Speech Reconstruction on GRID (speaker-dependent)
0.738STOIProposed Method
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Proposed MethodSetting=speaker-dependent2022.04 | 0.738 | 0.579 | 1.984 | |
| Lip2WavSetting=speaker-dependent2022.04 | 0.731 | 0.535 | 1.772 | |
| Yadav et al.Setting=speaker-dependent2022.04 | 0.724 | 0.54 | 1.932 | |
| Ephrat et al.Setting=speaker-dependent2022.04 | 0.659 | 0.376 | 1.825 | |
| Vougioukas et al.Setting=speaker-dependent2022.04 | 0.564 | 0.361 | 1.684 | |
| Lip2AudSpecSetting=speaker-dependent2022.04 | 0.513 | 0.352 | 1.673 | |
| Vid2SpeechSetting=speaker-dependent2022.04 | 0.491 | 0.335 | 1.734 |