Model fails to separate sources

zhr1201 / deep-clustering

A tensorflow implementation for Deep clustering: Discriminative embeddings for segmentation and separation

135 stars 70 forks source link

Model fails to separate sources #25

Closed wzhang017 closed 4 years ago

wzhang017 commented 4 years ago

I used your code to train the model with 358000 iterations on TIMIT dataset. But the model fails to separate sources in "audio_test". The two speakers' voices are still mixed in each output file. I have tried to change the FRAMES_PER_SAMPLE to bigger but it dose not work either. Any suggestions is appreciated. And if possible could you share your pretrained weights file for me to have a try? My email is wzhang017@gmail.com Thanks a lot

wzhang017 commented 4 years ago

Hi, the issue is resolved, thanks.