├── 1. create-speaker-mixtures-V1 ├── create_wav_2speakers.m ├── create_wav_3speakers.m ├── mix_2_spk_cv.txt ├── mix_2_spk_tr.txt ├── mix_2_spk_tt.txt ├── mix_3_spk_cv.txt ├── mix_3_spk_tr.txt ├── mix_3_spk_tt.txt └── readme.txt ├── 2. create-speaker-mixtures-V2 ├── activlev.m ├── create_wav_2speakers.m ├── create_wav_3speakers.m ├── maxfilt.m ├── mix_2_spk_cv.txt ├── mix_2_spk_tr.txt ├── mix_2_spk_tt.txt ├── mix_3_spk_cv.txt ├── mix_3_spk_tr.txt ├── mix_3_spk_tt.txt └── readme.txt ├── 3. SPHFile2Wav ├── README.md ├── SA1.WAV ├── SPH2Wav.py └── converted.wav ├── 4. introduction_to_mask ├── .DS_Store ├── .ipynb_checkpoints │ └── Introduction to Ideal Binary Mask-checkpoint.ipynb ├── Introduction to Ideal Binary Mask.ipynb ├── MPM14-Time-Frequency-Masking.pdf ├── SA1.wav ├── SA2.wav ├── TIMIT │ ├── SA1.WAV │ └── SA2.WAV ├── masks.png ├── mixed.wav ├── mixturesignals.png ├── recoverd1.png ├── recoverd2.png └── spectrograms.png ├── 5. step_to_CASA_DL ├── ProjectReport-Speech Separation in Supervised Setting.pdf ├── evaluation_metric.py ├── speech_preprocess.py └── train_test_model.py ├── 6. separated_result_LSTM ├── one_man_one_woman_1.wav ├── one_man_one_woman_2.wav ├── two_men_1.wav ├── two_men_2.wav ├── two_women_1.wav └── two_women_2.wav ├── 7. separated_result_BLSTM ├── one_man_one_woman_1.wav ├── one_man_one_woman_2.wav ├── two_men_1.wav ├── two_men_2.wav ├── two_women_1.wav └── two_women_2.wav ├── README.md ├── blstm.py ├── data_create_Nspeakers_mix.py ├── evaluate_2speaker_ori.m ├── evaluate_2speaker_separated.m ├── gen_tfrecords.py ├── make_wav_list.py ├── run.sh ├── run_lstm.py ├── signal_processing.py ├── spectrogram.PNG ├── tfrecords_io.py ├── utils.py └── wsj0-train-spkrinfo.txt /1. create-speaker-mixtures-V1/create_wav_2speakers.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/1. create-speaker-mixtures-V1/create_wav_2speakers.m -------------------------------------------------------------------------------- /1. create-speaker-mixtures-V1/create_wav_3speakers.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/1. create-speaker-mixtures-V1/create_wav_3speakers.m -------------------------------------------------------------------------------- /1. create-speaker-mixtures-V1/mix_2_spk_cv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/1. create-speaker-mixtures-V1/mix_2_spk_cv.txt -------------------------------------------------------------------------------- /1. create-speaker-mixtures-V1/mix_2_spk_tr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/1. create-speaker-mixtures-V1/mix_2_spk_tr.txt -------------------------------------------------------------------------------- /1. create-speaker-mixtures-V1/mix_2_spk_tt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/1. create-speaker-mixtures-V1/mix_2_spk_tt.txt -------------------------------------------------------------------------------- /1. create-speaker-mixtures-V1/mix_3_spk_cv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/1. create-speaker-mixtures-V1/mix_3_spk_cv.txt -------------------------------------------------------------------------------- /1. create-speaker-mixtures-V1/mix_3_spk_tr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/1. create-speaker-mixtures-V1/mix_3_spk_tr.txt -------------------------------------------------------------------------------- /1. create-speaker-mixtures-V1/mix_3_spk_tt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/1. create-speaker-mixtures-V1/mix_3_spk_tt.txt -------------------------------------------------------------------------------- /1. create-speaker-mixtures-V1/readme.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/1. create-speaker-mixtures-V1/readme.txt -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/activlev.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/activlev.m -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/create_wav_2speakers.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/create_wav_2speakers.m -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/create_wav_3speakers.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/create_wav_3speakers.m -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/maxfilt.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/maxfilt.m -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/mix_2_spk_cv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/mix_2_spk_cv.txt -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/mix_2_spk_tr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/mix_2_spk_tr.txt -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/mix_2_spk_tt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/mix_2_spk_tt.txt -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/mix_3_spk_cv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/mix_3_spk_cv.txt -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/mix_3_spk_tr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/mix_3_spk_tr.txt -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/mix_3_spk_tt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/mix_3_spk_tt.txt -------------------------------------------------------------------------------- /2. create-speaker-mixtures-V2/readme.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/2. create-speaker-mixtures-V2/readme.txt -------------------------------------------------------------------------------- /3. SPHFile2Wav/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/3. SPHFile2Wav/README.md -------------------------------------------------------------------------------- /3. SPHFile2Wav/SA1.WAV: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/3. SPHFile2Wav/SA1.WAV -------------------------------------------------------------------------------- /3. SPHFile2Wav/SPH2Wav.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/3. SPHFile2Wav/SPH2Wav.py -------------------------------------------------------------------------------- /3. SPHFile2Wav/converted.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/3. SPHFile2Wav/converted.wav -------------------------------------------------------------------------------- /4. introduction_to_mask/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/.DS_Store -------------------------------------------------------------------------------- /4. introduction_to_mask/.ipynb_checkpoints/Introduction to Ideal Binary Mask-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/.ipynb_checkpoints/Introduction to Ideal Binary Mask-checkpoint.ipynb -------------------------------------------------------------------------------- /4. introduction_to_mask/Introduction to Ideal Binary Mask.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/Introduction to Ideal Binary Mask.ipynb -------------------------------------------------------------------------------- /4. introduction_to_mask/MPM14-Time-Frequency-Masking.