Skip to main content
SpringerLink
Log in

Granular methods in automatic music genre classification: a case study

  • Published:
Journal of Intelligent Information Systems Aims and scope Submit manuscript

Abstract

Classification of music files by using the characteristics of the songs based on its genre is a very popular application of machine learning. The focus of this work is on automatic music genre classification based on granular computing methods (fuzzy rough, rough and near sets). We have proposed a modified form of supervised learning algorithm based on tolerance near sets (TCL 2.0) with a goal of exploring the scalability of the learning algorithm to a well researched music database composed of several genres. In the tolerance near set method, tolerance classes are directly induced from the dataset using the tolerance level ε and a distance function. We have compared the tolerance-based near set algorithm to a family of nearest neighbour (NN) algorithms based on fuzzy rough methods (FRNN) available in the WEKA platform. In terms of performance, the classification accuracy of TCL 2.0 is identical to the Bayesian Networks (BN) Algorithm, and comparable with the Sequential Minimal Optimization (SMO) Algorithm. However, the average classification accuracy of FRNN algorithms and the classical rough sets algorithm is better than TCL 2.0, BN and SMO algorithms. For this dataset, any accuracy over 90% is considered a very good classification accuracy which is achieved by all tested classifiers in this work.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Notes

  1. http://www.music-ir.org/mirex/wiki/2005

  2. http://www.ismir.net/

  3. http://www.hdfgroup.org/HDF5/

  4. https://labrosa.ee.columbia.edu/projects/musicsim/uspop2002.html

  5. http://mirg.city.ac.uk/codeapps/the-magnatagatune-dataset

  6. https://staff.aist.go.jp/m.goto/RWC-MDB/

  7. http://www.ismir.net/resources.html

  8. R.V. Hogg and E.A. Tanis, E.A: Probability and Statistical Inference. Macmillan Publishing Co., Inc., New York, 1977.

References

  • Alusaifeer, T., Ramanna, S., Henry, C. (2013). GPU implementation of MCE approach to finding near neighbourhoods. In Proceedings of the International Conference on Rough Sets and Knowledge Technology (RSKT2013), Lecture Notes in Computer Science (pp. 251–262): Springer.

  • Banerjee, S., Saha, M., Arun, I., Basak, B., Agarwal, S., Ahmed, R., Chatterjee, S., Mahanta, L. B., Chakraborty, C. (2017). Near-set based mucin segmentation in histopathology images for detecting mucinous carcinoma. Journal of Medical Systems, 41, 144 (2017). https://doi.org/10.1007/s10916-017-0792-6.

  • Barbosa, J., McKay, C., Fujinaga, I. (2015). Evaluating automated classification techniques for folk music genres from the brazilian northeast. In Proceedings of 15th Brazilian symposium on computer music, XV (pp. 1–12).

  • Basili, R., Serafini, A., Stellato, A. (2004). Classification of musical genre: a machine learning approach. In 5th International Society for Music Information Retrieval Conference (ISMIR-2004) (pp. 268–281).

  • Bazan, J. G., & Szczuka, M. (2005). The Rough Set Exploration System. Springer Transactions on Rough Sets III, LNCS 3400, 37–56.

    Article  MATH  Google Scholar 

  • Chang, K. K., Jang, J. S. R., Iliopoulos, C. S. (2010). Music genre classification via compressive sampling. In 11th International Society for Music Information Retrieval Conference (ISMIR-2010) (pp. 387–392).

  • Choi, K., Fazekas, G., Cho, K., Sandler, M. (2017). On the robustness of deep convolutional neural networks for music classification. arXiv:1706.02361.

  • Cornelis, C., Cock, M. D., Radzikowska, A. M. (2007). Vaguely quantified rough sets. In An, A., Stefanowski, J., Ramanna, S., Butz, C. J., Pedrycz, W., Wang, G. (Eds.) Rough Sets, Fuzzy Sets, Data Mining and Granular Computing: 11th International Conference, RSFDGrC 2007, Toronto, Canada, May 14-16, 2007. Proceedings (pp. 87–94). Berlin: Springer.

  • Cornelis, C., De Cock, M., Radzikowska, A. M. (2008). Fuzzy Rough Sets: From Theory into Practice, (pp. 533–552). Hoboken: Wiley.

    Google Scholar 

  • Costa, Y. M., Oliveira, L. S., Silla, C. N. (2017). An evaluation of convolutional neural networks for music classification using spectrograms. Applied Soft Computing, 52, 28–38.

