Reduced Convolutional Recurrent Neural Network Using MFCC for Music Genre Classification on the GTZAN Dataset

Ela Setiorini, Moeljono Widjaja, Arya Wicaksana

Abstract


This study presents a reduced Convolutional Recurrent Neural Network (CRNN) model for music genre classification, leveraging the GTZAN dataset and Mel-Frequency Cepstral Coefficient (MFCC) feature extraction. Unlike more complex architectures, this model simplifies the CRNN structure to three convolutional layers and two BiLSTM layers, maintaining competitive performance while reducing computational complexity. Key experimental parameters included learning rate tuning (0.1, 0.01, 0.001, and 0.0001) and dropout usage (30% before the BiLSTM layers) to mitigate overfitting. The best configuration, utilizing a learning rate of 0.001 and dropout, achieved an accuracy of 88.64%, outperforming more complex CRNN models by approximately 15%. These results underscore the potential of streamlined architectures in music information retrieval tasks, particularly for applications where computational resources are constrained. Future work will address overfitting issues and refine the dataset for enhanced model performance.

Full Text:

PDF

References


Aritonang, P.A., Johan, M.E. and Prasetiawan, I. 2022. Aspect-Based Sentiment Analysis on Application Review using CNN (Case Study : Peduli Lindungi Application). Ultima Infosys : Jurnal Ilmu Sistem Informasi. 13, 1 (2022), 54–61.

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. Applied Sciences (Switzerland). 13, 3 (2023). DOI:https://doi.org/10.3390/app13031476.

Ghosh, P., Mahapatra, S., Jana, S. and Kr. Jha, R. 2023. A Study on Music Genre Classification using Machine Learning. International Journal of Engineering Business and Social Science. 1, 04 (2023), 308–320. DOI:https://doi.org/10.58451/ijebss.v1i04.55.

Heriyanto, H., Wahyuningrum, T. and Fitriana, G.F. 2021. Classification of Javanese Script Hanacara Voice Using Mel Frequency Cepstral Coefficient MFCC and Selection of Dominant Weight Features. Jurnal Infotel. 13, 2 (2021), 84–93. DOI:https://doi.org/10.20895/infotel.v13i2.657.

Katrompas, A. and Metsis, V. 2022. Enhancing LSTM Models with Self-attention and Stateful Training. Lecture Notes in Networks and Systems (2022), 217–235.

Kumar, M.K., Sujanasri, K., Neha, B., Akshara, G., Chugh, P. and Haindavi, P. 2023. Automated Music Genre Classification through Deep Learning Techniques. E3S Web of Conferences. 430, (2023). DOI:https://doi.org/10.1051/e3sconf/202343001033.

Luo, X. 2023. Automatic Music Genre Classification based on CNN and LSTM. Highlights in Science, Engineering and Technology. 39, (2023), 61–66. DOI:https://doi.org/10.54097/hset.v39i.6494.

McFee, B., Raffel, C., Liang, D., Ellis, D., McVicar, M., Battenberg, E. and Nieto, O. 2015. librosa: Audio and Music Signal Analysis in Python. Proceedings of the 14th Python in Science Conference. August 2020 (2015), 18–24. DOI:https://doi.org/10.25080/majora-7b98e3ed-003.

Mendes, J. 2020. Deep Learning Techniques for Music Genre Classification and Building a Music Recommendation System. National College of Ireland.

Prayogo, K.A., Suryadibrata, A. and Young, J.C. 2020. Classification of pneumonia from X-ray images using siamese convolutional network. Telkomnika (Telecommunication Computing Electronics and Control). 18, 3 (2020), 1302–1309. DOI:https://doi.org/10.12928/TELKOMNIKA.v18i3.14751.

Sang, J., Park, S. and Lee, J. 2018. Convolutional recurrent neural networks for urban sound classification using raw waveforms. European Signal Processing Conference. 2018-Septe, (2018), 2444–2448. DOI:https://doi.org/10.23919/EUSIPCO.2018.8553247.

Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R. 2014. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research. 15, (2014), 1929–1958.

Stefani, D. and Turchet, L. 2022. On the Challenges of Embedded Real-time Music Information Retrieval. Proceedings of the International Conference on Digital Audio Effects, DAFx (2022), 177–184.

Tzanetakis, G. and Cook, P. MARSYAS: A framework for audio analysis.

Tzanetakis, G. and Cook, P. 2002. Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing. 10, 5 (2002), 293–302. DOI:https://doi.org/10.1109/TSA.2002.800560.

Wibawa, I.D.G.Y.A. and Darmawan, I.D.M.B.A. 2021.

Implementation of audio recognition using mel frequency cepstrum coefficient and dynamic time warping in wirama praharsini. Journal of Physics: Conference Series. 1722, 1 (2021). DOI:https://doi.org/10.1088/1742-6596/1722/1/012014.

Yamashita, R., Nishio, M., Kinh, R., Do, G. and Togashi, K. 2018. Convolutional neural networks : an overview and application in radiology. (2018), 611–629.

Yehezkiel, S.Y. and Suyanto, Y. 2022. Music Genre Identification Using SVM and MFCC Feature Extraction. IJEIS (Indonesian Journal of Electronics and Instrumentation Systems). 12, 2 (2022), 115. DOI:https://doi.org/10.22146/ijeis.70898.




DOI: https://doi.org/10.31449/inf.v49i17.6885

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.