Research on Music Classification Technology Based on Integrated Deep Learning Methods

Sujie He; Yuxian Li

doi:10.4108/eetsis.4954

Authors

Sujie He Shan Dong University Of Art
Yuxian Li Jinan Technician College, Jinan 250000, Shandong, China

DOI:

https://doi.org/10.4108/eetsis.4954

Keywords:

deep learning, music classification, convolutional networks, recurrent neural networks

Abstract

INTRODUCTION: Music classification techniques are of great importance in the current era of digitized music. With the dramatic increase in music data, effectively categorizing music has become a challenging task. Traditional music classification methods have some limitations, so this study aims to explore music classification techniques based on integrated deep-learning methods to improve classification accuracy and robustness.

OBJECTIVES: The purpose of this study is to improve the performance of music classification by using an integrated deep learning approach that combines the advantages of different deep learning models. The author aims to explore the effectiveness of this approach in coping with the diversity and complexity of music and to compare its performance differences with traditional approaches.

METHODS: The study employs several deep learning models including, but not limited to, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory Networks (LSTM). These models were integrated into an overall framework to perform the final music classification by combining their predictions. The training dataset contains rich music samples covering different styles, genres and emotions.

RESULTS: Experimental results show that music classification techniques based on integrated deep learning methods perform better in terms of classification accuracy and robustness compared to traditional methods. The advantages of integrating different deep learning models are fully utilized, enabling the system to better adapt to different types of music inputs.

CONCLUSION: This study demonstrates the effectiveness of the integrated deep learning approach in music classification tasks and provides valuable insights for further improving music classification techniques. This approach not only improves the classification performance but also promises to be applied to other areas and promote the application of deep learning techniques in music analysis.

References

Alkhodari, M., & Fraiwan, L. (2021). Convolutional and recurrent neural networks for the detection of valvular heart diseases in phonocardiogram recordings. Computer Methods and Programs in Biomedicine, 200(38), 105940.

Anjum, S., Hussain, L., Ali, M., Alkinani, M. H., & Duong, T. Q. (2021). Detecting brain tumours using deep learning convolutional neural network with the transfer learning approach. International Journal of Imaging Systems and Technology, 142, 56–88.

Cheng, L., Khalitov, R., Yu, T., & Yang, Z. (2022). Classification of long sequential data using circular dilated convolutional neural networks. arXiv E-Prints, 6, 88–103.

D'Angelo, G., & Palmieri, F. (2021). Network traffic classification using deep convolutional recurrent autoencoder neural networks for spatial–temporal feature extraction. Journal of Network and Computer Applications, 173, 102890.

Ding, Y., Zhao, X., Zhang, Z., Cai, W., Yang, N., & Zhan, Y. (2022). Semi-supervised locality preserving dense graph neural network with ARMA filters and context-aware learning for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–24.

Efficient classification of handwritten medical prescription recognition using convolutional neural network architecture and comparing with novel customized recurrent neural network architecture. (2023). AIP Conference Proceedings, 2822(1), 1–17.

Fu, Z., Wang, B., Wu, X., & Chen, J. (2021). Auditory attention decoding from EEG using convolutional recurrent neural network. 33, 111–147. https://doi.org/10.23919/EUSIPCO54536.2021.9616195

Gan, J. (2021). Music feature classification is based on recurrent neural networks with a channel attention mechanism. Mobile Information Systems, 44, 1–44. https://doi.org/10.1155/2021/7629994

Jaouedi, N., Boujnah, N., & Bouhlel, M. (2021). A novel recurrent neural network architecture for behavior analysis. The International Arab Journal of Information Technology, 2, 18. https://doi.org/10.34028/iajit/18/2/1

Jia, W., Ren, Q. Q., Zhao, Y., Li, S., Min, H., & Chen, Y. X. (2022). EEPNet: An efficient and effective convolutional neural network for palmprint recognition. Pattern Recognition Letters, 159, 140–149. https://doi.org/10.1016/j.patrec.2022.05.015

Liao, K., Zhao, Y., Gu, J., Zhang, Y., & Zhong, Y. (2021). Sequential convolutional recurrent neural networks for fast, automatic modulation classification. IEEE Access : Practical Innovations, Open Solutions, PP(99), 1–1.

Linden, T., Jong, J., Lu, C., & Froehlich, H. (2021). An explainable multimodal neural network architecture for predicting epilepsy comorbidities based on administrative claims data. Frontiers in Artificial Intelligence, 22, 133–179. https://doi.org/10.3389/frai.2021.610197

Lyu, S., & Liu, J. (2021). Convolutional recurrent neural networks for text classification. Journal of Database Management: An Official Publication of the International Data Management Institute of the Information Resources Management Association, 4, 32.

Mangla, P., Arora, S., & Bhatia, M. P. S. (2021). Intelligent audio analysis techniques for identification of music in smart devices. Internet Technology Letters, 111, 46–88.

Mitra, J., Vijayran, K., Verma, K., & Goel, A. (2023). Blood cell classification using neural network models. 2023 2nd International Conference on Smart Technologies and Systems for Next Generation Computing (ICSTSN), 11, 1–5. https://doi.org/10.1109/ICSTSN57873.2023.10151543

Naga, K. E. M. V., & Madan, G. (2021). Extraction of the features of fingerprints using conventional methods and convolutional neural networks. 44, 6–17.

Pokaprakarn, T., Kitzmiller, R. R., Moorman, J. R., Lake, D. E., Krishnamurthy, A. K., & Kosorok, M. R. (2022). Sequence to sequence ECG cardiac rhythm classification using convolutional recurrent neural networks. IEEE Journal of Biomedical and Health Informatics, 2, 26. https://doi.org/10.1109/JBHI.2021.3098662

Venkatesh, S., Moffat, D., Kirke, A., Shakeri, G., Brewster, S., Fachner, J., Odell-Miller, H., Street, A., Farina, N., & Banerjee, S. (2021). Artificially synthesizing data for audio classification and segmentation to improve speech and music detection in a radio broadcast. 33, 45–89. https://doi.org/10.1109/ICASSP39728.2021.9413597

Wang, Q., Tian, J., Li, M., & Lu, M. (2023). Text classification based on CNN-BiGRU and its application in telephone comments recognition. International Journal of Computational Intelligence and Applications, 22(04), 5. https://doi.org/10.1142/S1469026823500219

Zheng, J., & Du, M. (2023). Study on tomato disease classification based on leaf image recognition based on deep learning technology. International Journal of Advanced Computer Science and Applications, 66, 55–88.