Audio Visual Speech Recognition On Lrs2
Metrics
Test WER
Results
Performance results of various models on this benchmark
Model Name | Test WER | Paper Title | Repository |
|---|---|---|---|
| End2end Conformer | 3.7 | End-to-end Audio-visual Speech Recognition with Conformers | - |
| TM-CTC | 8.2 | Deep Audio-Visual Speech Recognition | - |
| CTC/Attention | 1.5 | Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels | - |
| TM-Seq2seq | 8.5 | Deep Audio-Visual Speech Recognition | - |
| LF-MMI TDNN | 5.9 | Audio-visual Recognition of Overlapped speech for the LRS2 dataset | - |
| Whisper-Flamingo | 1.4 | Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation | - |
| MoCo + wav2vec (w/o extLM) | 2.6 | Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition | - |
| CTC/Attention | 7.0 | Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture | - |
0 of 8 row(s) selected.