Table 1 Euclidean distance and cosine similarity between the hidden distributions obtained from the source and target speakers’ speech of Figs. 3 (H=16) and 4 (H=64)
From: Speaker-adaptive-trainable Boltzmann machine and its application to non-parallel voice conversion
| Euclidean dist. | Cosine sim. | |
|---|---|---|
| H=16 | 0.660 | 0.526 |
| H=64 | 0.869 | 0.337 |