    Article  Google Scholar 

  • Dieleman, S., Brakel, P., Schrauwen, B. (2011). Audio-based music classification with a pretrained convolutional network. In 12th International Society for Music Information Retrieval Conference (ISMIR-2011) (pp. 669–674): University of Miami.

  • Dieleman, S., & Schrauwen, B. (2013). Multiscale approaches to music audio feature learning. In 14th International Society for Music Information Retrieval Conference (ISMIR-2013) (pp. 116–121): Pontifícia Universidade Católica do Paraná.

  • Doraisamy, S., & Golzari, S. (2010). Automatic Musical Genre Classification and Artificial Immune Recognition System, (pp. 390–402). Berlin: Springer.

    Google Scholar 

  • Dubois, D., & Prade, H. (1990). Rough fuzzy sets and fuzzy rough sets. International Journal of General System, 17(2-3), 191–209.

    Article  MATH  Google Scholar 

  • Henaff, M., Jarrett, K., Kavukcuoglu, K., LeCun, Y. (2011). Unsupervised learning of sparse features for scalable audio classification. In 12th International Society for Music Information Retrieval Conference (ISMIR-2011), (Vol. 11 pp. 681–686).

  • Henry, C. J. (2011). Near Sets: Theory and Applications. Ph.D. thesis, University of Manitoba.

  • Herrera-Boyer, P., & Gouyon, F. E. (2013). Mirrors: Music information research reflects on its future. Journal of Intelligent Information Systems, 41(3), 1–22.

    Article  Google Scholar 

  • Hoffmann, P., & Kostek, B. (2014). Music data processing and mining in large databases for active media, (pp. 85–95). Switzerland: Springer International Publishing.

    Google Scholar 

  • Hoffmann, P., & Kostek, B. (2015). Music genre recognition in the rough set-based environment. In Proceedings of 6th International Conference, PReMI 2015 (pp. 377–386).

  • Hunt, M., Lennig, M., Mermelstein, P. (1996). Experiments in syllable-based recognition of continuous speech. Proceedings of International Conference on Acoustics, Speech and Signal Processing (pp. 880–883).

  • Jensen, R., & Cornelis, C. (2011). Fuzzy-rough nearest neighbour classification. Transactions on Rough Sets XIII (56–72).

  • Keller, J., Gray, M., Givens, J. (1985). A fuzzy k-nearest neighbor algorithm. IEEE Transaction on Systems Man Cybernetics, 15(4), 580585.

    Google Scholar 

  • Khan, M. K., & Wasfi, A. G. (2006). Machine-learning based classification of speech and music. Multimedia Systems, 12(1), 55–67.

    Article  Google Scholar 

  • Knees, P., & Schedl, M. (2013). A survey of music similarity and recommendation from music context data. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 10(1), 2:1–2:21.

    Google Scholar 

  • Konstantin, M., & Tomoko, M. (2014). Music genre and emotion recognition using gaussian processes. IEEE access, 2, 688–697.

    Article  Google Scholar 

  • Kostek, B., & Kaczmarek, A. (2013). Music recommendation based on multidimensional description and similarity measures. Fundamenta Informaticae, 50 (1-4), 325–340.

    Article  Google Scholar 

  • Kostek, B., Hoffmann, P., Kaczmarek, A., Spaleniak, P. (2014). Creating a reliable music discovery and recommendation system. In Intelligent Tools for Building a Scientific Information Platform: From Research to Implementation (pp. 107–130): Springer.

  • Kostek, B. (2005). Perception-Based Data processing in Acoustics, Applications to Music Information Retrieval and Psychophysiology of Hearing. Series on Cognitive Technologies. Berlin: Springer Verlag.

    Google Scholar 

  • Logan, B. (2000). Mel frequency cepstral coefficients for music modeling. Plymouth: Proceedings of 1st International Conference on Music Information Retrieval.

    Google Scholar 

  • Mandel, M. I., & Ellis, D. P. (2008). Multiple-instance learning for music information retrieval. In 9th International Society for Music Information Retrieval Conference (ISMIR-2008) (pp. 577–582).

  • Marques, C. M., Guilherme, I. R., Nakamura, R. Y., Papa, J. P. (2011). New trends in musical genre classification using optimum-path forest. In 12th International Society for Music Information Retrieval Conference (ISMIR-2011) (pp. 699–704).

  • Orio, N. (2006). Music retrieval: A tutorial and review. Foundations and Trends®; in Information Retrieval, 1(1), 1–90.

