Automatic Speech Recognition on LRS3 30h labeled low-resource (test)
1.5WERLLama-AVSR
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LLama-AVSRUnlab.=1759h, Lab.=30h, Shared=false2025.10 | 1.5 | — | |
| UASR-LLM-BUnlab.=433h, Lab.=30h, Shared=true2025.10 | 2.2 | 39.2 | |
| UASR-LLM-LUnlab.=433h, Lab.=30h, Shared=true2025.10 | 2.2 | 38.7 | |
| DistillAV-LUnlab.=1759h, Lab.=30h, Shared=false2025.10 | 2.2 | 41.4 | |
| BRAVEn-LUnlab.=1759h, Lab.=30h, Shared=false2025.10 | 2.3 | — | |
| UASR-LLM-BUnlab.=1759h, Lab.=30h, Shared=true2025.10 | 2.3 | 38.3 | |
| DistillAV-LUnlab.=433h, Lab.=30h, Shared=false2025.10 | 2.4 | 45.3 | |
| USR-LUnlab.=1759h, Lab.=30h, Shared=true2025.10 | 2.4 | — | |
| UASR-LLM-B*Unlab.=1759h, Lab.=30h, Shared=true2025.10 | 2.4 | 39.8 | |
| DistillAV-BUnlab.=1759h, Lab.=30h, Shared=false2025.10 | 2.5 | 44.6 | |
| UASR-LLM-LUnlab.=1759h, Lab.=30h, Shared=true2025.10 | 2.5 | 39.2 | |
| USR-BUnlab.=1759h, Lab.=30h, Shared=true2025.10 | 2.6 | — | |
| AV-data2vec-LUnlab.=1759h, Lab.=30h, Shared=false2025.10 | 2.7 | — | |
| AV-HuBERT-LUnlab.=1759h, Lab.=30h, Shared=false2025.10 | 2.9 | — | |
| DistillAV-BUnlab.=433h, Lab.=30h, Shared=false2025.10 | 3 | 50.5 | |
| BRAVEn-BUnlab.=1759h, Lab.=30h, Shared=false2025.10 | 3 | — | |
| USRUnlab.=433h, Lab.=30h, Shared=true2025.10 | 3.2 | — | |
| VATLM-BUnlab.=433h, Lab.=30h, Shared=false2025.10 | 3.6 | — | |
| AV-data2vec-BUnlab.=1759h, Lab.=30h, Shared=false2025.10 | 3.7 | — | |
| BRAVEn-BUnlab.=433h, Lab.=30h, Shared=false2025.10 | 4 | — | |
| AV-data2vec-BUnlab.=433h, Lab.=30h, Shared=false2025.10 | 4.4 | — | |
| AV-HuBERT-LUnlab.=433h, Lab.=30h, Shared=false2025.10 | 4.5 | — | |
| AV-HuBERT-BUnlab.=1759h, Lab.=30h, Shared=false2025.10 | 4.6 | — | |
| RAVEn-BUnlab.=433h, Lab.=30h, Shared=false2025.10 | 4.7 | — | |
| AV-HuBERT-BUnlab.=433h, Lab.=30h, Shared=false2025.10 | 4.9 | — | |
| AV2vec-MLMUnlab.=433h, Lab.=30h, Shared=false2025.10 | 5.6 | — |