Database proposal for automatic classification of Brazilian musical genres
DOI:
https://doi.org/10.24208/rebecin.v8i.234Keywords:
Database; Music Genre Classification; Music Genres; Brazilian Music; Music Information RetrievalAbstract
Due to the amount of music currently available, classifying songs manually is an arduous task. In this sense, automatic music genre classification is a pertinent approach, helping to organize, search, retrieve and recommend music. Although there are traditional databases related to the music genre classification, these databases only considered traditional genres, such as Jazz and Classical Music. Also, they ignore regional genres, such as those of Brazilian culture, for example. Thus, the objective of this study is to present a database for the automatic Brazilian music genres classification. For that, we used Spotify to identify music related to the genres Axé, Bossa Nova, Brega, Choro, Forró, Frevo, Funk Carioca, Maracatu, Música Sertaneja, Pagode, and Samba. As a result, we developed a database with 1,907 records related to these genres, and compared this database with six other databases, identifying that the proposed base exceeds four bases in the number of records and consists of the most comprehensive about the total number of records genders considered. Finally, we provide the basis for further studies and encourage its application in research involving Data Mining and Deep Learning.
Downloads
References
AGUIAR, R. L.; COSTA, Y. M. G.; SILLA JR., C. N. Exploring data augmentation to improve music genre classification with ConvNets. In: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 29., 2018, Rio de Janeiro. Proceedings [...] . Rio de Janeiro: IEEE, 2018, p. 1-8. Disponível em: https://doi.org/10.1109/IJCNN.2018.8489166. Acesso em: 17 mar. 2021.
FURINI, M. automatic music playlist generation based on music-programming of FM radios. In: ANNUAL CONSUMER COMMUNICATIONS & NETWORKING CONFERENCE (CCNC), 18., 2021, Las Vegas. Proceedings [...] . Las Vegas: IEEE, 2021, p. 1-4. Disponível em: https://doi.org/10.1109/CCNC49032.2021.9369526. Acesso em: 18 mar. 2021.
GOULART, A. J. H. et al. Music genre classification based on entropy and fractal lacunarity. In: IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA, 14., 2011, Dana Point. Proceedings [...] . Dana Point: IEEE, 2011, p. 533-536. Disponível em: https://doi.org/10.1109/ISM.2011.94. Acesso em: 19 mar. 2021.
HOMBURG, H. et al. A benchmark dataset for audio classification and clustering. In: INTERNATIONAL SOCIETY FOR MUSIC INFORMATION RETRIEVAL CONFERENCE, 6., 2005, Londres. Proceedings [...] . Londres: ISMIR, 2005, p. 528-531. Disponível em: https://archives.ismir.net/ismir2005/paper/000117.pdf. Acesso em: 17 mar. 2021.
LI, T.; OGIHARA, M.; LI, Q. A comparative study on content-based music genre classification. In: ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMAION RETRIEVAL, 26., 2003, Toronto. Proceedings [...] . Toronto: ACM, 2003, p. 282-289. Disponível em: https://doi.org/10.1145/860435.860487. Acesso em: 18 mar. 2021.
LIU, C. et al. Bottom-up broadcast neural network for music genre classification. Multimedia Tools and Applications, v. 80, n. 5, p. 7313-7331, fev. 2021. Disponível em: https://doi.org/10.1007/s11042-020-09643-6. Acesso em: 17 mar. 2021.
MCKKAY, C.; MCENNIS, D.; FUJINAGA, I. A large publicly accessible prototype audio database for music research. In: INTERNATIONAL SOCIETY FOR MUSIC INFORMATION RETRIEVAL CONFERENCE, 7., 2006, Victoria. Proceedings [...] . Victoria: ISMIR, 2006, p. 1-4. Disponível em: http://www.music.mcgill.ca/~cmckay/NEMA/publications/ISMIR_2006_Codaich_jMusicMetaManager.pdf. Acesso em: 17 mar. 2021.
PEREIRA, R. M.; SILLA JR., C.N. Using simplified chords sequences to classify songs genres. In: IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND Expo (ICME), 18., 2017, Hong Kong. Proceedings [...] . Hong Kong: IEEE, 2017, p. 1446-1451. Disponível em: https://doi.org/10.1109/ICME.2017.8019531. Acesso em: 18 mar. 2021.
