Showing eess.ASShow all
2 papers · 1 filter
eess.AS2026
AVSRBench: A Multi-Condition AVSR Benchmark
Rishabh Jain, Naomi Harte
While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true generalization or just domain a…
eess.AS2026
Assessing True Generalisability of Audio-Visual Speech Recognisers
Zhaofeng Lin, Stavros Petridis, Maja Pantic +1
Current Audio-Visual Speech Recognition (AVSR) models achieve near-perfect performance on the standard LRS3 benchmark, raising concerns of adaptive overfitting. To systematically a…