A lightweight VAE adapter bridges a frozen text-to-speech model and a frozen talking-head model to generate face-consistent speech and animation from a single image and text.
Early works, such as Chen et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Face2VoiceSync: Lightweight Face-Voice Consistency for Text-Driven Talking Face Generation
A lightweight VAE adapter bridges a frozen text-to-speech model and a frozen talking-head model to generate face-consistent speech and animation from a single image and text.