Advertisement

Automatic Music Genre Classification Using Hybrid Genetic Algorithms

  • George V. Karkavitsas
  • George A. Tsihrintzis
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 11)

Abstract

This paper aims at developing an Automatic Music Genre Classification system and focuses on calculating algorithms that (ideally) can predict the music class in which a music file belongs. The proposed system is based on techniques from the fields of Signal Processing, Pattern Recognition, and Information Retrieval, as well as Heuristic Optimization Methods. One thousand music files are used for training and validating the classification system. These files are distributed equally in ten classes. From each file, eighty one (81) features are extracted and used to create 81 similarity matrices. These 81 similarity matrices constitute the training instances. During the training phase, feature selection takes place via a modified hybrid Genetic Algorithm in order to improve the class discrimination clarity and reduce the calculating cost. In this algorithm, the crossover probability is replaced by a parent pair number that produces new solutions via a taboo list. Also, an adaptive mutation, an adaptive local exhaustive search and an adaptive replace strategy are used, depending on whether the system has reached a local extreme. Local exhaustive search takes place in the most optimal up to the current solution neighboring chromosomes. The Genetic Algorithm fitness function constitutes a weighted nearest neighbors classifier. Thus, the chromosome fitness is proportional to the classifier accuracy that the chromosome creates. During the classification phase, the features selected via the Genetic Algorithm create an adjusted nearest neighbor classifier that performs the classifications. From each new music file pending classification, selected features are extracted and then compared with the corresponding features of the database music files. The music file is assigned to the class indicated by the k nearest music files.

