Controllable and Interpretable Singing Voice Decomposition via Assem-VC

10/25/2021
by   Kang-wook Kim, et al.
0

We propose a singing decomposition system that encodes time-aligned linguistic content, pitch, and source speaker identity via Assem-VC. With decomposed speaker-independent information and the target speaker's embedding, we could synthesize the singing voice of the target speaker. In conclusion, we made a perfectly synced duet with the user's singing voice and the target singer's converted singing voice.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset