Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Video-to-speech synthesis on LRS3-TED (test)
Loading...
4.031
UTMOS
Ours
1.17308
1.91504
2.657
3.39896
Mar 21, 2025
UTMOS
DNSMOS
RMSE f0
WER
Updated 4d ago
Evaluation Results
Method
Method
Links
UTMOS
DNSMOS
RMSE f0
WER
Ours
Speaker embedding type...
2025.03
4.031
2.789
39.013
30.45
Ours
Speaker embedding type...
2025.03
3.993
2.759
38.928
30.37
Ground Truth
2025.03
3.545
2.582
-
2.29
DiffV2S
Speaker embedding type...
2025.03
3.058
2.558
40.893
41.07
Intelligible
Speaker embedding type...
2025.03
2.702
2.395
39.377
29.6
LTBS
Speaker embedding type...
2025.03
2.417
2.361
40.006
84.08
SVTS
Speaker embedding type...
2025.03
1.283
1.86
56.929
84.98
Feedback
Search any
task
Search any
task