| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Audio Synthesis | Singing Voice MUSHRA (evaluation) | MUSHRA Score86.78 | 21 | |
| Audio Synthesis | Singing Voice Industrial setting | MOS Prediction4.33 | 21 | |
| Audio Synthesis | Singing Voice Academic setting | MOS Prediction Score4.18 | 21 | |
| Singing Voice Synthesis | Singing Voice Industrial Setting | MOS Prediction4.33 | 11 | |
| Singing Voice Synthesis | Singing Voice (Academic Setting) | MOS Prediction Score4.17 | 11 | |
| Zero-shot Text-to-Speech | Singing Voice | WER7.66 | 8 | |
| Singing Lyric Editing | Singing Voice Editing | WER17.98 | 4 |