Wav2Sem improves 3D lip-sync from speech by aligning audio features with BERT sentence embeddings and fusing them into existing animation pipelines.
Talking head generation with audio and speech related facial action units
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation
Wav2Sem improves 3D lip-sync from speech by aligning audio features with BERT sentence embeddings and fusing them into existing animation pipelines.