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/MPM14-Time-Frequency-Masking.pdf -------------------------------------------------------------------------------- /4. introduction_to_mask/SA1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/SA1.wav -------------------------------------------------------------------------------- /4. introduction_to_mask/SA2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/SA2.wav -------------------------------------------------------------------------------- /4. introduction_to_mask/TIMIT/SA1.WAV: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/TIMIT/SA1.WAV -------------------------------------------------------------------------------- /4. introduction_to_mask/TIMIT/SA2.WAV: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/TIMIT/SA2.WAV -------------------------------------------------------------------------------- /4. introduction_to_mask/masks.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/masks.png -------------------------------------------------------------------------------- /4. introduction_to_mask/mixed.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/mixed.wav -------------------------------------------------------------------------------- /4. introduction_to_mask/mixturesignals.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/mixturesignals.png -------------------------------------------------------------------------------- /4. introduction_to_mask/recoverd1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/recoverd1.png -------------------------------------------------------------------------------- /4. introduction_to_mask/recoverd2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/recoverd2.png -------------------------------------------------------------------------------- /4. introduction_to_mask/spectrograms.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/4. introduction_to_mask/spectrograms.png -------------------------------------------------------------------------------- /5. step_to_CASA_DL/ProjectReport-Speech Separation in Supervised Setting.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/5. step_to_CASA_DL/ProjectReport-Speech Separation in Supervised Setting.pdf -------------------------------------------------------------------------------- /5. step_to_CASA_DL/evaluation_metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/5. step_to_CASA_DL/evaluation_metric.py -------------------------------------------------------------------------------- /5. step_to_CASA_DL/speech_preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/5. step_to_CASA_DL/speech_preprocess.py -------------------------------------------------------------------------------- /5. step_to_CASA_DL/train_test_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/5. step_to_CASA_DL/train_test_model.py -------------------------------------------------------------------------------- /6. separated_result_LSTM/one_man_one_woman_1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/6. separated_result_LSTM/one_man_one_woman_1.wav -------------------------------------------------------------------------------- /6. separated_result_LSTM/one_man_one_woman_2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/6. separated_result_LSTM/one_man_one_woman_2.wav -------------------------------------------------------------------------------- /6. separated_result_LSTM/two_men_1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/6. separated_result_LSTM/two_men_1.wav -------------------------------------------------------------------------------- /6. separated_result_LSTM/two_men_2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/6. separated_result_LSTM/two_men_2.wav -------------------------------------------------------------------------------- /6. separated_result_LSTM/two_women_1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/6. separated_result_LSTM/two_women_1.wav -------------------------------------------------------------------------------- /6. separated_result_LSTM/two_women_2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/6. separated_result_LSTM/two_women_2.wav -------------------------------------------------------------------------------- /7. separated_result_BLSTM/one_man_one_woman_1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/7. separated_result_BLSTM/one_man_one_woman_1.wav -------------------------------------------------------------------------------- /7. separated_result_BLSTM/one_man_one_woman_2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/7. separated_result_BLSTM/one_man_one_woman_2.wav -------------------------------------------------------------------------------- /7. separated_result_BLSTM/two_men_1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/7. separated_result_BLSTM/two_men_1.wav -------------------------------------------------------------------------------- /7. separated_result_BLSTM/two_men_2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/7. separated_result_BLSTM/two_men_2.wav -------------------------------------------------------------------------------- /7. separated_result_BLSTM/two_women_1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/7. separated_result_BLSTM/two_women_1.wav -------------------------------------------------------------------------------- /7. separated_result_BLSTM/two_women_2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/7. separated_result_BLSTM/two_women_2.wav -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/README.md -------------------------------------------------------------------------------- /blstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/blstm.py -------------------------------------------------------------------------------- /data_create_Nspeakers_mix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/data_create_Nspeakers_mix.py -------------------------------------------------------------------------------- /evaluate_2speaker_ori.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/evaluate_2speaker_ori.m -------------------------------------------------------------------------------- /evaluate_2speaker_separated.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/evaluate_2speaker_separated.m -------------------------------------------------------------------------------- /gen_tfrecords.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/gen_tfrecords.py -------------------------------------------------------------------------------- /make_wav_list.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/make_wav_list.py -------------------------------------------------------------------------------- /run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/run.sh -------------------------------------------------------------------------------- /run_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/run_lstm.py -------------------------------------------------------------------------------- /signal_processing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/signal_processing.py -------------------------------------------------------------------------------- /spectrogram.PNG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/spectrogram.PNG -------------------------------------------------------------------------------- /tfrecords_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/tfrecords_io.py -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/utils.py -------------------------------------------------------------------------------- /wsj0-train-spkrinfo.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aishoot/LSTM_PIT_Speech_Separation/HEAD/wsj0-train-spkrinfo.txt --------------------------------------------------------------------------------