Locally Activated Gated Neural Network for Automatic Music Genre Classification
Source abstract
Abstract
Automatic music genre classification is a prevailing pattern recognition task, and many algorithms have been proposed for accurate classification. Considering that the genre of music is a very broad concept, even music within the same genre can have significant differences. The current methods have not paid attention to the characteristics of large intra-class differences. This paper presents a novel approach to address this issue, using a locally activated gated neural network (LGNet). By incorporating multiple locally activated multi-layer perceptrons and a gated routing network, LGNet adaptively employs different network layers as multi-learners to learn from music signals with diverse characteristics. Our experimental results demonstrate that LGNet significantly outperforms the existing methods for music genre classification, achieving a superior performance on the filtered GTZAN dataset.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Music and Audio Processing · Music Technology and Sound Studies · Speech and Audio Processing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
School of Railway Transportation, Shanghai Institute of Technology, Shanghai 201418, China
References (26)
Show source-provided references
1. Musical genre classification of audio signals10.1109/TSA.2002.800560 ↗
2. Liu, J., Wang, C., and Zha, L. (2021). A middle-level learning feature interaction method with deep learning for multi-feature music genre classification. Electronics, 10.10.3390/electronics10182206 ↗
3. Chaudhury, M., Karami, A., and Ghazanfar, M.A. (2022). Large-Scale Music Genre Analysis and Classification Using Machine Learning with Apache Spark. Electronics, 11.10.3390/electronics11162567 ↗
4. Music genre classification and music recommendation by using deep learning10.1049/el.2019.4202 ↗
5. Rajanna, A.R., Aryafar, K., Shokoufandeh, A., and Ptucha, R. (2015, January 9–11). Deep neural networks: A case study for music genre classification. Proceedings of the 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), Miami, FL, USA.10.1109/ICMLA.2015.160 ↗
6. Xu, C., Maddage, N.C., Shao, X., Cao, F., and Tian, Q. (2003, January 6–10). Musical genre classification using support vector machines. Proceedings of the 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, Hong Kong, China.
7. Music genre classification using MFCC, SVM and BPNN
8. Music genre classification using MFCC, K-NN and SVM classifier
9. Khasgiwala, Y., and Tailor, J. (2021, January 23–25). Vision transformer for music genre classification using mel-frequency cepstrum coefficient. Proceedings of the 2021 IEEE 4th International Conference on Computing, Power and Communication Technologies (GUCON), Kuala Lumpur, Malaysia.10.1109/GUCON50781.2021.9573568 ↗
10. Neural network music genre classification10.1109/CJECE.2020.2970144 ↗
11. Cheng, Y.H., and Kuo, C.N. (2022). Machine Learning for Music Genre Classification Using Visual Mel Spectrum. Mathematics, 10.10.3390/math10234427 ↗
12. Jena, K.K., Bhoi, S.K., Mohapatra, S., and Bakshi, S. (2023). A hybrid deep learning approach for classification of music genres using wavelet and spectrogram analysis. Neural Comput. Appl., 1–26.10.1007/s00521-023-08294-6 ↗
13. Zhao, H., Zhang, C., Zhu, B., Ma, Z., and Zhang, K. (2022, January 22–27). S3t: Self-supervised pre-training with swin transformer for music classification. Proceedings of the ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore.10.1109/ICASSP43922.2022.9746056 ↗
14. A machine learning approach to automatic music genre classification10.1007/BF03192561 ↗
15. Bahuleyan, H. (2018). Music genre classification using machine learning techniques. arXiv.
16. Deep learning10.1038/nature14539 ↗
17. Dai, J., Liang, S., Xue, W., Ni, C., and Liu, W. (2016, January 17–20). Long short-term memory recurrent neural network based segment features for music genre classification. Proceedings of the 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), Tianjin, China.10.1109/ISCSLP.2016.7918369 ↗
18. Ashraf, M., Abid, F., Din, I.U., Rasheed, J., Yesiltepe, M., Yeo, S.F., and Ersoy, M.T. (2023). A Hybrid CNN and RNN Variant Model for Music Classification. Appl. Sci., 13.10.3390/app13031476 ↗
19. Kurdish Music Genre Recognition Using a CNN and DNN
20. Beyond omnivores and univores: The promise of a concept of musical habitus10.1177/1749975511401278 ↗
21. Artificial neural networks (the multilayer perceptron)—A review of applications in the atmospheric sciences10.1016/S1352-2310(97)00447-0 ↗
22. An alternative model for mixtures of experts
23. Abeßer, J., and Müller, M. (2021). Jazz bass transcription using a U-net architecture. Electronics, 10.10.3390/electronics10060670 ↗
24. Zhuang, Y., Chen, Y., and Zheng, J. (2020, January 19–21). Music genre classification with transformer classifier. Proceedings of the 2020 4th International Conference on Digital Signal Processing, Chengdu, China.10.1145/3408127.3408137 ↗
25. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
26. Multi-level and multi-scale feature aggregation using pretrained convolutional neural networks for music auto-tagging10.1109/LSP.2017.2713830 ↗