{"case": {"id": "librispeech_8463-294828-0014", "language": "en", "style": "normal", "speaker": "librispeech_8463", "source_utterance_id": "8463-294828-0014", "speaker_gender_as_distributed": "F", "excerpt_start_sample": 0, "excerpt_samples": 91600, "kind": "natural_speech", "sr": 16000, "source_file": "audio/librispeech_8463-294828-0014.wav", "source_file_sha256": "19262df0247f7490d6eb26c12b01eb091436ae2b13b8e24c14e533b83686c986", "decoded_pcm_sha256": "c608aedb889e9a3c3821520a449396c5b4cd1264e1d081a38be40b0b66f8b285", "original_source_sha256": "b61f11aa0c2b3d1adca49e6199328637c6ecc84c003dab03fc8c97b95cab4c63", "corpus_entry_id": "librispeech_8463-294828-0014"}, "original": {"method": "identity", "mos": {"status": "measured", "value": 3.6556341648101807, "predicted_mos": 3.6556341648101807, "model": "UTMOSv2", "language": "en", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 91600, "input_sample_rate": 16000, "input_seconds": 5.725, "input_float32_sha256": "1703405f5a666ca2ab8bcb794a4ce99e1c5f5977c71ded9ac683e4496e61c71b", "internal_samples": 91600, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.323729218001972, "cpu_threads": 4, "reused_from": {"path": "experiments/2026-10-12/noise-envelope/results/run-001/results.json", "row_method": "identity", "case": "librispeech_8463-294828-0014", "results_sha256": "c50df39a5300056809a18c03e2793a1dbf00ab9a19810a3683b367351e8a0b21", "input_float32_sha256": "1703405f5a666ca2ab8bcb794a4ce99e1c5f5977c71ded9ac683e4496e61c71b", "measurement_environment": "historical_Linux_not_new_Windows"}}, "waveform_sha256": "57c0273c8992ab87674c0b415b90f57ef6597f45937ac6ef94c308d8b0bb1aaf"}, "rows": [{"case": "librispeech_8463-294828-0014", "method": "hnm", "status": "measured", "mos": {"status": "measured", "value": 2.779000997543335, "predicted_mos": 2.779000997543335, "model": "UTMOSv2", "language": "en", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 91600, "input_sample_rate": 16000, "input_seconds": 5.725, "input_float32_sha256": "84d67632246b72cc92be30d6e584cde59deb74a4dd77c6e248fa28114aac8cb7", "internal_samples": 91600, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.4331756020001194, "cpu_threads": 4, "reused_from": {"path": "experiments/2026-10-12/noise-envelope/results/run-001/results.json", "row_method": "candidate", "case": "librispeech_8463-294828-0014", "results_sha256": "c50df39a5300056809a18c03e2793a1dbf00ab9a19810a3683b367351e8a0b21", "input_float32_sha256": "84d67632246b72cc92be30d6e584cde59deb74a4dd77c6e248fa28114aac8cb7", "measurement_environment": "historical_Linux_not_new_Windows"}}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8237900961393593, "全帯域_10ms_rms_envelope_nrmse": 0.06888436242421275, "全帯域_10ms_envelope_correlation": 0.9957085257137671, "全帯域_10ms_modulation_mae_db": 0.45234008315555085, "全帯域_40ms_log_rms_mae_db": 0.43050556065231926, "全帯域_40ms_rms_envelope_nrmse": 0.0359898067213902, "全帯域_40ms_envelope_correlation": 0.998812439375806, "全帯域_40ms_modulation_mae_db": 0.59272385414067, "300–1000 Hz_10ms_log_rms_mae_db": 1.4150836034582555, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08293628116813814, "300–1000 Hz_10ms_envelope_correlation": 0.9948957654627206, "300–1000 Hz_10ms_modulation_mae_db": 0.38038317686634543, "300–1000 Hz_40ms_log_rms_mae_db": 0.7453870349180723, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.046100758605174444, "300–1000 Hz_40ms_envelope_correlation": 0.9983848067058712, "300–1000 Hz_40ms_modulation_mae_db": 0.6188784522672263, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4573658140410073, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11385277290697875, "1000–3000 Hz_10ms_envelope_correlation": 0.9901679045277655, "1000–3000 Hz_10ms_modulation_mae_db": 0.3325916880985152, "1000–3000 Hz_40ms_log_rms_mae_db": 0.894299473259644, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06803937545741119, "1000–3000 Hz_40ms_envelope_correlation": 0.996768654140322, "1000–3000 Hz_40ms_modulation_mae_db": 0.47333743665160055, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4229431611047743, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1513560796802832, "3000–6000 Hz_10ms_envelope_correlation": 0.979853332693383, "3000–6000 Hz_10ms_modulation_mae_db": 0.34152209795073013, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8410108967641878, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0855493020406172, "3000–6000 Hz_40ms_envelope_correlation": 0.9928784526455626, "3000–6000 Hz_40ms_modulation_mae_db": 0.28609279272105853, "mr_stft_db": 5.504106923737197, "band_mae_db": 0.20013708784363593, "rms_gain_error_db": -0.0924017384091841, "output_peak": 0.5359342638480773}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8585053822333484, "全帯域_10ms_rms_envelope_nrmse": 0.08022559484601191, "全帯域_10ms_envelope_correlation": 0.9941486312460386, "全帯域_10ms_modulation_mae_db": 0.28655787675791694, "全帯域_40ms_log_rms_mae_db": 0.470630410125582, "全帯域_40ms_rms_envelope_nrmse": 0.04058727468631933, "全帯域_40ms_envelope_correlation": 0.9984849616570962, "全帯域_40ms_modulation_mae_db": 0.6764301628274193, "300–1000 Hz_10ms_log_rms_mae_db": 1.398326585623096, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08652644935805151, "300–1000 Hz_10ms_envelope_correlation": 0.9944760768997156, "300–1000 Hz_10ms_modulation_mae_db": 0.2055341702746709, "300–1000 Hz_40ms_log_rms_mae_db": 0.7560658000189573, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043058836005729906, "300–1000 Hz_40ms_envelope_correlation": 0.9986704796988846, "300–1000 Hz_40ms_modulation_mae_db": 0.5809677916036016, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4655204510368525, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12293375904448713, "1000–3000 Hz_10ms_envelope_correlation": 0.9879587826148614, "1000–3000 Hz_10ms_modulation_mae_db": 0.30971788170067277, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8842449899959085, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06757686608680782, "1000–3000 Hz_40ms_envelope_correlation": 0.9961657822075004, "1000–3000 Hz_40ms_modulation_mae_db": 0.23046327896230254, "3000–6000 Hz_10ms_log_rms_mae_db": 1.401723058913467, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15515482944580294, "3000–6000 Hz_10ms_envelope_correlation": 0.9787050836218599, "3000–6000 Hz_10ms_modulation_mae_db": 0.21368282556542348, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8149505323466718, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08851924699692726, "3000–6000 Hz_40ms_envelope_correlation": 0.9924268141822365, "3000–6000 Hz_40ms_modulation_mae_db": 0.16766198730432477, "mr_stft_db": 5.49964613295406, "band_mae_db": 0.1734077564409824, "rms_gain_error_db": -0.09174457907787545, "output_peak": 0.5135357278801437}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8289824066949407, "全帯域_10ms_rms_envelope_nrmse": 0.06932135992620075, "全帯域_10ms_envelope_correlation": 0.9956106649899017, "全帯域_10ms_modulation_mae_db": 0.3316366204596584, "全帯域_40ms_log_rms_mae_db": 0.41111980001284903, "全帯域_40ms_rms_envelope_nrmse": 0.03305092130222472, "全帯域_40ms_envelope_correlation": 0.9989719137598088, "全帯域_40ms_modulation_mae_db": 0.4369270445516937, "300–1000 Hz_10ms_log_rms_mae_db": 1.427819140326855, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07586453558260649, "300–1000 Hz_10ms_envelope_correlation": 0.9957069467705606, "300–1000 Hz_10ms_modulation_mae_db": 0.2785580901561153, "300–1000 Hz_40ms_log_rms_mae_db": 0.7680635055005873, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0375806988281093, "300–1000 Hz_40ms_envelope_correlation": 0.9989122342496434, "300–1000 Hz_40ms_modulation_mae_db": 0.41682253195824653, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4198470485242818, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11022442302076041, "1000–3000 Hz_10ms_envelope_correlation": 0.9903142811260187, "1000–3000 Hz_10ms_modulation_mae_db": 0.18659852330703006, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8270683556221259, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06233014888906299, "1000–3000 Hz_40ms_envelope_correlation": 0.9966767601234489, "1000–3000 Hz_40ms_modulation_mae_db": 0.22632864674237543, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4226282980881138, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17382662457470602, "3000–6000 Hz_10ms_envelope_correlation": 0.9742170803551066, "3000–6000 Hz_10ms_modulation_mae_db": 0.6587561073602555, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8491677541599, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.11073163751494165, "3000–6000 Hz_40ms_envelope_correlation": 0.9897190214225818, "3000–6000 Hz_40ms_modulation_mae_db": 0.597632755093745, "mr_stft_db": 5.520790289270141, "band_mae_db": 0.19323819738284395, "rms_gain_error_db": -0.075835293295488, "output_peak": 0.5532965916133972}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8318657085955763, "全帯域_10ms_rms_envelope_nrmse": 0.07115816306186497, "全帯域_10ms_envelope_correlation": 0.9954435693319146, "全帯域_10ms_modulation_mae_db": 0.3581081683198944, "全帯域_40ms_log_rms_mae_db": 0.4317521342113571, "全帯域_40ms_rms_envelope_nrmse": 0.04275190644768448, "全帯域_40ms_envelope_correlation": 0.9983124506861156, "全帯域_40ms_modulation_mae_db": 0.26349766072105063, "300–1000 Hz_10ms_log_rms_mae_db": 1.4442460474065215, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08675884362083625, "300–1000 Hz_10ms_envelope_correlation": 0.9943954484486007, "300–1000 Hz_10ms_modulation_mae_db": 0.21664309187160855, "300–1000 Hz_40ms_log_rms_mae_db": 0.8331000195316165, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0570251279820191, "300–1000 Hz_40ms_envelope_correlation": 0.9974654451830003, "300–1000 Hz_40ms_modulation_mae_db": 0.0755148472165542, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3923633896102794, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1099430242216707, "1000–3000 Hz_10ms_envelope_correlation": 0.9905951324556742, "1000–3000 Hz_10ms_modulation_mae_db": 0.5464854484292128, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8191204764186341, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06098894076766291, "1000–3000 Hz_40ms_envelope_correlation": 0.9971916578717342, "1000–3000 Hz_40ms_modulation_mae_db": 0.6331359595407277, "3000–6000 Hz_10ms_log_rms_mae_db": 1.427402327888486, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1511255031313956, "3000–6000 Hz_10ms_envelope_correlation": 0.9802046676224055, "3000–6000 Hz_10ms_modulation_mae_db": 0.8218749355375671, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8258729207013055, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08158572295925022, "3000–6000 Hz_40ms_envelope_correlation": 0.9943106405163198, "3000–6000 Hz_40ms_modulation_mae_db": 0.75776686619129, "mr_stft_db": 5.502222308266614, "band_mae_db": 0.2140937909966373, "rms_gain_error_db": -0.10478574469587026, "output_peak": 0.5431993947408312}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.839613179157479, "全帯域_10ms_rms_envelope_nrmse": 0.06799493185533038, "全帯域_10ms_envelope_correlation": 0.995824735956942, "全帯域_10ms_modulation_mae_db": 0.3050800647655119, "全帯域_40ms_log_rms_mae_db": 0.43924066813969265, "全帯域_40ms_rms_envelope_nrmse": 0.038504621750471604, "全帯域_40ms_envelope_correlation": 0.9986239348888423, "全帯域_40ms_modulation_mae_db": 0.45004556190763784, "300–1000 Hz_10ms_log_rms_mae_db": 1.4399099623191727, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07997148586409943, "300–1000 Hz_10ms_envelope_correlation": 0.9952483700193469, "300–1000 Hz_10ms_modulation_mae_db": 0.4421206310315304, "300–1000 Hz_40ms_log_rms_mae_db": 0.8227636649606538, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.0461762162205874, "300–1000 Hz_40ms_envelope_correlation": 0.9983691394752114, "300–1000 Hz_40ms_modulation_mae_db": 0.3351019070306244, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4430288933464508, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10158574417489127, "1000–3000 Hz_10ms_envelope_correlation": 0.9918718939924533, "1000–3000 Hz_10ms_modulation_mae_db": 0.21108830371721873, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8553286742195785, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04960306150733273, "1000–3000 Hz_40ms_envelope_correlation": 0.9980797137721392, "1000–3000 Hz_40ms_modulation_mae_db": 0.193109384286536, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3870404301884005, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15837576757292235, "3000–6000 Hz_10ms_envelope_correlation": 0.9779473553082607, "3000–6000 Hz_10ms_modulation_mae_db": 0.7846074316230007, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8247706791449041, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09554348520798119, "3000–6000 Hz_40ms_envelope_correlation": 0.9914280857986877, "3000–6000 Hz_40ms_modulation_mae_db": 0.5750830536722124, "mr_stft_db": 5.497353042534024, "band_mae_db": 0.2072380906840489, "rms_gain_error_db": -0.08761339566243839, "output_peak": 0.5376177493418046}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8364990959780512, "全帯域_10ms_rms_envelope_nrmse": 0.06802231065835879, "全帯域_10ms_envelope_correlation": 0.9957661260483189, "全帯域_10ms_modulation_mae_db": 0.3209167060162984, "全帯域_40ms_log_rms_mae_db": 0.4217500236712957, "全帯域_40ms_rms_envelope_nrmse": 0.03539013422740402, "全帯域_40ms_envelope_correlation": 0.9987849281508989, "全帯域_40ms_modulation_mae_db": 0.3475662974402369, "300–1000 Hz_10ms_log_rms_mae_db": 1.4205733881397644, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07908305205290558, "300–1000 Hz_10ms_envelope_correlation": 0.9953311399271847, "300–1000 Hz_10ms_modulation_mae_db": 0.21627309973525902, "300–1000 Hz_40ms_log_rms_mae_db": 0.7637152147468114, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.045146760047435376, "300–1000 Hz_40ms_envelope_correlation": 0.9983970919052869, "300–1000 Hz_40ms_modulation_mae_db": 0.2469202796216392, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3896232683050291, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11569533227392682, "1000–3000 Hz_10ms_envelope_correlation": 0.9893928963045252, "1000–3000 Hz_10ms_modulation_mae_db": 0.5632890038467558, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8257630331136945, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06608327659829946, "1000–3000 Hz_40ms_envelope_correlation": 0.996410321274258, "1000–3000 Hz_40ms_modulation_mae_db": 0.6507176556234064, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4413434541158023, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14825095035428615, "3000–6000 Hz_10ms_envelope_correlation": 0.9806214704984451, "3000–6000 Hz_10ms_modulation_mae_db": 0.45963656513933704, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8230499734349573, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07962651615325078, "3000–6000 Hz_40ms_envelope_correlation": 0.9939964730165315, "3000–6000 Hz_40ms_modulation_mae_db": 0.4068918358666371, "mr_stft_db": 5.506318765569234, "band_mae_db": 0.14421193732589246, "rms_gain_error_db": -0.056536748954784374, "output_peak": 0.5321994200032626}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8260152779736865, "全帯域_10ms_rms_envelope_nrmse": 0.06388553106166886, "全帯域_10ms_envelope_correlation": 0.9964712744393446, "全帯域_10ms_modulation_mae_db": 0.4209578987720095, "全帯域_40ms_log_rms_mae_db": 0.4363645724408269, "全帯域_40ms_rms_envelope_nrmse": 0.035629572249840064, "全帯域_40ms_envelope_correlation": 0.9990073516439455, "全帯域_40ms_modulation_mae_db": 0.452653016040306, "300–1000 Hz_10ms_log_rms_mae_db": 1.4810342175059328, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07419896325047776, "300–1000 Hz_10ms_envelope_correlation": 0.9960494175959789, "300–1000 Hz_10ms_modulation_mae_db": 0.3430545607816078, "300–1000 Hz_40ms_log_rms_mae_db": 0.811953722450833, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043662271224743164, "300–1000 Hz_40ms_envelope_correlation": 0.9987055416273669, "300–1000 Hz_40ms_modulation_mae_db": 0.6245555658680244, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4685620733690559, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12204433883106795, "1000–3000 Hz_10ms_envelope_correlation": 0.9882095009461417, "1000–3000 Hz_10ms_modulation_mae_db": 0.33898810463589973, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8783641455684934, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07219161879606943, "1000–3000 Hz_40ms_envelope_correlation": 0.9957483570141343, "1000–3000 Hz_40ms_modulation_mae_db": 0.4333801606400259, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4409735310487621, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15858524489632955, "3000–6000 Hz_10ms_envelope_correlation": 0.9783651802945114, "3000–6000 Hz_10ms_modulation_mae_db": 0.7843888601860604, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8702157730888198, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08790571351010412, "3000–6000 Hz_40ms_envelope_correlation": 0.9936412589886194, "3000–6000 Hz_40ms_modulation_mae_db": 0.7966163875627079, "mr_stft_db": 5.517295339798316, "band_mae_db": 0.21354228926534738, "rms_gain_error_db": -0.14618344019297697, "output_peak": 0.5194902684032043}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8356344544774593, "全帯域_10ms_rms_envelope_nrmse": 0.06872970224215928, "全帯域_10ms_envelope_correlation": 0.9957114664148313, "全帯域_10ms_modulation_mae_db": 0.10607161447006304, "全帯域_40ms_log_rms_mae_db": 0.4480521323673224, "全帯域_40ms_rms_envelope_nrmse": 0.03592351001237135, "全帯域_40ms_envelope_correlation": 0.9988034095895469, "全帯域_40ms_modulation_mae_db": 0.2734700574024291, "300–1000 Hz_10ms_log_rms_mae_db": 1.479651286626603, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07873979854663955, "300–1000 Hz_10ms_envelope_correlation": 0.9954090463000581, "300–1000 Hz_10ms_modulation_mae_db": 0.18326228362570549, "300–1000 Hz_40ms_log_rms_mae_db": 0.7986652206978488, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04510159720443142, "300–1000 Hz_40ms_envelope_correlation": 0.9984663263797467, "300–1000 Hz_40ms_modulation_mae_db": 0.19556638215526814, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4417222833941346, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1147602126402464, "1000–3000 Hz_10ms_envelope_correlation": 0.9895161633536128, "1000–3000 Hz_10ms_modulation_mae_db": 0.2522026938661674, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8433073116890702, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06523747065594278, "1000–3000 Hz_40ms_envelope_correlation": 0.9964191935169834, "1000–3000 Hz_40ms_modulation_mae_db": 0.2071606420503841, "3000–6000 Hz_10ms_log_rms_mae_db": 1.444438643849094, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15837395283482536, "3000–6000 Hz_10ms_envelope_correlation": 0.9787748075021915, "3000–6000 Hz_10ms_modulation_mae_db": 1.0377197404499505, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8469751562365447, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08924234938892757, "3000–6000 Hz_40ms_envelope_correlation": 0.9938709901766398, "3000–6000 Hz_40ms_modulation_mae_db": 1.16356222734519, "mr_stft_db": 5.49752328771697, "band_mae_db": 0.22128328874524472, "rms_gain_error_db": -0.08804591026966027, "output_peak": 0.5304003862172045}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 91600, "output_samples": 91600, "length_delta_samples": 0, "sample_rate": 16000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 80, "hop_samples": 20, "log_magnitude_mae_db": 5.5892472665166295, "spectral_convergence": 0.2597526402976283, "spectral_convergence_status": "ok", "amplitude_floor": 1.4112644553101518e-06}, {"window_ms": 20, "window_samples": 320, "hop_samples": 80, "log_magnitude_mae_db": 5.326628354183193, "spectral_convergence": 0.2529959314783747, "spectral_convergence_status": "ok", "amplitude_floor": 1.1975531593072457e-06}, {"window_ms": 80, "window_samples": 1280, "hop_samples": 320, "log_magnitude_mae_db": 5.5964451505117685, "spectral_convergence": 0.26107468430814323, "spectral_convergence_status": "ok", "amplitude_floor": 1.114415465542996e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.564075826256522e-05, "output_power": 6.275969326866997e-05, "delta_db": 0.5228777250205187, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0010000129923479963, "output_power": 0.0009781109475367417, "delta_db": -0.09617522680659038, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0018259392170112694, "output_power": 0.0018036109432331311, "delta_db": -0.05343454694978731, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0005127219920465177, "output_power": 0.0004889503819131302, "delta_db": -0.20617156229663106, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 0.00033320627903786135, "output_power": 0.00031247891983837245, "delta_db": -0.2789245208701837, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 0.0002817706196064759, "output_power": 0.00027897919223767326, "delta_db": -0.04323894511810428, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 6, "band_count": 6, "active_band_mae_db": 0.20013708784363593, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.0924017384091841, "pitch": null, "output_rms_dbfs": -24.061725017657317, "output_peak": 0.5359342638480773, "reference_rms_dbfs": -23.96932327924813, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.504106923737197}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 16000, "samples": 91600, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00020825955187282386, "log_rms_mae_db": 0.8237900961393593, "rms_envelope_nrmse": 0.06888436242421275, "envelope_correlation": 0.9957085257137671, "rms_gain_error_db": -0.09238576483120148, "reference_mean_power": 0.004012756910556895, "output_mean_power": 0.003928296634029046}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 2.2120307480210933e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008889321025104637, "output_power": 0.0008513607347526479, "reference_active": true, "delta_db": -0.18754974015085438}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00022980725896418495, "output_power": 0.00021126421836042194, "reference_active": true, "delta_db": -0.3653779551212929}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.1131932747773025e-05, "output_power": 3.4179827110353887e-05, "reference_active": true, "delta_db": -0.8040925541945054}], "active_band_count": 3, "active_band_mae_db": 0.45234008315555085}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.0001984160011662782, "log_rms_mae_db": 0.43050556065231926, "rms_envelope_nrmse": 0.0359898067213902, "envelope_correlation": 0.998812439375806, "rms_gain_error_db": -0.09240959189156253, "reference_mean_power": 0.0040337408532874226, "output_mean_power": 0.003948817243155761}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 2.0115882799069226e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008024963383362849, "output_power": 0.0007707041557857889, "reference_active": true, "delta_db": -0.17555358672360938}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00011463438169489824, "output_power": 0.00010312321705571267, "reference_active": true, "delta_db": -0.45958439950042196}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.4945953602736586e-06, "output_power": 2.6859228774569513e-06, "reference_active": true, "delta_db": -1.1430335761979784}], "active_band_count": 3, "active_band_mae_db": 0.59272385414067}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00019054595180557928, "log_rms_mae_db": 1.4150836034582555, "rms_envelope_nrmse": 0.08293628116813814, "envelope_correlation": 0.9948957654627206, "rms_gain_error_db": -0.08383850690991496, "reference_mean_power": 0.0025757888112863028, "output_mean_power": 0.0025265412992953157}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.7595886306573375e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007279305516452219, "output_power": 0.000709155034250302, "reference_active": true, "delta_db": -0.11348757067165444}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019010480993234813, "output_power": 0.00016904663804806613, "reference_active": true, "delta_db": -0.5098656723469376}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6294378423488108e-05, "output_power": 2.333905568322953e-05, "reference_active": true, "delta_db": -0.5177962875804442}], "active_band_count": 3, "active_band_mae_db": 0.38038317686634543}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.00018019065505981728, "log_rms_mae_db": 0.7453870349180723, "rms_envelope_nrmse": 0.046100758605174444, "envelope_correlation": 0.9983848067058712, "rms_gain_error_db": -0.08383460460145711, "reference_mean_power": 0.0025893611436675294, "output_mean_power": 0.0025398564191153462}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.6269545971301712e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006780414214466183, "output_power": 0.0006614477545447039, "reference_active": true, "delta_db": -0.10760679191810102}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.548437806715927e-05, "output_power": 8.331108664742104e-05, "reference_active": true, "delta_db": -0.5922952456755906}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.9327510117604047e-06, "output_power": 2.246993734135949e-06, "reference_active": true, "delta_db": -1.1567333192079872}], "active_band_count": 3, "active_band_mae_db": 0.6188784522672263}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.327720993461315e-05, "log_rms_mae_db": 1.4573658140410073, "rms_envelope_nrmse": 0.11385277290697875, "envelope_correlation": 0.9901679045277655, "rms_gain_error_db": -0.2765198314461534, "reference_mean_power": 0.0007122971869413385, "output_mean_power": 0.0006683581466462924}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 4.689927289528067e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00023362430343497353, "output_power": 