activity
20202022
most citedIQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion

7 citations · 8 across the 6 of their papers we have counts for

collaborators
Showing 2020Show all

1 paper · 1 filter

cs.SD2020

Optimizing voice conversion network with cycle consistency loss of speaker identity

Hongqiang Du, Xiaohai Tian, Lei Xie +1

We propose a novel training scheme to optimize voice conversion network with a speaker identity loss function. The training scheme not only minimizes frame-level spectral loss, but…