CorxLabs/TriStream-SVS-300M
Updated • 20 • 3
SVS Models
Singing-voice synthesis: TriStream separates glottal source, vocal-tract filter and breath noise.
Note 300M singing-voice synthesis model, three-stream source-filter design.
Singing-voice synthesis: TriStream separates glottal source, vocal-tract filter and breath noise.
Note 300M singing-voice synthesis model, three-stream source-filter design.