0.00021757022474449192, "reference_active": true, "delta_db": -0.309185591581464}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.797902128989837e-05, "output_power": 3.573481644847603e-05, "reference_active": true, "delta_db": -0.26452213188791873}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.042184778585592e-05, "output_power": 9.452310770181072e-06, "reference_active": true, "delta_db": -0.4240673408261628}], "active_band_count": 3, "active_band_mae_db": 0.3325916880985152}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 8.747046012456969e-05, "log_rms_mae_db": 0.894299473259644, "rms_envelope_nrmse": 0.06803937545741119, "envelope_correlation": 0.996768654140322, "rms_gain_error_db": -0.2766581268520318, "reference_mean_power": 0.0007159674763911086, "output_mean_power": 0.0006717806368811551}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 4.328159646639031e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021700970165722394, "output_power": 0.00020282821935151292, "reference_active": true, "delta_db": -0.2935077193527849}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.702508733600319e-05, "output_power": 1.6779541346764924e-05, "reference_active": true, "delta_db": -0.06309262835336381}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.679451250427792e-07, "output_power": 6.794399388468699e-07, "reference_active": true, "delta_db": -1.0634119622486529}], "active_band_count": 3, "active_band_mae_db": 0.47333743665160055}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.039773028293347e-05, "log_rms_mae_db": 1.4229431611047743, "rms_envelope_nrmse": 0.1513560796802832, "envelope_correlation": 0.979853332693383, "rms_gain_error_db": -0.0483838549027785, "reference_mean_power": 0.0003237352885604671, "output_mean_power": 0.00032014863647525984}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.2480235329901466e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.70846061617512e-05, "output_power": 5.673725945488424e-05, "reference_active": true, "delta_db": -0.02650654609467537}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9595191589145483e-05, "output_power": 1.9934174213103893e-05, "reference_active": true, "delta_db": 0.07448735336793884}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.074204859780537e-06, "output_power": 4.1021426387187786e-06, "reference_active": true, "delta_db": -0.9235723943895762}], "active_band_count": 3, "active_band_mae_db": 0.34152209795073013}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 6.399293414479695e-05, "log_rms_mae_db": 0.8410108967641878, "rms_envelope_nrmse": 0.0855493020406172, "envelope_correlation": 0.9928784526455626, "rms_gain_error_db": -0.048460191489175464, "reference_mean_power": 0.0003253818281247376, "output_mean_power": 0.00032177127821326785}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.1005868407421181e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.4497636322434906e-05, "output_power": 5.4437068491289674e-05, "reference_active": true, "delta_db": -0.004829365922044011}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.385752117634814e-06, "output_power": 9.51205405596293e-06, "reference_active": true, "delta_db": 0.058052295702680334}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.7591737704275347e-07, "output_power": 3.130060486405888e-07, "reference_active": true, "delta_db": -0.7953967165384512}], "active_band_count": 3, "active_band_mae_db": 0.28609279272105853}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.877223232083865, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "53a915e5c8e9175102e4ea57d0351e497867abe83fdd26308a5569383cae632b", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9897533194151316, "standard_deviation": 0.0012802595663432286, "minimum": 0.9879587826148614, "maximum": 0.9918718939924533, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4347541527033862, "standard_deviation": 0.031107760392731387, "minimum": 1.3896232683050291, "maximum": 1.4685620733690559, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.34262020595018405, "standard_deviation": 0.1420617647256273, "minimum": 0.18659852330703006, "maximum": 0.5632890038467558, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.11387995088925368, "standard_deviation": 0.006894197102944556, "minimum": 0.10158574417489127, "maximum": 0.12293375904448713, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9966825549900651, "standard_deviation": 0.000707302267084837, "minimum": 0.9957483570141343, "maximum": 0.9980797137721392, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8534370574858936, "standard_deviation": 0.029240879436502974, "minimum": 0.8191204764186341, "maximum": 0.894299473259644, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.38095414556216983, "standard_deviation": 0.19261269807139003, "minimum": 0.193109384286536, "maximum": 0.6507176556234064, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06400634484482366, "standard_deviation": 0.006774014582388552, "minimum": 0.04960306150733273, "maximum": 0.07219161879606943, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9785861222370205, "standard_deviation": 0.0019986879084639597, "minimum": 0.9742170803551066, "maximum": 0.9806214704984451, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.4235616131496125, "standard_deviation": 0.020290543432676278, "minimum": 1.3870404301884005, "maximum": 1.444438643849094, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6377735704765406, "standard_deviation": 0.2768953984725944, "minimum": 0.21368282556542348, "maximum": 1.0377197404499505, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1568811190613189, "standard_deviation": 0.007888778571558931, "minimum": 0.14825095035428615, "maximum": 0.17382662457470602, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9927839670933973, "standard_deviation": 0.0015623362864140113, "minimum": 0.9897190214225818, "maximum": 0.9943106405163198, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8370017107346615, "standard_deviation": 0.018209429589497842, "minimum": 0.8149505323466718, "maximum": 0.8702157730888198, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.5939134882196457, "standard_deviation": 0.3171807776854657, "minimum": 0.16766198730432477, "maximum": 1.16356222734519, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0898379967215, "standard_deviation": 0.009751862087192243, "minimum": 0.07962651615325078, "maximum": 0.11073163751494165, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9951890264280208, "standard_deviation": 0.0005737976408834634, "minimum": 0.9943954484486007, "maximum": 0.9960494175959789, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.438330528925775, "standard_deviation": 0.029604628901309955, "minimum": 1.398326585623096, "maximum": 1.4810342175059328, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.28322863804285536, "standard_deviation": 0.09504360375656429, "minimum": 0.18326228362570549, "maximum": 0.4421206310315304, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08050992618046934, "standard_deviation": 0.004598165245116519, "minimum": 0.07419896325047776, "maximum": 0.08675884362083625, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9984213831531265, "standard_deviation": 0.0004316454441169831, "minimum": 0.9974654451830003, "maximum": 0.9989122342496434, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7874642728531726, "standard_deviation": 0.033275105271162814, "minimum": 0.7453870349180723, "maximum": 0.8331000195316165, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.38679096971514815, "standard_deviation": 0.2086344623307225, "minimum": 0.0755148472165542, "maximum": 0.6245555658680244, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04548153326477876, "standard_deviation": 0.005424539336849066, "minimum": 0.0375806988281093, "maximum": 0.0570251279820191, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.19589405483557912, "standard_deviation": 0.025684132723653885, "minimum": 0.14421193732589246, "maximum": 0.22128328874524472, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.50565701123082, "standard_deviation": 0.008866861922994714, "minimum": 5.497353042534024, "maximum": 5.520790289270141, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.5332092252559908, "standard_deviation": 0.012617064708313482, "minimum": 0.5135357278801437, "maximum": 0.5532965916133972, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.09289335631978474, "standard_deviation": 0.025765368364771953, "minimum": -0.14618344019297697, "maximum": -0.056536748954784374, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9955856242676324, "standard_deviation": 0.0006536521702344925, "minimum": 0.9941486312460386, "maximum": 0.9964712744393446, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.8351132001562376, "standard_deviation": 0.010880875156209228, "minimum": 0.8237900961393593, "maximum": 0.8585053822333484, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.32270862908961295, "standard_deviation": 0.1044321512820931, "minimum": 0.10607161447006304, "maximum": 0.45234008315555085, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.06977774450947596, "standard_deviation": 0.00469264000242607, "minimum": 0.06388553106166886, "maximum": 0.08022559484601191, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9987251737190075, "standard_deviation": 0.0002378784818177689, "minimum": 0.9983124506861156, "maximum": 0.9990073516439455, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.43617691270265563, "standard_deviation": 0.017829442193661175, "minimum": 0.41111980001284903, "maximum": 0.470630410125582, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4366642068789304, "standard_deviation": 0.144832178497218, "minimum": 0.26349766072105063, "maximum": 0.6764301628274193, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.037228468424713224, "standard_deviation": 0.0031632613197753114, "minimum": 0.03305092130222472, "maximum": 0.04275190644768448, "valid_count": 8, "planned_count": 8}}}, {"case": "librispeech_8463-294828-0014", "method": "A", "status": "measured", "mos": {"status": "measured", "value": 2.475177764892578, "predicted_mos": 2.475177764892578, "model": "UTMOSv2", "language": "en", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 91600, "input_sample_rate": 16000, "input_seconds": 5.725, "input_float32_sha256": "0531a557033c790ff53d69224fbb452816b1e1f76e2f63d59ade6e3654c13677", "internal_samples": 91600, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 3.9535029996186495, "cpu_threads": 4}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8387719200385727, "全帯域_10ms_rms_envelope_nrmse": 0.06928352846813671, "全帯域_10ms_envelope_correlation": 0.9956557897827184, "全帯域_10ms_modulation_mae_db": 0.3827181758291262, "全帯域_40ms_log_rms_mae_db": 0.43229366017215914, "全帯域_40ms_rms_envelope_nrmse": 0.035505776341888604, "全帯域_40ms_envelope_correlation": 0.9988465830131633, "全帯域_40ms_modulation_mae_db": 0.5266486562780334, "300–1000 Hz_10ms_log_rms_mae_db": 1.4214141342046833, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08255539697789854, "300–1000 Hz_10ms_envelope_correlation": 0.9949332728275956, "300–1000 Hz_10ms_modulation_mae_db": 0.29942673388996094, "300–1000 Hz_40ms_log_rms_mae_db": 0.7215655501665419, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04459439659231298, "300–1000 Hz_40ms_envelope_correlation": 0.9984820569917022, "300–1000 Hz_40ms_modulation_mae_db": 0.5319645095776028, "1000–3000 Hz_10ms_log_rms_mae_db": 1.461238711755153, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11392679353123143, "1000–3000 Hz_10ms_envelope_correlation": 0.9901272303284759, "1000–3000 Hz_10ms_modulation_mae_db": 0.3078851185032709, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8670612204311741, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06687483464307632, "1000–3000 Hz_40ms_envelope_correlation": 0.9968743881888192, "1000–3000 Hz_40ms_modulation_mae_db": 0.5090706905928122, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4443047639719677, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14904423971136105, "3000–6000 Hz_10ms_envelope_correlation": 0.9804579686724403, "3000–6000 Hz_10ms_modulation_mae_db": 0.34695880614572344, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8687471729830932, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08499265848782823, "3000–6000 Hz_40ms_envelope_correlation": 0.993032482069486, "3000–6000 Hz_40ms_modulation_mae_db": 0.31506678507131664, "mr_stft_db": 5.46430149997295, "band_mae_db": 0.19799921168973997, "rms_gain_error_db": -0.09076923036205559, "output_peak": 0.5361557004650915}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8636919166146789, "全帯域_10ms_rms_envelope_nrmse": 0.08272771173257883, "全帯域_10ms_envelope_correlation": 0.9937500065935589, "全帯域_10ms_modulation_mae_db": 0.23818116176000223, "全帯域_40ms_log_rms_mae_db": 0.47803072195684987, "全帯域_40ms_rms_envelope_nrmse": 0.04194789431773518, "全帯域_40ms_envelope_correlation": 0.9983470499110161, "全帯域_40ms_modulation_mae_db": 0.6067150950019481, "300–1000 Hz_10ms_log_rms_mae_db": 1.3972690516269601, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08992150922017869, "300–1000 Hz_10ms_envelope_correlation": 0.9939905903177912, "300–1000 Hz_10ms_modulation_mae_db": 0.17441425057493856, "300–1000 Hz_40ms_log_rms_mae_db": 0.7620557147494076, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04676167226009155, "300–1000 Hz_40ms_envelope_correlation": 0.9983553003895077, "300–1000 Hz_40ms_modulation_mae_db": 0.5042547698911001, "1000–3000 Hz_10ms_log_rms_mae_db": 1.471146884127763, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12278608117922439, "1000–3000 Hz_10ms_envelope_correlation": 0.9880200610357713, "1000–3000 Hz_10ms_modulation_mae_db": 0.2711143691281323, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8726463315421389, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0697244203796671, "1000–3000 Hz_40ms_envelope_correlation": 0.9959655841908029, "1000–3000 Hz_40ms_modulation_mae_db": 0.269169992628924, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4090934810613938, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15636905921569483, "3000–6000 Hz_10ms_envelope_correlation": 0.9783827000271853, "3000–6000 Hz_10ms_modulation_mae_db": 0.3575797723160914, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8088575129615801, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08947951287738105, "3000–6000 Hz_40ms_envelope_correlation": 0.992284410353375, "3000–6000 Hz_40ms_modulation_mae_db": 0.3279805035606564, "mr_stft_db": 5.455504567003186, "band_mae_db": 0.17960052917220826, "rms_gain_error_db": -0.08233091246065126, "output_peak": 0.5114691255884032}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8372970596712898, "全帯域_10ms_rms_envelope_nrmse": 0.06956961204005488, "全帯域_10ms_envelope_correlation": 0.9955788908453856, "全帯域_10ms_modulation_mae_db": 0.38433537226262754, "全帯域_40ms_log_rms_mae_db": 0.417591626068676, "全帯域_40ms_rms_envelope_nrmse": 0.033456392792029575, "全帯域_40ms_envelope_correlation": 0.9989432849254556, "全帯域_40ms_modulation_mae_db": 0.5015116704591901, "300–1000 Hz_10ms_log_rms_mae_db": 1.4508088456173833, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07627488256138959, "300–1000 Hz_10ms_envelope_correlation": 0.9956538570058138, "300–1000 Hz_10ms_modulation_mae_db": 0.3386876028183237, "300–1000 Hz_40ms_log_rms_mae_db": 0.7528218866618509, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.038587372478063896, "300–1000 Hz_40ms_envelope_correlation": 0.998839760493837, "300–1000 Hz_40ms_modulation_mae_db": 0.4780911529742588, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4445804217153189, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1138101477712268, "1000–3000 Hz_10ms_envelope_correlation": 0.9896753167165496, "1000–3000 Hz_10ms_modulation_mae_db": 0.12718480505850135, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8099918384496752, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06448834073276676, "1000–3000 Hz_40ms_envelope_correlation": 0.9964639998849651, "1000–3000 Hz_40ms_modulation_mae_db": 0.30142948821089416, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4516923194464597, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1678603427778609, "3000–6000 Hz_10ms_envelope_correlation": 0.9760118736436085, "3000–6000 Hz_10ms_modulation_mae_db": 0.6868978122879169, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8599974734603286, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10468037307869807, "3000–6000 Hz_40ms_envelope_correlation": 0.9909346616057547, "3000–6000 Hz_40ms_modulation_mae_db": 0.6088947640626896, "mr_stft_db": 5.484244416283601, "band_mae_db": 0.1924062803557931, "rms_gain_error_db": -0.07492639930991879, "output_peak": 0.5521351471988357}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.81983778399532, "全帯域_10ms_rms_envelope_nrmse": 0.07082238109113809, "全帯域_10ms_envelope_correlation": 0.9954847417566658, "全帯域_10ms_modulation_mae_db": 0.2761816000898419, "全帯域_40ms_log_rms_mae_db": 0.4249490648604041, "全帯域_40ms_rms_envelope_nrmse": 0.041397125796346405, "全帯域_40ms_envelope_correlation": 0.9984262390268298, "全帯域_40ms_modulation_mae_db": 0.20707994204018365, "300–1000 Hz_10ms_log_rms_mae_db": 1.4312371750937602, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08548295124596147, "300–1000 Hz_10ms_envelope_correlation": 0.9945570030633936, "300–1000 Hz_10ms_modulation_mae_db": 0.14627452158574747, "300–1000 Hz_40ms_log_rms_mae_db": 0.8075790606788783, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05445172531955506, "300–1000 Hz_40ms_envelope_correlation": 0.9976906073786133, "300–1000 Hz_40ms_modulation_mae_db": 0.07217106136784975, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4165052435349295, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11239631887749395, "1000–3000 Hz_10ms_envelope_correlation": 0.9902179899110366, "1000–3000 Hz_10ms_modulation_mae_db": 0.47696252830846647, "1000–3000 Hz_40ms_log_rms_mae_db": 0.788573813215356, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06184288505961243, "1000–3000 Hz_40ms_envelope_correlation": 0.9971937595607983, "1000–3000 Hz_40ms_modulation_mae_db": 0.5977382851896901, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4332082091075748, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15059388372563695, "3000–6000 Hz_10ms_envelope_correlation": 0.9802941764901685, "3000–6000 Hz_10ms_modulation_mae_db": 0.7729827519157687, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8325222825153735, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.081696692701147, "3000–6000 Hz_40ms_envelope_correlation": 0.9941908085840617, "3000–6000 Hz_40ms_modulation_mae_db": 0.796988288156841, "mr_stft_db": 5.470909388520301, "band_mae_db": 0.21678766578512465, "rms_gain_error_db": -0.10573060518262081, "output_peak": 0.5422626436134419}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8393972368414045, "全帯域_10ms_rms_envelope_nrmse": 0.0659590744672181, "全帯域_10ms_envelope_correlation": 0.9960870790947174, "全帯域_10ms_modulation_mae_db": 0.35588811873029286, "全帯域_40ms_log_rms_mae_db": 0.44276282938454614, "全帯域_40ms_rms_envelope_nrmse": 0.03696530789095805, "全帯域_40ms_envelope_correlation": 0.9987485672833315, "全帯域_40ms_modulation_mae_db": 0.5161076242414958, "300–1000 Hz_10ms_log_rms_mae_db": 1.4547131686796044, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07487436804606207, "300–1000 Hz_10ms_envelope_correlation": 0.9958410822948613, "300–1000 Hz_10ms_modulation_mae_db": 0.33563968411698064, "300–1000 Hz_40ms_log_rms_mae_db": 0.7892188329698091, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04479192605521803, "300–1000 Hz_40ms_envelope_correlation": 0.9984605951893168, "300–1000 Hz_40ms_modulation_mae_db": 0.4192176527765438, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4684108082162626, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10195632135165765, "1000–3000 Hz_10ms_envelope_correlation": 0.9918725820421245, "1000–3000 Hz_10ms_modulation_mae_db": 0.38400141704888174, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8313497274499716, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04919637083463172, "1000–3000 Hz_40ms_envelope_correlation": 0.9982008484604632, "1000–3000 Hz_40ms_modulation_mae_db": 0.4704351814900021, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4022636499722079, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1509872273862681, "3000–6000 Hz_10ms_envelope_correlation": 0.9800436046980022, "3000–6000 Hz_10ms_modulation_mae_db": 0.8591779893232986, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8413549208464829, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09059206529163508, "3000–6000 Hz_40ms_envelope_correlation": 0.992402247785291, "3000–6000 Hz_40ms_modulation_mae_db": 0.6810167244843001, "mr_stft_db": 5.4647094999889125, "band_mae_db": 0.21294720983494722, "rms_gain_error_db": -0.09010159363839339, "output_peak": 0.537891730823039}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8447480116129256, "全帯域_10ms_rms_envelope_nrmse": 0.07073174797375559, "全帯域_10ms_envelope_correlation": 0.995420602887112, "全帯域_10ms_modulation_mae_db": 0.3100592565128255, "全帯域_40ms_log_rms_mae_db": 0.4258072754338517, "全帯域_40ms_rms_envelope_nrmse": 0.037250619492614795, "全帯域_40ms_envelope_correlation": 0.9986535500711121, "全帯域_40ms_modulation_mae_db": 0.3245089670702434, "300–1000 Hz_10ms_log_rms_mae_db": 1.441919998883582, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.083587071057654, "300–1000 Hz_10ms_envelope_correlation": 0.9947806039578623, "300–1000 Hz_10ms_modulation_mae_db": 0.18493282370552264, "300–1000 Hz_40ms_log_rms_mae_db": 0.7955650962547343, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.049006746446299175, "300–1000 Hz_40ms_envelope_correlation": 0.9981056593416412, "300–1000 Hz_40ms_modulation_mae_db": 0.2516023226394489, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4139303231796694, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11495819174437868, "1000–3000 Hz_10ms_envelope_correlation": 0.9895895605513881, "1000–3000 Hz_10ms_modulation_mae_db": 0.5969238103430575, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8365673700710796, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06423322097966967, "1000–3000 Hz_40ms_envelope_correlation": 0.9967133249750434, "1000–3000 Hz_40ms_modulation_mae_db": 0.6816757560465572, "3000–6000 Hz_10ms_log_rms_mae_db": 1.453861612358319, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1504399875825207, "3000–6000 Hz_10ms_envelope_correlation": 0.9800489311833065, "3000–6000 Hz_10ms_modulation_mae_db": 0.4764747393112225, "3000–6000 Hz_40ms_log_rms_mae_db": 0.822919992052922, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08260170516584452, "3000–6000 Hz_40ms_envelope_correlation": 0.9935163003122075, "3000–6000 Hz_40ms_modulation_mae_db": 0.3844985771588405, "mr_stft_db": 5.47367352839652, "band_mae_db": 0.15281945969165267, "rms_gain_error_db": -0.05821855759546091, "output_peak": 0.5322243646208106}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8242243231891656, "全帯域_10ms_rms_envelope_nrmse": 0.062480845792399105, "全帯域_10ms_envelope_correlation": 0.9966161233855662, "全帯域_10ms_modulation_mae_db": 0.39119586833923387, "全帯域_40ms_log_rms_mae_db": 0.43700894296188275, "全帯域_40ms_rms_envelope_nrmse": 0.034290427728413835, "全帯域_40ms_envelope_correlation": 0.9990803572880249, "全帯域_40ms_modulation_mae_db": 0.40643496087175784, "300–1000 Hz_10ms_log_rms_mae_db": 1.443841706912496, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07069742044447182, "300–1000 Hz_10ms_envelope_correlation": 0.9964120421156871, "300–1000 Hz_10ms_modulation_mae_db": 0.3294443860698519, "300–1000 Hz_40ms_log_rms_mae_db": 0.7509565641014267, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.041042811454255174, "300–1000 Hz_40ms_envelope_correlation": 0.9988569707130867, "300–1000 Hz_40ms_modulation_mae_db": 0.6080435664585859, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5219465176767808, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12205975133764461, "1000–3000 Hz_10ms_envelope_correlation": 0.988244734664218, "1000–3000 Hz_10ms_modulation_mae_db": 0.2992651182185468, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8777185684711263, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07027270464635471, "1000–3000 Hz_40ms_envelope_correlation": 0.9960444456019378, "1000–3000 Hz_40ms_modulation_mae_db": 0.41271336145970494, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4628418982405185, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1608692356238239, "3000–6000 Hz_10ms_envelope_correlation": 0.9775215502640547, "3000–6000 Hz_10ms_modulation_mae_db": 0.6199195337135436, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8668309882989745, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0853580525536596, "3000–6000 Hz_40ms_envelope_correlation": 0.9938062458817338, "3000–6000 Hz_40ms_modulation_mae_db": 0.6404143844487685, "mr_stft_db": 5.480078869369369, "band_mae_db": 0.2029111333832002, "rms_gain_error_db": -0.1409133738497702, "output_peak": 0.5264648361743363}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.846008778801731, "全帯域_10ms_rms_envelope_nrmse": 0.06928624417076161, "全帯域_10ms_envelope_correlation": 0.9956372715928189, "全帯域_10ms_modulation_mae_db": 0.09456150686090509, "全帯域_40ms_log_rms_mae_db": 0.44775282518004694, "全帯域_40ms_rms_envelope_nrmse": 0.03671439542390115, "全帯域_40ms_envelope_correlation": 0.9987420860297087, "全帯域_40ms_modulation_mae_db": 0.22548329249172064, "300–1000 Hz_10ms_log_rms_mae_db": 1.4936915956658343, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07821700437794757, "300–1000 Hz_10ms_envelope_correlation": 0.9954597091423174, "300–1000 Hz_10ms_modulation_mae_db": 