Sound Classification Based on Multihead Attention and Support Vector Machine

Table 4

Comparison of the classification accuracy with six methods on UrbanSound8K.

Methods	Preprocessing	Accuracy (%)
DenseNet [28]	MFCC + GFCC	85.1
MelNet [29]	Mel-spectrogram	92.2
GoogleNet [30]	Mel-spectrogram	93.0
RawNet [29]	Wav	87.0
1D CNN [31]	Wav	89.1
MhaNN-SVM	Mel-spectrogram	94.6