Zero-AVSR

Reported on 1 benchmark across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech1 result

Audio-Visual Speech RecognitiononLRS3-TED
Word Error Rate (WER)· uses extra data· 2025-03-08
1.5
best: 0.74 (MMS-LLaMA)
Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations arXiv:2503.06273