Table 5 Results for the evaluation of the naturalness of synthesized speech using the proposed method
From: Speaker-dependent model interpolation for statistical emotional speech synthesis
Angry | Happy | Sad | Non-synthetic |
|---|---|---|---|
3.0 | 3.1 | 2.9 | 4.6 |
From: Speaker-dependent model interpolation for statistical emotional speech synthesis
Angry | Happy | Sad | Non-synthetic |
|---|---|---|---|
3.0 | 3.1 | 2.9 | 4.6 |