文件名称：LSTM_PIT_Speech_Separation:置换不变训练法与LSTMBLSTM的两口语语音分离
文件大小：5.56MB
文件格式：ZIP
更新时间：2024-05-25 23:06:53
multi-speaker audio-separation speech-separation speech-enhancement permutation-invariant-training
基于LSTM / BLSTM的两个扬声器的PIT ==================================================================================== Two-speaker speech separation with BLSTM and PIT Author: aishoot, EECS, Peking University Github: https://github.com/aishoot/LSTM_PIT_Speech_Separation Created in: June 2018 ========================================
【文件预览】：
LSTM_PIT_Speech_Separation-master
----run_lstm.py(16KB)
----tfrecords_io.py(5KB)
----signal_processing.py(8KB)
----gen_tfrecords.py(4KB)
----make_wav_list.py(1015B)
----wsj0-train-spkrinfo.txt(864B)
----evaluate_2speaker_ori.m(4KB)
----6. separated_result_LSTM()
--------two_women_2.wav(84KB)
--------two_women_1.wav(84KB)
--------two_men_2.wav(97KB)
--------one_man_one_woman_2.wav(87KB)
--------one_man_one_woman_1.wav(87KB)
--------two_men_1.wav(97KB)
----spectrogram.PNG(822KB)
----4. introduction_to_mask()
--------masks.png(21KB)
--------.ipynb_checkpoints()
--------SA2.wav(95KB)
--------SA1.wav(105KB)
--------recoverd2.png(20KB)
--------Introduction to Ideal Binary Mask.ipynb(186KB)
--------.DS_Store(10KB)
--------recoverd1.png(19KB)
--------mixed.wav(125KB)
--------MPM14-Time-Frequency-Masking.pdf(1.08MB)
--------mixturesignals.png(25KB)
--------spectrograms.png(52KB)
--------TIMIT()
----utils.py(4KB)
----README.md(8KB)
----blstm.py(9KB)
----run.sh(5KB)
----2. create-speaker-mixtures-V2()
--------mix_2_spk_tt.txt(230KB)
--------mix_3_spk_cv.txt(531KB)
--------mix_2_spk_cv.txt(374KB)
--------mix_3_spk_tt.txt(327KB)
--------create_wav_2speakers.m(9KB)
--------activlev.m(16KB)
--------maxfilt.m(5KB)
--------create_wav_3speakers.m(9KB)
--------mix_2_spk_tr.txt(1.46MB)
--------readme.txt(781B)
--------mix_3_spk_tr.txt(2.07MB)
----3. SPHFile2Wav()
--------SA1.WAV(110KB)
--------SPH2Wav.py(435B)
--------README.md(362B)
--------converted.wav(109KB)
----evaluate_2speaker_separated.m(3KB)
----7. separated_result_BLSTM()
--------two_women_2.wav(84KB)
--------two_women_1.wav(84KB)
--------two_men_2.wav(97KB)
--------one_man_one_woman_2.wav(87KB)
--------one_man_one_woman_1.wav(87KB)
--------two_men_1.wav(97KB)
----data_create_Nspeakers_mix.py(4KB)
----5. step_to_CASA_DL()
--------train_test_model.py(8KB)
--------evaluation_metric.py(2KB)
--------ProjectReport-Speech Separation in Supervised Setting.pdf(158KB)
--------speech_preprocess.py(13KB)
----1. create-speaker-mixtures-V1()
--------mix_2_spk_tt.txt(230KB)
--------mix_3_spk_cv.txt(531KB)
--------mix_2_spk_cv.txt(374KB)
--------mix_3_spk_tt.txt(327KB)
--------create_wav_2speakers.m(8KB)
--------create_wav_3speakers.m(9KB)
--------mix_2_spk_tr.txt(1.46MB)
--------readme.txt(672B)
--------mix_3_spk_tr.txt(2.07MB)