Research Article
Sound Classification Based on Multihead Attention and Support Vector Machine
Table 7
Comparison of the classification accuracy with six methods on GTZAN.
| Methods | Preprocessing | Accuracy (%) |
| Hybrid model [32] | MFCC, SSD, etc. | 88.3 | CVAF [33] | Mel-spectrogram, SSD, etc | 90.9 | Transfer learning [16] | MFCC | 89.8 | AuDeep [34] | Mel-spectrogram | 85.4 | BBNN [35] | Mel-spectrogram | 93.3 | MhaNN-SVM | Mel-spectrogram | 88.4 |
|
|