SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention.

Junjie Li Yiwei Guo Xie Chen Kai Yu

Published in: CoRR (2023)

Keyphrases

speech recognition
speaker verification
vector space
synthesized speech
visual attention
nonlinear dimensionality reduction
speaker recognition
prosodic features
face recognition
object recognition
upper bound
multi modal
vc dimension