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

Why is the snr range of mixed audio selected from 0-15? #48

Closed srdfjy closed 3 years ago

srdfjy commented 3 years ago

Hi，When the wsj0 data set mixes audio, the snr range selected is 0-5dB. In "scripts/make_dataset.py", the snr range of mixed audio is 0-15dB. What does this choice have to do with?

adiyoss commented 3 years ago

Hi @srdfjy, The make_dataset.py script is used to generate the noisy-reverberant dataset from this paper: https://arxiv.org/pdf/2011.02329.pdf

srdfjy commented 3 years ago

Using svoice, if I generate a noise-free data set by myself, without using the "make_dataset.py" script, should I also use the snr range of 0-15dB when mixing audio?

adiyoss commented 3 years ago

Hi @srdfjy, You can mix between the speakers in the range of 0-15dB. But it is up to you, the model does not have any assumption on the dataset generation process.

srdfjy commented 3 years ago

thanks @adiyoss