A transformer model learns to transform poorly mixed audio into well-balanced audio guided by video content, trained on a new pseudo-data set derived from movies.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning to Highlight Audio by Watching Movies
A transformer model learns to transform poorly mixed audio into well-balanced audio guided by video content, trained on a new pseudo-data set derived from movies.