0.1648052911816121, "300–1000 Hz_40ms_log_rms_mae_db": 0.7432193645746513, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04496603835306491, "300–1000 Hz_40ms_envelope_correlation": 0.9984568122373195, "300–1000 Hz_40ms_modulation_mae_db": 0.15486638897648433, "1000–3000 Hz_10ms_log_rms_mae_db": 1.479939162067536, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11707664246060137, "1000–3000 Hz_10ms_envelope_correlation": 0.9891097620457914, "1000–3000 Hz_10ms_modulation_mae_db": 0.2279196386452164, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8480778724503505, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0667391034582844, "1000–3000 Hz_40ms_envelope_correlation": 0.9962905897596203, "1000–3000 Hz_40ms_modulation_mae_db": 0.3116899577743184, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4712010073982682, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1601025917761575, "3000–6000 Hz_10ms_envelope_correlation": 0.9784152981269078, "3000–6000 Hz_10ms_modulation_mae_db": 1.0058273954695833, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8608070346822836, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09121880745882173, "3000–6000 Hz_40ms_envelope_correlation": 0.9937271449069782, "3000–6000 Hz_40ms_modulation_mae_db": 1.1644057707677027, "mr_stft_db": 5.459397746274175, "band_mae_db": 0.22815401748051745, "rms_gain_error_db": -0.08665274108635654, "output_peak": 0.5342260803766763}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 91600, "output_samples": 91600, "length_delta_samples": 0, "sample_rate": 16000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 80, "hop_samples": 20, "log_magnitude_mae_db": 5.5489843643627745, "spectral_convergence": 0.2605071025392575, "spectral_convergence_status": "ok", "amplitude_floor": 1.4112644553101518e-06}, {"window_ms": 20, "window_samples": 320, "hop_samples": 80, "log_magnitude_mae_db": 5.287969579278841, "spectral_convergence": 0.25423314997382823, "spectral_convergence_status": "ok", "amplitude_floor": 1.1975531593072457e-06}, {"window_ms": 80, "window_samples": 1280, "hop_samples": 320, "log_magnitude_mae_db": 5.555950556277235, "spectral_convergence": 0.2600507192963697, "spectral_convergence_status": "ok", "amplitude_floor": 1.114415465542996e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.564075826256522e-05, "output_power": 6.24367369232617e-05, "delta_db": 0.5004715797973235, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0010000129923479963, "output_power": 0.0009810223672825635, "delta_db": -0.08326733073502733, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0018259392170112694, "output_power": 0.001804244184646908, "delta_db": -0.05191002201853475, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0005127219920465177, "output_power": 0.00048808881669390003, "delta_db": -0.21383088892405194, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 0.00033320627903786135, "output_power": 0.00031390921565008277, "delta_db": -0.2590911101491752, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 0.0002817706196064759, "output_power": 0.0002766643959018127, "delta_db": -0.07942433851432688, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 6, "band_count": 6, "active_band_mae_db": 0.19799921168973997, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.09076923036205559, "pitch": null, "output_rms_dbfs": -24.060092509610186, "output_peak": 0.5361557004650915, "reference_rms_dbfs": -23.96932327924813, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.46430149997295}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 16000, "samples": 91600, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00020825955187282386, "log_rms_mae_db": 0.8387719200385727, "rms_envelope_nrmse": 0.06928352846813671, "envelope_correlation": 0.9956557897827184, "rms_gain_error_db": -0.09075150654418036, "reference_mean_power": 0.004012756910556895, "output_mean_power": 0.00392977513759015}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 2.2120307480210933e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008889321025104637, "output_power": 0.0008502748336235272, "reference_active": true, "delta_db": -0.19309265358134292}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00022980725896418495, "output_power": 0.00021083930662776936, "reference_active": true, "delta_db": -0.3741216339676431}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.1131932747773025e-05, "output_power": 3.598198291851102e-05, "reference_active": true, "delta_db": -0.5809402399383924}], "active_band_count": 3, "active_band_mae_db": 0.3827181758291262}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.0001984160011662782, "log_rms_mae_db": 0.43229366017215914, "rms_envelope_nrmse": 0.035505776341888604, "envelope_correlation": 0.9988465830131633, "rms_gain_error_db": -0.09076885311536811, "reference_mean_power": 0.0040337408532874226, "output_mean_power": 0.0039503093647126186}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 2.0115882799069226e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008024963383362849, "output_power": 0.000770059993749875, "reference_active": true, "delta_db": -0.17918498006869457}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00011463438169489824, "output_power": 0.00010235562586913543, "reference_active": true, "delta_db": -0.49203174664562543}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.4945953602736586e-06, "output_power": 2.8348101022137652e-06, "reference_active": true, "delta_db": -0.9087292421197801}], "active_band_count": 3, "active_band_mae_db": 0.5266486562780334}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00019054595180557928, "log_rms_mae_db": 1.4214141342046833, "rms_envelope_nrmse": 0.08255539697789854, "envelope_correlation": 0.9949332728275956, "rms_gain_error_db": -0.07594429569946859, "reference_mean_power": 0.0025757888112863028, "output_mean_power": 0.002531137993386716}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.7595886306573375e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007279305516452219, "output_power": 0.0007105964788776634, "reference_active": true, "delta_db": -0.10466896182440517}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019010480993234813, "output_power": 0.00016973210220627593, "reference_active": true, "delta_db": -0.4922911511433545}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6294378423488108e-05, "output_power": 2.4531883865044254e-05, "reference_active": true, "delta_db": -0.3013200887021231}], "active_band_count": 3, "active_band_mae_db": 0.29942673388996094}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.00018019065505981728, "log_rms_mae_db": 0.7215655501665419, "rms_envelope_nrmse": 0.04459439659231298, "envelope_correlation": 0.9984820569917022, "rms_gain_error_db": -0.07594019771446246, "reference_mean_power": 0.0025893611436675294, "output_mean_power": 0.0025444774528787626}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.6269545971301712e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006780414214466183, "output_power": 0.0006628366304531308, "reference_active": true, "delta_db": -0.09849724760777823}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.548437806715927e-05, "output_power": 8.347224153911056e-05, "reference_active": true, "delta_db": -0.583902476118224}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.9327510117604047e-06, "output_power": 2.3764343038097252e-06, "reference_active": true, "delta_db": -0.913493805006806}], "active_band_count": 3, "active_band_mae_db": 0.5319645095776028}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.327720993461315e-05, "log_rms_mae_db": 1.461238711755153, "rms_envelope_nrmse": 0.11392679353123143, "envelope_correlation": 0.9901272303284759, "rms_gain_error_db": -0.2706418994900166, "reference_mean_power": 0.0007122971869413385, "output_mean_power": 0.0006692633442983755}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 4.689927289528067e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00023362430343497353, "output_power": 0.00021889766770035542, "reference_active": true, "delta_db": -0.2827688521947962}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.797902128989837e-05, "output_power": 3.4993359803415606e-05, "reference_active": true, "delta_db": -0.3555812665584188}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.042184778585592e-05, "output_power": 9.759199638295347e-06, "reference_active": true, "delta_db": -0.2853052367565975}], "active_band_count": 3, "active_band_mae_db": 0.3078851185032709}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 8.747046012456969e-05, "log_rms_mae_db": 0.8670612204311741, "rms_envelope_nrmse": 0.06687483464307632, "envelope_correlation": 0.9968743881888192, "rms_gain_error_db": -0.270752400335616, "reference_mean_power": 0.0007159674763911086, "output_mean_power": 0.000672694775006086}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 4.328159646639031e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021700970165722394, "output_power": 0.00020408140518479785, "reference_active": true, "delta_db": -0.2667571398569934}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.702508733600319e-05, "output_power": 1.6200445233607836e-05, "reference_active": true, "delta_db": -0.215623981171426}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.679451250427792e-07, "output_power": 6.823531066042717e-07, "reference_active": true, "delta_db": -1.044830950750017}], "active_band_count": 3, "active_band_mae_db": 0.5090706905928122}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.039773028293347e-05, "log_rms_mae_db": 1.4443047639719677, "rms_envelope_nrmse": 0.14904423971136105, "envelope_correlation": 0.9804579686724403, "rms_gain_error_db": -0.0869047972427448, "reference_mean_power": 0.0003237352885604671, "output_mean_power": 0.00031732154654006637}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.2480235329901466e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.70846061617512e-05, "output_power": 5.634586702618996e-05, "reference_active": true, "delta_db": -0.05656943099659425}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9595191589145483e-05, "output_power": 1.9590896480051483e-05, "reference_active": true, "delta_db": -0.0009520430734871517}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.074204859780537e-06, "output_power": 4.046061711798828e-06, "reference_active": true, "delta_db": -0.983354944367089}], "active_band_count": 3, "active_band_mae_db": 0.34695880614572344}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 6.399293414479695e-05, "log_rms_mae_db": 0.8687471729830932, "rms_envelope_nrmse": 0.08499265848782823, "envelope_correlation": 0.993032482069486, "rms_gain_error_db": -0.08697242089907693, "reference_mean_power": 0.0003253818281247376, "output_mean_power": 0.0003189304992981227}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.1005868407421181e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.4497636322434906e-05, "output_power": 5.411772699503306e-05, "reference_active": true, "delta_db": -0.030381189609469242}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.385752117634814e-06, "output_power": 9.251211170305516e-06, "reference_active": true, "delta_db": -0.06270485718930693}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.7591737704275347e-07, "output_power": 3.089448576998586e-07, "reference_active": true, "delta_db": -0.8521143084151738}], "active_band_count": 3, "active_band_mae_db": 0.31506678507131664}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8802243108213782, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "9b1c91aea6c917a99d98fb18915fd168d6a5b6cc12888998f479d91f9d6ffcd6", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9896071546619194, "standard_deviation": 0.0012190844970587573, "minimum": 0.9880200610357713, "maximum": 0.9918725820421245, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4597122590341767, "standard_deviation": 0.03521927305470213, "minimum": 1.4139303231796694, "maximum": 1.5219465176767808, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.33640710065675916, "standard_deviation": 0.14730419096256334, "minimum": 0.12718480505850135, "maximum": 0.5969238103430575, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.11487128103168236, "standard_deviation": 0.006482162567446801, "minimum": 0.10195632135165765, "maximum": 0.12278608117922439, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9967183675778062, "standard_deviation": 0.0007286646696957499, "minimum": 0.9959655841908029, "maximum": 0.9982008484604632, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.841498342760109, "standard_deviation": 0.031395694443808755, "minimum": 0.788573813215356, "maximum": 0.8777185684711263, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.4442403391741129, "standard_deviation": 0.14853304594829383, "minimum": 0.269169992628924, "maximum": 0.6816757560465572, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0641714850917579, "standard_deviation": 0.006673415993740992, "minimum": 0.04919637083463172, "maximum": 0.07027270464635471, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9788970128882092, "standard_deviation": 0.001592066507462177, "minimum": 0.9760118736436085, "maximum": 0.9804579686724403, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.4410583676945885, "standard_deviation": 0.02466649872193635, "minimum": 1.4022636499722079, "maximum": 1.4712010073982682, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6407273500603935, "standard_deviation": 0.23740451355368972, "minimum": 0.34695880614572344, "maximum": 1.0058273954695833, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15578332097491548, "standard_deviation": 0.006704149820183969, "minimum": 0.14904423971136105, "maximum": 0.1678603427778609, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.992986787687361, "standard_deviation": 0.0010689127140833903, "minimum": 0.9909346616057547, "maximum": 0.9941908085840617, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8452546722251297, "standard_deviation": 0.022288927817666414, "minimum": 0.8088575129615801, "maximum": 0.8687471729830932, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.6149082247138895, "standard_deviation": 0.2842229441923141, "minimum": 0.31506678507131664, "maximum": 1.1644057707677027, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08882748345187691, "standard_deviation": 0.007337990740242723, "minimum": 0.081696692701147, "maximum": 0.10468037307869807, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9952035200906653, "standard_deviation": 0.0007816211866163033, "minimum": 0.9939905903177912, "maximum": 0.9964120421156871, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.441861959585538, "standard_deviation": 0.02791559046637804, "minimum": 1.3972690516269601, "maximum": 1.4936915956658343, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.24670316174286727, "standard_deviation": 0.08604912382754097, "minimum": 0.14627452158574747, "maximum": 0.3386876028183237, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08020132549144547, "standard_deviation": 0.006295549891616245, "minimum": 0.07069742044447182, "maximum": 0.08992150922017869, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9984059703418781, "standard_deviation": 0.0003793662933075985, "minimum": 0.9976906073786133, "maximum": 0.9988569707130867, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7653727587696626, "standard_deviation": 0.029393348758791234, "minimum": 0.7215655501665419, "maximum": 0.8075790606788783, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.3775264280827343, "standard_deviation": 0.1940460328873954, "minimum": 0.07217106136784975, "maximum": 0.6080435664585859, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.045525336119857596, "standard_deviation": 0.00482959460955594, "minimum": 0.038587372478063896, "maximum": 0.05445172531955506, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.19795318842414794, "standard_deviation": 0.023666955225780606, "minimum": 0.15281945969165267, "maximum": 0.22815401748051745, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.469102439476127, "standard_deviation": 0.009966741386026896, "minimum": 5.455504567003186, "maximum": 5.484244416283601, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.5341037036075793, "standard_deviation": 0.011859200226959814, "minimum": 0.5114691255884032, "maximum": 0.5521351471988357, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.09120542668565343, "standard_deviation": 0.024307240984169892, "minimum": -0.1409133738497702, "maximum": -0.05821855759546091, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9955288132423179, "standard_deviation": 0.0008195907517074604, "minimum": 0.9937500065935589, "maximum": 0.9966161233855662, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.839247128845636, "standard_deviation": 0.013522392821526914, "minimum": 0.81983778399532, "maximum": 0.8636919166146789, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3041401325481069, "standard_deviation": 0.10138529218839334, "minimum": 0.09456150686090509, "maximum": 0.39119586833923387, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07010764321700537, "standard_deviation": 0.005821002454185343, "minimum": 0.062480845792399105, "maximum": 0.08272771173257883, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9987234646935803, "standard_deviation": 0.0002469087492063444, "minimum": 0.9983470499110161, "maximum": 0.9990803572880249, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4382746182523021, "standard_deviation": 0.018855439521405788, "minimum": 0.417591626068676, "maximum": 0.47803072195684987, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4143112760568216, "standard_deviation": 0.14848407612703357, "minimum": 0.20707994204018365, "maximum": 0.6067150950019481, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03719099247298595, "standard_deviation": 0.0030659831883021052, "minimum": 0.033456392792029575, "maximum": 0.04194789431773518, "valid_count": 8, "planned_count": 8}}}, {"case": "librispeech_8463-294828-0014", "method": "B", "status": "measured", "mos": {"status": "measured", "value": 2.5378358364105225, "predicted_mos": 2.5378358364105225, "model": "UTMOSv2", "language": "en", "style": "normal", "domain_validation": "未校正の探索的予測", "extraction_seed": 20261012, "repetitions": 1, "input_samples": 91600, "input_sample_rate": 16000, "input_seconds": 5.725, "input_float32_sha256": "824819a74625481b87bafb213ce4d19f51fc34ab037d5d1765a62f4905a594c6", "internal_samples": 91600, "ssl_processed_samples": 48000, "spectrogram_processed_samples_per_frame": 22400, "ssl_tile_repetitions": 1, "spectrogram_tile_repetitions": 1, "reason": null, "seconds": 4.207346900366247, "cpu_threads": 4}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8554980214390965, "全帯域_10ms_rms_envelope_nrmse": 0.0800082925326661, "全帯域_10ms_envelope_correlation": 0.9941108190156774, "全帯域_10ms_modulation_mae_db": 0.22924958379389745, "全帯域_40ms_log_rms_mae_db": 0.45395469238554476, "全帯域_40ms_rms_envelope_nrmse": 0.04080019383875991, "全帯域_40ms_envelope_correlation": 0.9983587436930712, "全帯域_40ms_modulation_mae_db": 0.2440155392099271, "300–1000 Hz_10ms_log_rms_mae_db": 1.7832454852226203, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.1067653164155368, "300–1000 Hz_10ms_envelope_correlation": 0.9914671772952389, "300–1000 Hz_10ms_modulation_mae_db": 0.7138403470900833, "300–1000 Hz_40ms_log_rms_mae_db": 1.0013027654155617, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.06021105620452401, "300–1000 Hz_40ms_envelope_correlation": 0.997123717130426, "300–1000 Hz_40ms_modulation_mae_db": 0.3290157533468916, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6322421150985964, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11535333369476275, "1000–3000 Hz_10ms_envelope_correlation": 0.9894889646382525, "1000–3000 Hz_10ms_modulation_mae_db": 0.5983344671383826, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9681556352890618, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0637228920090621, "1000–3000 Hz_40ms_envelope_correlation": 0.9967266720068106, "1000–3000 Hz_40ms_modulation_mae_db": 0.8120242613909543, "3000–6000 Hz_10ms_log_rms_mae_db": 1.566493462635116, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17260614016325826, "3000–6000 Hz_10ms_envelope_correlation": 0.9743450257609665, "3000–6000 Hz_10ms_modulation_mae_db": 1.702301304926955, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9331115958498675, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09913465331474296, "3000–6000 Hz_40ms_envelope_correlation": 0.991815501659275, "3000–6000 Hz_40ms_modulation_mae_db": 1.7932251688392575, "mr_stft_db": 5.713600841023035, "band_mae_db": 0.2584157898278401, "rms_gain_error_db": -0.0449450293609604, "output_peak": 0.5323458346142188}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8288415256094962, "全帯域_10ms_rms_envelope_nrmse": 0.07641987031075688, "全帯域_10ms_envelope_correlation": 0.9947572700239526, "全帯域_10ms_modulation_mae_db": 0.5491490707729314, "全帯域_40ms_log_rms_mae_db": 0.44416759173429954, "全帯域_40ms_rms_envelope_nrmse": 0.03986536986114584, "全帯域_40ms_envelope_correlation": 0.99860819541078, "全帯域_40ms_modulation_mae_db": 0.8778774895312228, "300–1000 Hz_10ms_log_rms_mae_db": 1.6559252126250417, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08910072533084326, "300–1000 Hz_10ms_envelope_correlation": 0.994103011781052, "300–1000 Hz_10ms_modulation_mae_db": 0.32767280966907936, "300–1000 Hz_40ms_log_rms_mae_db": 0.9577133964286279, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04635536951764492, "300–1000 Hz_40ms_envelope_correlation": 0.9983789050079271, "300–1000 Hz_40ms_modulation_mae_db": 0.6794539740158854, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6532941598221438, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11572174049818228, "1000–3000 Hz_10ms_envelope_correlation": 0.9898612035558966, "1000–3000 Hz_10ms_modulation_mae_db": 0.8739091783356684, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9869720496390267, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0662568130884565, "1000–3000 Hz_40ms_envelope_correlation": 0.9970296405455559, "1000–3000 Hz_40ms_modulation_mae_db": 1.2123872947858991, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6461026021742564, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17826103020931866, "3000–6000 Hz_10ms_envelope_correlation": 0.9726197342440189, "3000–6000 Hz_10ms_modulation_mae_db": 1.1627798198393606, "3000–6000 Hz_40ms_log_rms_mae_db": 0.98973570597247, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10271683946712744, "3000–6000 Hz_40ms_envelope_correlation": 0.9912801531204807, "3000–6000 Hz_40ms_modulation_mae_db": 1.5345102387248364, "mr_stft_db": 5.70789471756338, "band_mae_db": 0.24968892797097375, "rms_gain_error_db": -0.12574588659352448, "output_peak": 0.5489207743155798}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8193312456073294, "全帯域_10ms_rms_envelope_nrmse": 0.06542692840005956, "全帯域_10ms_envelope_correlation": 0.996280086068742, "全帯域_10ms_modulation_mae_db": 0.4891241491202945, "全帯域_40ms_log_rms_mae_db": 0.4118928273384515, "全帯域_40ms_rms_envelope_nrmse": 0.03705846236046492, "全帯域_40ms_envelope_correlation": 0.9989072305912402, "全帯域_40ms_modulation_mae_db": 0.680176020297742, "300–1000 Hz_10ms_log_rms_mae_db": 1.6166849179660483, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08355325027515381, "300–1000 Hz_10ms_envelope_correlation": 0.9949075390608297, "300–1000 Hz_10ms_modulation_mae_db": 0.35332690841061626, "300–1000 Hz_40ms_log_rms_mae_db": 0.9072394584076817, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.052413268368203744, "300–1000 Hz_40ms_envelope_correlation": 0.9979989394716606, "300–1000 Hz_40ms_modulation_mae_db": 0.6061079571451461, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5885275099054905, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12116585012056877, "1000–3000 Hz_10ms_envelope_correlation": 0.9887021330969525, "1000–3000 Hz_10ms_modulation_mae_db": 0.8047444863244398, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9322982985738878, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07504434039568161, "1000–3000 Hz_40ms_envelope_correlation": 0.9958073748771333, "1000–3000 Hz_40ms_modulation_mae_db": 1.012916699949744, "3000–6000 Hz_10ms_log_rms_mae_db": 1.577780733635216, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16528823893116917, "3000–6000 Hz_10ms_envelope_correlation": 0.9761342672014366, "3000–6000 Hz_10ms_modulation_mae_db": 0.9243859747267528, "3000–6000 Hz_40ms_log_rms_mae_db": 0.914159216809801, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0946435843884844, "3000–6000 Hz_40ms_envelope_correlation": 0.9919735043579593, "3000–6000 Hz_40ms_modulation_mae_db": 1.0349928265413102, "mr_stft_db": 5.703609244669349, "band_mae_db": 0.2903144577675634, "rms_gain_error_db": -0.15237685634391943, "output_peak": 0.5352880541404852}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8136329128610471, "全帯域_10ms_rms_envelope_nrmse": 0.06809623690991935, "全帯域_10ms_envelope_correlation": 0.995849823725841, "全帯域_10ms_modulation_mae_db": 0.8263684764705573, "全帯域_40ms_log_rms_mae_db": 0.4620340715843189, "全帯域_40ms_rms_envelope_nrmse": 0.039825952458794805, "全帯域_40ms_envelope_correlation": 0.9985667754432617, "全帯域_40ms_modulation_mae_db": 0.9621943207080634, "300–1000 Hz_10ms_log_rms_mae_db": 1.6841545398067623, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08940653026942665, "300–1000 Hz_10ms_envelope_correlation": 0.9940754411546555, "300–1000 Hz_10ms_modulation_mae_db": 0.721127486667888, "300–1000 Hz_40ms_log_rms_mae_db": 0.9688846601313335, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05940024010314428, "300–1000 Hz_40ms_envelope_correlation": 0.9972818201084339, "300–1000 Hz_40ms_modulation_mae_db": 