SANTANA, I. A. P. et al. Music4All: a new music database and its applications. In: INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING (IWSSIP), 27., 2020, Niterói. Proceedings [...] . Niterói: IEEE, 2020, p. 399-404. Disponível em: https://doi.org/10.1109/IWSSIP48289.2020.9145170. Acesso em: 18 mar. 2021.
SILLA JR., C. N.; KOERICH, A. L.; KAESTNER, C. A.A. The latin music database. In: INTERNATIONAL CONFERENCE ON MUSIC INFORMATION RETRIEVAL, 9., 2008. Filadélfia. Proceedings [...] . Filadélfia: ISMIR, 2008. p. 451-456. Disponível em: https://archives.ismir.net/ismir2008/paper/000106.pdf. Acesso em: 17 mar. 2021.
SIMAS FILHO, E. F.; BORGES J.R., E. A.; FERNANDES JR., A. C.L. Genre classification for brazilian music using independent and discriminant features. Journal of Communication and Information Systems, v. 33, n. 1, maio 2018. Disponível em: https://jcis.emnuvens.com.br/jcis/article/view/515. Acesso em: 17 mar. 2021.
SOUSA, J. M.; PEREIRA, E. T.; VELOSO, L. R. A robust music genre classification approach for global and regional music datasets evaluation. In: IEEE INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING (DSP), 21., 2016, Pequim. Proceedings [...] . Pequim: IEEE, 2016. p. 109-113. Disponível em: https://doi.org/10.1109/ICDSP.2016.7868526. Acesso em: 18 mar. 2021.
TZANETAKIS, G.; COOK, P. Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing, v. 10, n. 5, p. 293-302, nov. 2002. Disponível em: https://doi.org/10.1109/TSA.2002.800560. Acesso em: 17 mar. 2021.
VISHNUPRIYA, S.; MEENAKSHI, K. Automatic music genre classification using Convolution Neural Network. In: INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND INFORMATICS (ICCCI), 7., 2018, Coimbatore. Proceedings [...] . Coimbatore: IEEE, 2018. p. 1-4. Disponível em: https://doi.org/10.1109/ICCCI.2018.8441340. Acesso em: 17 mar. 2021.
VÖLKEL, T. et al. Automatic genre classification of Latin American music using characteristic rhythmic patterns. In: AUDIO MOSTLY CONFERENCE: A CONFERENCE ON INTERACTION WITH SOUND, 5., 2010, Piteå. Proceedings [...] . Piteå: ACM, 2010. p. 1-7. Disponível em: https://doi.org/10.1145/1859799.1859815. Acesso em: 19 mar. 2021.
YANG, R. et al. Parallel recurrent convolutional neural networks-based music genre classification method for mobile devices. IEEE Access, v. 8, p. 19629-19637, jan. 2020. Disponível em: https://doi.org/10.1109/ACCESS.2020.2968170. Acesso em: 17 mar. 2021.
YU, Y. et al. Deep attention based music genre classification. Neurocomputing, v. 372, p. 84-91, jan. 2020. Disponível em: https://doi.org/10.1016/j.neucom.2019.09.054. Acesso em: 17 mar. 2021.
Published
How to Cite
Issue
Section
License
A REBECIN adota a licença Creative Commons CC-BY 4.0 (https://creativecommons.org/licenses/by/4.0/deed.pt_BR) , a qual permite:
- Compartilhar— copiar e redistribuir o material em qualquer suporte ou formato
- Adaptar— remixar, transformar, e criar a partir do material para qualquer fim, mesmo que comercial.
A REBECIN considera que o autor detém o direito autoral sobre sua produção, porém o autor deve concordar em ceder à revista o direito à primeira publicação. Além disso, o autor deve concordar que:
- em quaisquer publicações em repositórios institucionais, capítulos de livro ou outras produções decorrentes de trabalhos publicados na REBECIN, devem ser dados os devidos créditos à publicação inicial.
- estão autorizados a publicar e distribuir seu trabalho online (ex.: em repositórios institucionais ou na sua página pessoal) a qualquer momento antes ou durante o processo editorial, já que isso pode gerar alterações produtivas, bem como aumentar o impacto e a citação do trabalho publicado pela REBECIN.
Licenciada por 