CTC/Attention (LRW+LRS2/3+AVSpeech)
Reported on 4 benchmarks across 2 tasks · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Computer Vision2 results
- Word Error Rate (WER)· uses extra data· 2022-02-2625.5best: 14.6 (Auto-AVSR)
- Word Error Rate (WER)· uses extra data· 2022-02-2631.5best: 12.8 (LP + Conformer)
Natural Language Processing2 results
- Word Error Rate (WER)· uses extra data· 2022-02-2625.5best: 14.6 (Auto-AVSR)
- Word Error Rate (WER)· uses extra data· 2022-02-2631.5best: 12.8 (LP + Conformer)