Table 7 Subjective comparison results with standard deviation (std dev) of mono-lingual conversion in seen-to-seen scenario. The results are listd as MOS/std dev
From: U2-VC: one-shot voice conversion using two-level nested U-structure
| Â | MOS (similarity)/std dev | MOS (naturalness)/std dev | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Â | SF2TF | SF2TM | SM2TF | SM2TM | Average | SF2TF | SF2TM | SM2TF | SM2TM | Average |
AdaIN-VC | 2.00/0.30 | 2.04/0.37 | 2.04/0.30 | 2.19/0.40 | 2.07 | 2.07/0.77 | 2.01/0.35 | 2.10/0.32 | 2.21/0.46 | 2.10 |
AGAIN-VC | 2.92/0.46 | 2.76/0.40 | 2.87/0.45 | 3.40/0.59 | 2.99 | 3.38/0.65 | 3.18/0.49 | 3.12/0.41 | 3.62/0.43 | 3.33 |
U2-VC | 3.30/0.41 | 3.24/0.40 | 3.28/0.38 | 4.02/0.42 | 3.46 | 3.91/0.56 | 3.92/0.47 | 3.78/0.31 | 4.16/0.32 | 3.94 |