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

How to use MUSDB to get the experimental results of the 3.4 Music Source Separation section in paper ? #27

Closed shuxinli6176 closed 3 years ago

adiyoss commented 3 years ago

Hi @shuxinli6176, We did not uploaded the music source separation recipe since it is not the main focus of the paper. But you implement if easily. You should change the separation model in: https://github.com/facebookresearch/demucs to svoice (the one we are using). Next, you should modify the number of outputs to match the number of sources you would like to separate, in the case of MUSDB it would be four, iirc.

shuxinli6176 commented 3 years ago

Thank you for the response, I'll follow your advice.

------------------ 原始邮件 ------------------ 发件人: "facebookresearch/svoice" @.>; 发送时间: 2021年5月4日(星期二) 晚上8:07 @.>; @.**@.>; 主题: Re: [facebookresearch/svoice] How to use MUSDB to get the experimental results of the 3.4 Music Source Separation section in paper ? (#27)

Hi @shuxinli6176, We did not uploaded the music source separation recipe since it is not the main focus of the paper. But you implement if easily. You should change the separation model in: https://github.com/facebookresearch/demucs to svoice (the one we are using). Next, you should modify the number of outputs to match the number of sources you would like to separate, in the case of MUSDB it would be four, iirc.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

adiyoss commented 3 years ago

Closing the issue for now. Feel free to reopen it once you have interesting findings :)