Journal of Information Processing Systems

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Musical Genre Classification Based on Deep Residual Auto-Encoder and Support Vector Machine

  • Xue Han (School of Arts, Northeast Agricultural University) ;
  • Wenzhuo Chen (Dept. of Data and Computing, Northeast Agricultural University) ;
  • Changjian Zhou (Dept. of Data and Computing, Northeast Agricultural University)
  • Received : 2021.12.20
  • Accepted : 2022.05.25
  • Published : 2024.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

Music brings pleasure and relaxation to people. Therefore, it is necessary to classify musical genres based on scenes. Identifying favorite musical genres from massive music data is a time-consuming and laborious task. Recent studies have suggested that machine learning algorithms are effective in distinguishing between various musical genres. However, meeting the actual requirements in terms of accuracy or timeliness is challenging. In this study, a hybrid machine learning model that combines a deep residual auto-encoder (DRAE) and support vector machine (SVM) for musical genre recognition was proposed. Eight manually extracted features from the Mel-frequency cepstral coefficients (MFCC) were employed in the preprocessing stage as the hybrid music data source. During the training stage, DRAE was employed to extract feature maps, which were then used as input for the SVM classifier. The experimental results indicated that this method achieved a 91.54% F1-score and 91.58% top-1 accuracy, outperforming existing approaches. This novel approach leverages deep architecture and conventional machine learning algorithms and provides a new horizon for musical genre classification tasks.

Keywords

References

  1. R. Sarkar, N. Biswas, and S. Chakraborty, "Music genre classification using frequency domain features,' in Proceedings of 2018 5th International Conference on Emerging Applications of Information Technology (EAIT), Kolkata, India, 2018, pp. 1-4. https://doi.org/10.1109/EAIT.2018.8470441
  2. C. Weiss, F. Brand, and M. Muller, "Mid-level chord transition features for musical style analysis," in Proceedings of 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 2019, pp. 341-345. https://doi.org/10.1109/ICASSP.2019.8682293
  3. J. H. Foleis and T. F. Tavares, "Texture selection for automatic music genre classification," Applied Soft Computing, vol. 89, article no. 106127, 2020. https://doi.org/10.1016/j.asoc.2020.106127
  4. A. Vidwans, P. Verma, and P. Rao, "Classifying cultural music using melodic features," in Proceedings of 2020 International Conference on Signal Processing and Communications (SPCOM), Bangalore, India, 2020, pp. 1-5. https://doi.org/10.1109/SPCOM50965.2020.9179597
  5. L. K. Puppala, S. S. R. Muvva, S. R. Chinige, and P. S. Rajendran, "A novel music genre classification using convolutional neural network," in Proceedings of 2021 6th International Conference on Communication and Electronics Systems (ICCES), Coimbatre, India, 2021, pp. 1246-1249. https://doi.org/10.1109/ICCES51350.2021.9489022
  6. C. Chen and X. Steven, "Combined transfer and active learning for high accuracy music genre classification method," in Proceedings of 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Nanchang, China, 2021, pp. 53-56. https://doi.org/10.1109/ICBAIE52039.2021.9390062
  7. J. L. Conceicao, R. de Freitas, B. Gadelha, J. G. Kienen, S. Anders, and B. Cavalcante, "Applying supervised learning techniques to Brazilian music genre classification," in Proceedings of 2020 XLVI Latin American Computing Conference (CLEI), Loja, Ecuador, 2020, pp. 102-107. https://doi.org/10.1109/CLEI52000.2020.00019
  8. N. Pelchat and C. M. Gelowitz, "Neural network music genre classification" Canadian Journal of Electrical and Computer Engineering, vol. 43, no. 3, pp. 170-173, 2020. https://doi.org/10.1109/CJECE.2020.2970144
  9. J. S. Luz, M. C. Oliveira, F. H. Araujo, and D. M. Magalhaes, "Ensemble of handcrafted and deep features for urban sound classification," Applied Acoustics, vol. 175, article no. 107819, 2021. https://doi.org/10.1016/j.apacoust.2020.107819
  10. D. Taufik and N. Hanafiah, "AutoVAT: an automated visual acuity test using spoken digit recognition with MEL frequency cepstral coefficients and convolutional neural network," Procedia Computer Science, vol. 179, pp. 458-467, 2021. https://doi.org/10.1016/j.procs.2021.01.029
  11. S. Wang, H. Wang, Q. Gao, and L. Hao, "Auto-encoder neural network based prediction of Texas poker opponent's behavior," Entertainment Computing, vol. 40, article no. 100446, 2022. https://doi.org/10.1016/j.entcom.2021.100446
  12. M. Seo and K. Y. Lee, "A graph embedding technique for weighted graphs based on LSTM autoencoders," Journal of Information Processing Systems, vol. 16, no. 6, pp. 1407-1423, 2020. https://doi.org/10.3745/JIPS.04.0197
  13. B. M. Aslahi-Shahri, R. Rahmani, M. Chizari, A. Maralani, M. Eslami, M. J. Golkar, and A. Ebrahimi, "A hybrid method consisting of GA and SVM for intrusion detection system," Neural Computing and Applications, vol. 27, pp. 1669-1676, 2016. https://doi.org/10.1007/s00521-015-1964-2
  14. A. C. Enache and V. Sgarciu, "Anomaly intrusions detection based on support vector machines with an improved bat algorithm," in Proceedings of 2015 20th International Conference on Control Systems and Computer Science, Bucharest, Romania, 2015, pp. 317-321. https://doi.org/10.1109/CSCS.2015.12
  15. Y. Chen and R. Zhang, "Default prediction of automobile credit based on support vector machine," Journal of Information Processing Systems, vol. 17, no. 1, pp. 75-88, 2021. https://doi.org/10.3745/JIPS.04.0207
  16. H. Dai, J. Li, Y. Kuang, J. Liao, Q. Zhang, and Y. Kang, "Multiscale fuzzy entropy and PSO-SVM based fault diagnoses for airborne fuel pumps," Human-centric Computing and Information Sciences, vol. 11, article no. 25, 2021. https://doi.org/10.22967/HCIS.2021.11.025
  17. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," 2015 [Online]. Available: https://arxiv.org/abs/1512.03385.
  18. Andrada, "GTZAN Dataset - Music Genre Classification," 2022 [Online]. Available: https://www.kaggle.com/andradaolteanu/gtzan-dataset-music-genre-classification.
  19. Y. Singh and A. Biswas, "Robustness of musical features on deep learning models for music genre classification," Expert Systems with Applications, vol. 199, article no. 116879, 2022. https://doi.org/10.1016/j.eswa.2022.116879
  20. Y. Yu, S. Luo, S. Liu, H. Qiao, Y. Liu, and L. Feng, "Deep attention based music genre classification," Neurocomputing, vol. 372, pp. 84-91, 2020. https://doi.org/10.1016/j.neucom.2019.09.054
  21. C. Liu, L. Feng, G. Liu, H. Wang, and S. Liu, "Bottom-up broadcast neural network for music genre classification," Multimedia Tools and Applications, vol. 80, pp. 7313-7331, 2021. https://doi.org/10.1007/s11042-020-09643-6