Picture for Bolong Wen

Bolong Wen

IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion

Add code
Jan 02, 2022
Figure 1 for IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion
Figure 2 for IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion
Figure 3 for IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion
Figure 4 for IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion
Viaarxiv icon