Scene-aware visually driven speech synthesis on Vivid-210K (test)
7.15WER
VividVoice
Updated 4d ago
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.02 | 7.15 | 3.98 | 1.53 | 0.25 | 3.95 | 3.08 | 4.3 | 3.88 | |
2026.02 | 9.23 | 4.74 | 1.79 | 0.27 | 3.23 | 1.75 | 2.56 | 3.41 | |
2026.02 | 10.62 | - | - | 0.39 | 4.36 | 4.03 | 4.11 | 4.25 |