0.970905419982491, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6123111919189577, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12301774002697734, "1000–3000 Hz_10ms_envelope_correlation": 0.9880381812782231, "1000–3000 Hz_10ms_modulation_mae_db": 0.6452059150552804, "1000–3000 Hz_40ms_log_rms_mae_db": 1.0125494860275817, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07401388484865869, "1000–3000 Hz_40ms_envelope_correlation": 0.9955418940245505, "1000–3000 Hz_40ms_modulation_mae_db": 0.6616371715546998, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6163976103610103, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17833544430208922, "3000–6000 Hz_10ms_envelope_correlation": 0.9725927950131121, "3000–6000 Hz_10ms_modulation_mae_db": 1.472742898952032, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9435036752673915, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10089150347026267, "3000–6000 Hz_40ms_envelope_correlation": 0.9916684378297393, "3000–6000 Hz_40ms_modulation_mae_db": 1.5776699640966534, "mr_stft_db": 5.694235753841279, "band_mae_db": 0.24661949994193477, "rms_gain_error_db": -0.11401550094213932, "output_peak": 0.5193279042992052}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8176180119747551, "全帯域_10ms_rms_envelope_nrmse": 0.06651026496070457, "全帯域_10ms_envelope_correlation": 0.996126301758405, "全帯域_10ms_modulation_mae_db": 0.6695625009559354, "全帯域_40ms_log_rms_mae_db": 0.43171092135413464, "全帯域_40ms_rms_envelope_nrmse": 0.038464541999462046, "全帯域_40ms_envelope_correlation": 0.9987664436699512, "全帯域_40ms_modulation_mae_db": 0.9118367118902363, "300–1000 Hz_10ms_log_rms_mae_db": 1.652373253467967, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07852593874516715, "300–1000 Hz_10ms_envelope_correlation": 0.9954919446813324, "300–1000 Hz_10ms_modulation_mae_db": 0.4452647767312053, "300–1000 Hz_40ms_log_rms_mae_db": 0.9642474810274932, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04713040978001054, "300–1000 Hz_40ms_envelope_correlation": 0.9983780762222966, "300–1000 Hz_40ms_modulation_mae_db": 0.729298759673198, "1000–3000 Hz_10ms_log_rms_mae_db": 1.6060800753966262, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11898097628771143, "1000–3000 Hz_10ms_envelope_correlation": 0.9895154090211601, "1000–3000 Hz_10ms_modulation_mae_db": 0.9764761436458644, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9924837594014906, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0744606092914218, "1000–3000 Hz_40ms_envelope_correlation": 0.9963644364233787, "1000–3000 Hz_40ms_modulation_mae_db": 1.1972934846352155, "3000–6000 Hz_10ms_log_rms_mae_db": 1.637466987694015, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17323833563401417, "3000–6000 Hz_10ms_envelope_correlation": 0.9734117317460367, "3000–6000 Hz_10ms_modulation_mae_db": 0.5632421060588916, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9686528909966262, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09487962774705877, "3000–6000 Hz_40ms_envelope_correlation": 0.9914212257654864, "3000–6000 Hz_40ms_modulation_mae_db": 0.637031262282907, "mr_stft_db": 5.707622317777681, "band_mae_db": 0.2561774397912614, "rms_gain_error_db": -0.14096820366075483, "output_peak": 0.552544282101526}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8283223274987301, "全帯域_10ms_rms_envelope_nrmse": 0.07000561593528987, "全帯域_10ms_envelope_correlation": 0.9955127662719163, "全帯域_10ms_modulation_mae_db": 0.395046515608674, "全帯域_40ms_log_rms_mae_db": 0.4410694799418849, "全帯域_40ms_rms_envelope_nrmse": 0.03878346696998454, "全帯域_40ms_envelope_correlation": 0.998536086600141, "全帯域_40ms_modulation_mae_db": 0.51719905218961, "300–1000 Hz_10ms_log_rms_mae_db": 1.725021137809427, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.081260996677714, "300–1000 Hz_10ms_envelope_correlation": 0.995065742827726, "300–1000 Hz_10ms_modulation_mae_db": 0.09497630023711283, "300–1000 Hz_40ms_log_rms_mae_db": 0.9968477633487617, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04751083928937265, "300–1000 Hz_40ms_envelope_correlation": 0.9982030032457058, "300–1000 Hz_40ms_modulation_mae_db": 0.26480060463084126, "1000–3000 Hz_10ms_log_rms_mae_db": 1.639316468703814, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1125819491991731, "1000–3000 Hz_10ms_envelope_correlation": 0.9905278593529031, "1000–3000 Hz_10ms_modulation_mae_db": 0.4946109675496046, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9721473554067198, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06302257669284886, "1000–3000 Hz_40ms_envelope_correlation": 0.9974973117437828, "1000–3000 Hz_40ms_modulation_mae_db": 0.9151420442392665, "3000–6000 Hz_10ms_log_rms_mae_db": 1.614898479018531, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16830126775208087, "3000–6000 Hz_10ms_envelope_correlation": 0.975603415204703, "3000–6000 Hz_10ms_modulation_mae_db": 1.4112428286973548, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9279662020903927, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09542276372215026, "3000–6000 Hz_40ms_envelope_correlation": 0.9924498250174786, "3000–6000 Hz_40ms_modulation_mae_db": 1.4832327228586226, "mr_stft_db": 5.70713213768206, "band_mae_db": 0.24897496008449907, "rms_gain_error_db": -0.06364230777177149, "output_peak": 0.569810028240914}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8202603055553286, "全帯域_10ms_rms_envelope_nrmse": 0.07193405016784706, "全帯域_10ms_envelope_correlation": 0.9952464419037622, "全帯域_10ms_modulation_mae_db": 0.20725686382739764, "全帯域_40ms_log_rms_mae_db": 0.4133450739940347, "全帯域_40ms_rms_envelope_nrmse": 0.03818345297145783, "全帯域_40ms_envelope_correlation": 0.9985636337726141, "全帯域_40ms_modulation_mae_db": 0.16349066816277394, "300–1000 Hz_10ms_log_rms_mae_db": 1.706805747635708, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08689702125393232, "300–1000 Hz_10ms_envelope_correlation": 0.9943849962737507, "300–1000 Hz_10ms_modulation_mae_db": 0.062479790894899266, "300–1000 Hz_40ms_log_rms_mae_db": 0.9937466403461185, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05028216490807334, "300–1000 Hz_40ms_envelope_correlation": 0.9980327353566609, "300–1000 Hz_40ms_modulation_mae_db": 0.04278825477161977, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5433426274691824, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1101826434095582, "1000–3000 Hz_10ms_envelope_correlation": 0.9905299121253551, "1000–3000 Hz_10ms_modulation_mae_db": 0.17249408294105373, "1000–3000 Hz_40ms_log_rms_mae_db": 0.9181046669693275, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06766900810492184, "1000–3000 Hz_40ms_envelope_correlation": 0.996395938996712, "1000–3000 Hz_40ms_modulation_mae_db": 0.34916510470393497, "3000–6000 Hz_10ms_log_rms_mae_db": 1.6172924590547504, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1752429035959437, "3000–6000 Hz_10ms_envelope_correlation": 0.9728345416068848, "3000–6000 Hz_10ms_modulation_mae_db": 1.245317069738322, "3000–6000 Hz_40ms_log_rms_mae_db": 0.9218040131390125, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.10085320547963084, "3000–6000 Hz_40ms_envelope_correlation": 0.9903663789750259, "3000–6000 Hz_40ms_modulation_mae_db": 1.262977238684744, "mr_stft_db": 5.708866904160405, "band_mae_db": 0.1699390654047034, "rms_gain_error_db": -0.03521839629558429, "output_peak": 0.5275069243495719}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7984487878784056, "全帯域_10ms_rms_envelope_nrmse": 0.06592243150297081, "全帯域_10ms_envelope_correlation": 0.9960400856043479, "全帯域_10ms_modulation_mae_db": 0.10506897936926092, "全帯域_40ms_log_rms_mae_db": 0.3946922869956277, "全帯域_40ms_rms_envelope_nrmse": 0.03267430794700025, "全帯域_40ms_envelope_correlation": 0.9989937797877739, "全帯域_40ms_modulation_mae_db": 0.12591785572974065, "300–1000 Hz_10ms_log_rms_mae_db": 1.6721062646212554, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07845904509047734, "300–1000 Hz_10ms_envelope_correlation": 0.9954094947588684, "300–1000 Hz_10ms_modulation_mae_db": 0.31610442269509237, "300–1000 Hz_40ms_log_rms_mae_db": 0.8875991417927401, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04014475112007622, "300–1000 Hz_40ms_envelope_correlation": 0.9987544931240698, "300–1000 Hz_40ms_modulation_mae_db": 0.22140103453725038, "1000–3000 Hz_10ms_log_rms_mae_db": 1.5403390559520593, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10806309566079689, "1000–3000 Hz_10ms_envelope_correlation": 0.9909899151340815, "1000–3000 Hz_10ms_modulation_mae_db": 0.817610022042464, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8976745255202642, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06144810002196429, "1000–3000 Hz_40ms_envelope_correlation": 0.9972027597399686, "1000–3000 Hz_40ms_modulation_mae_db": 0.8825381728963911, "3000–6000 Hz_10ms_log_rms_mae_db": 1.5972278420083452, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1704217819570103, "3000–6000 Hz_10ms_envelope_correlation": 0.9745695047642372, "3000–6000 Hz_10ms_modulation_mae_db": 1.0270877594064562, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8880464221027886, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08706965270201548, "3000–6000 Hz_40ms_envelope_correlation": 0.9934392782053677, "3000–6000 Hz_40ms_modulation_mae_db": 1.0252717603773678, "mr_stft_db": 5.710321352823013, "band_mae_db": 0.27559154396776003, "rms_gain_error_db": -0.06549736914203522, "output_peak": 0.5454872519836395}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 91600, "output_samples": 91600, "length_delta_samples": 0, "sample_rate": 16000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 80, "hop_samples": 20, "log_magnitude_mae_db": 5.829721452067407, "spectral_convergence": 0.2728116873857294, "spectral_convergence_status": "ok", "amplitude_floor": 1.4112644553101518e-06}, {"window_ms": 20, "window_samples": 320, "hop_samples": 80, "log_magnitude_mae_db": 5.575052321107012, "spectral_convergence": 0.265918938028395, "spectral_convergence_status": "ok", "amplitude_floor": 1.1975531593072457e-06}, {"window_ms": 80, "window_samples": 1280, "hop_samples": 320, "log_magnitude_mae_db": 5.736028749894684, "spectral_convergence": 0.2677833164182978, "spectral_convergence_status": "ok", "amplitude_floor": 1.114415465542996e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.564075826256522e-05, "output_power": 6.301000504917583e-05, "delta_db": 0.5401647456649854, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0010000129923479963, "output_power": 0.001051871441031418, "delta_db": 0.21957021434488538, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0018259392170112694, "output_power": 0.0017791838282398037, "delta_db": -0.1126549394459252, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0005127219920465177, "output_power": 0.0004931323361288829, "delta_db": -0.16918464492684754, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 0.00033320627903786135, "output_power": 0.0003192352477449045, "delta_db": -0.18602339671040483, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 0.0002817706196064759, "output_power": 0.0002615808985017485, "delta_db": -0.3228967978739921, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 6, "band_count": 6, "active_band_mae_db": 0.2584157898278401, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.0449450293609604, "pitch": null, "output_rms_dbfs": -24.014268308609093, "output_peak": 0.5323458346142188, "reference_rms_dbfs": -23.96932327924813, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.713600841023035}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 16000, "samples": 91600, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00020825955187282386, "log_rms_mae_db": 0.8554980214390965, "rms_envelope_nrmse": 0.0800082925326661, "envelope_correlation": 0.9941108190156774, "rms_gain_error_db": -0.0449334793485868, "reference_mean_power": 0.004012756910556895, "output_mean_power": 0.003971453696138742}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 2.2120307480210933e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008889321025104637, "output_power": 0.0008813544610514682, "reference_active": true, "delta_db": -0.03717983335138528}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00022980725896418495, "output_power": 0.00021134255613612586, "reference_active": true, "delta_db": -0.3637678690481105}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.1131932747773025e-05, "output_power": 4.393991595951728e-05, "reference_active": true, "delta_db": 0.2868010489821966}], "active_band_count": 3, "active_band_mae_db": 0.22924958379389745}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.0001984160011662782, "log_rms_mae_db": 0.45395469238554476, "rms_envelope_nrmse": 0.04080019383875991, "envelope_correlation": 0.9983587436930712, "rms_gain_error_db": -0.04493670712097244, "reference_mean_power": 0.0040337408532874226, "output_mean_power": 0.003992218684524169}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 2.0115882799069226e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008024963383362849, "output_power": 0.0008014301309965742, "reference_active": true, "delta_db": -0.005773930928382166}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00011463438169489824, "output_power": 0.0001067421920334354, "reference_active": true, "delta_db": -0.309787757256695}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.4945953602736586e-06, "output_power": 3.1750341660195293e-06, "reference_active": true, "delta_db": -0.41648492944470417}], "active_band_count": 3, "active_band_mae_db": 0.2440155392099271}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00019054595180557928, "log_rms_mae_db": 1.7832454852226203, "rms_envelope_nrmse": 0.1067653164155368, "envelope_correlation": 0.9914671772952389, "rms_gain_error_db": -0.009585102316738528, "reference_mean_power": 0.0025757888112863028, "output_mean_power": 0.0025701101818776124}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.7595886306573375e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007279305516452219, "output_power": 0.000729229898577579, "reference_active": true, "delta_db": 0.007745191715534406}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019010480993234813, "output_power": 0.00017374419997169882, "reference_active": true, "delta_db": -0.3908278965877553}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6294378423488108e-05, "output_power": 3.927875414183769e-05, "reference_active": true, "delta_db": 1.74294795296696}], "active_band_count": 3, "active_band_mae_db": 0.7138403470900833}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.00018019065505981728, "log_rms_mae_db": 1.0013027654155617, "rms_envelope_nrmse": 0.06021105620452401, "envelope_correlation": 0.997123717130426, "rms_gain_error_db": -0.009587432573413527, "reference_mean_power": 0.0025893611436675294, "output_mean_power": 0.002583651206167721}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.6269545971301712e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006780414214466183, "output_power": 0.0006851047850888433, "reference_active": true, "delta_db": 0.04500775182716807}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.548437806715927e-05, "output_power": 8.776509960273547e-05, "reference_active": true, "delta_db": -0.36610473648189595}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.9327510117604047e-06, "output_power": 3.348641617807541e-06, "reference_active": true, "delta_db": 0.5759347717316108}], "active_band_count": 3, "active_band_mae_db": 0.3290157533468916}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.327720993461315e-05, "log_rms_mae_db": 1.6322421150985964, "rms_envelope_nrmse": 0.11535333369476275, "envelope_correlation": 0.9894889646382525, "rms_gain_error_db": -0.1550321349439242, "reference_mean_power": 0.0007122971869413385, "output_mean_power": 0.000687318471643407}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 4.689927289528067e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00023362430343497353, "output_power": 0.00022189574471062867, "reference_active": true, "delta_db": -0.22369045656480432}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.797902128989837e-05, "output_power": 3.133053069346508e-05, "reference_active": true, "delta_db": -0.8357601762377713}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.042184778585592e-05, "output_power": 8.79811124580044e-06, "reference_active": true, "delta_db": -0.7355527686125719}], "active_band_count": 3, "active_band_mae_db": 0.5983344671383826}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 8.747046012456969e-05, "log_rms_mae_db": 0.9681556352890618, "rms_envelope_nrmse": 0.0637228920090621, "envelope_correlation": 0.9967266720068106, "rms_gain_error_db": -0.15504080445715185, "reference_mean_power": 0.0007159674763911086, "output_mean_power": 0.0006908586729000991}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 4.328159646639031e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021700970165722394, "output_power": 0.00020575602462172604, "reference_active": true, "delta_db": -0.2312658950167039}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.702508733600319e-05, "output_power": 1.413780950810203e-05, "reference_active": true, "delta_db": -0.8070722274253208}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.679451250427792e-07, "output_power": 6.290987207156614e-07, "reference_active": true, "delta_db": -1.3977346617308382}], "active_band_count": 3, "active_band_mae_db": 0.8120242613909543}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.039773028293347e-05, "log_rms_mae_db": 1.566493462635116, "rms_envelope_nrmse": 0.17260614016325826, "envelope_correlation": 0.9743450257609665, "rms_gain_error_db": -0.3710810245202244, "reference_mean_power": 0.0003237352885604671, "output_mean_power": 0.0002972226756981404}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.2480235329901466e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.70846061617512e-05, "output_power": 5.1456974324829594e-05, "reference_active": true, "delta_db": -0.45074763048715966}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9595191589145483e-05, "output_power": 1.612394660002393e-05, "reference_active": true, "delta_db": -0.846781629178742}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.074204859780537e-06, "output_power": 2.1107195437006773e-06, "reference_active": true, "delta_db": -3.8093746551149636}], "active_band_count": 3, "active_band_mae_db": 1.702301304926955}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 6.399293414479695e-05, "log_rms_mae_db": 0.9331115958498675, "rms_envelope_nrmse": 0.09913465331474296, "envelope_correlation": 0.991815501659275, "rms_gain_error_db": -0.37120310504677373, "reference_mean_power": 0.0003253818281247376, "output_mean_power": 0.0002987259729919243}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.1005868407421181e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.4497636322434906e-05, "output_power": 4.794599468703662e-05, "reference_active": true, "delta_db": -0.5562533349098124}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.385752117634814e-06, "output_power": 7.816836140777993e-06, "reference_active": true, "delta_db": -0.7943807187398473}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.7591737704275347e-07, "output_power": 1.4865799001078656e-07, "reference_active": true, "delta_db": -4.029041452868112}], "active_band_count": 3, "active_band_mae_db": 1.7932251688392575}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8707143079366993, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "eb8d11e6c338f7bc53669a4c76799daffc95868ae5384b6e1a636fcdda461ade", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.989706697275353, "standard_deviation": 0.000992802931762422, "minimum": 0.9880381812782231, "maximum": 0.9909899151340815, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.6019316505333587, "standard_deviation": 0.04223301497525902, "minimum": 1.5403390559520593, "maximum": 1.6532941598221438, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.6729231578790947, "standard_deviation": 0.2561827365325182, "minimum": 0.17249408294105373, "maximum": 0.9764761436458644, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.11563341611221634, "standard_deviation": 0.005247592609075813, "minimum": 0.10806309566079689, "maximum": 0.12301774002697734, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9965707535447366, "standard_deviation": 0.0006768894778494946, "minimum": 0.9955418940245505, "maximum": 0.9974973117437828, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.96004822210342, "standard_deviation": 0.03993790994692167, "minimum": 0.8976745255202642, "maximum": 1.0125494860275817, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.8803880292695132, "standard_deviation": 0.2838893726345559, "minimum": 0.34916510470393497, "maximum": 1.2123872947858991, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06820477805662697, "standard_deviation": 0.005559259813138555, "minimum": 0.06144810002196429, "maximum": 0.07504434039568161, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9740138769426745, "standard_deviation": 0.0013710052067565982, "minimum": 0.9725927950131121, "maximum": 0.9761342672014366, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.609207522072655, "standard_deviation": 0.027425070748796406, "minimum": 1.566493462635116, "maximum": 1.6461026021742564, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 1.1886374702932656, "standard_deviation": 0.3555774566767666, "minimum": 0.5632421060588916, "maximum": 1.702301304926955, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.17271189281811056, "standard_deviation": 0.004612412702413742, "minimum": 0.16528823893116917, "maximum": 0.17833544430208922, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9918017881163517, "standard_deviation": 0.0008965101082605896, "minimum": 0.9903663789750259, "maximum": 0.9934392782053677, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.9358724652785437, "standard_deviation": 0.031760012329801024, "minimum": 0.8880464221027886, "maximum": 0.98973570597247, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 1.2936138978007123, "standard_deviation": 0.3770595519840399, "minimum": 0.637031262282907, "maximum": 1.7932251688392575, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.0969514787864341, "standard_deviation": 0.005047761884369242, "minimum": 0.08706965270201548, "maximum": 0.10271683946712744, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9943631684791817, "standard_deviation": 0.0012926492372782243, "minimum": 0.9914671772952389, "maximum": 0.9954919446813324, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.6870395698943537, "standard_deviation": 0.05132507073787533, "minimum": 1.6166849179660483, "maximum": 1.7832454852226203, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.37934910529949706, "standard_deviation": 0.24543351364901977, "minimum": 0.062479790894899266, "maximum": 0.721127486667888, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08674610300728142, "standard_deviation": 0.009180265563654515, "minimum": 0.07845904509047734, "maximum": 0.1067653164155368, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9980189612083976, "standard_deviation": 0.0005579082566666341, "minimum": 0.997123717130426, "maximum": 0.9987544931240698, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.9596976633622898, "standard_deviation": 0.041968604634506856, "minimum": 0.8875991417927401, "maximum": 1.0013027654155617, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.48047146976291544, "standard_deviation": 0.31303945139040545, "minimum": 0.04278825477161977, "maximum": 0.970905419982491, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.05043101241138122, "standard_deviation": 0.0067811421434009036, "minimum": 0.04014475112007622, "maximum": 0.06021105620452401, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.249465210594567, "standard_deviation": 0.03547475845570185, "minimum": 0.1699390654047034, "maximum": 0.2903144577675634, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.706660408692525, "standard_deviation": 0.005766822607392972, "minimum": 5.694235753841279, "maximum": 5.713600841023035, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.5414038817556425, "standard_deviation": 0.016054020570844277, "minimum": 0.5193279042992052, "maximum": 0.569810028240914, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.09280119376383618, "standard_deviation": 0.04567970874291809, "minimum": -0.15237685634391943, "maximum": -0.03521839629558429, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9954904492965806, "standard_deviation": 0.0007521449185319631, "minimum": 0.9941108190156774, "maximum": 0.996280086068742, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.8227441423030235, "standard_deviation": 0.01629410104158356, "minimum": 0.7984487878784056, "maximum": 0.8554980214390965, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4338532674898686, "standard_deviation": 0.2474985409118537, "minimum": 0.10506897936926092, "maximum": 0.8263684764705573, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07054046134002678, "standard_deviation": 0.005293210764610429, "minimum": 0.06542692840005956, "maximum": 0.0800082925326661, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9986626111211041, "standard_deviation": 0.00021063797635128978, "minimum": 0.9983587436930712, "maximum": 0.9989937797877739, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4316083681660371, "standard_deviation": 0.023168286198308796, "minimum": 0.3946922869956277, "maximum": 0.4620340715843189, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5603384572149146, "standard_deviation": 0.34813007832152737, "minimum": 0.12591785572974065, "maximum": 0.9621943207080634, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03820696855088376, "standard_deviation": 