Visual Speech Recognition On Lrs3 Ted
評価指標
Word Error Rate (WER)
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Word Error Rate (WER) | Paper Title | Repository |
|---|---|---|---|
| CTC/Attention | 19.1 | Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels | |
| VTP | 40.6 | Sub-word Level Lip Reading With Visual Attention | - |
| VTP with more data | 30.7 | Sub-word Level Lip Reading With Visual Attention | - |
0 of 3 row(s) selected.