摘要：Folk music style classification is of great significance. Traditional folk music style classification has difficulties in feature selection, and the existing folk music style methods based on deep learning also have shortcomings. In this paper, we use artificial neural networks to classify folk music styles and transform audio signals into a sound spectrum. In this paper, we use artificial neural networks to classify folk music styles and transform audio signals into a sound spectrum to avoid the problem of manually selecting features. Further, we combine the characteristics of the music signal and a variety of music data enhancement methods to enhance the music data. The proposed model can extract elements of the sound spectrum that are more closely associated with a certain music style category. Experimental results reveal that the proposed method achieves a high accuracy rate, which verifies the effectiveness of our model.
