search

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
1.26k stars 181 forks source link

Train dataset #11

Closed charlesXu86 closed 3 years ago

charlesXu86 commented 3 years ago

How to get more train dataset?

adiyoss commented 3 years ago

You can get a pretty big dataset under the following link: https://github.com/JorisCos/LibriMix I highly recommend augment it with reverb using some room-impulse-response generator such as this one: https://github.com/LCAV/pyroomacoustics

charlesXu86 commented 3 years ago

You can get a pretty big dataset under the following link: https://github.com/JorisCos/LibriMix I highly recommend augment it with reverb using some room-impulse-response generator such as this one: https://github.com/LCAV/pyroomacoustics

thank you so much！

adiyoss commented 3 years ago

Closing this issue, if you have more questions, feel free to open another one or reopen this one!