├── README.md ├── adapt.py ├── adapt_data └── adaptation_data_loc.txt ├── adapt_speaker_list.txt ├── beamformer ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-36.pyc │ ├── cgmm_help.cpython-36.pyc │ ├── complexGMM_mvdr.cpython-36.pyc │ ├── complexGMM_mvdr_iterative.cpython-36.pyc │ ├── complexGMM_mvdr_snr_selective.cpython-36.pyc │ ├── delaysum.cpython-36.pyc │ ├── minimum_variance_distortioless_response.cpython-36.pyc │ ├── speaker_diarization_by_delaysum.cpython-36.pyc │ ├── util.cpython-36.pyc │ ├── vad.cpython-36.pyc │ └── weighted_prediction_error.cpython-36.pyc ├── complexGMM_mvdr.py ├── complexGMM_mvdr_snr_selective.py ├── delaysum.py └── util.py ├── dataset ├── adaptation_data │ ├── speaker1 │ │ ├── 251-136532-0000.flac │ │ ├── 251-136532-0001.flac │ │ ├── 251-136532-0002.flac │ │ ├── 251-136532-0003.flac │ │ └── 251-136532-0004.flac │ ├── speaker1_2 │ │ └── 251-137823-0023.flac │ └── speaker2 │ │ ├── 2412-153954-0002.flac │ │ ├── 2412-153954-0003.flac │ │ ├── 2412-153954-0004.flac │ │ ├── 2412-153954-0005.flac │ │ ├── 2412-153954-0006.flac │ │ └── 2412-153954-0007.flac ├── data_for_beamforming │ ├── F02_011C021A_BUS.CH1.wav │ ├── F02_011C021A_BUS.CH2.wav │ ├── F02_011C021A_BUS.CH3.wav │ ├── F02_011C021A_BUS.CH4.wav │ ├── F02_011C021A_BUS.CH5.wav │ └── F02_011C021A_BUS.CH6.wav ├── train │ ├── noise │ │ ├── 447o0301_0.32331_445c020s_-0.32331_12.244375.wav │ │ ├── 447o0301_0.56098_22ha010i_-0.56098_12.603875.wav │ │ ├── 447o0301_0.69862_050o020g_-0.69862_12.1389375.wav │ │ ├── 447o0301_0.9755_423o0308_-0.9755_13.431875.wav │ │ ├── 447o0302_1.3388_22ho010i_-1.3388_12.69025.wav │ │ ├── 447o0302_2.1067_422o030k_-2.1067_11.834.wav │ │ ├── 447o030x_0.98832_441o0308_-0.98832_16.4556875.wav │ │ ├── 447o030x_1.4783_422o030p_-1.4783_16.124125.wav │ │ └── 447o030x_1.6276_440o0304_-1.6276_14.556125.wav │ └── speech │ │ ├── 652-130737-0001.flac │ │ ├── 652-130737-0002.flac │ │ ├── 652-130737-0003.flac │ │ ├── 652-130737-0004.flac │ │ ├── 652-130737-0005.flac │ │ ├── 652-130737-0006.flac │ │ ├── 777-126732-0002.flac │ │ ├── 777-126732-0003.flac │ │ ├── 777-126732-0004.flac │ │ └── 777-126732-0005.flac └── validate │ ├── noise │ ├── 447o030q_2.4332_440o0309_-2.4332_12.56975.wav │ ├── 447o030r_0.25387_442c020t_-0.25387_14.1650625.wav │ ├── 447o030r_1.6517_422o0312_-1.6517_14.6394375.wav │ ├── 447o030t_1.3876_442o0305_-1.3876_11.87325.wav │ └── 447o030u_1.9508_051c0109_-1.9508_16.297875.wav │ └── speech │ ├── 174-84280-0001.flac │ ├── 174-84280-0002.flac │ ├── 174-84280-0003.flac │ ├── 174-84280-0004.flac │ ├── 174-84280-0005.flac │ ├── 84-121123-0001.flac │ ├── 84-121123-0002.flac │ ├── 84-121123-0003.flac │ ├── 84-121123-0004.flac │ ├── 84-121123-0005.flac │ └── 84-121123-0006.flac ├── generate_validate_data.py ├── image ├── model.png ├── sample_mask.png └── sample_mask_multi.png ├── maskestimator ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-36.pyc │ ├── adapt_model.cpython-36.pyc │ ├── augment.cpython-36.pyc │ ├── feature.cpython-36.pyc │ ├── model.cpython-36.pyc │ ├── shaper.cpython-36.pyc │ └── util.cpython-36.pyc ├── adapt_model.py ├── augment.py ├── feature.py ├── model.py ├── shaper.py └── util.py ├── model ├── 194sequence_false_e1.hdf5.data-00000-of-00001 ├── 194sequence_false_e1.hdf5.index └── checkpoint ├── non_adapt_speaker_list.txt ├── predict.py ├── predict_single.py ├── result ├── enhacement.wav ├── enhacement_all_channels.wav ├── enhacement_snr_select.wav ├── speech_clean.wav └── speech_noisy.wav ├── sp1_list.txt ├── sp2_list.txt ├── speaker_aware_mask_predict.py ├── tflog └── tflog_loc.txt ├── train.py └── validation_features └── val_data.txt /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/README.md -------------------------------------------------------------------------------- /adapt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/adapt.py -------------------------------------------------------------------------------- /adapt_data/adaptation_data_loc.txt: -------------------------------------------------------------------------------- 1 | adaptation -------------------------------------------------------------------------------- /adapt_speaker_list.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/adapt_speaker_list.txt -------------------------------------------------------------------------------- /beamformer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__init__.py -------------------------------------------------------------------------------- /beamformer/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/__pycache__/cgmm_help.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/cgmm_help.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/__pycache__/complexGMM_mvdr.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/complexGMM_mvdr.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/__pycache__/complexGMM_mvdr_iterative.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/complexGMM_mvdr_iterative.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/__pycache__/complexGMM_mvdr_snr_selective.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/complexGMM_mvdr_snr_selective.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/__pycache__/delaysum.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/delaysum.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/__pycache__/minimum_variance_distortioless_response.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/minimum_variance_distortioless_response.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/__pycache__/speaker_diarization_by_delaysum.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/speaker_diarization_by_delaysum.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/__pycache__/util.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/util.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/__pycache__/vad.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/vad.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/__pycache__/weighted_prediction_error.