MAVL is a five-language lyrics benchmark pairing animated-song lyrics with audio and video, and the SylAVL-CoT prompt method improves syllable-count fit and user-rated singability over text-only translation baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translation
MAVL is a five-language lyrics benchmark pairing animated-song lyrics with audio and video, and the SylAVL-CoT prompt method improves syllable-count fit and user-rated singability over text-only translation baselines.