VQTalker learns a discrete facial-motion codebook via GRFSQ and generates talking heads from speech tokens, reporting improved lip sync on non-Indo-European languages at lower bitrate.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VQTalker: Towards Multilingual Talking Avatars through Facial Motion Tokenization
VQTalker learns a discrete facial-motion codebook via GRFSQ and generates talking heads from speech tokens, reporting improved lip sync on non-Indo-European languages at lower bitrate.