A Class Centric Feature and Classifier Ensemble Selection Approach for Music Genre Classification

  • Hasitha Bimsara Ariyaratne
  • Dengsheng Zhang
  • Guojun Lu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7626)

Abstract

Music genre classification has attracted a lot of research interest due to the rapid growth of digital music. Despite the availability of a vast number of audio features and classification techniques, genre classification still remains a challenging task. In this work we propose a class centric feature and classifier ensemble selection method which deviates from the conventional practice of employing a single, or an ensemble of classifiers trained with a selected set of audio features. We adopt a binary decomposition technique to divide the multiclass problem into a set of binary problems which are then treated in a class specific manner. This differs from the traditional techniques which operate on the naive assumption that a specific set of features and/or classifiers can perform equally well in identifying all the classes. Experimental results obtained on a popular genre dataset and a newly created dataset suggest significant improvements over traditional techniques.

Keywords

music retrieval feature selection classifier ensemble music genre classification 

References

  1. 1.
    McKay, C., Fujinaga, I.: Musical Genre Classification: Is it worth pursuing and how can it be improved? In: Proc. ISMIR (2006)Google Scholar
  2. 2.
    Aucouturier, J., Pachet, F.: Improving timbre similarity: How high is the sky? Journal of Negative Results in Speech and Audio Sciences 1(1) (2004)Google Scholar
  3. 3.
    Doraisamy, S., Golzari, S., Norowi, N.M., Sulaiman, M.N., Udzir, N.I.: A Study on Feature Selection and Classification Techniques for Automatic Genre Classification of Traditional Malay Music. In: Proc. ISMIR (2008)Google Scholar
  4. 4.
    Yaslan, Y., Cataltepe, Z.: Audio Music Genre Classification Using Different Classifiers and Feature Selection Methods. In: Proc. ICPR (2006)Google Scholar
  5. 5.
    Soares, C., Williams, P., Gilbert, J.E., Dozier, G.V.: A Class-Specific Ensemble Feature Selection Approach for Classification Problems. In: Proc. ACMse (2010)Google Scholar
  6. 6.
    Zhang, T.: Semiautomatic approach for music classification. In: Proc. SPIE Conf. on Internet Multimedia Management Systems (2003)Google Scholar
  7. 7.
    Silla, C., Freitas, A.: Novel top-down approaches for hierarchical classification and their application to automatic music genre classification. In: Proc. IEEE SMC (2009)Google Scholar
  8. 8.
    Ariyaratne, H.B., Zhang, D.: A novel automatic hierarchical approach to music genre classification. In: Proc. ICME Workshop on Advances in Large Scale Multimedia Data Collection, Mining and Retrieval (2012)Google Scholar
  9. 9.
    Galar, M., Fernndez, A., Barrenechea, E., Bustince, H., Herrera, F.: An Overview of Ensemble Methods for Binary Classifiers in Multiclass Problems: Experimental Study on One-vs-One and One-vs-All Schemes. In: Pattern Recognition, vol. 44(8), pp. 1761–1776. Elsevier Science Inc. (2011)Google Scholar
  10. 10.
    Silla Jr., C.N., Koerich, A.L., Kaestner, C.A.A.: Feature Selection in Automatic Music Genre Classification. In: Proc. ISM (2008)Google Scholar
  11. 11.
    Rokach, L.: Taxonomy for Characterizing Ensemble Methods in classification Tasks: a review and annotated bibliography. In: Azen, S.P., Kontoghiorghes, E.J., Lee, L.C. (eds.) Computational Statistics & Data Analysis, vol. 53(12), pp. 4046–4072 (2009)Google Scholar
  12. 12.
    Caruana, R., Niculescu-Mizil, A., Crew, G., Ksikes, A.: Ensemble selection from libraries of models. In: Proc. ICML (2004)Google Scholar
  13. 13.
    Tzanetakis, G., Cook, P.: Musical Genre Classification of Audio Signals. IEEE Speech Audio Process 10(5), 293–302 (2002)CrossRefGoogle Scholar
  14. 14.
    Witten, I., Frank, E., Hall, M.: Data Mining: Practical Machine Learning Tools and Techniques, 3rd edn. Morgan Kaufmann (2011)Google Scholar
  15. 15.
    Cevikalp, H.: Feature Extraction Techniques in High-dimensional Spaces: Linear and Nonlinear Approaches. Ph.D Thesis, Vanderbilt University (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Hasitha Bimsara Ariyaratne
    • 1
  • Dengsheng Zhang
    • 1
  • Guojun Lu
    • 1
  1. 1.Gippsland School of ITMonash UniversityChurchillAustralia

Personalised recommendations