REAL-TIME TARGET SOUND EXTRACTION #7
Description
https://waveformer.cs.washington.edu/
https://github.com/vb000/Waveformer
Could this be trained and focussed on user voice profiles for target speaker extraction?
{{ message }}
https://waveformer.cs.washington.edu/
https://github.com/vb000/Waveformer
Could this be trained and focussed on user voice profiles for target speaker extraction?