Audio-visual Recognition of Overlapped speech for the LRS2 dataset
Open paper
Benchmark
Model
Rank
Results
audio-visual-speech-recognition-on-lrs2
LF-MMI TDNN
–
Test WER: 5.9
automatic-speech-recognition-on-lrs2
LF-MMI TDNN
–
Test WER: 6.7
lipreading-on-lrs2
LF-MMI TDNN
–
Word Error Rate (WER): 48.86
Rank counts only results with a code link.