| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video-to-Speech synthesis | V2C-Animation | Sim-O79 | 11 | |
| Video-to-Speech Synthesis | V2C Dub 3.0 | MOS-S3.94 | 10 | |
| Dubbing | V2C-Animation + Chem + GRID (test) | MCD (DTW)0 | 8 | |
| Dubbing | V2C-Animation | DD0 | 6 | |
| Video-conditioned sound-speech joint generation | V2C (test) | WER19.4 | 5 |