Login / Signup
SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention.
Junjie Li
Yiwei Guo
Xie Chen
Kai Yu
Published in:
ICASSP (2024)
Keyphrases
</>
speech recognition
vector space
synthesized speech
neural network
audio visual
prosodic features
real time
language model
visual attention
nonlinear dimensionality reduction
text to speech