0.002519208166750112, "minimum": 0.03267430794700025, "maximum": 0.04080019383875991, "valid_count": 8, "planned_count": 8}}}, {"case": "librispeech_8463-294828-0014", "method": "C", "status": "measured", "mos": {"status": "pending", "value": null}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8429217028249015, "全帯域_10ms_rms_envelope_nrmse": 0.0680008516088581, "全帯域_10ms_envelope_correlation": 0.9957821482650732, "全帯域_10ms_modulation_mae_db": 0.24661162730485542, "全帯域_40ms_log_rms_mae_db": 0.43202746523018076, "全帯域_40ms_rms_envelope_nrmse": 0.034312186835629074, "全帯域_40ms_envelope_correlation": 0.9988822204432637, "全帯域_40ms_modulation_mae_db": 0.4072972326558486, "300–1000 Hz_10ms_log_rms_mae_db": 1.378905350751675, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07976169285276245, "300–1000 Hz_10ms_envelope_correlation": 0.9952427042411239, "300–1000 Hz_10ms_modulation_mae_db": 0.4115998648184656, "300–1000 Hz_40ms_log_rms_mae_db": 0.8092162543609015, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.041944106229267045, "300–1000 Hz_40ms_envelope_correlation": 0.9986178806979206, "300–1000 Hz_40ms_modulation_mae_db": 0.38920495172366604, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3647110277045018, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10036117869983811, "1000–3000 Hz_10ms_envelope_correlation": 0.9921328419112964, "1000–3000 Hz_10ms_modulation_mae_db": 0.3852544256420288, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7855792224912868, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05747073260586687, "1000–3000 Hz_40ms_envelope_correlation": 0.9974263909608585, "1000–3000 Hz_40ms_modulation_mae_db": 0.5869687867161496, "3000–6000 Hz_10ms_log_rms_mae_db": 1.347249121769675, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14665032280241475, "3000–6000 Hz_10ms_envelope_correlation": 0.9815314766695558, "3000–6000 Hz_10ms_modulation_mae_db": 0.34828534461650373, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7967707155140565, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07815256332461751, "3000–6000 Hz_40ms_envelope_correlation": 0.995033678932814, "3000–6000 Hz_40ms_modulation_mae_db": 0.34429444660162273, "mr_stft_db": 5.434595819009947, "band_mae_db": 0.2101786265221676, "rms_gain_error_db": -0.06674816652080302, "output_peak": 0.5569887868377952}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8570484309259239, "全帯域_10ms_rms_envelope_nrmse": 0.0725144365231212, "全帯域_10ms_envelope_correlation": 0.9954148677512392, "全帯域_10ms_modulation_mae_db": 0.5202649701516529, "全帯域_40ms_log_rms_mae_db": 0.453729848297837, "全帯域_40ms_rms_envelope_nrmse": 0.04255174014110374, "全帯域_40ms_envelope_correlation": 0.9985199213812926, "全帯域_40ms_modulation_mae_db": 0.7036344675629113, "300–1000 Hz_10ms_log_rms_mae_db": 1.3834903149515876, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08695151473631474, "300–1000 Hz_10ms_envelope_correlation": 0.9945461904472376, "300–1000 Hz_10ms_modulation_mae_db": 0.470805630407094, "300–1000 Hz_40ms_log_rms_mae_db": 0.7444307184186582, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.055066304752861485, "300–1000 Hz_40ms_envelope_correlation": 0.9978683540832867, "300–1000 Hz_40ms_modulation_mae_db": 0.7775024169728098, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3628310091584974, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11219300356728377, "1000–3000 Hz_10ms_envelope_correlation": 0.9902973283145078, "1000–3000 Hz_10ms_modulation_mae_db": 0.573844910875803, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8228015376052328, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06598107819361637, "1000–3000 Hz_40ms_envelope_correlation": 0.9967830599357592, "1000–3000 Hz_40ms_modulation_mae_db": 0.48318806069376824, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3610995703321553, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15349751929918065, "3000–6000 Hz_10ms_envelope_correlation": 0.9793459363901097, "3000–6000 Hz_10ms_modulation_mae_db": 0.4313815974686801, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8283178154065108, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08367007109002962, "3000–6000 Hz_40ms_envelope_correlation": 0.9936358005017691, "3000–6000 Hz_40ms_modulation_mae_db": 0.541028566566036, "mr_stft_db": 5.433782044597218, "band_mae_db": 0.24432232713931654, "rms_gain_error_db": -0.16308635548388972, "output_peak": 0.5405773080474057}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8496895263485286, "全帯域_10ms_rms_envelope_nrmse": 0.07604746726840243, "全帯域_10ms_envelope_correlation": 0.9949786998102386, "全帯域_10ms_modulation_mae_db": 0.4496898757162218, "全帯域_40ms_log_rms_mae_db": 0.4563511648472474, "全帯域_40ms_rms_envelope_nrmse": 0.04855659470464923, "全帯域_40ms_envelope_correlation": 0.9980293092296916, "全帯域_40ms_modulation_mae_db": 0.580061646086623, "300–1000 Hz_10ms_log_rms_mae_db": 1.297410595789358, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.09589818275973208, "300–1000 Hz_10ms_envelope_correlation": 0.9933873274856431, "300–1000 Hz_10ms_modulation_mae_db": 0.3816551388667582, "300–1000 Hz_40ms_log_rms_mae_db": 0.7391880560235246, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.06772961616352093, "300–1000 Hz_40ms_envelope_correlation": 0.9967134082428089, "300–1000 Hz_40ms_modulation_mae_db": 0.6167052183780205, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3277183856707948, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1054589040995258, "1000–3000 Hz_10ms_envelope_correlation": 0.9912306300254032, "1000–3000 Hz_10ms_modulation_mae_db": 0.14595961355005646, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7780761861485289, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05738209774172291, "1000–3000 Hz_40ms_envelope_correlation": 0.9973622389592678, "1000–3000 Hz_40ms_modulation_mae_db": 0.211576480543979, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3002223009870713, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15136685523219823, "3000–6000 Hz_10ms_envelope_correlation": 0.9814721982691191, "3000–6000 Hz_10ms_modulation_mae_db": 0.39598736887073055, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8005723428598203, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09558325745860327, "3000–6000 Hz_40ms_envelope_correlation": 0.9935752725004245, "3000–6000 Hz_40ms_modulation_mae_db": 0.5945207421413371, "mr_stft_db": 5.428560734377686, "band_mae_db": 0.2882872450578862, "rms_gain_error_db": -0.18228054693350515, "output_peak": 0.5391269184375072}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8262717154767412, "全帯域_10ms_rms_envelope_nrmse": 0.07199863093584145, "全帯域_10ms_envelope_correlation": 0.995325416518658, "全帯域_10ms_modulation_mae_db": 0.20861967361775133, "全帯域_40ms_log_rms_mae_db": 0.45279461210926986, "全帯域_40ms_rms_envelope_nrmse": 0.042426227240851065, "全帯域_40ms_envelope_correlation": 0.9983374615123451, "全帯域_40ms_modulation_mae_db": 0.26010569852204085, "300–1000 Hz_10ms_log_rms_mae_db": 1.3565461527757876, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08333681383412778, "300–1000 Hz_10ms_envelope_correlation": 0.9948425905860864, "300–1000 Hz_10ms_modulation_mae_db": 0.15552132432808563, "300–1000 Hz_40ms_log_rms_mae_db": 0.7933244840219293, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04930542615275998, "300–1000 Hz_40ms_envelope_correlation": 0.9981376145793706, "300–1000 Hz_40ms_modulation_mae_db": 0.3194773612966805, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3247263449123186, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11101410820210762, "1000–3000 Hz_10ms_envelope_correlation": 0.9905139899325478, "1000–3000 Hz_10ms_modulation_mae_db": 0.28091573217801585, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8020025167330441, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07103513839273622, "1000–3000 Hz_40ms_envelope_correlation": 0.996175966192631, "1000–3000 Hz_40ms_modulation_mae_db": 0.2897053409469039, "3000–6000 Hz_10ms_log_rms_mae_db": 1.373442014030199, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1623581143122221, "3000–6000 Hz_10ms_envelope_correlation": 0.9771021658453326, "3000–6000 Hz_10ms_modulation_mae_db": 0.31322973374077573, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8666768145940252, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09949382138362274, "3000–6000 Hz_40ms_envelope_correlation": 0.9911395921629154, "3000–6000 Hz_40ms_modulation_mae_db": 0.35374638294527205, "mr_stft_db": 5.429137954040935, "band_mae_db": 0.24304073201368762, "rms_gain_error_db": -0.11007121991085526, "output_peak": 0.5150230365208661}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8754260889577178, "全帯域_10ms_rms_envelope_nrmse": 0.07555977321843049, "全帯域_10ms_envelope_correlation": 0.9947929265850568, "全帯域_10ms_modulation_mae_db": 0.43507792428855635, "全帯域_40ms_log_rms_mae_db": 0.4501593069003331, "全帯域_40ms_rms_envelope_nrmse": 0.03962701938161587, "全帯域_40ms_envelope_correlation": 0.9985173785816104, "全帯域_40ms_modulation_mae_db": 0.6130445512096467, "300–1000 Hz_10ms_log_rms_mae_db": 1.357865665019843, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07966649404889521, "300–1000 Hz_10ms_envelope_correlation": 0.9952844139878937, "300–1000 Hz_10ms_modulation_mae_db": 0.3002845989988035, "300–1000 Hz_40ms_log_rms_mae_db": 0.7695937472762211, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04196437928465103, "300–1000 Hz_40ms_envelope_correlation": 0.9986650426286942, "300–1000 Hz_40ms_modulation_mae_db": 0.6222604004748294, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3920020890610747, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11786134625713367, "1000–3000 Hz_10ms_envelope_correlation": 0.9891440418371084, "1000–3000 Hz_10ms_modulation_mae_db": 0.3732863652655489, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8390278650636552, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07107521264266686, "1000–3000 Hz_40ms_envelope_correlation": 0.9960275443871596, "1000–3000 Hz_40ms_modulation_mae_db": 0.3934518012412677, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3735620185592847, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16218091937593093, "3000–6000 Hz_10ms_envelope_correlation": 0.9767590626705434, "3000–6000 Hz_10ms_modulation_mae_db": 0.3432945296324532, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8178866851774449, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08978160210548876, "3000–6000 Hz_40ms_envelope_correlation": 0.9921992735068813, "3000–6000 Hz_40ms_modulation_mae_db": 0.37117663772480775, "mr_stft_db": 5.432229417957174, "band_mae_db": 0.22760379672035047, "rms_gain_error_db": -0.08738125318199405, "output_peak": 0.5265015771642484}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8297871040024277, "全帯域_10ms_rms_envelope_nrmse": 0.06414617804731344, "全帯域_10ms_envelope_correlation": 0.9962292797038282, "全帯域_10ms_modulation_mae_db": 0.5577376372963946, "全帯域_40ms_log_rms_mae_db": 0.4216422192482545, "全帯域_40ms_rms_envelope_nrmse": 0.033457586766940856, "全帯域_40ms_envelope_correlation": 0.9989109847115458, "全帯域_40ms_modulation_mae_db": 0.6111355616189028, "300–1000 Hz_10ms_log_rms_mae_db": 1.394589364816414, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07177135831036072, "300–1000 Hz_10ms_envelope_correlation": 0.9961435027221386, "300–1000 Hz_10ms_modulation_mae_db": 0.5725446037028762, "300–1000 Hz_40ms_log_rms_mae_db": 0.7924033358260306, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04292712027651109, "300–1000 Hz_40ms_envelope_correlation": 0.9985307440047834, "300–1000 Hz_40ms_modulation_mae_db": 0.6244770557424407, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3416298826559976, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1076675475644415, "1000–3000 Hz_10ms_envelope_correlation": 0.9909676434635093, "1000–3000 Hz_10ms_modulation_mae_db": 0.6957560670027978, "1000–3000 Hz_40ms_log_rms_mae_db": 0.7816440712946174, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05813412046523157, "1000–3000 Hz_40ms_envelope_correlation": 0.9974534357471797, "1000–3000 Hz_40ms_modulation_mae_db": 0.923774511660162, "3000–6000 Hz_10ms_log_rms_mae_db": 1.302049911426378, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15197305637889041, "3000–6000 Hz_10ms_envelope_correlation": 0.9797294042351395, "3000–6000 Hz_10ms_modulation_mae_db": 0.5667616445590612, "3000–6000 Hz_40ms_log_rms_mae_db": 0.76247518209114, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08771494109990507, "3000–6000 Hz_40ms_envelope_correlation": 0.9928486440893413, "3000–6000 Hz_40ms_modulation_mae_db": 0.5159709983358716, "mr_stft_db": 5.43599479085685, "band_mae_db": 0.21603113317863054, "rms_gain_error_db": -0.0547343529393366, "output_peak": 0.5695439562658142}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8340365019684286, "全帯域_10ms_rms_envelope_nrmse": 0.07114681898017426, "全帯域_10ms_envelope_correlation": 0.9954844884418447, "全帯域_10ms_modulation_mae_db": 0.5263613548577148, "全帯域_40ms_log_rms_mae_db": 0.4370848447840462, "全帯域_40ms_rms_envelope_nrmse": 0.038929955421374604, "全帯域_40ms_envelope_correlation": 0.9986775796573412, "全帯域_40ms_modulation_mae_db": 0.8090544638537315, "300–1000 Hz_10ms_log_rms_mae_db": 1.3586772400133695, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08563595835236648, "300–1000 Hz_10ms_envelope_correlation": 0.9946317269387175, "300–1000 Hz_10ms_modulation_mae_db": 0.4574990870101927, "300–1000 Hz_40ms_log_rms_mae_db": 0.7857650553392658, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.054849979976789184, "300–1000 Hz_40ms_envelope_correlation": 0.997780958180911, "300–1000 Hz_40ms_modulation_mae_db": 0.6984689218274694, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3729854605788063, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11345988716131136, "1000–3000 Hz_10ms_envelope_correlation": 0.9898184341467275, "1000–3000 Hz_10ms_modulation_mae_db": 0.1908756574703102, "1000–3000 Hz_40ms_log_rms_mae_db": 0.813630920633073, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0599713833935792, "1000–3000 Hz_40ms_envelope_correlation": 0.9970906725985039, "1000–3000 Hz_40ms_modulation_mae_db": 0.39433566095272665, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3567335354030599, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15021355406432974, "3000–6000 Hz_10ms_envelope_correlation": 0.9803086978910934, "3000–6000 Hz_10ms_modulation_mae_db": 0.7278310072916884, "3000–6000 Hz_40ms_log_rms_mae_db": 0.801278847651294, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07660057469963925, "3000–6000 Hz_40ms_envelope_correlation": 0.9948569120742577, "3000–6000 Hz_40ms_modulation_mae_db": 0.7618551066534889, "mr_stft_db": 5.44010601257035, "band_mae_db": 0.22084244598658684, "rms_gain_error_db": -0.12634308488505733, "output_peak": 0.6115871988074393}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8234043342743508, "全帯域_10ms_rms_envelope_nrmse": 0.0678301176858133, "全帯域_10ms_envelope_correlation": 0.9958594019700232, "全帯域_10ms_modulation_mae_db": 0.4803426871776482, "全帯域_40ms_log_rms_mae_db": 0.4372167381564708, "全帯域_40ms_rms_envelope_nrmse": 0.036859670102475504, "全帯域_40ms_envelope_correlation": 0.9987701312195197, "全帯域_40ms_modulation_mae_db": 0.6361403766220408, "300–1000 Hz_10ms_log_rms_mae_db": 1.379581117840713, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07991185124726988, "300–1000 Hz_10ms_envelope_correlation": 0.9952688999718664, "300–1000 Hz_10ms_modulation_mae_db": 0.5504199851069272, "300–1000 Hz_40ms_log_rms_mae_db": 0.7436476387334638, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04273666583400038, "300–1000 Hz_40ms_envelope_correlation": 0.9986276462464898, "300–1000 Hz_40ms_modulation_mae_db": 0.673792834087609, "1000–3000 Hz_10ms_log_rms_mae_db": 1.294126806600143, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10100432217297724, "1000–3000 Hz_10ms_envelope_correlation": 0.992199852320084, "1000–3000 Hz_10ms_modulation_mae_db": 0.12897607440648404, "1000–3000 Hz_40ms_log_rms_mae_db": 0.756697425819619, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.05464499149912496, "1000–3000 Hz_40ms_envelope_correlation": 0.9979285282072027, "1000–3000 Hz_40ms_modulation_mae_db": 0.27151094133516956, "3000–6000 Hz_10ms_log_rms_mae_db": 1.332804335929086, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15759486836691194, "3000–6000 Hz_10ms_envelope_correlation": 0.9781243843492923, "3000–6000 Hz_10ms_modulation_mae_db": 0.5025900240695828, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7868319162997252, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09316814479939077, "3000–6000 Hz_40ms_envelope_correlation": 0.9917138707905203, "3000–6000 Hz_40ms_modulation_mae_db": 0.5287876836800326, "mr_stft_db": 5.425019296243022, "band_mae_db": 0.20478837461874097, "rms_gain_error_db": -0.09972495204385348, "output_peak": 0.515145985962732}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 91600, "output_samples": 91600, "length_delta_samples": 0, "sample_rate": 16000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 80, "hop_samples": 20, "log_magnitude_mae_db": 5.471842882522276, "spectral_convergence": 0.2586398647568361, "spectral_convergence_status": "ok", "amplitude_floor": 1.4112644553101518e-06}, {"window_ms": 20, "window_samples": 320, "hop_samples": 80, "log_magnitude_mae_db": 5.236619740101511, "spectral_convergence": 0.2530208844343124, "spectral_convergence_status": "ok", "amplitude_floor": 1.1975531593072457e-06}, {"window_ms": 80, "window_samples": 1280, "hop_samples": 320, "log_magnitude_mae_db": 5.5953248344060516, "spectral_convergence": 0.2668376318212157, "spectral_convergence_status": "ok", "amplitude_floor": 1.114415465542996e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.564075826256522e-05, "output_power": 6.253703170165351e-05, "delta_db": 0.5074422391044062, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0010000129923479963, "output_power": 0.0009797326956383912, "delta_db": -0.08898040902709604, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0018259392170112694, "output_power": 0.0018291865056922364, "delta_db": 0.007716724585266656, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0005127219920465177, "output_power": 0.0004973095434586674, "delta_db": -0.13255152415720162, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 0.00033320627903786135, "output_power": 0.00031634086996156174, "delta_db": -0.22557872153818048, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 0.0002817706196064759, "output_power": 0.000263036182509183, "delta_db": -0.29880214072085465, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 6, "band_count": 6, "active_band_mae_db": 0.2101786265221676, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.06674816652080302, "pitch": null, "output_rms_dbfs": -24.036071445768936, "output_peak": 0.5569887868377952, "reference_rms_dbfs": -23.96932327924813, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.434595819009947}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 16000, "samples": 91600, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00020825955187282386, "log_rms_mae_db": 0.8429217028249015, "rms_envelope_nrmse": 0.0680008516088581, "envelope_correlation": 0.9957821482650732, "rms_gain_error_db": -0.06673580092030565, "reference_mean_power": 0.004012756910556895, "output_mean_power": 0.003951566284043822}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 2.2120307480210933e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008889321025104637, "output_power": 0.0008472035838024522, "reference_active": true, "delta_db": -0.2088080617020974}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00022980725896418495, "output_power": 0.00020603172470031852, "reference_active": true, "delta_db": -0.4742964466242817}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.1131932747773025e-05, "output_power": 4.1672749400270236e-05, "reference_active": true, "delta_db": 0.05673037358818713}], "active_band_count": 3, "active_band_mae_db": 0.24661162730485542}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.0001984160011662782, "log_rms_mae_db": 0.43202746523018076, "rms_envelope_nrmse": 0.034312186835629074, "envelope_correlation": 0.9988822204432637, "rms_gain_error_db": -0.06673577215729949, "reference_mean_power": 0.0040337408532874226, "output_mean_power": 0.003972230268435422}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 2.0115882799069226e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008024963383362849, "output_power": 0.0007645648727291518, "reference_active": true, "delta_db": -0.21028718606923535}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00011463438169489824, "output_power": 0.00010469187715014434, "reference_active": true, "delta_db": -0.39401905980440555}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.4945953602736586e-06, "output_power": 3.0313658292145496e-06, "reference_active": true, "delta_db": -0.6175854520939049}], "active_band_count": 3, "active_band_mae_db": 0.4072972326558486}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00019054595180557928, "log_rms_mae_db": 1.378905350751675, "rms_envelope_nrmse": 0.07976169285276245, "envelope_correlation": 0.9952427042411239, "rms_gain_error_db": -0.04078158779236343, "reference_mean_power": 0.0025757888112863028, "output_mean_power": 0.002551714571166099}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.7595886306573375e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007279305516452219, "output_power": 0.0007010608811182008, "reference_active": true, "delta_db": -0.16334212989303293}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019010480993234813, "output_power": 0.00017035974878012569, "reference_active": true, "delta_db": -0.47626114323303825}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6294378423488108e-05, "output_power": 3.015661149510209e-05, "reference_active": true, "delta_db": 0.5951963213293257}], "active_band_count": 3, "active_band_mae_db": 0.4115998648184656}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.00018019065505981728, "log_rms_mae_db": 0.8092162543609015, "rms_envelope_nrmse": 0.041944106229267045, "envelope_correlation": 0.9986178806979206, "rms_gain_error_db": -0.040781744921863435, "reference_mean_power": 0.0025893611436675294, "output_mean_power": 0.0025651599588838235}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.6269545971301712e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006780414214466183, "output_power": 0.0006530264576032469, "reference_active": true, "delta_db": -0.16325448431259687}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.548437806715927e-05, "output_power": 8.721296818685273e-05, "reference_active": true, "delta_db": -0.39351256262519346}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.9327510117604047e-06, "output_power": 2.5479471319641253e-06, "reference_active": true, "delta_db": -0.6108478082332078}], "active_band_count": 3, "active_band_mae_db": 0.38920495172366604}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.327720993461315e-05, "log_rms_mae_db": 1.3647110277045018, "rms_envelope_nrmse": 0.10036117869983811, "envelope_correlation": 0.9921328419112964, "rms_gain_error_db": -0.1665323490650334, "reference_mean_power": 0.0007122971869413385, "output_mean_power": 0.0006855008447197039}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 4.689927289528067e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00023362430343497353, "output_power": 0.00021529710263182422, "reference_active": true, "delta_db": -0.35479834183626224}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.797902128989837e-05, "output_power": 3.284694995928671e-05, "reference_active": true, "delta_db": -0.630487200201342}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.042184778585592e-05, "output_power": 1.0020674434222024e-05, "reference_active": true, "delta_db": -0.17047773488848206}], "active_band_count": 3, "active_band_mae_db": 0.3852544256420288}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 8.747046012456969e-05, "log_rms_mae_db": 0.7855792224912868, "rms_envelope_nrmse": 0.05747073260586687, "envelope_correlation": 0.9974263909608585, "rms_gain_error_db": -0.16655162288022834, "reference_mean_power": 0.0007159674763911086, "output_mean_power": 0.0006890300014182466}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 4.328159646639031e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021700970165722394, "output_power": 0.00020093222250225473, "reference_active": true, "delta_db": -0.3342956191306096}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.702508733600319e-05, "output_power": 1.4969486177059562e-05, "reference_active": true, "delta_db": -0.558824548761305}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.679451250427792e-07, "output_power": 7.107447313110727e-07, "reference_active": true, "delta_db": -0.867786192256534}], "active_band_count": 3, "active_band_mae_db": 0.5869687867161496}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.039773028293347e-05, "log_rms_mae_db": 1.347249121769675, "rms_envelope_nrmse": 0.14665032280241475, "envelope_correlation": 0.9815314766695558, "rms_gain_error_db": -0.3120638513326798, "reference_mean_power": 0.0003237352885604671, "output_mean_power": 0.0003012892642368484}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.2480235329901466e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.70846061617512e-05, "output_power": 5.438015508377684e-05, "reference_active": true, "delta_db": -0.2107856732155684}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9595191589145483e-05, "output_power": 1.7573772060650264e-05, "reference_active": true, "delta_db": -0.4728452496987418}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.074204859780537e-06, "output_power": 