Multi-speaker Dubbing on V2C-Animation Dub 1.0 (test)
100Speaker Similarity (SPK-SIM)GT
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GT2024.02 | 100 | 22.55 | 99.96 | 0 | 0 | |
| GT Mel + Vocoder2024.02 | 96.96 | 24.58 | 97.09 | 3.77 | 3.8 | |
| StyleDubber2024.02 | 82.26 | 31.49 | 45.62 | 9.37 | 9.46 | |
| StyleSpeechVideo embedding input=false2024.02 | 54.99 | 106.73 | 44.12 | 11.5 | 15.1 | |
| HPMDubbing2024.02 | 53.76 | 164.16 | 46.61 | 11.12 | 11.22 | |
| Face-TTS2024.02 | 52.81 | 201.13 | 44.04 | 13.44 | 26.94 | |
| Zero-shot TTSVideo embedding input=false2024.02 | 48.98 | 68.81 | 42.75 | 9.98 | 12.51 | |
| Zero-shot TTSVideo embedding input=true2024.02 | 48.93 | 68.05 | 43.97 | 10.03 | 12.01 | |
| StyleSpeechVideo embedding input=true2024.02 | 42.53 | 108 | 42.53 | 11.62 | 14.23 | |
| V2C-Net2024.02 | 40.61 | 73.08 | 43.08 | 14.12 | 18.49 | |
| Fastspeech2Video embedding input=true2024.02 | 25.47 | 33.53 | 42.39 | 11.35 | 14.73 | |
| Fastspeech2Video embedding input=false2024.02 | 24.87 | 34.48 | 42.21 | 11.2 | 14.48 |