Automatic Visual Speech Recognition on LRS2 noisy (test)
7WERMIR-GAN
Evaluation results
| Method | Links | |
|---|---|---|
| MIR-GANBackbone=Transformer, Criterion=S2S, Unlabeled data (hrs)=1759, Labeled data (hrs)=224, DataAug=true, LM=false, Learning Strategy=Proposed (Self-Supervised)2023.06 | 7 | |
| Base modelBackbone=Transformer, Criterion=S2S, Unlabeled data (hrs)=1759, Labeled data (hrs)=224, DataAug=true, LM=false, Learning Strategy=Proposed (Self-Supervised)2023.06 | 7.3 | |
| MIR-GANBackbone=Conformer, Criterion=S2S, Unlabeled data (hrs)=0, Labeled data (hrs)=224, DataAug=true, LM=false, Learning Strategy=Proposed (Supervised)2023.06 | 11.9 | |
| Base modelBackbone=Conformer, Criterion=S2S, Unlabeled data (hrs)=0, Labeled data (hrs)=224, DataAug=true, LM=false, Learning Strategy=Proposed (Supervised)2023.06 | 15.8 | |
| MIR-GANBackbone=Transformer, Criterion=S2S, Unlabeled data (hrs)=0, Labeled data (hrs)=224, DataAug=true, LM=false, Learning Strategy=Proposed (Supervised)2023.06 | 16.7 | |
| Base modelBackbone=Transformer, Criterion=S2S, Unlabeled data (hrs)=0, Labeled data (hrs)=224, DataAug=true, LM=false, Learning Strategy=Proposed (Supervised)2023.06 | 21.2 |