A Convolutional Neural Networks (CNN) Approach to Music Genre Classification

Abdulsalam Auwal Jamilu¹ , Lawal Abubakar² , Ubaidullah Abdallah³

Section:Research Paper, Product Type: Journal-Paper
Vol.10 , Issue.5 , pp.37-44, Oct-2022

Online published on Oct 31, 2022

Copyright © Abdulsalam Auwal Jamilu, Lawal Abubakar, Ubaidullah Abdallah . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

Abstract :
Music is becoming easier to access through the internet, and musical applications like Spotify and Apple Music have common services that help their customers automatically classify music into different genres, the classification of music genres is a fundamental step in developing a powerful music recommendation engine.With the escalating number of music available digitally on the internet, there is a growing demand for the systematic organization of audio files and thus a rise in the interest in automatic music genre classification. Moreover, detecting and grouping music in a similar genre is a keen part of the music recommendation system and playlist that are personalized to soothe listeners’ mood and their unique music taste. However, Convolutional Neural Networks have appeared to be accurate in classifying music into different genres. Over the last decade, Convolutional Neural Networks have achieved breakthroughs in domains ranging from pattern recognition, image processing and voice recognition. For the Convolution Neural Network model to be able to classify music into different genres there would be a need for pre-processing of data by converting the raw audio into Mel-spectrograms. These features that have been extracted would then be used for training and classification. Additionally, Mel-spectrograms are visual, and CNN works better with images. This research focuses on a review, in the identification of music genres. Music Information Retrieval (MIR) can make it easier to identify essential information like trends, popular genres, and performers.

Key-Words / Index Term :
Convolution Neural Network, Deep learning, Classification, Music genre classification.

References :
[1] D. A. Huang, A. A. Serafini, and E. J. Pugh, "Music Genre Classification," CS229 Stanford, 2018.
[2] L. Aguiar and J. Waldfogel, "Platforms, promotion, and product discovery: Evidence from Spotify playlists," National Bureau of Economic Research, 2018.
[3] Lam Hoang.”Literature Review about Music Genre Classification. In Woodstock “18: ACM Symposium on Neural Gaze Detection, June 03–05, 2018, Woodstock, NY . ACM, New York, NY, USA, 3 pages.
[4] G. Tzanetakis and P. Cook, "Musical genre classification of audio signals," IEEE Transactions on speech and audio processing, vol. 10, no. 5, pp. 293-302, 2002.
[5] Sciforce. "3 reasons to use ai in music industry, April 26, ." 2020.
[6] M. Serwach and B. Stasiak, "GA-based parameterization and feature selection for automatic music genre recognition," 17th International Conference Computational Problems , 2016
[7] K. Kashino, K. Nakadai, T. Kinoshita, and H. Tanaka, "Organization of hierarchical perceptual sounds," in Proc. 14th Int. conf. On Artificial Intelligence, 1995, vol. 1: Citeseer, pp. 158-164.
[8] M. Dörfler, R. Bammer, and T. Grill, "Inside the spectrogram: Convolutional Neural Networks in audio processing," in 2017 international conference on sampling theory and applications (SampTA), IEEE, pp. 152-155, 2017.
[9] K. O`Shea and R. Nash, "An introduction to convolutional neural networks," arXiv preprint arXiv:1511.08458, 2015.
[10] L. Nanni, S. Ghidoni, and S. Brahnam, "Handcrafted vs. non-handcrafted features for computer vision classification," Pattern Recognition, vol. 71, pp. 158-172, 2017.
[11] Octaviano. "Music Genre Classification using Convolutional Neural Network." April 26, 2022.
[12] N. Scaringella, G. Zoia, and D. Mlynek, "Automatic genre classification of music content: a survey," IEEE Signal Processing Magazine, vol. 23, no. 2, pp. 133-141, 2006.
[13] N. Scaringella, G. Zoia, and D. Mlynek, "Automatic genre classification of music content: a survey," IEEE Signal Processing Magazine, vol. 23, no. 2, pp. 133-141, 2006.
[14] J. Mehta, D. Gandhi, G. Thakur, and P. Kanani, "Music Genre Classification using Transfer Learning on log-based MEL Spectrogram," in 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), IEEE, pp. 1101-1107, 2021.
[15] F. Yang, "Artificial intelligence in music education," in 2020 International Conference on Robots & Intelligent System (ICRIS), IEEE, pp. 483-484, 2020.
[16] M. A. Boden, "Creativity and artificial intelligence," Artificial intelligence, vol. 103, no. 1- 2, pp. 347-356, 1998.
[17] S. Colton, R. L. De Mantaras, and O. Stock, "Computational creativity: Coming of age," AI Magazine, vol. 30, no. 3, pp. 11-11, 2009.
[18] C. Roads, "Artificial intelligence and music," Computer Music Journal, vol. 4, no. 2, pp. 13-25, 1980.
[19] C. Roads, "Artificial intelligence and music,"Computer Music Journal, vol. 4, no. 2, pp. 13-25, 1980.
[20] A. C. Ashton, "Electronics, music and computers," University of Utah Salt Lake City, 1970.
[21] C. Roads, "Research in music and artificial intelligence," ACM Computing Surveys (CSUR), vol. 17, no. 2, pp. 163-190, 1985.
[22] A. Khan, A. Sohail, U. Zahoora, and A. S. Qureshi, "A survey of the recent architectures of deep convolutional neural networks," Artificial intelligence review, vol. 53, no. 8, pp. 5455-5516, 2020.
[23] E. W. Weisstein, "Convolution," https://mathworld. wolfram. com/, 2003.
[24] MK Gurucharan. "Basic cnn architecture: Explaining 5 layers of convolutional neural network." 2022
[25] AISmartz. "CNNs architectures over a timeline (1998-2019)."
[26] Q. Zhou et al., "Cough recognition based on mel- spectrogram and convolutional neural network," Frontiers in Robotics and AI, p. 112, 2021.
[27] Sawan Rai."Music genres classification using deep learning techniques." 2021
[28] Dillon Ranwala. "The evolution of music and ai technology."https://wattai.github.io/blog/music_ai_evolution/ July 2020
[29] B. Caramiaux and M. Donnarumma, "Artificial intelligence in music and performance: a subjective art-research inquiry," in Handbook of Artificial Intelligence for Music: Springer, pp. 75-95, 2021.
[30] A. Koh, "Music for AI Reports: Dual Prospects in Music Production," 2018.
[31] M. Rohrmeier, "On Creativity, Music’s AI Completeness, and Four Challenges for Artificial Musical Creativity," Transactions of the International Society for Music Information Retrieval, vol. 5, no. 1, 2022.
[32] Ya Yue, "Note Detection in Music Teaching Based on Intelligent Bidirectional Recurrent Neural Network", Security and Communication Networks, vol. 2022, Article ID 8135583, 9 pages, 2022.
[33] Solanki, Arun & Pandey, Sachin. Music instrument recognition using deep convolutional neural networks. International Journal of Information Technology. 14, 2019