4.6692323502674404e-06, "reference_active": true, "delta_db": -0.36122511093520093}], "active_band_count": 3, "active_band_mae_db": 0.34828534461650373}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 6.399293414479695e-05, "log_rms_mae_db": 0.7967707155140565, "rms_envelope_nrmse": 0.07815256332461751, "envelope_correlation": 0.995033678932814, "rms_gain_error_db": -0.3121133743855095, "reference_mean_power": 0.0003253818281247376, "output_mean_power": 0.0003028181887168249}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.1005868407421181e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.4497636322434906e-05, "output_power": 5.1625565547702285e-05, "reference_active": true, "delta_db": -0.23512844117029907}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.385752117634814e-06, "output_power": 8.348939836604786e-06, "reference_active": true, "delta_db": -0.5083774860510376}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.7591737704275347e-07, "output_power": 3.516856601501205e-07, "reference_active": true, "delta_db": -0.28937741258353167}], "active_band_count": 3, "active_band_mae_db": 0.34429444660162273}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8962901445863074, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "d662a41e6ad65ba77511d2c85d4781ea66c0d2ad75b41e995147346ed4fe3ae2", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9907880952438981, "standard_deviation": 0.0010682840971846708, "minimum": 0.9891440418371084, "maximum": 0.992199852320084, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.3475913757927667, "standard_deviation": 0.03151925677773541, "minimum": 1.294126806600143, "maximum": 1.3920020890610747, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.3468586057988806, "standard_deviation": 0.20421880139485926, "minimum": 0.12897607440648404, "maximum": 0.6957560670027978, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.10862753721557739, "standard_deviation": 0.006146206884200406, "minimum": 0.10036117869983811, "maximum": 0.11786134625713367, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9970309796235703, "standard_deviation": 0.0006604222862377317, "minimum": 0.9960275443871596, "maximum": 0.9979285282072027, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.7974324682236321, "standard_deviation": 0.02694126991071496, "minimum": 0.756697425819619, "maximum": 0.8390278650636552, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.44431394801126584, "standard_deviation": 0.22827309714037441, "minimum": 0.211576480543979, "maximum": 0.923774511660162, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06196184436681812, "standard_deviation": 0.006489841417896852, "minimum": 0.05464499149912496, "maximum": 0.07107521264266686, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9792966657900233, "standard_deviation": 0.0018350057897110938, "minimum": 0.9767590626705434, "maximum": 0.9815314766695558, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.3433953510546135, "standard_deviation": 0.02928811340201792, "minimum": 1.3002223009870713, "maximum": 1.3735620185592847, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.45367015628118446, "standard_deviation": 0.1399915017831696, "minimum": 0.31322973374077573, "maximum": 0.7278310072916884, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15447940122900983, "standard_deviation": 0.005701119656430683, "minimum": 0.14665032280241475, "maximum": 0.1623581143122221, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9931253805698654, "standard_deviation": 0.0014128344395438546, "minimum": 0.9911395921629154, "maximum": 0.995033678932814, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8076012899492522, "standard_deviation": 0.030936096814206185, "minimum": 0.76247518209114, "maximum": 0.8666768145940252, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.5014225705810587, "standard_deviation": 0.142669960418911, "minimum": 0.34429444660162273, "maximum": 0.7618551066534889, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08802062199516211, "standard_deviation": 0.008152498280320974, "minimum": 0.07660057469963925, "maximum": 0.09949382138362274, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9949184195475884, "standard_deviation": 0.0007958389907016857, "minimum": 0.9933873274856431, "maximum": 0.9961435027221386, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.3633832252448435, "standard_deviation": 0.03007882376425034, "minimum": 1.297410595789358, "maximum": 1.394589364816414, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.4125412791549004, "standard_deviation": 0.13608988619768947, "minimum": 0.15552132432808563, "maximum": 0.5725446037028762, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08286673326772867, "standard_deviation": 0.007031715692415994, "minimum": 0.07177135831036072, "maximum": 0.09589818275973208, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9981177060830331, "standard_deviation": 0.0006685181455332125, "minimum": 0.9967134082428089, "maximum": 0.9986650426286942, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7721961612499993, "standard_deviation": 0.026969781054456417, "minimum": 0.7391880560235246, "maximum": 0.8092162543609015, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.5902361450629406, "standard_deviation": 0.15601610505922145, "minimum": 0.3194773612966805, "maximum": 0.7775024169728098, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.04956544983379514, "standard_deviation": 0.009217615716657374, "minimum": 0.041944106229267045, "maximum": 0.06772961616352093, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.23188683515467085, "standard_deviation": 0.026878978068959097, "minimum": 0.20478837461874097, "maximum": 0.2882872450578862, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.432428258706648, "standard_deviation": 0.004764679895339432, "minimum": 5.425019296243022, "maximum": 5.44010601257035, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.546811846005476, "standard_deviation": 0.03238133278070975, "minimum": 0.5150230365208661, "maximum": 0.6115871988074393, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.11129624148741182, "standard_deviation": 0.044462657407117814, "minimum": -0.18228054693350515, "maximum": -0.0547343529393366, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9954834036307453, "standard_deviation": 0.0004702730198382246, "minimum": 0.9947929265850568, "maximum": 0.9962292797038282, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.8423231755973775, "standard_deviation": 0.017762928312080657, "minimum": 0.8234043342743508, "maximum": 0.8754260889577178, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.4280882188013494, "standard_deviation": 0.13055340838779775, "minimum": 0.20861967361775133, "maximum": 0.5577376372963946, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.07090553428349433, "standard_deviation": 0.004062499675866074, "minimum": 0.06414617804731344, "maximum": 0.07604746726840243, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9985806233420763, "standard_deviation": 0.0002966895352498505, "minimum": 0.9980293092296916, "maximum": 0.9989109847115458, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.44262577494670496, "standard_deviation": 0.012446683382143234, "minimum": 0.4216422192482545, "maximum": 0.4563511648472474, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5775592497664682, "standard_deviation": 0.17116220047626526, "minimum": 0.26010569852204085, "maximum": 0.8090544638537315, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03959012257432999, "standard_deviation": 0.004936300589816062, "minimum": 0.033457586766940856, "maximum": 0.04855659470464923, "valid_count": 8, "planned_count": 8}}}, {"case": "librispeech_8463-294828-0014", "method": "D", "status": "measured", "mos": {"status": "pending", "value": null}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8204545284283772, "全帯域_10ms_rms_envelope_nrmse": 0.0688790831220481, "全帯域_10ms_envelope_correlation": 0.9957091102864258, "全帯域_10ms_modulation_mae_db": 0.4528384096303089, "全帯域_40ms_log_rms_mae_db": 0.4287175672714079, "全帯域_40ms_rms_envelope_nrmse": 0.03599188185672352, "全帯域_40ms_envelope_correlation": 0.9988122246491989, "全帯域_40ms_modulation_mae_db": 0.5936237695557376, "300–1000 Hz_10ms_log_rms_mae_db": 1.4171390099155707, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08294554433695009, "300–1000 Hz_10ms_envelope_correlation": 0.9948947128772926, "300–1000 Hz_10ms_modulation_mae_db": 0.3804945479175356, "300–1000 Hz_40ms_log_rms_mae_db": 0.7481023810809877, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04610514821299589, "300–1000 Hz_40ms_envelope_correlation": 0.9983845647512296, "300–1000 Hz_40ms_modulation_mae_db": 0.6190864697590758, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4593138317215946, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11385699362727889, "1000–3000 Hz_10ms_envelope_correlation": 0.9901664313305489, "1000–3000 Hz_10ms_modulation_mae_db": 0.33259378684857555, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8957063338518877, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06803298280112165, "1000–3000 Hz_40ms_envelope_correlation": 0.9967685373699922, "1000–3000 Hz_40ms_modulation_mae_db": 0.47339816743698454, "3000–6000 Hz_10ms_log_rms_mae_db": 1.42614099814294, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1513619591434766, "3000–6000 Hz_10ms_envelope_correlation": 0.9798506583357064, "3000–6000 Hz_10ms_modulation_mae_db": 0.3414206500664201, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8442726553411123, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08554591784444984, "3000–6000 Hz_40ms_envelope_correlation": 0.9928774070080326, "3000–6000 Hz_40ms_modulation_mae_db": 0.28594305283893345, "mr_stft_db": 5.503721699504539, "band_mae_db": 0.1987610817889697, "rms_gain_error_db": -0.09241860283307396, "output_peak": 0.5358252616616783}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8585193466404187, "全帯域_10ms_rms_envelope_nrmse": 0.08023663396888774, "全帯域_10ms_envelope_correlation": 0.9941470198967022, "全帯域_10ms_modulation_mae_db": 0.28726097852021, "全帯域_40ms_log_rms_mae_db": 0.4702553601521473, "全帯域_40ms_rms_envelope_nrmse": 0.040599827134462065, "全帯域_40ms_envelope_correlation": 0.9984838512640216, "全帯域_40ms_modulation_mae_db": 0.6777314304085551, "300–1000 Hz_10ms_log_rms_mae_db": 1.4005181484574016, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08653550333188408, "300–1000 Hz_10ms_envelope_correlation": 0.9944749577844257, "300–1000 Hz_10ms_modulation_mae_db": 0.20565435646875918, "300–1000 Hz_40ms_log_rms_mae_db": 0.7569055484999009, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043062700894321196, "300–1000 Hz_40ms_envelope_correlation": 0.9986702675849806, "300–1000 Hz_40ms_modulation_mae_db": 0.5812267487458851, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4675473772544412, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12293996870446898, "1000–3000 Hz_10ms_envelope_correlation": 0.9879572300190393, "1000–3000 Hz_10ms_modulation_mae_db": 0.30989306278011824, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8859354472126671, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06757406347743448, "1000–3000 Hz_40ms_envelope_correlation": 0.9961657425730328, "1000–3000 Hz_40ms_modulation_mae_db": 0.23064657965381452, "3000–6000 Hz_10ms_log_rms_mae_db": 1.403559624996863, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15516592462860354, "3000–6000 Hz_10ms_envelope_correlation": 0.9787017686516605, "3000–6000 Hz_10ms_modulation_mae_db": 0.21400597743683256, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8173316305448809, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08852480251081427, "3000–6000 Hz_40ms_envelope_correlation": 0.9924252656363334, "3000–6000 Hz_40ms_modulation_mae_db": 0.16814857176895578, "mr_stft_db": 5.499544420645731, "band_mae_db": 0.1721072181036463, "rms_gain_error_db": -0.09174781131241969, "output_peak": 0.5137030733440797}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8312812746764398, "全帯域_10ms_rms_envelope_nrmse": 0.06932832620054395, "全帯域_10ms_envelope_correlation": 0.9956097538818942, "全帯域_10ms_modulation_mae_db": 0.3311275300997705, "全帯域_40ms_log_rms_mae_db": 0.41317785998955225, "全帯域_40ms_rms_envelope_nrmse": 0.03305436539933669, "全帯域_40ms_envelope_correlation": 0.99897167187411, "全帯域_40ms_modulation_mae_db": 0.4362833283725605, "300–1000 Hz_10ms_log_rms_mae_db": 1.4296232479271314, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07586557029262268, "300–1000 Hz_10ms_envelope_correlation": 0.9957068331490128, "300–1000 Hz_10ms_modulation_mae_db": 0.27842051299318876, "300–1000 Hz_40ms_log_rms_mae_db": 0.7693587408007998, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.037575921223666195, "300–1000 Hz_40ms_envelope_correlation": 0.9989125138261371, "300–1000 Hz_40ms_modulation_mae_db": 0.4167286774967996, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4223367403599734, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11023444486958107, "1000–3000 Hz_10ms_envelope_correlation": 0.990312395118935, "1000–3000 Hz_10ms_modulation_mae_db": 0.1865975984613449, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8288053333332265, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06233367897163653, "1000–3000 Hz_40ms_envelope_correlation": 0.9966761676972337, "1000–3000 Hz_40ms_modulation_mae_db": 0.22620324605026232, "3000–6000 Hz_10ms_log_rms_mae_db": 1.424266559781547, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.17383207145319637, "3000–6000 Hz_10ms_envelope_correlation": 0.974214375176385, "3000–6000 Hz_10ms_modulation_mae_db": 0.6591743844505961, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8504642472830837, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.1107273853597853, "3000–6000 Hz_40ms_envelope_correlation": 0.989718181571117, "3000–6000 Hz_40ms_modulation_mae_db": 0.5982307149278046, "mr_stft_db": 5.519928102660224, "band_mae_db": 0.19200601710758827, "rms_gain_error_db": -0.07582960466799933, "output_peak": 0.5532071625777708}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8287910931862612, "全帯域_10ms_rms_envelope_nrmse": 0.0711625817340183, "全帯域_10ms_envelope_correlation": 0.9954429715579649, "全帯域_10ms_modulation_mae_db": 0.3582758055737439, "全帯域_40ms_log_rms_mae_db": 0.43189551072158433, "全帯域_40ms_rms_envelope_nrmse": 0.04275289005732821, "全帯域_40ms_envelope_correlation": 0.9983124094173546, "全帯域_40ms_modulation_mae_db": 0.26364595869260826, "300–1000 Hz_10ms_log_rms_mae_db": 1.4466682245387428, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08676410743759444, "300–1000 Hz_10ms_envelope_correlation": 0.9943948566101479, "300–1000 Hz_10ms_modulation_mae_db": 0.21668597507184553, "300–1000 Hz_40ms_log_rms_mae_db": 0.834693609169993, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.05702530254964689, "300–1000 Hz_40ms_envelope_correlation": 0.9974655087176585, "300–1000 Hz_40ms_modulation_mae_db": 0.07556947567088972, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3943430107271872, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1099506093057764, "1000–3000 Hz_10ms_envelope_correlation": 0.9905935871359768, "1000–3000 Hz_10ms_modulation_mae_db": 0.546436172339797, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8206023656477484, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06098831873445822, "1000–3000 Hz_40ms_envelope_correlation": 0.9971913643187182, "1000–3000 Hz_40ms_modulation_mae_db": 0.6331809977369687, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4306084594150394, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15113734353475144, "3000–6000 Hz_10ms_envelope_correlation": 0.9802001596716873, "3000–6000 Hz_10ms_modulation_mae_db": 0.8221763006889725, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8291929728786954, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08159062952278888, "3000–6000 Hz_40ms_envelope_correlation": 0.9943080045805496, "3000–6000 Hz_40ms_modulation_mae_db": 0.7583618693815734, "mr_stft_db": 5.501360599521519, "band_mae_db": 0.2130670428421232, "rms_gain_error_db": -0.10476411931254664, "output_peak": 0.543218422801965}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8394702777223496, "全帯域_10ms_rms_envelope_nrmse": 0.06799847791061397, "全帯域_10ms_envelope_correlation": 0.9958242294422902, "全帯域_10ms_modulation_mae_db": 0.30597174288895507, "全帯域_40ms_log_rms_mae_db": 0.4381252158737537, "全帯域_40ms_rms_envelope_nrmse": 0.038505961635079855, "全帯域_40ms_envelope_correlation": 0.998623695432725, "全帯域_40ms_modulation_mae_db": 0.4512931273701504, "300–1000 Hz_10ms_log_rms_mae_db": 1.4410844346896388, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07997991991278379, "300–1000 Hz_10ms_envelope_correlation": 0.9952473886145412, "300–1000 Hz_10ms_modulation_mae_db": 0.4421956637386866, "300–1000 Hz_40ms_log_rms_mae_db": 0.8230350227042716, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04618065134429219, "300–1000 Hz_40ms_envelope_correlation": 0.9983688385663718, "300–1000 Hz_40ms_modulation_mae_db": 0.33524044012248116, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4456384533315132, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10159283410032058, "1000–3000 Hz_10ms_envelope_correlation": 0.9918705118194201, "1000–3000 Hz_10ms_modulation_mae_db": 0.21086852746869653, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8572417573603182, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.04960377099634432, "1000–3000 Hz_40ms_envelope_correlation": 0.9980793676685026, "1000–3000 Hz_40ms_modulation_mae_db": 0.19305331556446945, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3908813365754014, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15838590438461322, "3000–6000 Hz_10ms_envelope_correlation": 0.977943847740865, "3000–6000 Hz_10ms_modulation_mae_db": 0.7849425710362818, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8277291847312896, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.09554530319757795, "3000–6000 Hz_40ms_envelope_correlation": 0.9914264529985504, "3000–6000 Hz_40ms_modulation_mae_db": 0.575734708346897, "mr_stft_db": 5.497239158846855, "band_mae_db": 0.20577751274482647, "rms_gain_error_db": -0.087632859673715, "output_peak": 0.5375524700220461}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8353290478041002, "全帯域_10ms_rms_envelope_nrmse": 0.0680138849159102, "全帯域_10ms_envelope_correlation": 0.995767199610516, "全帯域_10ms_modulation_mae_db": 0.3217769596882672, "全帯域_40ms_log_rms_mae_db": 0.4222837002277448, "全帯域_40ms_rms_envelope_nrmse": 0.03538744204256405, "全帯域_40ms_envelope_correlation": 0.9987851186523881, "全帯域_40ms_modulation_mae_db": 0.34843665779933897, "300–1000 Hz_10ms_log_rms_mae_db": 1.4223990649085156, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07909112464099179, "300–1000 Hz_10ms_envelope_correlation": 0.9953302957445874, "300–1000 Hz_10ms_modulation_mae_db": 0.21620887627933327, "300–1000 Hz_40ms_log_rms_mae_db": 0.7641522940995648, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04515424165364139, "300–1000 Hz_40ms_envelope_correlation": 0.9983966218092111, "300–1000 Hz_40ms_modulation_mae_db": 0.24721679769997917, "1000–3000 Hz_10ms_log_rms_mae_db": 1.3927360854166533, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11569683746894904, "1000–3000 Hz_10ms_envelope_correlation": 0.9893920176546102, "1000–3000 Hz_10ms_modulation_mae_db": 0.5630533683916078, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8291585504755291, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06607702576351987, "1000–3000 Hz_40ms_envelope_correlation": 0.9964102241890738, "1000–3000 Hz_40ms_modulation_mae_db": 0.6505252881946765, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4428128298544274, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14826243883314516, "3000–6000 Hz_10ms_envelope_correlation": 0.9806177398887816, "3000–6000 Hz_10ms_modulation_mae_db": 0.45938608224437233, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8237281497292691, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07962773431887461, "3000–6000 Hz_40ms_envelope_correlation": 0.9939951481171792, "3000–6000 Hz_40ms_modulation_mae_db": 0.40736391173838166, "mr_stft_db": 5.504857833533272, "band_mae_db": 0.14290647148691168, "rms_gain_error_db": -0.0565355095963084, "output_peak": 0.5322272020771863}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8219505124312512, "全帯域_10ms_rms_envelope_nrmse": 0.06389343524955216, "全帯域_10ms_envelope_correlation": 0.9964703489209336, "全帯域_10ms_modulation_mae_db": 0.42095469288908854, "全帯域_40ms_log_rms_mae_db": 0.4353937886720335, "全帯域_40ms_rms_envelope_nrmse": 0.03564019227315479, "全帯域_40ms_envelope_correlation": 0.9990066294252271, "全帯域_40ms_modulation_mae_db": 0.45260889958773554, "300–1000 Hz_10ms_log_rms_mae_db": 1.4837308540350658, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07420603117831548, "300–1000 Hz_10ms_envelope_correlation": 0.9960485459627167, "300–1000 Hz_10ms_modulation_mae_db": 0.34312814614544207, "300–1000 Hz_40ms_log_rms_mae_db": 0.8118450912532426, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.043661019265149044, "300–1000 Hz_40ms_envelope_correlation": 0.9987055031228833, "300–1000 Hz_40ms_modulation_mae_db": 0.624721352035784, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4714706806444118, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.12205845055605781, "1000–3000 Hz_10ms_envelope_correlation": 0.98820649947416, "1000–3000 Hz_10ms_modulation_mae_db": 0.33904847933542975, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8793174500774051, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07220245738466591, "1000–3000 Hz_40ms_envelope_correlation": 0.995746717810013, "1000–3000 Hz_40ms_modulation_mae_db": 0.43334353130494335, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4435190834426306, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15859442936462956, "3000–6000 Hz_10ms_envelope_correlation": 0.9783610923931035, "3000–6000 Hz_10ms_modulation_mae_db": 0.7848359018738619, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8713143263147438, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08790869573446032, "3000–6000 Hz_40ms_envelope_correlation": 0.9936386701188269, "3000–6000 Hz_40ms_modulation_mae_db": 0.7973259824584761, "mr_stft_db": 5.516188031249219, "band_mae_db": 0.2118506036941469, "rms_gain_error_db": -0.14620836721492952, "output_peak": 0.5195451944106615}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8323723268366408, "全帯域_10ms_rms_envelope_nrmse": 0.06872648455378597, "全帯域_10ms_envelope_correlation": 0.9957118020003415, "全帯域_10ms_modulation_mae_db": 0.10600493528271161, "全帯域_40ms_log_rms_mae_db": 0.4454046031745244, "全帯域_40ms_rms_envelope_nrmse": 0.03591835153550854, "全帯域_40ms_envelope_correlation": 0.9988037298045727, "全帯域_40ms_modulation_mae_db": 0.2732904868158728, "300–1000 Hz_10ms_log_rms_mae_db": 1.481576706424441, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07874614222295627, "300–1000 Hz_10ms_envelope_correlation": 0.995408398595054, "300–1000 Hz_10ms_modulation_mae_db": 0.1832647294155727, "300–1000 Hz_40ms_log_rms_mae_db": 0.8008004159671565, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04510274238828414, "300–1000 Hz_40ms_envelope_correlation": 0.9984663444538998, "300–1000 Hz_40ms_modulation_mae_db": 0.1957747446442181, "1000–3000 Hz_10ms_log_rms_mae_db": 1.445023945409587, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.1147667391302128, "1000–3000 Hz_10ms_envelope_correlation": 0.9895146464273842, "1000–3000 Hz_10ms_modulation_mae_db": 0.25242264957009014, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8458079773395663, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0652357711552557, "1000–3000 Hz_40ms_envelope_correlation": 0.9964189424414706, "1000–3000 Hz_40ms_modulation_mae_db": 0.20732431073839305, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4467764691720437, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1583825325127647, "3000–6000 Hz_10ms_envelope_correlation": 0.9787711819449058, "3000–6000 Hz_10ms_modulation_mae_db": 1.0382547287799528, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8489592850840283, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0892361149989285, "3000–6000 Hz_40ms_envelope_correlation": 0.993870020163607, "3000–6000 Hz_40ms_modulation_mae_db": 1.1644088060178315, "mr_stft_db": 5.4964635132431665, "band_mae_db": 0.22030623626284696, "rms_gain_error_db": -0.08801894785913003, "output_peak": 0.5305659563371626}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 91600, "output_samples": 91600, "length_delta_samples": 0, "sample_rate": 16000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 80, "hop_samples": 20, "log_magnitude_mae_db": 5.58888518220821, "spectral_convergence": 0.2597228845660181, "spectral_convergence_status": "ok", "amplitude_floor": 1.4112644553101518e-06}, {"window_ms": 20, "window_samples": 320, "hop_samples": 80, "log_magnitude_mae_db": 5.326468803804368, "spectral_convergence": 0.25296619711491797, "spectral_convergence_status": "ok", "amplitude_floor": 1.1975531593072457e-06}, {"window_ms": 80, "window_samples": 1280, "hop_samples": 320, "log_magnitude_mae_db": 5.595811112501041, "spectral_convergence": 0.26104685642068376, "spectral_convergence_status": "ok", "amplitude_floor": 1.114415465542996e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.564075826256522e-05, "output_power": 6.265227784331508e-05, "delta_db": 0.5154382537329449, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0010000129923479963, "output_power": 0.0009781228059635454, "delta_db": -0.09612257410784476, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0018259392170112694, "output_power": 0.001803637445220007, "delta_db": -0.05337073284318584, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0005127219920465177, "output_power": 