Machine learning model for classifying popular music genres from the international legal Amazon region
Keywords:
music information retrieval, machine learning, musical genres, data-set, computer musicAbstract
The musical preference of today’s society presents a continuous appreciation for international musical genres at the preconception of national or local ones. Music is one of the most used means of communication for the facilitation and ergonomics in the organization of the social structure, influencing the lifestyle, tastes and interpersonal coexistence. Several applications with musical concept within several tools use music classifiers. This current work presents a machine learning model of automatic classification of popular Amazonian music genres. Introducing the new version, the database contains the popular musical genres: andean, brega, carimb ́o, cumbia, merengue, pasillo, salsa and vaqueirada, from the region of the Legal Amazon International. The created database has 125 tracks for each rhythm with 788 parameters. These parameters were extracted in three temporal versions: beginning, middle and end of the song. For tests, the accuracy of the KNN, SVC, MLP and XGB models was analyzed, obtaining 57.58%, 56.79%, 61.33%, 61.17%, respectively. Concluding that the support vector machine (SVC) model presented the best robustness for the scenarios used.
Downloads
References
Aucouturier, J.-J. and Pachet, F. (2003). Representing musical genre: A state of the art. Journal of new music research, 32(1):83–93.
Bigliassi, M., Altimari, L. R., and Ito, W. M. (2013). Ritmos e estilos musicais: um estudo descritivo das preferências e percepções no exercício físico. Brazilian Journal of Biomotricity, 7(4):165–173.
Defferrard, M., Benzi, K., Vandergheynst, P., and Bresson, X. (2016). Fma: A dataset for music analysis. arXiv preprint arXiv:1612.01840.
Dim, C., Alves, L., and Sousa, P. (2019). Predição de gêneros musicais utilizando técnicas de aprendizado de máquina. In Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional, pages 344–352. SBC.
Fabbri, F. and Pinho, M. G. (2017). Uma teoria dos gêneros musicais: duas aplicações [tradução]. Revista Vórtex, 5(3).
Geleilate, J. M. G. and Marcelino, D. M. N. (2010). A influência de estilos musicais no humor, tempo percebido e decisão de retorno em loja de consumo popular. IV Encontro de Marketing da ANPAD.
Geron, A. (2019). Mãos à Obra: Aprendizado de Máquina com Scikit-Learn & TensorFlow. Alta Books.
Guggari, S., Kadappa, V., Umadevi, V., and Abraham, A. (2020). Music rhythm tree based partitioning approach to decision tree classifier. Journal of King Saud University Computer and Information Sciences.
Holzapfel, A., Sturm, B., and Coeckelbergh, M. (2018). Ethical dimensions of music information retrieval technology. Transactions of the International Society for Music Information Retrieval, 1(1):44–55.
Junior, J. S. J. (2021). Nem original, nem cópia: versões musicais entre o mainstream e a periferia. Números.
Karunakaran, N. and Arya, A. (2018). A scalable hybrid classifier for music genre classification using machine learning concepts and spark. In 2018 International Conference on Intelligent Autonomous Systems (ICoIAS), pages 128–135. IEEE.
Menezes Bastos, R. J. d. (2007). As contribuições da música popular brasileira às músicas populares do mundo: diálogos transatlânticos Brasil-Europa-África - Segunda parte. Universidade Federal de Santa Catarina.
Mondelli, M. L. B., Gadelha Jr, L. M., and Ziviani, A. (2018). O que os pa ́ıses escutam: Analisando a rede de gêneros musicais ao redor do mundo. In Anais do VII Brazilian Workshop on Social Network Analysis and Mining. SBC.
Schreibman, S., Siemens, R., and Unsworth, J. (2015). A new companion to digital humanities. John Wiley & Sons.
Silla Jr, C. N., Kaestner, C. A., and Koerich, A. L. (2007). Automatic music genre classification using ensemble of classifiers. In 2007 IEEE International Conference on Systems, Man and Cybernetics, pages 1687–1692. IEEE.
Silla Jr, C. N., Koerich, A. L., and Kaestner, C. A. (2008). The latin music database. In ISMIR, pages 451–456.
Sturm, B. L. (2013). The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future use. CoRR, abs/1306.1461.
Sturm, B. L. (2014). The state of the art ten years after a state of the art: Future research in music information retrieval. Journal of new music research, 43(2):147–172.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Os Autores
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
