List your company
ResearchFormerly WizWand

Audio-Visual Speech Recognition on LRS3 Noisy w.r.t Missing Modality 0.1 Masking Ratio (test)

4.07Word Error Rate (%)Auto-AVSR
3.7026.1868.6711.154Jun 4, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Auto-AVSRModality=A+V, Labeled Training Data (hrs)=3,4482026.064.07
MMS-LlamaModality=A+V, Labeled Training Data (hrs)=1,7592026.064.53
M2S-AVSRModality=A+V, Labeled Training Data (hrs)=ms1,759, Multi-view Synthesis=true2026.064.6
M2S-AVSRModality=A+V, Labeled Training Data (hrs)=1,7592026.064.64
Llama-AVSRModality=A+V, Labeled Training Data (hrs)=1,7592026.064.73
MMS-LlamaModality=A+V, Labeled Training Data (hrs)=4332026.064.79
M2S-AVSRModality=A+V, Labeled Training Data (hrs)=ms433, Multi-view Synthesis=true2026.065.3
M2S-AVSRModality=A+V, Labeled Training Data (hrs)=4332026.065.38
Whisper-FlamingoModality=A+V, Labeled Training Data (hrs)=ms1,759, Multi-view Synthesis=true2026.066.16
Whisper-FlamingoModality=A+V, Labeled Training Data (hrs)=1,7592026.066.17
CMAModality=A+V, Labeled Training Data (hrs)=4332026.066.33
Whisper-FlamingoModality=A+V, Labeled Training Data (hrs)=ms433, Multi-view Synthesis=true2026.066.37
Whisper-FlamingoModality=A+V, Labeled Training Data (hrs)=4332026.066.72
AV-HuBERTModality=A+V, Labeled Training Data (hrs)=4332026.067.29
AV-RelScoreModality=A+V, Labeled Training Data (hrs)=4332026.068.81
V-CAFEModality=A+V, Labeled Training Data (hrs)=4332026.0613.27