Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Speech Recognition on CMU-MOSEAS French
Loading...
59.1
Mean WER
VSR model with prediction-based auxiliary tasks
58.268
63.884
69.5
75.116
Feb 26, 2022
Mean WER
Std Dev WER
Best WER
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean WER
Std Dev WER
Best WER
VSR model with prediction-based auxiliary tasks
Pre-training Set=LRW+L...
2022.02
59.1
0.5
58.3
VSR model with prediction-based auxiliary tasks
Pre-training Set=LRW+L...
2022.02
60.1
0.3
59.5
VSR model with prediction-based auxiliary tasks
Pre-training Set=LRW,...
2022.02
68.4
0.5
67.5
CM-seq2seq
Pre-training Set=LRW,...
2022.02
79.9
0.4
79.6
Feedback
Search any
task
Search any
task