Statistical Comparison of Classifiers for Multi-objective Feature Selection in Instrument Recognition

  • Igor Vatolkin
  • Bernd Bischl
  • Günter Rudolph
  • Claus Weihs
Conference paper
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)

Abstract

Many published articles in automatic music classification deal with the development and experimental comparison of algorithms—however the final statements are often based on figures and simple statistics in tables and only a few related studies apply proper statistical testing for a reliable discussion of results and measurements of the propositions’ significance. Therefore we provide two simple examples for a reasonable application of statistical tests for our previous study recognizing instruments in polyphonic audio. This task is solved by multi-objective feature selection starting from a large number of up-to-date audio descriptors and optimization of classification error and number of selected features at the same time by an evolutionary algorithm. The performance of several classifiers and their impact on the pareto front are analyzed by means of statistical tests.

References

  1. Bischl, B., Eichhoff, M., & Weihs, C. (2010). Selecting groups of audio features by statistical tests and the group lasso. In Proceedings of the 9th ITG Fachtagung Sprachkommunikation. Berlin: VDE Verlag.Google Scholar
  2. Blume, H., Bischl, B., Botteck, M., Igel, C., Martin, R., & Rötter, G. (2011). Huge music archives on mobile devices. IEEE Signal Processing Magazine, 28(4), 24–39.CrossRefGoogle Scholar
  3. Downie, S. (2003). Music information retrieval. Annual Review of Information Science and Technology, 37(1), 295–340.CrossRefGoogle Scholar
  4. Eronen, A. (2001). Automatic Musical Instrument Recognition (Master’s thesis). Department of Information Technology, Tampere University of Technology.Google Scholar
  5. Fiebrink, R., & Fujinaga, I. (2006). Feature selection pitfalls and music classification. In Proceedings of the 7th International Conference on Music Information Retrieval (ISMIR) (pp. 340–341). University of Victoria.Google Scholar
  6. Fuhrmann, S. (2012). Automatic Musical Instrument Recognition from Polyphonic Music Audio Signals (Ph.D. thesis). Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona.Google Scholar
  7. Gillick, L., & Cox, S. (1989). Some statistical issues in the comparison of speech recognition algorithms. In Proceedings of the IEEE Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 532–535). New York: IEEE.Google Scholar
  8. Hollander, M., & Wolfe, D. A. (1973). Nonparametric statistical methods. New York: Wiley.MATHGoogle Scholar
  9. Mckay, C. (2010). Automatic Music Classification with jMIR (Ph.D. thesis). Department of Music Research, Schulich School of Music, McGill University, Montreal.Google Scholar
  10. Meng, A., Ahrendt, P., Larsen, J., & Hansen, L. K. (2007). Temporal feature integration for music genre classification. IEEE Transactions on Audio, Speech and Language Processing, 15(5), 1654–1664.CrossRefGoogle Scholar
  11. Noland, K., & Sandler, M. (2009). Influences of signal processing, tone profiles, and chord progressions on a model for estimating the musical key from audio. Computer Music Journal, 33(1), 42–56.CrossRefGoogle Scholar
  12. Vatolkin, I., Preuß, & Rudolph, G. (2011). Multi-objective feature selection in music genre and style recognition tasks. In Proceedings of the 2011 Genetic and Evolutionary Computation Conference (GECCO) (pp. 411–418). New York: ACM.Google Scholar
  13. Vatolkin, I., Preuß, Rudolph, G., Eichhoff, M., & Weihs, C. (2012). Multi-objective evolutionary feature selection for instrument recognition in polyphonic audio mixtures. Soft Computing, 16(12), 2027–2047.Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Igor Vatolkin
    • 1
  • Bernd Bischl
    • 2
  • Günter Rudolph
    • 1
  • Claus Weihs
    • 2
  1. 1.Algorithm EngineeringTU DortmundDortmundGermany
  2. 2.Computational StatisticsTU DortmundDortmundGermany

Personalised recommendations