Recurrent Neural Network Transducer for Audio-Visual Speech Recognition
Open paper
Benchmark
Model
Rank
Results
audio-visual-speech-recognition-on-lrs3-ted
RNN-T
#10
Word Error Rate (WER): 4.5
lipreading-on-lrs3-ted
RNN-T
#12
Word Error Rate (WER): 33.6
Rank counts only results with a code link.