Table 6 Objective comparison results of mono-lingual conversion in seen-to-seen scenario
From: U2-VC: one-shot voice conversion using two-level nested U-structure
| Â | MCD (dB) | Predicted MOS by NISQA | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Â | SF2TF | SF2TM | SM2TF | SM2TM | Average | SF2TF | SF2TM | SM2TF | SM2TM | Average |
AdaIN-VC | 7.11 | 6.62 | 7.09 | 6.97 | 6.95 | 3.01 | 2.94 | 3.07 | 3.53 | 3.14 |
AGAIN-VC | 6.33 | 6.07 | 6.32 | 6.33 | 6.26 | 3.87 | 3.63 | 3.93 | 4.02 | 3.86 |
U2-VC | 6.36 | 6.11 | 6.32 | 6.39 | 6.29 | 4.13 | 3.93 | 4.14 | 4.05 | 4.06 |