SONBRA: uma base de dados para a classificação automática de gêneros brasileiros
Resumo
Este trabalho apresenta o SONBRA, um modelo de classificação automática dos gêneros musicais Bossa Nova, Forró, Forró Piseiro, Pagode, Samba, Samba-Enredo e Sertanejo. Para isso, criou-se uma base de dados musical contendo 10000 fragmentos de faixas musicais de 30s com 785 parâmetros das seguintes características extraídas: Chroma CENS, Chroma CQT, Chroma STFT, Fourier Tempograma, Mel-espectrograma, MFCC, RMS, Spectral Bandwith, Spectral Centroid, Spectral Roll-Off, Tempograma, Tonnetz e ZCR. A partir de cada faixa musical retirou-se fragmentos de 30s do início, meio, fim, do meio ao início e do meio ao final. Foram realizados testes com os modelos computacionais Decision Tree, KNN, MLP, Random Forest, SVM, XGBoost e um ensemble, mais especificamente um sistema de Voting. O Voting obteve o melhor desempenho com 83,2% de acurácia, enquanto o pior foi do Decision Tree com 62,7%. E as características que melhor geraram resultados foram combinações entre MFCC, Mel, Tempograma e Chroma CENS.
Palavras-chave:
aprendizado de máquina, recuperação de informação musical, classificação de gêneros musical
Referências
João Fortunato Soares de Quadros Júnior. Música Brasileira. PPGCOM/UFMG, Belo Horizonte, 2019.
Santosh Shirol and R S Kathiresan. A comprehensive survey of music genre classification using audio files. International Journal of Enhanced Research in Science, Technology & Engineering, 12:183–192, jun. 2023.
Júlia Conceição, Rosiane Freitas, Bruno Gadelha, Joao Kienen, Sergio Anders, and Brendo Cavalcante. Applying supervised learning techniques to brazilian music genre classification. 2020 XLVI Latin American Computing Conference (CLEI), pages 102–107, 10 2020.
Nacer Farajzadeh, Nima Sadeghzadeh, and Mahdi Hashemzadeh. Pmg-net: Persian music genre classification using deep neural networks. Entertainment Computing, 44:100518, 2023.
Douglas Silva and Cláudio Gomes. Modelo de aprendizado de máquina para classificação de gêneros musicais populares da região amazônica legal internacional. Revista Eletrônica de Iniciação Científica em Computação, 20(4), dez. 2022.
Carlos Nascimento Silla, Jr., Alessandro L. Koerich, and Celso A. A. Kaestner. The latin music database. In Proceedings of the 9th International Conference on Music Information Retrieval, pages 451–456, Philadelphia, 2018. ISMIR.
G. Tzanetakis and P. Cook. Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing, 10(5):293–302, 2002.
Michaël Deferrard, Kirell Benzi, Pierre Vandergheynst, and Xavier Bresson. Fma: A dataset for music analysis, 2017.
Khan Md. Hasib, Anika Tanzim, Jungpil Shin, Kazi Omar Faruk, Jubayer Al Mahmud, and M. F. Mridha. Bmnet-5: A novel approach of neural network to classify the genre of bengali music based on audio features. IEEE Access, 10:108545–108563, 2022.
Md. Afif Al Mamun, Imamul Kadir, AKM Shahariar Azad Rabby, and Abdullah Al Azmi. Bangla music genre classification using neural network. In 2019 8th International Conference System Modeling and Advancement in Research Trends (SMART), pages 397–403, 2019.
Júlia Bezerra. Funk: a batida dos bailes cariocas que contagiou o Brasil. Panda Books, São Paulo, 1 edition, 2017.
Lucina Reitenbach Viana. O funk no brasil: Música desintermediada na cibercultura. In Revista Sonora, Unicamp, volume 3, 2010.
Ivan Dias and Sandrinho Dupan. O que é o Forró? Meroveu, Campina Grande, 3 edition, 2022.
Gustavo Alonso. Cowboys do Asfalto. Doutorado em história, Programa de Pós-Graduação em História, Universidade Federal Fluminense, Niterói, 2011.
Waldenyr Caldas. O que é a música sertaneja? Brasiliense, São Paulo, 1987.
Meinard Müller. Fundamentals of Music Processing: Audio, Analysis, Algorithms, Applications. Springer, Cham, 1 edition, 2015.
Anssi Klapuri and Manuel Davy, editors. Signal Processing Methods for Music Transcription. Springer, New York, 2006.
Meinard Müller and Stefan Balke. Short-Time Fourier Transform and Chroma Features. International Audio Laboratories Erlangen, 2018.
Garima Sharma, Kartikeyan Umapathy, and Sridhar Krishnan. Trends in audio signal feature extraction methods. Applied Acoustics, 161:107201, 2020.
Christopher Harte, Mark Sandler, and Martin Gasser. Detecting harmonic change in musical audio. In Proceedings of the 1st ACM Workshop on Audio and Music Computing Multimedia, page 21–26, New York, 2006. Association for Computing Machinery.
Shan Suthaharan. Machine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning. Springer US, 2016.