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/__pycache__/weighted_prediction_error.cpython-36.pyc -------------------------------------------------------------------------------- /beamformer/complexGMM_mvdr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/complexGMM_mvdr.py -------------------------------------------------------------------------------- /beamformer/complexGMM_mvdr_snr_selective.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/complexGMM_mvdr_snr_selective.py -------------------------------------------------------------------------------- /beamformer/delaysum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/delaysum.py -------------------------------------------------------------------------------- /beamformer/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/beamformer/util.py -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker1/251-136532-0000.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker1/251-136532-0000.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker1/251-136532-0001.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker1/251-136532-0001.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker1/251-136532-0002.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker1/251-136532-0002.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker1/251-136532-0003.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker1/251-136532-0003.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker1/251-136532-0004.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker1/251-136532-0004.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker1_2/251-137823-0023.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker1_2/251-137823-0023.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker2/2412-153954-0002.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker2/2412-153954-0002.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker2/2412-153954-0003.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker2/2412-153954-0003.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker2/2412-153954-0004.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker2/2412-153954-0004.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker2/2412-153954-0005.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker2/2412-153954-0005.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker2/2412-153954-0006.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker2/2412-153954-0006.flac -------------------------------------------------------------------------------- /dataset/adaptation_data/speaker2/2412-153954-0007.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/adaptation_data/speaker2/2412-153954-0007.flac -------------------------------------------------------------------------------- /dataset/data_for_beamforming/F02_011C021A_BUS.CH1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/data_for_beamforming/F02_011C021A_BUS.CH1.wav -------------------------------------------------------------------------------- /dataset/data_for_beamforming/F02_011C021A_BUS.CH2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/data_for_beamforming/F02_011C021A_BUS.CH2.wav -------------------------------------------------------------------------------- /dataset/data_for_beamforming/F02_011C021A_BUS.CH3.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/data_for_beamforming/F02_011C021A_BUS.CH3.wav -------------------------------------------------------------------------------- /dataset/data_for_beamforming/F02_011C021A_BUS.CH4.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/data_for_beamforming/F02_011C021A_BUS.CH4.wav -------------------------------------------------------------------------------- /dataset/data_for_beamforming/F02_011C021A_BUS.CH5.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/data_for_beamforming/F02_011C021A_BUS.CH5.wav -------------------------------------------------------------------------------- /dataset/data_for_beamforming/F02_011C021A_BUS.CH6.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/data_for_beamforming/F02_011C021A_BUS.CH6.wav -------------------------------------------------------------------------------- /dataset/train/noise/447o0301_0.32331_445c020s_-0.32331_12.244375.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/noise/447o0301_0.32331_445c020s_-0.32331_12.244375.wav -------------------------------------------------------------------------------- /dataset/train/noise/447o0301_0.56098_22ha010i_-0.56098_12.603875.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/noise/447o0301_0.56098_22ha010i_-0.56098_12.603875.wav -------------------------------------------------------------------------------- /dataset/train/noise/447o0301_0.69862_050o020g_-0.69862_12.1389375.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/noise/447o0301_0.69862_050o020g_-0.69862_12.1389375.wav -------------------------------------------------------------------------------- /dataset/train/noise/447o0301_0.9755_423o0308_-0.9755_13.431875.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/noise/447o0301_0.9755_423o0308_-0.9755_13.431875.wav -------------------------------------------------------------------------------- /dataset/train/noise/447o0302_1.3388_22ho010i_-1.3388_12.69025.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/noise/447o0302_1.3388_22ho010i_-1.3388_12.69025.wav -------------------------------------------------------------------------------- /dataset/train/noise/447o0302_2.1067_422o030k_-2.1067_11.834.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/noise/447o0302_2.1067_422o030k_-2.1067_11.834.wav -------------------------------------------------------------------------------- /dataset/train/noise/447o030x_0.98832_441o0308_-0.98832_16.4556875.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/noise/447o030x_0.98832_441o0308_-0.98832_16.4556875.wav -------------------------------------------------------------------------------- /dataset/train/noise/447o030x_1.4783_422o030p_-1.4783_16.124125.