Lip-to-Speech Synthesis
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
4.166UTMOS
7
Feb 26, 2026
4.21UTMOS
7
Feb 26, 2026
4.82Intelligibility
5
Feb 26, 2026
4.02Naturalness
3
Feb 26, 2026
21.9WER
3
Feb 26, 2026
25.15GF0
2
Feb 26, 2026
0.342WER
2
Feb 26, 2026