From: U2-VC: one-shot voice conversion using two-level nested U-structure
Statistical significance of similarity | Statistical significance of naturalness | ||||||||
---|---|---|---|---|---|---|---|---|---|
VCTK2VCC | VCC2VCTK | VCC2VCC | Overall | VCTK2VCC | VCC2VCTK | VCC2VCC | Overall | ||
AdaIN-VC | AGAIN-VC | 0.001 | 0.041 | 0.004 | 0.000 | 0.001 | 0.002 | 0.029 | 0.000 |
U2-VC | 0.000 | 0.000 | 0.000 | 0.000 | 0.000 | 0.000 | 0.000 | 0.000 | |
AGAIN-VC | AdaIN-VC | 0.001 | 0.041 | 0.004 | 0.000 | 0.001 | 0.002 | 0.029 | 0.000 |
U2-VC | 0.090 | 0.049 | 0.070 | 0.001 | 0.017 | 0.007 | 0.013 | 0.001 | |
U2-VC | AdaIN-VC | 0.000 | 0.000 | 0.000 | 0.000 | 0.000 | 0.000 | 0.000 | 0.000 |
AGAIN-VC | 0.090 | 0.049 | 0.070 | 0.001 | 0.017 | 0.007 | 0.013 | 0.001 |