0.0004889667639150053, "delta_db": -0.2060260568609627, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 0.00033320627903786135, "output_power": 0.00031249575903285874, "delta_db": -0.27869048997280194, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 0.0002817706196064759, "output_power": 0.0002789997850392881, "delta_db": -0.042918383216078076, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 6, "band_count": 6, "active_band_mae_db": 0.1987610817889697, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.09241860283307396, "pitch": null, "output_rms_dbfs": -24.061741882081208, "output_peak": 0.5358252616616783, "reference_rms_dbfs": -23.96932327924813, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.503721699504539}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 16000, "samples": 91600, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00020825955187282386, "log_rms_mae_db": 0.8204545284283772, "rms_envelope_nrmse": 0.0688790831220481, "envelope_correlation": 0.9957091102864258, "rms_gain_error_db": -0.09240263367595077, "reference_mean_power": 0.004012756910556895, "output_mean_power": 0.003928281375788356}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 2.2120307480210933e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008889321025104637, "output_power": 0.0008513487667279843, "reference_active": true, "delta_db": -0.18761079163457822}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00022980725896418495, "output_power": 0.00021126466913366361, "reference_active": true, "delta_db": -0.3653686886149188}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.1131932747773025e-05, "output_power": 3.4168470774138926e-05, "reference_active": true, "delta_db": -0.8055357486414298}], "active_band_count": 3, "active_band_mae_db": 0.4528384096303089}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.0001984160011662782, "log_rms_mae_db": 0.4287175672714079, "rms_envelope_nrmse": 0.03599188185672352, "envelope_correlation": 0.9988122246491989, "rms_gain_error_db": -0.092426481289982, "reference_mean_power": 0.0040337408532874226, "output_mean_power": 0.00394880188652085}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 2.0115882799069226e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008024963383362849, "output_power": 0.0007706861778192544, "reference_active": true, "delta_db": -0.1756548943741364}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00011463438169489824, "output_power": 0.00010312642285956406, "reference_active": true, "delta_db": -0.45944939195098755}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.4945953602736586e-06, "output_power": 2.684232891547949e-06, "reference_active": true, "delta_db": -1.1457670223420888}], "active_band_count": 3, "active_band_mae_db": 0.5936237695557376}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00019054595180557928, "log_rms_mae_db": 1.4171390099155707, "rms_envelope_nrmse": 0.08294554433695009, "envelope_correlation": 0.9948947128772926, "rms_gain_error_db": -0.083780811638951, "reference_mean_power": 0.0025757888112863028, "output_mean_power": 0.0025265748641825534}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.7595886306573375e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007279305516452219, "output_power": 0.0007091478499143572, "reference_active": true, "delta_db": -0.11353156857212825}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019010480993234813, "output_power": 0.00016904378910070184, "reference_active": true, "delta_db": -0.5099388647250834}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6294378423488108e-05, "output_power": 2.3337889965304963e-05, "reference_active": true, "delta_db": -0.5180132104553952}], "active_band_count": 3, "active_band_mae_db": 0.3804945479175356}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.00018019065505981728, "log_rms_mae_db": 0.7481023810809877, "rms_envelope_nrmse": 0.04610514821299589, "envelope_correlation": 0.9983845647512296, "rms_gain_error_db": -0.08377691071559598, "reference_mean_power": 0.0025893611436675294, "output_mean_power": 0.0025398901600827716}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.6269545971301712e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006780414214466183, "output_power": 0.0006614422346955062, "reference_active": true, "delta_db": -0.10764303438825334}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.548437806715927e-05, "output_power": 8.33101939999591e-05, "reference_active": true, "delta_db": -0.5923417789713983}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.9327510117604047e-06, "output_power": 2.24671370074013e-06, "reference_active": true, "delta_db": -1.1572745959175756}], "active_band_count": 3, "active_band_mae_db": 0.6190864697590758}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.327720993461315e-05, "log_rms_mae_db": 1.4593138317215946, "rms_envelope_nrmse": 0.11385699362727889, "envelope_correlation": 0.9901664313305489, "rms_gain_error_db": -0.27636020932681854, "reference_mean_power": 0.0007122971869413385, "output_mean_power": 0.0006683827121678167}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 4.689927289528067e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00023362430343497353, "output_power": 0.0002175710296854955, "reference_active": true, "delta_db": -0.30916952408923903}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.797902128989837e-05, "output_power": 3.5732651272959725e-05, "reference_active": true, "delta_db": -0.26478527924974704}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.042184778585592e-05, "output_power": 9.452834844233962e-06, "reference_active": true, "delta_db": -0.4238265572067406}], "active_band_count": 3, "active_band_mae_db": 0.33259378684857555}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 8.747046012456969e-05, "log_rms_mae_db": 0.8957063338518877, "rms_envelope_nrmse": 0.06803298280112165, "envelope_correlation": 0.9967685373699922, "rms_gain_error_db": -0.27649857952126233, "reference_mean_power": 0.0007159674763911086, "output_mean_power": 0.000671805316627439}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 4.328159646639031e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021700970165722394, "output_power": 0.0002028305304632936, "reference_active": true, "delta_db": -0.2934582342575471}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.702508733600319e-05, "output_power": 1.6778389070273934e-05, "reference_active": true, "delta_db": -0.06339087518541901}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.679451250427792e-07, "output_power": 6.794503534951007e-07, "reference_active": true, "delta_db": -1.0633453928679875}], "active_band_count": 3, "active_band_mae_db": 0.47339816743698454}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.039773028293347e-05, "log_rms_mae_db": 1.42614099814294, "rms_envelope_nrmse": 0.1513619591434766, "envelope_correlation": 0.9798506583357064, "rms_gain_error_db": -0.0480809868728729, "reference_mean_power": 0.0003237352885604671, "output_mean_power": 0.00032017096376052776}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.2480235329901466e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.70846061617512e-05, "output_power": 5.673419554347542e-05, "reference_active": true, "delta_db": -0.026741079055980416}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9595191589145483e-05, "output_power": 1.993021132679303e-05, "reference_active": true, "delta_db": 0.07362389610422915}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.074204859780537e-06, "output_power": 4.101836066468137e-06, "reference_active": true, "delta_db": -0.9238969750390507}], "active_band_count": 3, "active_band_mae_db": 0.3414206500664201}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 6.399293414479695e-05, "log_rms_mae_db": 0.8442726553411123, "rms_envelope_nrmse": 0.08554591784444984, "envelope_correlation": 0.9928774070080326, "rms_gain_error_db": -0.0481573776369498, "reference_mean_power": 0.0003253818281247376, "output_mean_power": 0.00032179371464784016}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.1005868407421181e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.4497636322434906e-05, "output_power": 5.443389998366679e-05, "reference_active": true, "delta_db": -0.005082154226612463}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.385752117634814e-06, "output_power": 9.509890977832637e-06, "reference_active": true, "delta_db": 0.0570645808309443}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.7591737704275347e-07, "output_power": 3.129854577612288e-07, "reference_active": true, "delta_db": -0.7956824234592437}], "active_band_count": 3, "active_band_mae_db": 0.28594305283893345}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8771834304744682, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "a7fe6d02388b0a7d928488dede063cd11b94f187160f35587e01fce8ce02e41c", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9897516648725093, "standard_deviation": 0.001280505007654778, "minimum": 0.9879572300190393, "maximum": 0.9918705118194201, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4373012656081703, "standard_deviation": 0.031056358232852275, "minimum": 1.3927360854166533, "maximum": 1.4714706806444118, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.3426142056494575, "standard_deviation": 0.14200263437675148, "minimum": 0.1865975984613449, "maximum": 0.5630533683916078, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.1138871097203307, "standard_deviation": 0.0068947396645008315, "minimum": 0.10159283410032058, "maximum": 0.12293996870446898, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9966821330085047, "standard_deviation": 0.0007075053636444843, "minimum": 0.995746717810013, "maximum": 0.9980793676685026, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8553219019122935, "standard_deviation": 0.028862170006626473, "minimum": 0.8206023656477484, "maximum": 0.8957063338518877, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.380959429585064, "standard_deviation": 0.1925660470434302, "minimum": 0.19305331556446945, "maximum": 0.6505252881946765, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06400600866055459, "standard_deviation": 0.006774514469065947, "minimum": 0.04960377099634432, "maximum": 0.07220245738466591, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9785826029753869, "standard_deviation": 0.001998373913841503, "minimum": 0.974214375176385, "maximum": 0.9806177398887816, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.4260706701726114, "standard_deviation": 0.01993691763722078, "minimum": 1.3908813365754014, "maximum": 1.4467764691720437, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.6380245745721613, "standard_deviation": 0.27706605252331623, "minimum": 0.21400597743683256, "maximum": 1.0382547287799528, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.15689032548189757, "standard_deviation": 0.007887275345760732, "minimum": 0.14826243883314516, "maximum": 0.17383207145319637, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9927823937742745, "standard_deviation": 0.0015620015366838512, "minimum": 0.989718181571117, "maximum": 0.9943080045805496, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.839124056488388, "standard_deviation": 0.01784243132011288, "minimum": 0.8173316305448809, "maximum": 0.8713143263147438, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.5944397021848566, "standard_deviation": 0.3173898030178788, "minimum": 0.16814857176895578, "maximum": 1.1644088060178315, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08983832293595996, "standard_deviation": 0.009750013275529976, "minimum": 0.07962773431887461, "maximum": 0.1107273853597853, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9951882486672223, "standard_deviation": 0.0005739089396845833, "minimum": 0.9943948566101479, "maximum": 0.9960485459627167, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.4403424613620635, "standard_deviation": 0.02972402697940816, "minimum": 1.4005181484574016, "maximum": 1.4837308540350658, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.28325660100379546, "standard_deviation": 0.09507317634044513, "minimum": 0.1832647294155727, "maximum": 0.4421956637386866, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.08051674291926234, "standard_deviation": 0.004599195572170815, "minimum": 0.07420603117831548, "maximum": 0.08676410743759444, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9984212703540465, "standard_deviation": 0.0004316618983207637, "minimum": 0.9974655087176585, "maximum": 0.9989125138261371, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7886116379469896, "standard_deviation": 0.03297636968223321, "minimum": 0.7481023810809877, "maximum": 0.834693609169993, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.3869455882718891, "standard_deviation": 0.20865481974568145, "minimum": 0.07556947567088972, "maximum": 0.624721352035784, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.045483465941499615, "standard_deviation": 0.0054254764957787594, "minimum": 0.037575921223666195, "maximum": 0.05702530254964689, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.19459777300388242, "standard_deviation": 0.02570867505032475, "minimum": 0.14290647148691168, "maximum": 0.22030623626284696, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.5049129199005655, "standard_deviation": 0.00866622949538137, "minimum": 5.4964635132431665, "maximum": 5.519928102660224, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.5332305929040688, "standard_deviation": 0.012541088145181402, "minimum": 0.5137030733440797, "maximum": 0.5532071625777708, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.09289447780876532, "standard_deviation": 0.025772189819263647, "minimum": -0.14620836721492952, "maximum": -0.0565355095963084, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9955853044496336, "standard_deviation": 0.0006540339785183403, "minimum": 0.9941470198967022, "maximum": 0.9964703489209336, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.8335210509657298, "standard_deviation": 0.011933727575667819, "minimum": 0.8204545284283772, "maximum": 0.8585193466404187, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.32302638182163196, "standard_deviation": 0.10448455883632879, "minimum": 0.10600493528271161, "maximum": 0.4528384096303089, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.06977986345692005, "standard_deviation": 0.004695330648714832, "minimum": 0.06389343524955216, "maximum": 0.08023663396888774, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9987249163149498, "standard_deviation": 0.0002379163063013403, "minimum": 0.9983124094173546, "maximum": 0.9990066294252271, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4356567007603435, "standard_deviation": 0.01709087088204093, "minimum": 0.41317785998955225, "maximum": 0.4702553601521473, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.4371142073253199, "standard_deviation": 0.14522242113924697, "minimum": 0.26364595869260826, "maximum": 0.6777314304085551, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03723136399176972, "standard_deviation": 0.003164488306551675, "minimum": 0.03305436539933669, "maximum": 0.04275289005732821, "valid_count": 8, "planned_count": 8}}}, {"case": "librispeech_8463-294828-0014", "method": "E", "status": "measured", "mos": {"status": "pending", "value": null}, "seed_diagnostics": [{"seed": 0, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8305243136409391, "全帯域_10ms_rms_envelope_nrmse": 0.06670847420061062, "全帯域_10ms_envelope_correlation": 0.9960978580741917, "全帯域_10ms_modulation_mae_db": 0.5928932527440894, "全帯域_40ms_log_rms_mae_db": 0.406731755141378, "全帯域_40ms_rms_envelope_nrmse": 0.0345738979559748, "全帯域_40ms_envelope_correlation": 0.9990586855627756, "全帯域_40ms_modulation_mae_db": 0.6667830918941293, "300–1000 Hz_10ms_log_rms_mae_db": 1.4338402952716733, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07833409180388298, "300–1000 Hz_10ms_envelope_correlation": 0.9954656516081144, "300–1000 Hz_10ms_modulation_mae_db": 0.4397286450996598, "300–1000 Hz_40ms_log_rms_mae_db": 0.8032277607921974, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04452383643211352, "300–1000 Hz_40ms_envelope_correlation": 0.9985159679247742, "300–1000 Hz_40ms_modulation_mae_db": 0.5759256200994701, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4191165075786203, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10428968375266355, "1000–3000 Hz_10ms_envelope_correlation": 0.9920187604393522, "1000–3000 Hz_10ms_modulation_mae_db": 0.6825757602293231, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8360841302691889, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0625241465838079, "1000–3000 Hz_40ms_envelope_correlation": 0.9975654712800408, "1000–3000 Hz_40ms_modulation_mae_db": 0.7647150372498098, "3000–6000 Hz_10ms_log_rms_mae_db": 1.404111601772511, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14635005028872308, "3000–6000 Hz_10ms_envelope_correlation": 0.9822998717673412, "3000–6000 Hz_10ms_modulation_mae_db": 0.9691345938605015, "3000–6000 Hz_40ms_log_rms_mae_db": 0.85092886169183, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08573574100060351, "3000–6000 Hz_40ms_envelope_correlation": 0.9946720536597325, "3000–6000 Hz_40ms_modulation_mae_db": 1.0393251028611927, "mr_stft_db": 5.496446687657912, "band_mae_db": 0.2798785358704318, "rms_gain_error_db": -0.14282812564903846, "output_peak": 0.5337264746135173}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 1, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8433742083470764, "全帯域_10ms_rms_envelope_nrmse": 0.07162941840932467, "全帯域_10ms_envelope_correlation": 0.9954458166544748, "全帯域_10ms_modulation_mae_db": 0.5524722602484283, "全帯域_40ms_log_rms_mae_db": 0.43715312943500406, "全帯域_40ms_rms_envelope_nrmse": 0.03838220977846644, "全帯域_40ms_envelope_correlation": 0.9987558573504731, "全帯域_40ms_modulation_mae_db": 0.7118420271659867, "300–1000 Hz_10ms_log_rms_mae_db": 1.4626425702180301, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08150062074270586, "300–1000 Hz_10ms_envelope_correlation": 0.9951232463525823, "300–1000 Hz_10ms_modulation_mae_db": 0.4175669117448823, "300–1000 Hz_40ms_log_rms_mae_db": 0.8196722927027017, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.047704602283522274, "300–1000 Hz_40ms_envelope_correlation": 0.9983305564115691, "300–1000 Hz_40ms_modulation_mae_db": 0.6299231438390261, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4690599720165132, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11732247678400406, "1000–3000 Hz_10ms_envelope_correlation": 0.9894511852923861, "1000–3000 Hz_10ms_modulation_mae_db": 0.47935184865368763, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8727032846383611, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06628535960309018, "1000–3000 Hz_40ms_envelope_correlation": 0.996902436951756, "1000–3000 Hz_40ms_modulation_mae_db": 0.5849798367508809, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4572155242123819, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.16007959758048243, "3000–6000 Hz_10ms_envelope_correlation": 0.9777525721717706, "3000–6000 Hz_10ms_modulation_mae_db": 1.0411845943533373, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8528418045298352, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08698200011961324, "3000–6000 Hz_40ms_envelope_correlation": 0.9935244665893381, "3000–6000 Hz_40ms_modulation_mae_db": 0.9399681586869318, "mr_stft_db": 5.485975811579121, "band_mae_db": 0.25038768923048144, "rms_gain_error_db": -0.13801881212754472, "output_peak": 0.5586894220361461}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 2, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.804692395555694, "全帯域_10ms_rms_envelope_nrmse": 0.06662381267867544, "全帯域_10ms_envelope_correlation": 0.9960366344605452, "全帯域_10ms_modulation_mae_db": 0.3133083761776387, "全帯域_40ms_log_rms_mae_db": 0.4007635180148117, "全帯域_40ms_rms_envelope_nrmse": 0.03140748907616064, "全帯域_40ms_envelope_correlation": 0.9991840964965987, "全帯域_40ms_modulation_mae_db": 0.48515246839319137, "300–1000 Hz_10ms_log_rms_mae_db": 1.372165801191619, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07651125259384918, "300–1000 Hz_10ms_envelope_correlation": 0.9956798530543475, "300–1000 Hz_10ms_modulation_mae_db": 0.24056746606854318, "300–1000 Hz_40ms_log_rms_mae_db": 0.752599956718706, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.03950662213242991, "300–1000 Hz_40ms_envelope_correlation": 0.9988588501246951, "300–1000 Hz_40ms_modulation_mae_db": 0.4302558567445514, "1000–3000 Hz_10ms_log_rms_mae_db": 1.448748869891818, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11898318853688009, "1000–3000 Hz_10ms_envelope_correlation": 0.9890224792450596, "1000–3000 Hz_10ms_modulation_mae_db": 0.3698542691569267, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8721623151794554, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.07184504169660524, "1000–3000 Hz_40ms_envelope_correlation": 0.9960831430432102, "1000–3000 Hz_40ms_modulation_mae_db": 0.5024480388292889, "3000–6000 Hz_10ms_log_rms_mae_db": 1.360476039642474, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14596432816315516, "3000–6000 Hz_10ms_envelope_correlation": 0.9817975416743092, "3000–6000 Hz_10ms_modulation_mae_db": 0.6512478719310746, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8071162825005568, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08251154576983015, "3000–6000 Hz_40ms_envelope_correlation": 0.9944272145516287, "3000–6000 Hz_40ms_modulation_mae_db": 0.728706962282688, "mr_stft_db": 5.502127266238557, "band_mae_db": 0.24473259581386256, "rms_gain_error_db": -0.11634931556397436, "output_peak": 0.509944716627356}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 3, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8471859528831146, "全帯域_10ms_rms_envelope_nrmse": 0.07135260469410937, "全帯域_10ms_envelope_correlation": 0.9953432862908881, "全帯域_10ms_modulation_mae_db": 0.2758269379032026, "全帯域_40ms_log_rms_mae_db": 0.429223764329701, "全帯域_40ms_rms_envelope_nrmse": 0.03676503406925965, "全帯域_40ms_envelope_correlation": 0.9987072500816511, "全帯域_40ms_modulation_mae_db": 0.4608376430018947, "300–1000 Hz_10ms_log_rms_mae_db": 1.5316709888755473, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08566137928572418, "300–1000 Hz_10ms_envelope_correlation": 0.9945430508108772, "300–1000 Hz_10ms_modulation_mae_db": 0.27213789626604595, "300–1000 Hz_40ms_log_rms_mae_db": 0.837347013383441, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04245017570183581, "300–1000 Hz_40ms_envelope_correlation": 0.9986488049104152, "300–1000 Hz_40ms_modulation_mae_db": 0.4069548760535621, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4284487235446548, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11780322924451608, "1000–3000 Hz_10ms_envelope_correlation": 0.9890241712318073, "1000–3000 Hz_10ms_modulation_mae_db": 0.16348335267277675, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8514467213360352, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0674881298512192, "1000–3000 Hz_40ms_envelope_correlation": 0.9962983568696864, "1000–3000 Hz_40ms_modulation_mae_db": 0.40391085497844564, "3000–6000 Hz_10ms_log_rms_mae_db": 1.3965907511998084, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.148044202312053, "3000–6000 Hz_10ms_envelope_correlation": 0.9813849162082873, "3000–6000 Hz_10ms_modulation_mae_db": 0.74244328580494, "3000–6000 Hz_40ms_log_rms_mae_db": 0.817542855152745, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08940980288492575, "3000–6000 Hz_40ms_envelope_correlation": 0.9927234919773594, "3000–6000 Hz_40ms_modulation_mae_db": 0.6620116708073068, "mr_stft_db": 5.499670712361005, "band_mae_db": 0.16176996002259708, "rms_gain_error_db": -0.07339009293745971, "output_peak": 0.5375432340362811}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 4, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8166620954828925, "全帯域_10ms_rms_envelope_nrmse": 0.06661508964055658, "全帯域_10ms_envelope_correlation": 0.995968555048945, "全帯域_10ms_modulation_mae_db": 0.3590311801320478, "全帯域_40ms_log_rms_mae_db": 0.41177611521452007, "全帯域_40ms_rms_envelope_nrmse": 0.03606862869866116, "全帯域_40ms_envelope_correlation": 0.9987750191823702, "全帯域_40ms_modulation_mae_db": 0.4355116553586504, "300–1000 Hz_10ms_log_rms_mae_db": 1.4387380175135132, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07757908860694154, "300–1000 Hz_10ms_envelope_correlation": 0.9955253638776455, "300–1000 Hz_10ms_modulation_mae_db": 0.2844756267093136, "300–1000 Hz_40ms_log_rms_mae_db": 0.8109976611039903, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04787072121999266, "300–1000 Hz_40ms_envelope_correlation": 0.9982247817686106, "300–1000 Hz_40ms_modulation_mae_db": 0.4116426843216104, "1000–3000 Hz_10ms_log_rms_mae_db": 1.408032377194555, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11347543776664705, "1000–3000 Hz_10ms_envelope_correlation": 0.9898284837955176, "1000–3000 Hz_10ms_modulation_mae_db": 0.29830841176611006, "1000–3000 Hz_40ms_log_rms_mae_db": 0.862032338452907, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06641830825939153, "1000–3000 Hz_40ms_envelope_correlation": 0.9964137558144481, "1000–3000 Hz_40ms_modulation_mae_db": 0.3579103238167834, "3000–6000 Hz_10ms_log_rms_mae_db": 1.390885576874198, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15380769774413341, "3000–6000 Hz_10ms_envelope_correlation": 0.979121680589543, "3000–6000 Hz_10ms_modulation_mae_db": 0.4496388304997348, "3000–6000 Hz_40ms_log_rms_mae_db": 0.781433997349098, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.08111789120265724, "3000–6000 Hz_40ms_envelope_correlation": 0.993778282851517, "3000–6000 Hz_40ms_modulation_mae_db": 0.549902511605791, "mr_stft_db": 5.49560582637777, "band_mae_db": 