": 3.0, "spectrogram_crop_seconds": 1.4, "spectrogram_frames_per_repetition": 2, "spectrogram_inner_mixup": true, "short_input_extension": "tile", "code_license": "MIT", "weights_license": "MIT", "independent_human_rating_calibration": "not_performed_for_this_project", "scope": "JVS/LibriSpeechの再合成への適用は未校正。言語・発声別に集計する。", "paper_protocol_difference": "論文の5fold×5抽出平均ではなく、fold0と上記反復数。", "initialization": "official_architecture_then_complete_strict_state_dict", "packages": {"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", "numpy": "2.3.5", "utmosv2": "1.3.1.dev0"}, "checkpoint": {"url": "https://huggingface.co/sarulab-speech/UTMOSv2/resolve/506474f2b33dc77c234d668cc419be1861899cad/fold0_s42_best_model.pth", "sha256": "c8149d988e4bbf3f347e6966b5d769de347a5f8c59ffca1dc4bd4bf5b8585e57", "bytes": 818531314}, "feature_configuration": {"config.json": {"url": "https://huggingface.co/facebook/wav2vec2-base/resolve/0b5b8e868dd84f03fd87d01f9c4ff0f080fecfe8/config.json", "sha256": "4937977e24d12d1bba70cdce8709c3c04807a8e4ae8ddac4229c48c436ae99ae", "bytes": 1842}, "preprocessor_config.json": {"url": "https://huggingface.co/facebook/wav2vec2-base/resolve/0b5b8e868dd84f03fd87d01f9c4ff0f080fecfe8/preprocessor_config.json", "sha256": "b225d617c025463b9e157e06afea8b90dc7078fc70b013c533328423e0486b4a", "bytes": 159}}, "initialization_status": "ready"}}