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/noise/447o030x_1.4783_422o030p_-1.4783_16.124125.wav -------------------------------------------------------------------------------- /dataset/train/noise/447o030x_1.6276_440o0304_-1.6276_14.556125.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/noise/447o030x_1.6276_440o0304_-1.6276_14.556125.wav -------------------------------------------------------------------------------- /dataset/train/speech/652-130737-0001.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/speech/652-130737-0001.flac -------------------------------------------------------------------------------- /dataset/train/speech/652-130737-0002.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/speech/652-130737-0002.flac -------------------------------------------------------------------------------- /dataset/train/speech/652-130737-0003.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/speech/652-130737-0003.flac -------------------------------------------------------------------------------- /dataset/train/speech/652-130737-0004.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/speech/652-130737-0004.flac -------------------------------------------------------------------------------- /dataset/train/speech/652-130737-0005.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/speech/652-130737-0005.flac -------------------------------------------------------------------------------- /dataset/train/speech/652-130737-0006.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/speech/652-130737-0006.flac -------------------------------------------------------------------------------- /dataset/train/speech/777-126732-0002.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/speech/777-126732-0002.flac -------------------------------------------------------------------------------- /dataset/train/speech/777-126732-0003.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/speech/777-126732-0003.flac -------------------------------------------------------------------------------- /dataset/train/speech/777-126732-0004.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/speech/777-126732-0004.flac -------------------------------------------------------------------------------- /dataset/train/speech/777-126732-0005.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/train/speech/777-126732-0005.flac -------------------------------------------------------------------------------- /dataset/validate/noise/447o030q_2.4332_440o0309_-2.4332_12.56975.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/noise/447o030q_2.4332_440o0309_-2.4332_12.56975.wav -------------------------------------------------------------------------------- /dataset/validate/noise/447o030r_0.25387_442c020t_-0.25387_14.1650625.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/noise/447o030r_0.25387_442c020t_-0.25387_14.1650625.wav -------------------------------------------------------------------------------- /dataset/validate/noise/447o030r_1.6517_422o0312_-1.6517_14.6394375.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/noise/447o030r_1.6517_422o0312_-1.6517_14.6394375.wav -------------------------------------------------------------------------------- /dataset/validate/noise/447o030t_1.3876_442o0305_-1.3876_11.87325.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/noise/447o030t_1.3876_442o0305_-1.3876_11.87325.wav -------------------------------------------------------------------------------- /dataset/validate/noise/447o030u_1.9508_051c0109_-1.9508_16.297875.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/noise/447o030u_1.9508_051c0109_-1.9508_16.297875.wav -------------------------------------------------------------------------------- /dataset/validate/speech/174-84280-0001.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/174-84280-0001.flac -------------------------------------------------------------------------------- /dataset/validate/speech/174-84280-0002.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/174-84280-0002.flac -------------------------------------------------------------------------------- /dataset/validate/speech/174-84280-0003.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/174-84280-0003.flac -------------------------------------------------------------------------------- /dataset/validate/speech/174-84280-0004.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/174-84280-0004.flac -------------------------------------------------------------------------------- /dataset/validate/speech/174-84280-0005.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/174-84280-0005.flac -------------------------------------------------------------------------------- /dataset/validate/speech/84-121123-0001.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/84-121123-0001.flac -------------------------------------------------------------------------------- /dataset/validate/speech/84-121123-0002.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/84-121123-0002.flac -------------------------------------------------------------------------------- /dataset/validate/speech/84-121123-0003.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/84-121123-0003.flac -------------------------------------------------------------------------------- /dataset/validate/speech/84-121123-0004.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/84-121123-0004.flac -------------------------------------------------------------------------------- /dataset/validate/speech/84-121123-0005.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/84-121123-0005.flac -------------------------------------------------------------------------------- /dataset/validate/speech/84-121123-0006.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/dataset/validate/speech/84-121123-0006.flac -------------------------------------------------------------------------------- /generate_validate_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/generate_validate_data.py -------------------------------------------------------------------------------- /image/model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/image/model.png -------------------------------------------------------------------------------- /image/sample_mask.