Music Genre Classification Using Adam Algorithm of Convolutional Neural Network
DOI:
https://doi.org/10.21108/ijoict.v10i2.978Keywords:
Music Information Retrieval, music genre, Python; music classification, neural, Machine Learning, audio file, Adam optimizer, training processAbstract
Even though technology has been evolving rapidly lately, music classification is still definitely a major task in the Music Information Retrieval (MIR) domain. Music genre classification is a key challenge in Music Information Retrieval (MIR), aiming to identify the genre, style, and mood of audio tracks. This study explores the use of Convolutional Neural Networks (CNNs) with the Adam optimizer for music genre classification. We conducted experiments to evaluate the performance of our proposed model, which incorporates advanced machine learning techniques to improve classification accuracy. Our approach involves extracting features from audio files, converting them into Mel spectrograms, and training the CNN model using Python. The results demonstrate a high classification accuracy of 98.5%, significantly improving upon previous methods. Additionally, GPU acceleration enhanced the training speed by five times. Future work includes developing a mobile application for real-time classification and exploring integration with speech recognition technologies
Downloads
References
[1] G. Tzanetakis, P. Cook, “Musical genre classification of audio signals”, https://ieeexplore.ieee.org/abstract/document/1021072, 07 November 2002.
[2] J. Saunders, “Real time discrimination of broadcast speech/music,” inProc. Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), 1996,pp. 993–996
[3] F. Pachet and D. Cazaly, “A classification of musical genre,” in Proc.RIAO Content-Based Multimedia Information Access Conf., Paris,France, Mar. 2000
[4] N. Scaringella, G. Zoia, D. Mlynek, “Automatic genre classification of music content: a survey”, https://ieeexplore.ieee.org/abstract/document/1598089, 24 April 2006.
[5] Hiroki Nakamura, Hung-Hsuan Huang, Kyoji Kawagoe, “Detecting Musical Genre Borders for Multi-label Genre Classification”, https://ieeexplore.ieee.org/document/6746860, 24 February 2014.
[6] Ali Karatana, Oktay Yildiz, “Music genre classification with machine learning techniques”, https://ieeexplore.ieee.org/document/7960694, 29 June 2017.
[7] Chandanpreet Kaur, Ravi Kumar, “Study and analysis of feature based automatic music genre classification using Gaussian mixture model”, https://ieeexplore.ieee.org/document/8365395, 28 May 2018.
[8] R. Duda, P. Hart, and D. Stork, Pattern Classification. New York:Wiley, 2000
[9] D. Perrot and R. Gjerdigen, “Scanning the dial: An exploration of fac-tors in identification of musical style,” in Proc. Soc. Music PerceptionCognition, 1999, p. 88, (abstract).
[10] D. Pye, “Content-based methods for the management of digital music,”in Proc. Int. Conf Acoustics, Speech, Signal Processing (ICASSP), 2000.
[11] Y. He, H. Chen, D. Liu, and L. Zhang, “A Framework of Structural Damage Detection for Civil Structures Using Fast Fourier Transform and Deep Convolutional Neural Networks,” Appl. Sci., vol. 11, no. 19, p. 9345, Oct. 2021, doi: 10.3390/app11199345.
[12] E. Rajaby and S. M. Sayedi, “A structured review of sparse fast Fourier transform algorithms,” Digit. Signal Process., vol. 123, p. 103403, Apr. 2022, doi: 10.1016/j.dsp.2022.103403.
[13] A. Ustubioglu, B. Ustubioglu, and G. Ulutas, “Mel spectrogram-based audio forgery detection using CNN,” Signal Image Video Process., vol. 17, no. 5, pp. 2211–2219, Jul. 2023, doi: 10.1007/s11760-022-02436-4.
[14] C. Jiang and G. Goldsztein, “Convolutional Neural Network Approach to Classifying the CIFAR-10 Dataset: How can supervised machine learning be applied as a technique on a convolutional neural network to solve the image classification problem of recognizing and classifying images in the CIFAR-10 dataset?,” J. Stud. Res., vol. 12, no. 2, May 2023, doi: 10.47611/jsrhs.v12i2.4388.
[15] College of Electrical & Information Engineering, Southwest Minzu University, Chengdu 610041, China and X. Lv, “CIFAR-10 Image Classification Based on Convolutional Neural Network,” Front. Signal Process., vol. 4, no. 4, Oct. 2020, doi: 10.22606/fsp.2020.44004.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Manuscript submitted to IJoICT has to be an original work of the author(s), contains no element of plagiarism, and has never been published or is not being considered for publication in other journals. Author(s) shall agree to assign all copyright of published article to IJoICT. Requests related to future re-use and re-publication of major or substantial parts of the article must be consulted with the editors of IJoICT.
.png)
.jpg)