    Article  MATH  Google Scholar 

  • Panagakis, I., Benetos, E., Kotropoulos, C. (2008). Music genre classification: A multilinear approach. In 9th International Society for Music Information Retrieval Conference (ISMIR-2008) (pp. 583–588).

  • Pawlak, Z. (1982). Rough sets. International Journal of Computer & Information Sciences, 11(5), 341–356.

    Article  MathSciNet  MATH  Google Scholar 

  • Pawlak, Z., & Skowron, A. (2007). Rudiments of rough sets. Information sciences, 177(1), 3–27.

    Article  MathSciNet  MATH  Google Scholar 

  • Pedrycz, W., Skowron, A., Kreinovich, V. (2008). Handbook of Granular Computing. New York: Wiley-Interscience.

    Book  Google Scholar 

  • Peters, J. (2007a). Near sets. General theory about nearness of objects. Applied Mathematical Sciences, 1(53), 2609–2029.

  • Peters, J. (2007b). Near sets. Special theory about nearness of objects. Fundamenta Informaticae, 75(1-4), 407–433.

  • Peters, J. (2009). Tolerance near sets and image correspondence. International Journal of Bio-Inspired Computation, 1(4), 239–245.

    Article  Google Scholar 

  • Peters, J. F., & Wasilewski, P. (2009). Foundations of near sets. Information Sciences, 179(18), 3091–3109.

    Article  MathSciNet  MATH  Google Scholar 

  • Peters, J. (2010). Corrigenda and addenda: Tolerance near sets and image correspondence. International Journal of Bio-Inspired Computation, 2(5), 310–318.

    Article  Google Scholar 

  • Peters, J. F. (2013). Near Sets: An Introduction. Mathematics in Computer Science, 7(1), 3–9.

    Article  MathSciNet  MATH  Google Scholar 

  • Poli, G., Llapa, E., Cecatto, J., Saito, J., Peters, J., Ramanna, S., Nicoletti, M. (2014). Solar flare detection system based on tolerance near sets in a GPU-CUDA framework. Knowledge-Based Systems Journal, Elsevier, 70, 345–360.

    Article  Google Scholar 

  • Polkowski, L., Skowron, A., Zytkow, J. (1994). Tolerance based rough sets. In Lin, T. Y., & Wildberger, M (Eds.) Soft Computing: Rough Sets, Fuzzy Logic, Neural Networks, Uncertainty Management, Knowledge Discovery (pp. 55–58). San Diego: Simulation Councils Inc.

  • Ramanna, S., & Singh, A. (2016). Tolerance-based approach to audio signal classification. In Proceedings of 29th Canadian AI Conference, LNAI 9673 (pp. 83—88).

  • Ras, Z., & Wieczorkowska, A. A. (Eds.). (2010). Advances in Music Information Retrieval. Studies in Computational Intelligence, Vol. 274. Switzerland: Springer.

  • Riza, L. S., Janusz, A., Bergmeir, C., Cornelis, C., Herrera, F., Slezak, D., Benítez, J.M. (2014). Implementing algorithms of rough set theory and fuzzy rough set theory in the r package ”roughsets”. Information Sciences, 287, 68–89.

    Article  Google Scholar 

  • Rosner, A., & Kostek, B. (2018). Automatic music genre classification based on musical instrument track separation. Journal of Intelligent Information Systems, 50(2), 363–384.

    Article  Google Scholar 

  • Rough Set Exploration System(RSES). (2005) http://www.mimuw.edu.pl/szczuka/rses/start.html.

  • Sarkar, M. (2007). Fuzzy-rough nearest neighbor algorithms in classification. Fuzzy Sets and Systems, 158(19), 2134–2152.

    Article  MathSciNet  MATH  Google Scholar 

  • Schedl, M., Gómez, E., Urbano, J. (2014). Music information retrieval: Recent developments and applications. Foundations and trends®; in Information Retrieval, 8 (2-3), 127–261.

    Article  Google Scholar 

  • Schreiber, H. (2015). Improving genre annotations for the million song dataset. In 16th International Society for Music Information Retrieval Conference (ISMIR-2015) (pp. 241–247).

  • Silla, C. N., Carlos, N., Koerich, A. L., Kaestner, C. A. A. (2008). The Latin music database. In International Society for Music Information Retrieval Conference (pp. 451–456).

  • Singh, A. (2017). Application of Tolerance Near Sets to Audio Signal and Commercial Video Classification. Master’s thesis, University of Winnipeg. Supervisor: S.Ramanna.