Keywords

Signal Processing Pattern Recognition Music Information Retrieval Music Genre Classification Hybrid Genetic Algorithm k-nearest neighbors Classifier multi-class classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Muller, M.: Information Retrieval for Music and Motion. Springer, Heidelberg (2007); ISBN: 978-3-540-74047-6CrossRefGoogle Scholar
  2. 2.
    Xiao, H., Stephen Downie, J.: Exploring mood metadata: Relationships with genre, artist and usage metadata. In: Eighth International Conference on Music Information Retrieval, Vienna (2007)Google Scholar
  3. 3.
    Tzanetakis, G., Cook, P.: Musical Genre Classification of Audio Signals. IEEE Transactions on speech and audio processing 10 (2002)Google Scholar
  4. 4.
    Scaringella, N., Zoia, G., Mlynek, D.: Automatic genre classification of music content: a survey. Signal Processing Magazine (2006)Google Scholar
  5. 5.
    Sotiropoulos, N., Lampropoulos, A.S., Tsihrintzis, G.A.: MUSIPER: a system for modeling music similarity perception based on objective feature subset selection. In: User Modeling and User-Adapted Interaction, vol. 18, pp. 315–348 (2008)Google Scholar
  6. 6.
    Lampropoulou, P.S., Lampropoulos, A.S., Tsihrintzis, G.A.: Intelligent Mobile Content-based Retrieval from Digital Music Libraries. In: Intelligent Decision Technologies, vol. l. 3, pp. 123–138. IOS Press, Amsterdam (2009)Google Scholar
  7. 7.
    Lampropoulou, P.S., Lampropoulos, A.S., Tsihrintzis, G.A.: Music Genre Classification based on Ensemble of Signals produced by Source Separation Methods. In: Intelligent Decision Technologies, vol. 4, pp. 229–237. IOS Press, Amsterdam (2010)Google Scholar
  8. 8.
    Lampropoulos, A.S., Lampropoulou, P.S., Tsihrintzis, G.A.: A Cascade-Hybrid Music Recommender System for Mobile Services based on Musical Genre Classification and Personality Diagnosis. In: Multimedia Tools and Applications ( to appear in February 2011)Google Scholar
  9. 9.
    Duda, R., Hart, P., Stork, D.: Pattern classification. John Wiley & Sons, New York (2000)Google Scholar
  10. 10.
    Bandyopadhyay, S.: Classification and Learning Using Genetic Algorithms. Springer, Heidelberg (2007); ISBN-13 978-3-540-49606-9MATHGoogle Scholar
  11. 11.
    Dasarathy, B.V.: Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques (1991); ISBN 0-8186-8930-7Google Scholar
  12. 12.
    Holland, J.H.: Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. University of Michigan Press, Ann Arbor (1975)Google Scholar
  13. 13.
    Sivanandam, S.N., Deepa, S.N.: Introduction to Genetic Algorithms. Springer, Heidelberg (2007); ISBN 978-3-540-73189-4Google Scholar
  14. 14.
    Tang, K.S., Man, K.F., Kwong, S., He, Q.: Genetic Algorithms and their Applications. IEEE Signal Processing Magazine, November 96, 1053–1088 (1996)Google Scholar
  15. 15.
    Karkavitsas, G., Rangoussi, M.: Object localization in medical images using Genetic Algorithms. International Journal of Signal Processing 1(3), 204–207 (2004); ISSN:1304-4494Google Scholar
  16. 16.
    Tzanetakis, G.: Manipulation, Analysis and Retrieval systems for audio signals. phd dissertation (2002)Google Scholar
  17. 17.
    Lampropoulos, A.S.: Machine Learning-based Recommendation Methods for Multimedia Data. PhD Dissertation, The University of Piraeus, Piraeus, Greece (2010)Google Scholar
  18. 18.
    Lartillot, O.: MIR toolbox 1.3”, Finnish Centre of Exce!ence in Interdisciplinary Music Research. University of Jyväskylä, Finland (2010)Google Scholar
  19. 19.
    Pampalk, E., Dixon, S., Widmer, G.: Exploring music collections by browsing different views. In: Proc of ISMIR (2003)Google Scholar
  20. 20.
    Scheirer, E.D.: Tempo and beat analysis of acoustic musical signals. JASA 103(1) (1998)Google Scholar
  21. 21.
    Pampalk, E., Rauber, A., Merkl, D.: Content-based organization and visualization of music archives. In: Proc of ACM Multimedia (2002)Google Scholar
  22. 22.
    Lidy, T., Rauber, A.: Evaluation of feature extractors and psycho-acoustic transformations for music genre classification. In: Proceedings of the 6th International Conference on Music Information Retrieval, London, UK, pp. 34–41 (2005)Google Scholar
  23. 23.
    Zwicker, E., Fastl, H.: Psychoacoustics - Facts and Models. Springer Series of Information Sciences, vol. 22. Springer, Berlin (1999)Google Scholar
  24. 24.
    Kelly, J.D., Davis, L.: A Hybrid Genetic Algorithm for Classification (1991)Google Scholar
  25. 25.
    Syswerda, G.: Uniform crossover in genetic algorithms. In: Schafier, J.D. (ed.) Proceedings of the 3rd International Conference on Genetic Algorithms. Morgan Kaufmann, San Mateo (1989)Google Scholar
  26. 26.
    Whitley, D., Starkweather, T.: GENITOR-II: A distributed genetic algorithm. Journal of Experimental and Theoretical Artificial Intelligence 2, 189–214 (1990)CrossRefGoogle Scholar
  27. 27.
    Baeza-Yates, R., Ribeiro-Neto, B.: Modern Information Retrieval. ACM Press, Addison-Wesley (1999) ISBN 0-201-39829-XGoogle Scholar
  28. 28.
    Li, T., Ogihara, M., Li, Q.: A comparative study on content based music genre classification. In: 26th annual international ACM SIGIR Conference on Research and Development in Information Retrieval, Toronto, Canada (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • George V. Karkavitsas
    • 1
  • George A. Tsihrintzis
    • 2
  1. 1.Advantage S.E, Financial System ExpertsAlimosGreece
  2. 2.Department of InformaticsUniversity of PiraeusPiraeusGreece

Personalised recommendations