A preference optimization objective with input-side and output-side preference pairs improves audiovisual ASR word error rates on How2, VisSpeech, and Ego4D beyond prior state-of-the-art.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization
A preference optimization objective with input-side and output-side preference pairs improves audiovisual ASR word error rates on How2, VisSpeech, and Ego4D beyond prior state-of-the-art.