LF-MMI TDNN

Reported on 5 benchmarks across 5 tasks · 1 paper · 3 SOTA

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

Speech2 results

Audio-Visual Speech RecognitiononLRS2
Test WER· 2020-01-06
5.9
best: 1.4 (Whisper-Flamingo)
SOTA
Audio-visual Recognition of Overlapped speech for the LRS2 dataset arXiv:2001.01656
Automatic Speech Recognition (ASR)onLRS2
Test WER· 2020-01-06
6.7
best: 1.3 (Whisper)
SOTA
Audio-visual Recognition of Overlapped speech for the LRS2 dataset arXiv:2001.01656

Audio1 result

Speech RecognitiononLRS2
Test WER· 2020-01-06
6.7
best: 1.3 (Whisper)
SOTA
Audio-visual Recognition of Overlapped speech for the LRS2 dataset arXiv:2001.01656

Computer Vision1 result

LipreadingonLRS2
Word Error Rate (WER)· uses extra data· 2020-01-06
48.86
best: 14.6 (Auto-AVSR)
Audio-visual Recognition of Overlapped speech for the LRS2 dataset arXiv:2001.01656

Natural Language Processing1 result

Natural Language TransductiononLRS2
Word Error Rate (WER)· uses extra data· 2020-01-06
48.86
best: 14.6 (Auto-AVSR)
Audio-visual Recognition of Overlapped speech for the LRS2 dataset arXiv:2001.01656