Hybrid CTC / Attention

Reported on 2 benchmarks across 2 tasks · 2 papers · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

LipreadingonLRS2
Word Error Rate (WER)· 2021-02-12
39.1
best: 14.6 (Auto-AVSR)
SOTA
End-to-end Audio-visual Speech Recognition with Conformers arXiv:2102.06657
LipreadingonLRS2
Word Error Rate (WER)· 2018-09-28
50
best: 14.6 (Auto-AVSR)
Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture arXiv:1810.00108

Natural Language Processing2 results

Natural Language TransductiononLRS2
Word Error Rate (WER)· 2021-02-12
39.1
best: 14.6 (Auto-AVSR)
SOTA
End-to-end Audio-visual Speech Recognition with Conformers arXiv:2102.06657
Natural Language TransductiononLRS2
Word Error Rate (WER)· 2018-09-28
50
best: 14.6 (Auto-AVSR)
Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture arXiv:1810.00108