Deep Learning Approach for Music Genre Classification using Multi-Feature Audio Representations

Nurul Asanah, Irfan Pratama

Abstract


Automatic music genre classification is critical for enhancing user experience in streaming platforms and recommendation systems. This study proposes a Convolutional Neural Network (CNN)-based approach using the GTZAN dataset, which contains ten music genres. The original 30-second audio tracks were segmented into overlapping 3-second chunks, then preprocessed and converted into three feature representations: Mel-Spectrogram, Chroma, and Spectral Contrast. CNN model consisting of four convolutional layers with increasing filters (32–256). The model was trained over 13 epochs using the Adam optimizer. The proposed model achieved 91% accuracy, outperforming previous approaches based on single-feature extraction. The integration of diverse spectral and harmonic features enabled the model to better distinguish between similar genres and improved its generalization. This method offers practical value for real-time music classification, automatic tagging, and intelligent audio indexing in music streaming services and digital libraries.

Keywords


Audio Features; Chroma; CNN; Melspectogram; Music Information Retrieval; Spectral Contrast

Full Text:

PDF

References


X. Guo, “The Evolution of the Music Industry in the Digital Age: From Records to Streaming,” Journal of Sociology and Ethnology, Vol. 5, No. 10, 2023, doi: 10.23977/jsoce.2023.051002.

“Hasil Pencarian - KBBI VI Daring.” Accessed: Apr. 25, 2025. [Online]. Available: https://kbbi.kemdikbud.go.id/entri/musik

A. S. Pratama, “Klasifikasi Genre Musik Populer menggunakan Metode Convolutional Neural Network dengan Data Augmentation,” 2021.

S. Palve, S. Dubey, M. Dhanait, N. Purswani, K. P. Birla 1234 Student, and K. K. Wagh, “Music Genre Classification using Convolutional Neural Networks (CNN),” International Journal of Research and Analytical Reviews, 2023, Accessed: May 06, 2025. [Online]. Available: www.ijrar.org

A. N. Ilyasa, “Pengembangan Aplikasi Klasifikasi Sepuluh Genre Musik,” KALBISIANA Jurnal Sains, Bisnis dan Teknologi, Vol. 10, No. 4, pp. 388–394, Dec. 2024, doi: 10.53008/KALBISIANA.V10I4.633.

M. N. Farid, ¶‚½í, A. F. Rahman, H. Wicaksono, and I. T. Kalimantan, “Analisis Pengaruh Kombinasi Fitur Spektral terhadap Tingkat Akurasi Speech Emotion Recognition,” Jurnal Sistim Informasi dan Teknologi, Vol. 5, No. 2, pp. 120–129, Jun. 2023, doi: 10.37034/JSISFOTEK.V5I2.234.

S. M. Fardhani, Y. Wihardi, and E. Piantari, “Klasifikasi Genre Musik dengan Mel Frequency Cepstral Coefficient dan Spektogram menggunakan Convolutional Neural Network,” Jurnal Aplikasi dan Teori Ilmu Komputer, Vol. 4, No. 1, pp. 26–34, 2021, doi: 10.17509/JATIKOM.V4I1.41465.

J. A. R, “Rancang Bangun Aplikasi Musicmoo dengan Metode Mir (Music Information Retrieval) pada Modul Mood, Genre Recognition, dan Tempo Estimation,” Institut Teknologi Sepuluh Nopember , Surabaya, 2017. Accessed: Apr. 27, 2025. [Online]. Available: https://repository.its.ac.id/3713/2/5113100021-Undergraduate-Theses.pdf

L. A. A. R. P. Putri, “Seleksi Fitur dalam Klasifikasi Genre Musik”, Accessed: Apr. 27, 2025. [Online]. Available: https://ojs.unud.ac.id/index.php/jik/article/view/39772/24169

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, Jul. 2002, doi: 10.1109/TSA.2002.800560.

K. Zaman, M. Sah, C. Direkoglu, and M. Unoki, “A Survey of Audio Classification using Deep Learning,” IEEE Access, Vol. 11, pp. 106620–106649, 2023, doi: 10.1109/ACCESS.2023.3318015.

Y. Cui and F. Wang, “Research on Audio Recognition based on the Deep Neural Network in Music Teaching,” Comput Intell Neurosci, Vol. 2022, 2022, doi: 10.1155/2022/7055624.

J. Dias, V. Pillai, H. Deshmukh, and A. Shah, “Music Genre Classification & Recommendation System using CNN,” SSRN Electronic Journal, Apr. 2022, doi: 10.2139/SSRN.4111849.

Y. V. Via, I. Y. Purbasari, and A. P. Pratama, “Analisa Algoritma Convolution Neural Network (CNN) pada Klasifikasi Genre Musik berdasar Durasi Waktu,” Scan : Jurnal Teknologi Informasi dan Komunikasi, Vol. 17, No. 1, pp. 35–41, Feb. 2022, doi: 10.33005/scan.v17i1.3251.

D. Joshi, J. Pareek, and P. Ambatkar, “Comparative Study of Mfcc and Mel Spectrogram for Raga Classification using CNN,” Indian J Sci Technol, Vol. 16, No. 11, pp. 816–822, Mar. 2023, doi: 10.17485/IJST/V16I11.1809.

F. Korzeniowski and G. Widmer, “Feature Learning For Chord Recognition: The Deep Chroma Extractor”, Accessed: May 06, 2025. [Online]. Available: https://rodrigob.github.io/are

C.-H. Lee, J.-L. Shih, K.-M. Yu, and J.-M. Su, “Automatic Music Genre Classification Using Modulation Spectral Contrast Feature”.

X. Li, F. Li, Z. P. Lu, and Z. yue Yang, “Music Genre Classification: A Comprehensive Study on Feature Fusion with CNN and MLP Architectures,” Applied and Computational Engineering, Vol. 132, No. 1, pp. 159–166, Jan. 2025, doi: 10.54254/2755-2721/2024.20632.

W. Zhang, W. Lei, X. Xu, and X. Xing, “Improved Music Genre Classification with Convolutional Neural Networks,” 2016, doi: 10.21437/Interspeech.2016-1236.




DOI: https://doi.org/10.32520/stmsi.v14i5.5369

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.