Musical Style Classification from Symbolic Data: A Two-Styles Case Study

  • Pedro J. Ponce de León
  • José M. Iñesta
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2771)

Abstract

In this paper the classification of monophonic melodies from two different musical styles (Jazz and classical) is studied using different classification methods: Bayesian classifier, a k-NN classifier, and self-organising maps (SOM). From MIDI files, the monophonic melody track is extracted and cut into fragments of equal length. From these sequences, A number of melodic, harmonic, and rhythmic numerical descriptors are computed and analysed in terms of separability in two music classes, obtaining several reduced descriptor sets. Finally, the classification results for each type of classifier for the different descriptor models are compared. This scheme has a number of applications like indexing and selecting musical databases or the evaluation of style-specific automatic composition systems.

Keywords

music information retrieval self-organising maps bayesian classifier nearest neighbours (k-NN) feature selection 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Rauber, A., Frühwirth, M.: Automatically analyzing and organizing music archives. In: Constantopoulos, P., Sølvberg, I.T. (eds.) ECDL 2001. LNCS, vol. 2163, pp. 4–8. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  2. 2.
    Whitman, B., Flake, G., Lawrence, S.: Artist detection in music with minnowmatch. In: Proceedings of the 2001 IEEE Workshop on Neural Networks for Signal Processing, Falmouth, Massachusetts, pp. 559–568, September 10-12 (2001)Google Scholar
  3. 3.
    Soltau, H., Schultz, T., Westphal, M., Waibel, A.: Recognition of music types. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-1998), Seattle, Washington (May 1998)Google Scholar
  4. 4.
    Carpinteiro, O.A.S.: A self-organizing map model for analysis of musical time series. In: de Padua Braga, A., Ludermir, T.B. (eds.) Proceedings 5th Brazilian Symposium on Neural Networks, pp. 140–145. IEEE Comput. Soc., Los Alamitos (1998)CrossRefGoogle Scholar
  5. 5.
    Thom, B.: Unsupervised learning and interactive jazz/blues improvisation. In: Proceedings of the AAAI 2000, pp. 652–657 (2000)Google Scholar
  6. 6.
    Toiviainen, P., Eerola, T.: Method for comparative analysis of folk music based on musical feature extraction and neural networks. In: III International Conference on Cognitive Musicology, Jyväskylä, Finland, pp. 41–45 (2001) Google Scholar
  7. 7.
    Pickens, J.: A survey of feature selection techniques for music information retrieval. Technical report, Center for Intelligent Information Retrieval, Departament of Computer Science, University of Massachussetts (2001) Google Scholar
  8. 8.
    Blackburn, S.G.: Content Based Retrieval and Navigation of Music Using Melodic Pitch Contours. PhD thesis, Faculty of Engineering and Applied Science Department of Electronics and Computer Science (2000) Google Scholar
  9. 9.
    Duda, R.O., Hart, P.E.: Pattern classification and scene analysis. John Wiley and Sons, Chichester (1973)MATHGoogle Scholar
  10. 10.
    Kohonen, T.: Self-organizing map. Proceedings IEEE 78(9), 1464–1480 (1990)CrossRefGoogle Scholar
  11. 11.
    Kohonen, T., Hynninen, J., Kangas, J., Laaksonen, J.: Som pak, the self organizing map program package, v:3.1. Lab. of Computer and Information Science, Helsinki University of Technology, Finland (April 1995), http://www.cis.hut.fi/research/som_pak

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Pedro J. Ponce de León
    • 1
  • José M. Iñesta
    • 1
  1. 1.Departamento de Lenguajes y Sistemas InformáticosUniversidad de Alicante, Ap. 99AlicanteSpain

Personalised recommendations