Adding a SyncNet-based lip-synchrony loss plus a duration loss to a pre-trained audio-visual speech-to-speech model improves lip-sync of overlaid translated audio on original videos across four language pairs.
Baselines We use the latest work of A V2A V [6] as a strong baseline for this work
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.SD 1years
2024 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Improving Lip-synchrony in Direct Audio-Visual Speech-to-Speech Translation
Adding a SyncNet-based lip-synchrony loss plus a duration loss to a pre-trained audio-visual speech-to-speech model improves lip-sync of overlaid translated audio on original videos across four language pairs.