Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Speech-to-Singing conversion on English (test)
Loading...
2.512
LSD
GT (vocoder)
2.29068
3.78459
5.2785
6.77241
Jun 4, 2024
LSD
RCA
MOS-S
MOS-P
MOS-Q
Updated 4d ago
Evaluation Results
Method
Method
Links
LSD
RCA
MOS-S
MOS-P
MOS-Q
GT (vocoder)
source=Ground Truth ac...
2024.06
2.512
0.988
4.52
4.47
4.13
SVPT
semantic_features=XLSR...
2024.06
5.213
0.967
3.46
3.68
3.61
SVPT
semantic_features=wav2...
2024.06
5.462
0.956
3.44
3.48
3.39
AlignSTS
architecture=diffusion...
2024.06
5.519
0.941
3.45
3.47
3.41
Wu and Yang, 2020
architecture=GAN-based
2024.06
6.913
0.896
3.12
3.21
3.15
Parekh et al., 2020
architecture=CNN-based...
2024.06
8.045
0.842
3.02
2.99
3.01
Feedback
Search any
task
Search any
task