dsp6414 / utterancepit-speech-separation Goto Github PK

uPIT-for-speech-separation

Demo Pages: Results of pure speech separation model

• Support Multi-GPU Training
• Use the Dataloader Method That Comes With Pytorch
• Provide Pre-Training Models

• Pytorch==1.3.0
• tqdm==4.32.1
• librosa==0.7.1
• scipy==1.3.0
• numpy==1.16.4
• PyYAML==5.1.1

1. Generate dataset using create-speaker-mixtures.zip with WSJ0 or TIMI

2. Prepare scp file(The content of the scp file is "filename path")

    python create_scp.py

3. Prepare cmvn(Cepstral mean and variance normalization (CMVN) is a computationally efficient normalization technique for robust speech recognition.).

    #Calculated by the compute_cmvn.py script: 
    python compute_cmvn.py ./tt_mix.scp ./cmvn.dict

4. Modify the contents of yaml, mainly to modify the scp address, cmvn address. At the same time, the number of num_spk in run_pit.py is modified.

5. Training:

   sh train.sh

6. Inference:

   sh test.sh
   

• Kolbæk M, Yu D, Tan Z H, et al. Multitalker speech separation with utterance-level permutation invariant training of deep recurrent neural networks[J]. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), 2017, 25(10): 1901-1913.
• https://github.com/funcwj/uPIT-for-speech-separation