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/image/sample_mask.png -------------------------------------------------------------------------------- /image/sample_mask_multi.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/image/sample_mask_multi.png -------------------------------------------------------------------------------- /maskestimator/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/__init__.py -------------------------------------------------------------------------------- /maskestimator/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /maskestimator/__pycache__/adapt_model.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/__pycache__/adapt_model.cpython-36.pyc -------------------------------------------------------------------------------- /maskestimator/__pycache__/augment.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/__pycache__/augment.cpython-36.pyc -------------------------------------------------------------------------------- /maskestimator/__pycache__/feature.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/__pycache__/feature.cpython-36.pyc -------------------------------------------------------------------------------- /maskestimator/__pycache__/model.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/__pycache__/model.cpython-36.pyc -------------------------------------------------------------------------------- /maskestimator/__pycache__/shaper.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/__pycache__/shaper.cpython-36.pyc -------------------------------------------------------------------------------- /maskestimator/__pycache__/util.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/__pycache__/util.cpython-36.pyc -------------------------------------------------------------------------------- /maskestimator/adapt_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/adapt_model.py -------------------------------------------------------------------------------- /maskestimator/augment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/augment.py -------------------------------------------------------------------------------- /maskestimator/feature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/feature.py -------------------------------------------------------------------------------- /maskestimator/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/model.py -------------------------------------------------------------------------------- /maskestimator/shaper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/shaper.py -------------------------------------------------------------------------------- /maskestimator/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/maskestimator/util.py -------------------------------------------------------------------------------- /model/194sequence_false_e1.hdf5.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/model/194sequence_false_e1.hdf5.data-00000-of-00001 -------------------------------------------------------------------------------- /model/194sequence_false_e1.hdf5.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/model/194sequence_false_e1.hdf5.index -------------------------------------------------------------------------------- /model/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/model/checkpoint -------------------------------------------------------------------------------- /non_adapt_speaker_list.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/non_adapt_speaker_list.txt -------------------------------------------------------------------------------- /predict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/predict.py -------------------------------------------------------------------------------- /predict_single.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/predict_single.py -------------------------------------------------------------------------------- /result/enhacement.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/result/enhacement.wav -------------------------------------------------------------------------------- /result/enhacement_all_channels.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/result/enhacement_all_channels.wav -------------------------------------------------------------------------------- /result/enhacement_snr_select.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/result/enhacement_snr_select.wav -------------------------------------------------------------------------------- /result/speech_clean.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/result/speech_clean.wav -------------------------------------------------------------------------------- /result/speech_noisy.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/result/speech_noisy.wav -------------------------------------------------------------------------------- /sp1_list.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/sp1_list.txt -------------------------------------------------------------------------------- /sp2_list.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/sp2_list.txt -------------------------------------------------------------------------------- /speaker_aware_mask_predict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/speaker_aware_mask_predict.py -------------------------------------------------------------------------------- /tflog/tflog_loc.txt: -------------------------------------------------------------------------------- 1 | log -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AkojimaSLP/Neural-mask-estimation/HEAD/train.py -------------------------------------------------------------------------------- /validation_features/val_data.txt: -------------------------------------------------------------------------------- 1 | val_data --------------------------------------------------------------------------------