An LLM-based error corrector that re-reads both audio and lip video improves AVSR WER on clean LRS3 by 24%, but underperforms a prior method at low signal-to-noise ratios.
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
REJECT 1representative citing papers
citing papers explorer
-
Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition
An LLM-based error corrector that re-reads both audio and lip video improves AVSR WER on clean LRS3 by 24%, but underperforms a prior method at low signal-to-noise ratios.