0.17234431904886527, "rms_gain_error_db": -0.08054776131262281, "output_peak": 0.5163949856744044}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 5, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.839841579569095, "全帯域_10ms_rms_envelope_nrmse": 0.07084334618963135, "全帯域_10ms_envelope_correlation": 0.995443772501359, "全帯域_10ms_modulation_mae_db": 0.22971888090251188, "全帯域_40ms_log_rms_mae_db": 0.39508356934509076, "全帯域_40ms_rms_envelope_nrmse": 0.03563923520065332, "全帯域_40ms_envelope_correlation": 0.9988322001222298, "全帯域_40ms_modulation_mae_db": 0.42996135702802657, "300–1000 Hz_10ms_log_rms_mae_db": 1.4746817221175645, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.08634543932266946, "300–1000 Hz_10ms_envelope_correlation": 0.9944679922925018, "300–1000 Hz_10ms_modulation_mae_db": 0.3405390934811598, "300–1000 Hz_40ms_log_rms_mae_db": 0.7679406226117175, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.048972965070146986, "300–1000 Hz_40ms_envelope_correlation": 0.9981906575968998, "300–1000 Hz_40ms_modulation_mae_db": 0.3358926457640616, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4246702567732759, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.10434876180955907, "1000–3000 Hz_10ms_envelope_correlation": 0.9913954940384399, "1000–3000 Hz_10ms_modulation_mae_db": 0.28138031140647374, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8305265307608699, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.057171512233894134, "1000–3000 Hz_40ms_envelope_correlation": 0.9973480001436436, "1000–3000 Hz_40ms_modulation_mae_db": 0.3574901199951559, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4043203397121873, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.1449669620858629, "3000–6000 Hz_10ms_envelope_correlation": 0.981578220050874, "3000–6000 Hz_10ms_modulation_mae_db": 0.46125977320483297, "3000–6000 Hz_40ms_log_rms_mae_db": 0.822860616587573, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07947927768090672, "3000–6000 Hz_40ms_envelope_correlation": 0.9941859197702791, "3000–6000 Hz_40ms_modulation_mae_db": 0.28051314683445855, "mr_stft_db": 5.480450715097997, "band_mae_db": 0.19419384733770487, "rms_gain_error_db": -0.09081853538394416, "output_peak": 0.5878993314231252}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 6, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.7868749306405064, "全帯域_10ms_rms_envelope_nrmse": 0.06800720261113045, "全帯域_10ms_envelope_correlation": 0.995826325691869, "全帯域_10ms_modulation_mae_db": 0.38819869090937825, "全帯域_40ms_log_rms_mae_db": 0.4078648025657174, "全帯域_40ms_rms_envelope_nrmse": 0.03760671287893366, "全帯域_40ms_envelope_correlation": 0.9987046722792384, "全帯域_40ms_modulation_mae_db": 0.5811950839739369, "300–1000 Hz_10ms_log_rms_mae_db": 1.4570958452267597, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07664767309079641, "300–1000 Hz_10ms_envelope_correlation": 0.9956102378634011, "300–1000 Hz_10ms_modulation_mae_db": 0.20705874161597193, "300–1000 Hz_40ms_log_rms_mae_db": 0.7836625423126042, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.04596527865587908, "300–1000 Hz_40ms_envelope_correlation": 0.9983342557603258, "300–1000 Hz_40ms_modulation_mae_db": 0.35225009358618964, "1000–3000 Hz_10ms_log_rms_mae_db": 1.41681382505667, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11151446239992767, "1000–3000 Hz_10ms_envelope_correlation": 0.9907753229669821, "1000–3000 Hz_10ms_modulation_mae_db": 0.7520694955935675, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8431666701352734, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.06558042691672358, "1000–3000 Hz_40ms_envelope_correlation": 0.9972762531698984, "1000–3000 Hz_40ms_modulation_mae_db": 1.0258468323167584, "3000–6000 Hz_10ms_log_rms_mae_db": 1.366495385882323, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.15493411930002005, "3000–6000 Hz_10ms_envelope_correlation": 0.9795644616234135, "3000–6000 Hz_10ms_modulation_mae_db": 1.0752377778806252, "3000–6000 Hz_40ms_log_rms_mae_db": 0.7859713000346903, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.0841742499601006, "3000–6000 Hz_40ms_envelope_correlation": 0.9945073499926367, "3000–6000 Hz_40ms_modulation_mae_db": 1.20781516946192, "mr_stft_db": 5.485289546434732, "band_mae_db": 0.2315624128158232, "rms_gain_error_db": -0.10194202202562307, "output_peak": 0.5483584441455563}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}, {"seed": 7, "status": "measured", "values": {"全帯域_10ms_log_rms_mae_db": 0.8244153912001804, "全帯域_10ms_rms_envelope_nrmse": 0.062189333723341525, "全帯域_10ms_envelope_correlation": 0.996458771747904, "全帯域_10ms_modulation_mae_db": 0.4344498451768686, "全帯域_40ms_log_rms_mae_db": 0.4199859178210235, "全帯域_40ms_rms_envelope_nrmse": 0.03197963588989047, "全帯域_40ms_envelope_correlation": 0.9990077162022168, "全帯域_40ms_modulation_mae_db": 0.5972820060905696, "300–1000 Hz_10ms_log_rms_mae_db": 1.425990731304859, "300–1000 Hz_10ms_rms_envelope_nrmse": 0.07019166935878506, "300–1000 Hz_10ms_envelope_correlation": 0.9963188024169876, "300–1000 Hz_10ms_modulation_mae_db": 0.2822899621861618, "300–1000 Hz_40ms_log_rms_mae_db": 0.7188120834373289, "300–1000 Hz_40ms_rms_envelope_nrmse": 0.039075515783738246, "300–1000 Hz_40ms_envelope_correlation": 0.9987931456447054, "300–1000 Hz_40ms_modulation_mae_db": 0.5246899146839723, "1000–3000 Hz_10ms_log_rms_mae_db": 1.4358334745054961, "1000–3000 Hz_10ms_rms_envelope_nrmse": 0.11230906952254427, "1000–3000 Hz_10ms_envelope_correlation": 0.9901277323191557, "1000–3000 Hz_10ms_modulation_mae_db": 0.2816453898283748, "1000–3000 Hz_40ms_log_rms_mae_db": 0.8127148910649272, "1000–3000 Hz_40ms_rms_envelope_nrmse": 0.0593010495452181, "1000–3000 Hz_40ms_envelope_correlation": 0.9973235100150161, "1000–3000 Hz_40ms_modulation_mae_db": 0.3946982268222174, "3000–6000 Hz_10ms_log_rms_mae_db": 1.4310552760241366, "3000–6000 Hz_10ms_rms_envelope_nrmse": 0.14535593529612065, "3000–6000 Hz_10ms_envelope_correlation": 0.9815296570172687, "3000–6000 Hz_10ms_modulation_mae_db": 1.0337517757414103, "3000–6000 Hz_40ms_log_rms_mae_db": 0.8309210228463221, "3000–6000 Hz_40ms_rms_envelope_nrmse": 0.07937502950786343, "3000–6000 Hz_40ms_envelope_correlation": 0.9942952773532974, "3000–6000 Hz_40ms_modulation_mae_db": 1.2984932037938963, "mr_stft_db": 5.493758081207161, "band_mae_db": 0.19853450689958854, "rms_gain_error_db": -0.054547550986089294, "output_peak": 0.5216063564211952}, "full_scale": {"sample_count": 91600, "full_scale_amplitude": 1.0, "at_or_above_full_scale_samples": 0, "at_or_above_full_scale_fraction": 0.0, "near_full_scale_amplitude": 0.999, "near_full_scale_fraction": 0.0, "longest_full_scale_run_samples": 0, "meaning": "固定振幅尺度の閾値超過。録音時のクリッピング発生の証明ではない"}}], "measurement": {"status": "ok", "reference_samples": 91600, "output_samples": 91600, "length_delta_samples": 0, "sample_rate": 16000, "reference_finite": true, "output_finite": true, "alignment": "none", "gain_normalization": "none", "mr_stft": [{"window_ms": 5, "window_samples": 80, "hop_samples": 20, "log_magnitude_mae_db": 5.586975219173038, "spectral_convergence": 0.26165668682903326, "spectral_convergence_status": "ok", "amplitude_floor": 1.4112644553101518e-06}, {"window_ms": 20, "window_samples": 320, "hop_samples": 80, "log_magnitude_mae_db": 5.295926709587348, "spectral_convergence": 0.25541290278099105, "spectral_convergence_status": "ok", "amplitude_floor": 1.1975531593072457e-06}, {"window_ms": 80, "window_samples": 1280, "hop_samples": 320, "log_magnitude_mae_db": 5.606438134213348, "spectral_convergence": 0.2662839931521121, "spectral_convergence_status": "ok", "amplitude_floor": 1.114415465542996e-06}], "band_energy": {"bands": [{"low_hz": 0.0, "high_hz": 200.0, "reference_power": 5.564075826256522e-05, "output_power": 6.138493876070019e-05, "delta_db": 0.4266878706494296, "reference_active": true}, {"low_hz": 200.0, "high_hz": 500.0, "reference_power": 0.0010000129923479963, "output_power": 0.0010133935278550405, "delta_db": 0.0577248382747498, "reference_active": true}, {"low_hz": 500.0, "high_hz": 1000.0, "reference_power": 0.0018259392170112694, "output_power": 0.001760158275891859, "delta_db": -0.159345944400471, "reference_active": true}, {"low_hz": 1000.0, "high_hz": 2000.0, "reference_power": 0.0005127219920465177, "output_power": 0.0004830390179669901, "delta_db": -0.2589973317029804, "reference_active": true}, {"low_hz": 2000.0, "high_hz": 4000.0, "reference_power": 0.00033320627903786135, "output_power": 0.0002990879278648258, "delta_db": -0.4691429290022158, "reference_active": true}, {"low_hz": 4000.0, "high_hz": 8000.0, "reference_power": 0.0002817706196064759, "output_power": 0.0002625176312442529, "delta_db": -0.3073723011927442, "reference_active": true}], "power_floor": 1e-12, "active_band_count": 6, "band_count": 6, "active_band_mae_db": 0.2798785358704318, "active_policy": "reference power > max(1e-12, total reference power * 1e-6)", "status": "ok"}, "rms_gain_error_db": -0.14282812564903846, "pitch": null, "output_rms_dbfs": -24.11215140489717, "output_peak": 0.5337264746135173, "reference_rms_dbfs": -23.96932327924813, "rms_gain_status": "ok", "mr_stft_log_magnitude_mae_db": 5.496446687657912}, "temporal": {"schema": "temporal-diagnostics-v2", "status": "measured", "sample_rate": 16000, "samples": 91600, "alignment": "none", "normalization": "none", "bands": [{"name": "全帯域", "status": "measured", "filter": {"kind": "none"}, "windows": [{"window_ms": 10.0, "window_samples": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00020825955187282386, "log_rms_mae_db": 0.8305243136409391, "rms_envelope_nrmse": 0.06670847420061062, "envelope_correlation": 0.9960978580741917, "rms_gain_error_db": -0.14281312201148952, "reference_mean_power": 0.004012756910556895, "output_mean_power": 0.003882947683246203}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 2.2120307480210933e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008889321025104637, "output_power": 0.0008475914557544315, "reference_active": true, "delta_db": -0.20682020302374415}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00022980725896418495, "output_power": 0.00021267165467466322, "reference_active": true, "delta_db": -0.33654132630619676}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 4.1131932747773025e-05, "output_power": 3.0949047971081776e-05, "reference_active": true, "delta_db": -1.2353182289023272}], "active_band_count": 3, "active_band_mae_db": 0.5928932527440894}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.0001984160011662782, "log_rms_mae_db": 0.406731755141378, "rms_envelope_nrmse": 0.0345738979559748, "envelope_correlation": 0.9990586855627756, "rms_gain_error_db": -0.14282081247709025, "reference_mean_power": 0.0040337408532874226, "output_mean_power": 0.003903245901661234}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 2.0115882799069226e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0008024963383362849, "output_power": 0.0007657064920687584, "reference_active": true, "delta_db": -0.20380730174270673}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00011463438169489824, "output_power": 0.0001042786086576902, "reference_active": true, "delta_db": -0.41119664917642795}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.4945953602736586e-06, "output_power": 2.5401675486554903e-06, "reference_active": true, "delta_db": -1.3853453247632532}], "active_band_count": 3, "active_band_mae_db": 0.6667830918941293}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 0.00019054595180557928, "log_rms_mae_db": 1.4338402952716733, "rms_envelope_nrmse": 0.07833409180388298, "envelope_correlation": 0.9954656516081144, "rms_gain_error_db": -0.10016110620437758, "reference_mean_power": 0.0025757888112863028, "output_mean_power": 0.0025170633248100724}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.7595886306573375e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0007279305516452219, "output_power": 0.0007027094183705824, "reference_active": true, "delta_db": -0.15314172942420878}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 0.00019010480993234813, "output_power": 0.0001775359746485958, "reference_active": true, "delta_db": -0.2970673659030952}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.6294378423488108e-05, "output_power": 2.152609362862313e-05, "reference_active": true, "delta_db": -0.8689768399716755}], "active_band_count": 3, "active_band_mae_db": 0.4397286450996598}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 0.00018019065505981728, "log_rms_mae_db": 0.8032277607921974, "rms_envelope_nrmse": 0.04452383643211352, "envelope_correlation": 0.9985159679247742, "rms_gain_error_db": -0.10016056216692328, "reference_mean_power": 0.0025893611436675294, "output_mean_power": 0.00253032653814977}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.6269545971301712e-09, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.0006780414214466183, "output_power": 0.0006533974955354539, "reference_active": true, "delta_db": -0.1607876016367275}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.548437806715927e-05, "output_power": 8.76084652162673e-05, "reference_active": true, "delta_db": -0.37386251546960936}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 2.9327510117604047e-06, "output_power": 2.2282428363419786e-06, "reference_active": true, "delta_db": -1.1931267431920736}], "active_band_count": 3, "active_band_mae_db": 0.5759256200994701}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.327720993461315e-05, "log_rms_mae_db": 1.4191165075786203, "rms_envelope_nrmse": 0.10428968375266355, "envelope_correlation": 0.9920187604393522, "rms_gain_error_db": -0.3005609328340887, "reference_mean_power": 0.0007122971869413385, "output_mean_power": 0.0006646685593168326}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 4.689927289528067e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00023362430343497353, "output_power": 0.00021428083136083737, "reference_active": true, "delta_db": -0.3753469684568938}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 3.797902128989837e-05, "output_power": 3.397314887458409e-05, "reference_active": true, "delta_db": -0.4840796662601343}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 1.042184778585592e-05, "output_power": 7.927105922110278e-06, "reference_active": true, "delta_db": -1.1883006459709413}], "active_band_count": 3, "active_band_mae_db": 0.6825757602293231}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 8.747046012456969e-05, "log_rms_mae_db": 0.8360841302691889, "rms_envelope_nrmse": 0.0625241465838079, "envelope_correlation": 0.9975654712800408, "rms_gain_error_db": -0.3006010163174118, "reference_mean_power": 0.0007159674763911086, "output_mean_power": 0.0006680872641655747}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 4.328159646639031e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 0.00021700970165722394, "output_power": 0.00020027676756674832, "reference_active": true, "delta_db": -0.3484857655093635}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.702508733600319e-05, "output_power": 1.4563536306734827e-05, "reference_active": true, "delta_db": -0.6782250561657698}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 8.679451250427792e-07, "output_power": 6.482594243132968e-07, "reference_active": true, "delta_db": -1.2674342900742963}], "active_band_count": 3, "active_band_mae_db": 0.7647150372498098}}]}, {"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": 160, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1144, "rms_floor": 9.039773028293347e-05, "log_rms_mae_db": 1.404111601772511, "rms_envelope_nrmse": 0.14635005028872308, "envelope_correlation": 0.9822998717673412, "rms_gain_error_db": -0.4114011126913797, "reference_mean_power": 0.0003237352885604671, "output_mean_power": 0.00029447601725508295}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1144, "frequency_resolution_hz": 0.17482517482517484, "power_floor": 1.2480235329901466e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.70846061617512e-05, "output_power": 5.3980460352981275e-05, "reference_active": true, "delta_db": -0.24282425154477263}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 1.9595191589145483e-05, "output_power": 1.7386102053498813e-05, "reference_active": true, "delta_db": -0.5194728955392353}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 5.074204859780537e-06, "output_power": 3.0964019584140346e-06, "reference_active": true, "delta_db": -2.1451066344974965}], "active_band_count": 3, "active_band_mae_db": 0.9691345938605015}}, {"window_ms": 40.0, "window_samples": 640, "hop_samples": 80, "hop_ms": 5.0, "status": "measured", "covered_start_sample": 0, "covered_end_sample": 91600, "uncovered_tail_samples": 0, "metrics": {"frame_count": 1138, "rms_floor": 6.399293414479695e-05, "log_rms_mae_db": 0.85092886169183, "rms_envelope_nrmse": 0.08573574100060351, "envelope_correlation": 0.9946720536597325, "rms_gain_error_db": -0.41154798163225975, "reference_mean_power": 0.0003253818281247376, "output_mean_power": 0.0002959637331688749}, "modulation_bands": {"status": "measured", "envelope_rate_hz": 200.0, "frames": 1138, "frequency_resolution_hz": 0.17574692442882248, "power_floor": 1.1005868407421181e-10, "window": "hann", "detrend": "constant", "gain_normalization": "none", "bands": [{"low_hz": 2.0, "high_hz": 8.0, "reference_power": 5.4497636322434906e-05, "output_power": 5.114057327120271e-05, "reference_active": true, "delta_db": -0.27612074381815366}, {"low_hz": 8.0, "high_hz": 20.0, "reference_power": 9.385752117634814e-06, "output_power": 8.180567372474225e-06, "reference_active": true, "delta_db": -0.5968565439602921}, {"low_hz": 20.0, "high_hz": 50.0, "reference_power": 3.7591737704275347e-07, "output_power": 2.2417779835962893e-07, "reference_active": true, "delta_db": -2.2449980208051326}], "active_band_count": 3, "active_band_mae_db": 1.0393251028611927}}]}], "event": null, "silent_intervals": null, "limitations": ["有限長雑音の包絡差は独立seedでもゼロにならない", "帯域フィルタの端点過渡は測定に含むがイベント測定には使わない", "RMS包絡は有声・無声や知覚品質の正解測定ではない"]}, "estoi": {"value": 0.8892738170571406, "library": "pystoi", "version": "0.4.1", "extended": true, "reference_required": true, "internal_sample_rate": 10000, "evaluation_seed": 0, "internal_silence_removal_db": 40, "warnings": [], "normalization": "公式実装の行・列正規化", "scope": "明瞭性の推定。MOS・自然性・話者類似度ではない", "status": "measured"}, "waveform_sha256": "9e083006f66a0dba5d65d6f1154747ccdb7fa3812d524bcc1f216a944f5c7474", "seed_summary": {"1000–3000 Hz_10ms_envelope_correlation": {"mean": 0.9902054536660876, "standard_deviation": 0.0011045977226959922, "minimum": 0.9890224792450596, "maximum": 0.9920187604393522, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_log_rms_mae_db": {"mean": 1.4313405008202005, "standard_deviation": 0.019648955303069208, "minimum": 1.408032377194555, "maximum": 1.4690599720165132, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_modulation_mae_db": {"mean": 0.413583604913405, "standard_deviation": 0.2083579009579792, "minimum": 0.16348335267277675, "maximum": 0.7520694955935675, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.11250578872709273, "standard_deviation": 0.005722426843388714, "minimum": 0.10428968375266355, "maximum": 0.11898318853688009, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_envelope_correlation": {"mean": 0.9969013659109625, "standard_deviation": 0.0005644387223561833, "minimum": 0.9960831430432102, "maximum": 0.9975654712800408, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_log_rms_mae_db": {"mean": 0.8476046102296273, "standard_deviation": 0.021102862234608354, "minimum": 0.8127148910649272, "maximum": 0.8727032846383611, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_modulation_mae_db": {"mean": 0.5489999088449176, "standard_deviation": 0.2376758621736083, "minimum": 0.3574901199951559, "maximum": 1.0258468323167584, "valid_count": 8, "planned_count": 8}, "1000–3000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.06457674683624373, "standard_deviation": 0.004713294119856617, "minimum": 0.057171512233894134, "maximum": 0.07184504169660524, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_envelope_correlation": {"mean": 0.9806286151378509, "standard_deviation": 0.0016089039221785673, "minimum": 0.9777525721717706, "maximum": 0.9822998717673412, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_log_rms_mae_db": {"mean": 1.4013938119150025, "standard_deviation": 0.03170730782547874, "minimum": 1.360476039642474, "maximum": 1.4572155242123819, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_modulation_mae_db": {"mean": 0.802987312909557, "standard_deviation": 0.26187202856632946, "minimum": 0.4496388304997348, "maximum": 1.0752377778806252, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.14993786159631883, "standard_deviation": 0.005615593412186809, "minimum": 0.1449669620858629, "maximum": 0.16007959758048243, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_envelope_correlation": {"mean": 0.9940142570932236, "standard_deviation": 0.0006454748439114991, "minimum": 0.9927234919773594, "maximum": 0.9946720536597325, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_log_rms_mae_db": {"mean": 0.8187020925865813, "standard_deviation": 0.026636362599094493, "minimum": 0.781433997349098, "maximum": 0.8528418045298352, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_modulation_mae_db": {"mean": 0.8383419907917731, "standard_deviation": 0.34567826318040684, "minimum": 0.28051314683445855, "maximum": 1.2984932037938963, "valid_count": 8, "planned_count": 8}, "3000–6000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.08359819226581258, "standard_deviation": 0.0036304109497683605, "minimum": 0.07937502950786343, "maximum": 0.08940980288492575, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_envelope_correlation": {"mean": 0.9953417747845572, "standard_deviation": 0.0006140280662954606, "minimum": 0.9944679922925018, "maximum": 0.9963188024169876, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_log_rms_mae_db": {"mean": 1.4496032464649458, "standard_deviation": 0.04552995861236939, "minimum": 1.372165801191619, "maximum": 1.5316709888755473, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_modulation_mae_db": {"mean": 0.3105455428964673, "standard_deviation": 0.08246304395518048, "minimum": 0.20705874161597193, "maximum": 0.4397286450996598, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_10ms_rms_envelope_nrmse": {"mean": 0.07909640185066932, "standard_deviation": 0.0052953433388291515, "minimum": 0.07019166935878506, "maximum": 0.08634543932266946, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_envelope_correlation": {"mean": 0.9984871275177494, "standard_deviation": 0.00025729364282991356, "minimum": 0.9981906575968998, "maximum": 0.9988588501246951, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_log_rms_mae_db": {"mean": 0.7867824916328359, "standard_deviation": 0.03900275334587231, "minimum": 0.7188120834373289, "maximum": 0.837347013383441, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_modulation_mae_db": {"mean": 0.45844185438655544, "standard_deviation": 0.1065883896432076, "minimum": 0.3358926457640616, "maximum": 0.6299231438390261, "valid_count": 8, "planned_count": 8}, "300–1000 Hz_40ms_rms_envelope_nrmse": {"mean": 0.044508714659957316, "standard_deviation": 0.0038237283078142717, "minimum": 0.039075515783738246, "maximum": 0.048972965070146986, "valid_count": 8, "planned_count": 8}, "band_mae_db": {"mean": 0.21667548337991935, "standard_deviation": 0.04132510220620419, "minimum": 0.16176996002259708, "maximum": 0.2798785358704318, "valid_count": 8, "planned_count": 8}, "mr_stft_db": {"mean": 5.492415580869282, "standard_deviation": 0.007658725830008819, "minimum": 5.480450715097997, "maximum": 5.502127266238557, "valid_count": 8, "planned_count": 8}, "output_peak": {"mean": 0.5392703706221977, "standard_deviation": 0.025504847905927004, "minimum": 0.509944716627356, "maximum": 0.5878993314231252, "valid_count": 8, "planned_count": 8}, "rms_gain_error_db": {"mean": -0.09980527699828706, "standard_deviation": 0.03113828101610249, "minimum": -0.14282812564903846, "maximum": -0.054547550986089294, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_envelope_correlation": {"mean": 0.9958276275587721, "standard_deviation": 0.00038961966652273117, "minimum": 0.9953432862908881, "maximum": 0.996458771747904, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_log_rms_mae_db": {"mean": 0.8241963584149373, "standard_deviation": 0.02074069146031086, "minimum": 0.7868749306405064, "maximum": 0.8471859528831146, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_modulation_mae_db": {"mean": 0.3932374280242707, "standard_deviation": 0.12818752530376593, "minimum": 0.22971888090251188, "maximum": 0.5928932527440894, "valid_count": 8, "planned_count": 8}, "全帯域_10ms_rms_envelope_nrmse": {"mean": 0.0679961602684225, "standard_deviation": 0.003201359921402848, "minimum": 0.062189333723341525, "maximum": 0.07162941840932467, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_envelope_correlation": {"mean": 0.9988781871596942, "standard_deviation": 0.0001812606207924803, "minimum": 0.9987046722792384, "maximum": 0.9991840964965987, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_log_rms_mae_db": {"mean": 0.4135728214834058, "standard_deviation": 0.014296109669456356, "minimum": 0.39508356934509076, "maximum": 0.43715312943500406, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_modulation_mae_db": {"mean": 0.5460706666132982, "standard_deviation": 0.10862012541286814, "minimum": 0.42996135702802657, "maximum": 0.7118420271659867, "valid_count": 8, "planned_count": 8}, "全帯域_40ms_rms_envelope_nrmse": {"mean": 0.03530285544350002, "standard_deviation": 0.002517843604355606, "minimum": 0.03140748907616064, "maximum": 0.03838220977846644, "valid_count": 8, "planned_count": 8}}}]}
