Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Acoustic Matching on LibriSpeech unseen environments (test)
Loading...
0.21
RTE (s)
LeMARA
0.20408
0.24404
0.284
0.32396
Jul 27, 2023
RTE (s)
Updated 1mo ago
Evaluation Results
Method
Method
Links
RTE (s)
LeMARA
Train dataset=AVSpeech...
2023.07
0.21
LeMARA (no vis)
Train dataset=AVSpeech...
2023.07
0.223
AVITAR
Train dataset=AVSpeech...
2023.07
0.239
ViGAS
Train dataset=AVSpeech...
2023.07
0.254
Input audio
Train dataset=AVSpeech...
2023.07
0.358
Feedback
Search any
task
Search any
task