Singing Voice Synthesis on OpenSinger (ID)
4.5PESQGround Truth
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Ground Truth2025.12 | 4.5 | 0 | — | — | |
| HiFiGAN + UnivHDVocoder=HiFiGAN, Discriminator=UnivHD (+H)2025.12 | 3.19 | 2.27 | 28.94 | — | |
| iSTFTNet + UnivHDVocoder=iSTFTNet, Discriminator=UnivHD (+H)2025.12 | 3.14 | 2.09 | 26.32 | — | |
| HiFiGAN + MS-SB-CQTVocoder=HiFiGAN, Discriminator=MS-SB-CQT (+C)2025.12 | 3.1 | 2.29 | 29.98 | — | |
| iSTFTNet + MS-SB-CQTVocoder=iSTFTNet, Discriminator=MS-SB-CQT (+C)2025.12 | 3.09 | 2.12 | 27.4 | — | |
| iSTFTNetVocoder=iSTFTNet, Discriminator=Original2025.12 | 3.06 | 2.16 | 28.96 | — | |
| HiFiGAN + MS-STFTVocoder=HiFiGAN, Discriminator=MS-STFT (+S)2025.12 | 3.05 | 2.36 | 30.28 | — | |
| iSTFTNet + MS-STFTVocoder=iSTFTNet, Discriminator=MS-STFT (+S)2025.12 | 3.05 | 2.2 | 27.79 | — | |
| HiFiGANVocoder=HiFiGAN, Discriminator=Original2025.12 | 2.96 | 2.45 | 30.32 | — |