Multi-speaker Dubbing on GRID Dub 1.0 (test)
100SPK-SIM (%)GT
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GT2024.02 | 100 | 22.41 | 0 | 0 | |
| GT Mel + Vocoder2024.02 | 97.57 | 21.41 | 4.1 | 4.15 | |
| StyleDubber2024.02 | 93.79 | 18.88 | 5.61 | 5.69 | |
| StyleSpeechVideo embedding input=false2024.02 | 91.06 | 24.83 | 5.87 | 5.98 | |
| StyleSpeechVideo embedding input=true2024.02 | 90.04 | 22.62 | 5.74 | 5.88 | |
| Zero-shot TTSVideo embedding input=false2024.02 | 86.54 | 19.13 | 5.71 | 5.99 | |
| Zero-shot TTSVideo embedding input=true2024.02 | 85.93 | 20.05 | 5.75 | 6.4 | |
| HPMDubbing2024.02 | 85.11 | 45.11 | 6.49 | 6.78 | |
| Face-TTS2024.02 | 82.97 | 44.37 | 7.44 | 8.16 | |
| V2C-Net2024.02 | 80.98 | 47.82 | 6.79 | 7.23 | |
| Fastspeech2Video embedding input=true2024.02 | 59.58 | 19.61 | 7.24 | 7.95 | |
| Fastspeech2Video embedding input=false2024.02 | 47.41 | 19.05 | 7.67 | 8.43 |