Movie Dubbing on V2C-Animation Dub denoise 2.0
100Speaker SimilarityGT
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| GT2024.02 | 100 | 22.76 | 99.96 | — | — | — | — | |
| GT Mel + Vocoder2024.02 | 96.93 | 24.83 | 96.95 | 3.77 | 3.8 | — | — | |
| StyleDubberVisual input=true2024.02 | 81.27 | 31.7 | 41.35 | 10.59 | 10.68 | — | — | |
| StyleSpeech*Visual input=true2024.02 | 75.67 | 82.48 | 42.57 | 11.58 | 15.23 | — | — | |
| StyleSpeechVisual input=false2024.02 | 75.66 | 76.58 | 41.55 | 11.56 | 15.1 | — | — | |
| Face-TTSVisual input=true2024.02 | 51.98 | 200.18 | 43.56 | 13.78 | 28.03 | — | — | |
| Zero-shot TTSVisual input=false2024.02 | 47.79 | 58.82 | 39.11 | 10.68 | 13.52 | — | — | |
| Zero-shot TTS*Visual input=true2024.02 | 47.55 | 58.81 | 39.3 | 10.76 | 13.66 | — | — | |
| V2C-NetVisual input=true2024.02 | 34.07 | 61.61 | 41.01 | 14.58 | 18.73 | — | — | |
| HPMDubbingVisual input=true2024.02 | 31.42 | 171.03 | 43.97 | 11.88 | 11.98 | — | — | |
| Fastspeech2*Visual input=true2024.02 | 25.47 | 34.08 | 42.39 | 11.35 | 14.73 | — | — | |
| Fastspeech2Visual input=false2024.02 | 24.17 | 35.08 | 42.21 | 11.2 | 14.48 | — | — |