Speaker Specific Lip To Speech Synthesis On
Metrics
ESTOI
PESQ
STOI
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | ESTOI | PESQ | STOI |
|---|---|---|---|
| learning-individual-speaking-styles-for | 0.535 | 1.772 | 0.731 |
| speech-reconstruction-with-reminiscent-sound | 0.579 | 1.984 | 0.738 |