Pose Adaptive Dynamic FiLM Modulation for Visual Speech Recognition
Open paper
Benchmark
Model
Rank
Results
lipreading-on-lrs2
DR-FiLM
–
Word Error Rate (WER): 23.2
lipreading-on-lrs3-ted
DR-FiLM
–
Word Error Rate (WER): 34.4
Rank counts only results with a code link.