Voice Conversion on Elliot Miller target speaker
3.22WERGround truth
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Ground truthSSL model=WavLM2025.05 | 3.22 | 5.47 | — | — | 3.85 | |
| Eta-WavLMSSL model=WavLM2025.05 | 4.64 | 6.09 | 89.32 | 48.25 | 3.79 | |
| WavLMSSL model=WavLM2025.05 | 5.14 | 6.38 | 86.18 | 54.3 | 3.66 | |
| Utterance stdSSL model=WavLM2025.05 | 5.16 | 6.68 | 85.91 | 55.87 | 3.41 | |
| SoftSSL model=WavLM2025.05 | 5.5 | 6.75 | 86.69 | 53.36 | 3.32 | |
| Vector quantizationSSL model=WavLM2025.05 | 7.72 | 7.56 | 86.3 | 53.81 | 3.5 | |
| PerturbationSSL model=WavLM2025.05 | 10.76 | 8.43 | 87.41 | 52.67 | 3.13 |