Sotiris Kotsiantis, I. Zaharakis, and P. Pintelas. Machine learning: A review of classification and combining techniques. Artificial Intelligence Review, 26:159–190, 11 2006.
N. Scaringella, G. Zoia, and D. Mlynek. Automatic genre classification of music content: a survey. IEEE Signal Processing Magazine, 23(2):133–141, 2006.
Aurélien Géron. Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow. O’Reilly, Sebastopol, 2 edition, 2019.
Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, page 785–794, Nova York, 2016. Association for Computing Machinery.
Santosh Shirol and R S Kathiresan. A comprehensive survey of music genre classification using audio files. International Journal of Enhanced Research in Science, Technology & Engineering, 12:183–192, jun. 2023.
Júlia Conceição, Rosiane Freitas, Bruno Gadelha, Joao Kienen, Sergio Anders, and Brendo Cavalcante. Applying supervised learning techniques to brazilian music genre classification. 2020 XLVI Latin American Computing Conference (CLEI), pages 102–107, 10 2020.
Nacer Farajzadeh, Nima Sadeghzadeh, and Mahdi Hashemzadeh. Pmg-net: Persian music genre classification using deep neural networks. Entertainment Computing, 44:100518, 2023.
Douglas Silva and Cláudio Gomes. Modelo de aprendizado de máquina para classificação de gêneros musicais populares da região amazônica legal internacional. Revista Eletrônica de Iniciação Científica em Computação, 20(4), dez. 2022.
Carlos Nascimento Silla, Jr., Alessandro L. Koerich, and Celso A. A. Kaestner. The latin music database. In Proceedings of the 9th International Conference on Music Information Retrieval, pages 451–456, Philadelphia, 2018. ISMIR.
G. Tzanetakis and P. Cook. Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing, 10(5):293–302, 2002.
Michaël Deferrard, Kirell Benzi, Pierre Vandergheynst, and Xavier Bresson. Fma: A dataset for music analysis, 2017.
Khan Md. Hasib, Anika Tanzim, Jungpil Shin, Kazi Omar Faruk, Jubayer Al Mahmud, and M. F. Mridha. Bmnet-5: A novel approach of neural network to classify the genre of bengali music based on audio features. IEEE Access, 10:108545–108563, 2022.
Md. Afif Al Mamun, Imamul Kadir, AKM Shahariar Azad Rabby, and Abdullah Al Azmi. Bangla music genre classification using neural network. In 2019 8th International Conference System Modeling and Advancement in Research Trends (SMART), pages 397–403, 2019.
Júlia Bezerra. Funk: a batida dos bailes cariocas que contagiou o Brasil. Panda Books, São Paulo, 1 edition, 2017.
Lucina Reitenbach Viana. O funk no brasil: Música desintermediada na cibercultura. In Revista Sonora, Unicamp, volume 3, 2010.
Ivan Dias and Sandrinho Dupan. O que é o Forró? Meroveu, Campina Grande, 3 edition, 2022.
Gustavo Alonso. Cowboys do Asfalto. Doutorado em história, Programa de Pós-Graduação em História, Universidade Federal Fluminense, Niterói, 2011.
Waldenyr Caldas. O que é a música sertaneja? Brasiliense, São Paulo, 1987.
Meinard Müller. Fundamentals of Music Processing: Audio, Analysis, Algorithms, Applications. Springer, Cham, 1 edition, 2015.
Anssi Klapuri and Manuel Davy, editors. Signal Processing Methods for Music Transcription. Springer, New York, 2006.
Meinard Müller and Stefan Balke. Short-Time Fourier Transform and Chroma Features. International Audio Laboratories Erlangen, 2018.
Garima Sharma, Kartikeyan Umapathy, and Sridhar Krishnan. Trends in audio signal feature extraction methods. Applied Acoustics, 161:107201, 2020.
Christopher Harte, Mark Sandler, and Martin Gasser. Detecting harmonic change in musical audio. In Proceedings of the 1st ACM Workshop on Audio and Music Computing Multimedia, page 21–26, New York, 2006. Association for Computing Machinery.
Shan Suthaharan. Machine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning. Springer US, 2016.
Sotiris Kotsiantis, I. Zaharakis, and P. Pintelas. Machine learning: A review of classification and combining techniques. Artificial Intelligence Review, 26:159–190, 11 2006.
N. Scaringella, G. Zoia, and D. Mlynek. Automatic genre classification of music content: a survey. IEEE Signal Processing Magazine, 23(2):133–141, 2006.
Aurélien Géron. Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow. O’Reilly, Sebastopol, 2 edition, 2019.
Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, page 785–794, Nova York, 2016. Association for Computing Machinery.
Publicado
15/09/2025
Como Citar
SANTANA, João Marcos de Oliveira; AMORIM, Anderson Vinícius Ribeiro; OLIVEIRA, Marcos Abreu de; GOMES, Cláudio.
SONBRA: uma base de dados para a classificação automática de gêneros brasileiros. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO MUSICAL (SBCM), 19. , 2025, Campinas/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 54-58.
DOI: https://doi.org/10.5753/sbcm_estendido.2025.14801.
