Zero-shot Singing Voice Synthesis on SVS zero-shot unseen (test)
4.2MOS-QGT
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| GTtype=Ground Truth2025.09 | 4.2 | 4.35 | 4.55 | — | 4.41 | 0.932 | |
| GT (Acoustic Codec)type=Discrete Representation2025.09 | 4.07 | 4.22 | 4.32 | 0.015 | 4.66 | 0.921 | |
| SPSingerzero-shot=true2025.09 | 3.92 | 4.03 | 3.76 | 0.065 | 4.29 | 0.844 | |
| CoMelSingerzero-shot=true2025.09 | 3.87 | 4.11 | 4.14 | 0.048 | 4.25 | 0.897 | |
| DiffSingerzero-shot=true2025.09 | 3.75 | 3.72 | 3.25 | 0.098 | 4.11 | 0.658 | |
| VISinger2zero-shot=true2025.09 | 3.72 | 3.74 | 3.31 | 0.074 | 4.08 | 0.704 | |
| Vevo 1.5zero-shot=true2025.09 | 3.72 | 3.81 | 4.02 | 0.094 | 4.16 | 0.87 | |
| StyleSingerzero-shot=true2025.09 | 3.48 | 3.82 | 3.85 | 0.125 | 4.22 | 0.853 |