MUTUD trains audiovisual speech models with both modalities but lets them run with audio only, recovering much of the multimodal benefit at a fraction of the compute.
Discriminative multi-modality speech recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment
MUTUD trains audiovisual speech models with both modalities but lets them run with audio only, recovering much of the multimodal benefit at a fraction of the compute.