A dubbing system that combines an LLM, phoneme-level contrastive lip alignment, and flow matching with classifier-free guidance outperforms prior dubbing models on lip-sync and quality metrics.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing
A dubbing system that combines an LLM, phoneme-level contrastive lip alignment, and flow matching with classifier-free guidance outperforms prior dubbing models on lip-sync and quality metrics.