Abstract
Most of the studies on music genre classification are focused on classification quality only. However, listeners and musicologists would favor comprehensible models, which describe semantic properties of genres like instrument or chord statistics, instead of complex black-box transforms of signal features either manually engineered or learned by neural networks. Fuzzy rules – until now not a widely applied method in music classification – offer the advantage of understandability for end users, in particular in combination with carefully designed semantic features. In this work, we tune and compare three approaches which operate on fuzzy rules: a complete search of primitive rules, an evolutionary approach, and fuzzy pattern trees. Additionally, we include random forest classifier as a baseline. The experiments were conducted on an artist-filtered subset of the 1517-Artists database, for which 245 semantic properties describing instruments, moods, singing style, melody, harmony, influence on listener, and effects were extracted to train the classification models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
http://www.seyerlehner.info. Last accessed on 08.11.2019.
References
Berlanga, F.J., del Jesus, M.J., Gacto, M.J., Herrera, F.: A genetic-programming-based approach for the learning of compact fuzzy rule-based classification systems. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Żurada, J.M. (eds.) ICAISC 2006. LNCS (LNAI), vol. 4029, pp. 182–191. Springer, Heidelberg (2006). https://doi.org/10.1007/11785231_20
Breiman, L.: Random forests. Mach. Learn. J. 45(1), 5–32 (2001)
Fernández, F., Chávez, F.: Fuzzy rule based system ensemble for music genre classification. In: Machado, P., Romero, J., Carballal, A. (eds.) EvoMUSART 2012. LNCS, vol. 7247, pp. 84–95. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-29142-5_8
Fernández, F., Chávez, F., Alcalá, R., Herrera, F.: Musical genre classification by means of fuzzy rule-based systems: a preliminary approach. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 2571–2577 (2011)
Hoffmann, F.: Combining boosting and evolutionary algorithms for learning of fuzzy classification rules. Fuzzy Sets Syst. 141, 47–58 (2004). https://doi.org/10.1016/S0165-0114(03)00113-1
Huang, Z., Gedeon, T.D., Nikravesh, M.: Pattern trees induction: a new machine learning method. IEEE Trans. Fuzzy Syst. 16(4), 958–970 (2008). https://doi.org/10.1109/TFUZZ.2008.924348
Kostek, B., Kaczmarek, A.: Music recommendation based on multidimensional description and similarity measures. Fundam. Inform. 127(1–4), 325–340 (2013)
Linden, R., Bhaya, A.: Evolving fuzzy rules to model gene expression. Biosystems 88(1), 76–91 (2007). https://doi.org/10.1016/j.biosystems.2006.04.006
Salamon, J., Rocha, B., Gómez, E.: Musical genre classification using melody features extracted from polyphonic music signals. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 81–84 (2012). https://doi.org/10.1109/ICASSP.2012.6287822
Senge, R., Hüllermeier, E.: Top-down induction of fuzzy pattern trees. IEEE Trans. Fuzzy Syst. 19(2), 241–252 (2011). https://doi.org/10.1109/TFUZZ.2010.2093532
Senge, R., Hüllermeier, E.: Fast fuzzy pattern tree learning for classification. IEEE Trans. Fuzzy Syst. 23(6), 2024–2033 (2015). https://doi.org/10.1109/TFUZZ.2015.2396078
Vatolkin, I.: Improving supervised music classification by means of multi-objective evolutionary feature selection. Ph.D. thesis, Department of Computer Science, TU Dortmund (2013)
Vatolkin, I., Rudolph, G.: Interpretable music categorisation based on fuzzy rules and high-level audio features. In: Lausen, B., Krolak-Schwerdt, S., Böhmer, M. (eds.) Data Science, Learning by Latent Structures, and Knowledge Discovery. SCDAKO, pp. 423–432. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-44983-7_37
Yang, Y.H., Liu, C.C., Chen, H.H.: Music emotion classification: a fuzzy approach. In: Proceedings of the 14th ACM International Conference on Multimedia, pp. 81–84 (2006)
Zadeh, L.A.: Fuzzy sets. Inf. Control 8(3), 338–353 (1965). https://doi.org/10.1016/S0019-9958(65)90241-X
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Heerde, F., Vatolkin, I., Rudolph, G. (2020). Comparing Fuzzy Rule Based Approaches for Music Genre Classification. In: Romero, J., Ekárt, A., Martins, T., Correia, J. (eds) Artificial Intelligence in Music, Sound, Art and Design. EvoMUSART 2020. Lecture Notes in Computer Science(), vol 12103. Springer, Cham. https://doi.org/10.1007/978-3-030-43859-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-43859-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-43858-6
Online ISBN: 978-3-030-43859-3
eBook Packages: Computer ScienceComputer Science (R0)