facebookresearch / svoice

We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
Other
1.25k stars 179 forks source link

Weight of Speaker ID loss #70

Open hsiaohan0827 opened 2 years ago

hsiaohan0827 commented 2 years ago

Hi, I've noticed that you introduce a speaker ID loss in the paper. I'm currently implementing the loss in my separation model. It would be helpful if you can share the weight parameter of the loss during training. Thanks.