List your company
ResearchFormerly WizWand

Audio-Visual Speech Recognition on LRS3 Noisy w.r.t Viewpoint 15° Offset (test)

4.05WERM2S-AVSR
3.58846.70429.8212.9358Jun 4, 2026
Updated 5mo ago

Evaluation results

MethodLinks
M2S-AVSRModality=A+V, Labeled Training Data (hrs)=ms1,759, Multi-view Synthesis=true2026.064.05
M2S-AVSRModality=A+V, Labeled Training Data (hrs)=ms433, Multi-view Synthesis=true2026.065.78
M2S-AVSRModality=A+V, Labeled Training Data (hrs)=1,7592026.065.95
MMS-LlamaModality=A+V, Labeled Training Data (hrs)=1,7592026.066.19
M2S-AVSRModality=A+V, Labeled Training Data (hrs)=4332026.066.78
Auto-AVSRModality=A+V, Labeled Training Data (hrs)=3,4482026.066.86
MMS-LlamaModality=A+V, Labeled Training Data (hrs)=4332026.066.93
Whisper-FlamingoModality=A+V, Labeled Training Data (hrs)=ms1,759, Multi-view Synthesis=true2026.067.25
Whisper-FlamingoModality=A+V, Labeled Training Data (hrs)=1,7592026.067.26
Whisper-FlamingoModality=A+V, Labeled Training Data (hrs)=ms433, Multi-view Synthesis=true2026.067.3
Whisper-FlamingoModality=A+V, Labeled Training Data (hrs)=4332026.067.39
Llama-AVSRModality=A+V, Labeled Training Data (hrs)=1,7592026.069.48
CMAModality=A+V, Labeled Training Data (hrs)=4332026.0611.93
AV-RelScoreModality=A+V, Labeled Training Data (hrs)=4332026.0612.45
AV-HuBERTModality=A+V, Labeled Training Data (hrs)=4332026.0614.08
V-CAFEModality=A+V, Labeled Training Data (hrs)=4332026.0615.59