Research Article
Classifying Human Voices by Using Hybrid SFX Time-Series Preprocessing and Ensemble Feature Selection
Table 2
Distributions of classes in different datasets.
| Dataset name | No. of classes or labels | Notes |
| FM | 2 | Female and male | ES | 4 | Happiness, anger, sadness, and neutral | SI | 16 | 16 different speakers | LR | 3 | Cantonese, English, and Mandarin |
|
|