Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Speaker Separation on LRS3 synthetic (test)
Loading...
15.5
SDR
VoiceFormer (Ours A+V)
0.732
4.566
8.4
12.234
Jan 2, 2025
SDR
STOI
PESQ
Updated 4d ago
Evaluation Results
Method
Method
Links
SDR
STOI
PESQ
VoiceFormer (Ours A+V)
Video conditioning=tru...
2025.01
15.5
0.934
2.62
VoiceFormer (Ours A+V+T)
Video conditioning=tru...
2025.01
15.5
0.935
2.63
Visual Voice
Video conditioning=tru...
2025.01
11.7
0.9
2.41
Conversation
Video conditioning=fal...
2025.01
10.15
0.865
2.08
AVObjects
Video conditioning=tru...
2025.01
9.72
0.851
2.02
Noisy input
Video conditioning=fal...
2025.01
1.3
0.697
1.3
Denoiser
Video conditioning=fal...
2025.01
1.3
0.697
1.3
Feedback
Search any
task
Search any
task