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.
Dataset We leverage LRS3 [28] which is a large-scale video data consisting of thousands of spoken sentences collected from TED talks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
CONDITIONAL 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.