Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Audio-Visual Speech Recognition on LRS3 Noisy w.r.t Missing Modality 0.3 Masking Ratio (test)
Loading...
5.77
WER (%)
M2S-AVSR
5.406
7.863
10.32
12.777
Jun 4, 2026
WER (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
WER (%)
M2S-AVSR
Modality=A+V, Labeled...
2026.06
5.77
M2S-AVSR
Modality=A+V, Labeled...
2026.06
5.84
MMS-Llama
Modality=A+V, Labeled...
2026.06
5.9
M2S-AVSR
Modality=A+V, Labeled...
2026.06
6.01
Auto-AVSR
Modality=A+V, Labeled...
2026.06
6.11
MMS-Llama
Modality=A+V, Labeled...
2026.06
6.17
Llama-AVSR
Modality=A+V, Labeled...
2026.06
6.75
M2S-AVSR
Modality=A+V, Labeled...
2026.06
7.23
Whisper-Flamingo
Modality=A+V, Labeled...
2026.06
8.22
Whisper-Flamingo
Modality=A+V, Labeled...
2026.06
8.42
Whisper-Flamingo
Modality=A+V, Labeled...
2026.06
8.52
Whisper-Flamingo
Modality=A+V, Labeled...
2026.06
8.55
CMA
Modality=A+V, Labeled...
2026.06
9.35
AV-RelScore
Modality=A+V, Labeled...
2026.06
11.13
AV-HuBERT
Modality=A+V, Labeled...
2026.06
11.14
V-CAFE
Modality=A+V, Labeled...
2026.06
14.87
Feedback
Search any
task
Search any
task