Feature Analysis and Classification of Classical Musical Instruments: An Empirical Study

  • Christian Simmermacher
  • Da Deng
  • Stephen Cranefield
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4065)


We present an empirical study on classical music instrument classification. A methodology with feature extraction and evaluation is proposed and assessed with a number of experiments, whose final stage is to detect instruments in solo passages. In feature selection it is found that similar but different rankings for individual tone classification and solo passage instrument recognition are reported. Based on the feature selection results, excerpts from concerto and sonata files are processed, so as to detect and distinguish four major instruments in solo passages: trumpet, flute, violin, and piano. Nineteen features selected from the Mel-frequency cepstral coefficients (MFCC) and the MPEG-7 audio descriptors achieve a recognition rate of around 94% by the best classifier assessed by cross validation.


Feature Selection Gaussian Mixture Model Information Gain Audio Feature High Recognition Rate 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    ISO/IEC Working Group: MPEG-7 overview (2004) (accessed, February 8, 2006), URL
  2. 2.
    Tzanetakis, G., Cook, P.: Musical genre classification of audio signals. IEEE Transactions on speech and audio processing 10, 293–302 (2002)CrossRefGoogle Scholar
  3. 3.
    Aucouturier, J., Pachet, F.: Scaling up music playlist generation. In: Proc. ICME., vol. 1, pp. 105–108 (2002)Google Scholar
  4. 4.
    Divakaran, A., Regunathan, R., Xiong, Z., Casey, M.: Procedure for audio-assisted browsing of news video using generalized sound recognition. In: Proc. SPIE, vol. 5021, pp. 160–166 (2003)Google Scholar
  5. 5.
    Foote, J.: An overview of audio information retrieval. Multimedia Systems 7, 2–10 (1999)CrossRefGoogle Scholar
  6. 6.
    Marques, J., Moreno, P.: A study of musical instrument classification using gaussian mixture models and support vector machines. Technical Report CRL 99/4, Compaq Computer Corporation (1999)Google Scholar
  7. 7.
    Eronen, A.: Comparison of features for music instrument recognition. In: Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, pp. 19–22 (2001)Google Scholar
  8. 8.
    Essid, S., Richard, G., David, B.: Efficient musical instrument recognition on solo performance music using basic features. In: Proceedings of the Audio Engineering Society 25th International Conference (2004) (accessed, November 22, 2005)Google Scholar
  9. 9.
    Peeters, G., McAdams, S., Herrera, P.: Instrument sound description in the context of mpeg-7. In: Proc. of Inter. Computer Music Conf., pp. 166–169 (2000)Google Scholar
  10. 10.
    Xiong, Z., Radhakrishnan, R., Divakaran, A., Huang, T.: Comparing MFCC and MPEG-7 audio features for feature extraction, maximum likelihood HMM and entropic prior HMM for sports audio classification. In: Proc. of ICME, vol. 3, pp. 397–400 (2003)Google Scholar
  11. 11.
    Brown, J.C., Houix, O.: Feature dependence in the automatic identification of musical woodwind instruments. Journal of the Acoustical Society of America 109(3), 1064–1072 (2001)CrossRefGoogle Scholar
  12. 12.
    Essid, S., Richard, G., David, B.: Musical instrument recognition by pairwise classification strategies. IEEE Trans. on Speech and Audio Processing (accessed, December 2, 2005) (to appear, 2006)Google Scholar
  13. 13.
    Agostini, G., Longari, M., Poolastri, E.: Musical instrument timbres classification with spectral features. EURASIP Journal on Applied Signal Processing (1) (2003)Google Scholar
  14. 14.
    Livshin, A.A., Rodet, X.: Musical instrument identification in continuous recordings. In: Proceedings of the 7th International Conference on Digital Audio Effects (2004)Google Scholar
  15. 15.
    Eggink, J., Brown, G.J.: Instrument recognition in accompanied sonatas and concertos. In: Proc. of ICASSP, vol. IV, pp. 217–220 (2004)Google Scholar
  16. 16.
    Yu, L., Liu, H.: Efficient feature selection via analysis of relevance and redundancy. J. Machine Learning Research 5, 1205–1224 (2004)MathSciNetGoogle Scholar
  17. 17.
    Grimaldi, M., Cunningham, P., Kokaram, A.: An evaluation of alternative feature selection strategies and ensemble techniques of classifying music. In: Mladenic, D., Paa, G. (eds.) Workshop in Multimedia Discovery and Mining at ECML/PKDD-2003 (2003)Google Scholar
  18. 18.
    Yu, L., Liu, H.: Feature selection for high-dimensional data: A fast correlation-based filter solution. In: Proc. 20th Intl. Conf. Machine Learning, pp. 856–863 (2003)Google Scholar
  19. 19.
    Qinlan, J.: C4.5: Programs for machine learning. Morgan Kaufmann, San Francisco (1993)Google Scholar
  20. 20.
    Press, W.H., Flannery, B.P., Teukolsky, S.A., Vetterling, W.T.: Numerical recipes in C. Cambridge University Press, Cambridge (1988)MATHGoogle Scholar
  21. 21.
    Niemann, H.: Klassifikation von Mustern. Springer, Heidelberg (1983)MATHGoogle Scholar
  22. 22.
    IPEM.: IPEM-toolbox (2005) (accessed, September 10, 2005), URL
  23. 23.
    Slaney, M.: The Auditory Toolbox. Technical Report 1998-010, Interval Research Corporation (1998) (accessed, November 22, 2005), URL
  24. 24.
    Casey, M.: MPEG-7 sound-recognition tools. IEEE Trans. on Circuits and Systems for Video Technology 11(6), 737–747 (2001)CrossRefGoogle Scholar
  25. 25.
    Witten, I.H., Frank, E.: Data Mining: Practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, San Francisco (2005)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Christian Simmermacher
    • 1
  • Da Deng
    • 1
  • Stephen Cranefield
    • 1
  1. 1.Department of Information ScienceUniversity of OtagoNew Zealand

Personalised recommendations