Table 4 Results of misclassification for various network models using FMA dataset
From: Comparative study of singing voice detection based on deep neural networks and ensemble learning
| Â | Misclassify vocal as non-vocal | Misclassify non-vocal as vocal |
|---|---|---|
MCNN | 463.4 | 211.4 |
SCNN | 238.6 | 249.4 |
SLSTM | 304.8 | 347.8 |
CLSTM | 361.4 | 227.9 |
Capsule net | 579.3 | 462.3 |