  • Singh, A., & Ramanna, S. (2018). Application of tolerance near sets to audio signal classification. In Zielosko, B., Stanczyk, U., Jain, L.C. (Eds.) Advances in Feature Selection, and Data and Pattern Recognition. https://doi.org/10.1007/978-3-319-67588-613: Springer International Publishing.

  • Slaney, M., Weinberger, K., White, W. (2008). Learning a metric for music similarity. In International Symposium on Music Information Retrieval (ISMIR).

  • Sossinsky, A. B. (1986). Tolerance space theory and some applications. Acta Applicandae Mathematica, 5(2), 137–167.

    Article  MathSciNet  Google Scholar 

  • Sturm, B. L. (2012). An analysis of the GTZAN music genre dataset. In Proceedings of the second international ACM workshop on Music information retrieval with user-centered and multimodal strategies (pp. 7–12): ACM.

  • SYNAT Database. (2016) https://synat.eti.pg.gda.pl/.

  • Thierry, B. M., Ellis, D. P. W., Whitman, B., Lamere, P. (2011). The million song dataset. In Proceedings of the 12th International Conference on Music Information Retrieval (ISMIR 2011).

  • Typke, R., Wiering, F., Veltkamp, R. C. (2005). A survey of music information retrieval systems. In Proceedings of the 6th International Conference on Music Information Retrieval (pp. 153–160). Queen Mary: University of London.

  • Tzanetakis, G., & Cook, P. (2002). Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing, 10(5), 293–302.

    Article  Google Scholar 

  • Wang, X., Yang, J., Teng, X., Peng, N. (2005). Fuzzy-Rough Set Based Nearest Neighbor Clustering Classification Algorithm, (pp. 370–373). Berlin: Springer.

    Google Scholar 

  • WEKA Data Mining Software System. (2018) http://www.cs.waikato.ac.nz/ml/weka/index.html.

  • Weston, J., Bengio, S., Hamel, P. (2011). Large-scale music annotation and retrieval: Learning to rank in joint semantic spaces. CoRR arXiv:1105.5196.

  • Wold, S., Esbensen, K., Geladi, P. (1987). Principal component analysis. Chemometrics and intelligent laboratory systems, 2(1-3), 37–52.

    Article  Google Scholar 

  • Wold, E., Blum, T., Keislar, D., Wheaten, J. (1996). Content-based classification, search, and retrieval of audio. IEEE multimedia, 3(3), 27–36.

    Article  Google Scholar 

  • Wolski, M. (2010). Perception and classification. a note on near sets and rough sets. Fundamenta Informatica, 101, 143–155.

    Article  MathSciNet  MATH  Google Scholar 

  • Wolski, M. (2013). Granular computing: Topological and categorical aspects of near and rough set approaches to granulation of knowledge. In Transactions on Rough Sets XVI, Lecture Notes in Computer Science, (Vol. 7736 pp. 34–52): Springer Berlin Heidelberg.

  • Wolski, M., & Gomalínska, A. (2017). Rough and near: modal history of two theories. In Rough Sets: International Joint Conference, IJCRS 2017, Olsztyn, Poland, July 3?7, 2017, Proceedings, Part I: Springer International Publishing.

  • Zadeh, L. A. (1965). Fuzzy sets. Information and control, 8(3), 338–353.

    Article  MathSciNet  MATH  Google Scholar 

  • Zadeh, L. (1997). Towards a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Sets Systems, 177(19), 111–127.

    Article  MathSciNet  MATH  Google Scholar 

  • Zeeman, E., & Buneman, O. P. (1968). Tolerance spaces and the brain. Towards a Theoretical Biology, 1, 140–151. Published in C.H. Waddington (Ed.), Towards a Theoretical Biology. The Origin of Life, Aldine Pub. Co.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Applied Computer Science, University of Winnipeg, Winnipeg, Manitoba, R3B 2E9, Canada

    Arshia Sathya Ulaganathan & Sheela Ramanna

Authors
  1. Arshia Sathya Ulaganathan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sheela Ramanna
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sheela Ramanna.

Additional information

This research has been supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) grant 194376. We are very grateful to Professor Bozena Kostek and Piotr Hoffmann, Gdańsk University of Technology, Faculty of Electronics, Telecommunications and Informatics, Audio Acoustics Laboratory, Poland for sharing the SYNAT music dataset.

Appendix

Appendix

Table 10 List of features
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ulaganathan, A.S., Ramanna, S. Granular methods in automatic music genre classification: a case study. J Intell Inf Syst 52, 85–105 (2019). https://doi.org/10.1007/s10844-018-0505-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10844-018-0505-8

Keywords

Search

Navigation