Audio-visual speech recognition on MuAViC Noise environment (test)
49.5Accuracy (En)XLAVS-R 2B
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| XLAVS-R 2BTest Mode=A2024.03 | 49.5 | 98.9 | 66.3 | 50.6 | 36 | 30 | 36.8 | 40.6 | 48.3 | 50.8 | |
| XLS-R 300MTest Mode=A2024.03 | 43.8 | 97.3 | 69.8 | 74.8 | 47.6 | 37.1 | 47.9 | 54.4 | 59.8 | 59.2 | |
| XLAVS-R 300MTest Mode=A2024.03 | 42.4 | 100.1 | 69.4 | 56.2 | 39.9 | 33.4 | 40.5 | 45.4 | 53 | 53.4 | |
| AV-HuBERTTest Mode=A2024.03 | 39.3 | 111.2 | 87 | 85.2 | 65.6 | 58.1 | 69.5 | 69.9 | 75.9 | 73.5 | |
| u-HuBERTTest Mode=A2024.03 | 31.8 | 109.4 | 84.7 | 83.1 | 62.7 | 56.6 | 67.8 | 68.2 | 74.4 | 71 | |
| u-HuBERTTest Mode=AV2024.03 | 6.6 | 102.3 | 73.2 | 69.7 | 43.7 | 43.2 | 48.5 | 47.6 | 67 | 55.8 | |
| AV-HuBERTTest Mode=AV2024.03 | 6.4 | 104.7 | 74.2 | 70.4 | 43.1 | 43 | 48.2 | 47.5 | 67.4 | 56.1 | |
| XLAVS-R 2BTest Mode=AV2024.03 | 5.9 | 93.5 | 58.5 | 38.6 | 23.9 | 23.5 | 24.6 | 26.1 | 41 | 37.3 | |
| XLAVS-R 300MTest Mode=AV2024.03 | 5.8 | 95.8 | 61.4 | 44.7 | 28 | 27.2 | 29.4 | 30.6 | 47.8 | 41.2 |