Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Audio-Visual Speech Separation on VoxCeleb2 Scenario 2 (1 speaker + FMA music noise)
Loading...
7.49
SI-SNRi
Dolphin
1.822
3.2935
4.765
6.2365
Sep 28, 2025
SI-SNRi
SDRi
PESQ
Updated 1mo ago
Evaluation Results
Method
Method
Links
SI-SNRi
SDRi
PESQ
Dolphin
2025.09
7.49
8.52
1.85
AV-Mossformer2
2025.09
6.68
7.53
1.76
IIANet
2025.09
2.04
5.92
1.64
Feedback
Search any
task
Search any
task