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.
There is no discussion button, so I clicked the new problem button.
What I want to know is the following.
README.md contains information about noise.
Is a noise file absolutely necessary?
I only have clean voice files.
Should I create noise?
How should I create a learning data folder?
I don't know this part well.
There is a debug folder in the dataset folder and there are 3 folders.
Each folder contains a wav voice file. Should I create something similar to this?
How many voice files should I put in?
If I trained with an adult voice, is it possible to separate a child's voice as well?
There is no discussion button, so I clicked the new problem button. What I want to know is the following. README.md contains information about noise. Is a noise file absolutely necessary? I only have clean voice files. Should I create noise? How should I create a learning data folder? I don't know this part well. There is a debug folder in the dataset folder and there are 3 folders. Each folder contains a wav voice file. Should I create something similar to this? How many voice files should I put in? If I trained with an adult voice, is it possible to separate a child's voice as well?