Automatic Speech Recognition on L2-ARCTIC Unseen-accent (UA)
7.41WERW2V2-Large + SupCon
Evaluation Results
| Method | Links | |
|---|---|---|
| W2V2-Large + SupConBackbone=wav2vec 2.0 Large, Regularization=Supervised Contrastive (SupCon)2026.05 | 7.41 | |
| W2V2-Large (CTC)Backbone=wav2vec 2.0 Large, Objective=CTC2026.05 | 9.98 | |
| MAS-LoRA-QKVOModel Type=MAS-LoRA-QKVO2026.05 | 12.55 | |
| Whisper FTModel Type=Whisper Fine-tuned2026.05 | 17.12 |