Generalisation Performance of Western Instrument Recognition Models in Polyphonic Mixtures with Ethnic Samples

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10198)

Abstract

Instrument recognition in polyphonic audio recordings is a very complex task. Most research studies until now were focussed on the recognition of Western instruments in Western classical and popular music, but also an increasing number of recent works addressed the classification of ethnic/world recordings. However, such studies are typically restricted to one kind of music and do not measure the bias of “Western” effect, i.e., the danger of overfitting towards Western music when the classification models are optimised only for such tracks. In this paper, we analyse the performance of several instrument classification models which are trained and optimised on polyphonic mixtures of Western instruments, but independently validated on mixtures created with randomly added ethnic samples. The conducted experiments include evolutionary multi-objective feature selection from a large set of audio signal descriptors and the estimation of individual feature relevance.

Keywords

Music instrument recognition Evolutionary multi-objective feature selection Generalisation performance of classification models 

References

  1. 1.
    Abdoli, S.: Iranian traditional music dastgah classification. In: Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR), pp. 275–280 (2011)Google Scholar
  2. 2.
    Agarwal, P., Karnick, H., Raj, B.: A comparative study of Indian and western music forms. In: Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR), pp. 29–34 (2013)Google Scholar
  3. 3.
    Benetos, E., Holzapfel, A.: Automatic transcription of Turkish makam music. In: Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR), pp. 355–360 (2013)Google Scholar
  4. 4.
    Brown, J.C., Houix, O., Mcadams, S.: Feature dependence in the automatic identification of musical woodwind instruments. J. Acoust. Soc. Am. 109(3), 1064–1072 (2001)CrossRefGoogle Scholar
  5. 5.
    Ding, C.H.Q., Peng, H.: Minimum redundancy feature selection from microarray gene expression data. J. Bioinform. Comput. Biol. 3(2), 185–205 (2005)CrossRefGoogle Scholar
  6. 6.
    Eerola, T.: Are the emotions expressed in music genre-specific? An audio-based evaluation of datasets spanning classical, film, pop and mixed genres. J. New Music Res. 40(3), 349–366 (2011)CrossRefGoogle Scholar
  7. 7.
    Eerola, T., Ferrer, R.: Instrument library (MUMS) revised. Music Percept. 25(3), 253–255 (2008)CrossRefGoogle Scholar
  8. 8.
    Eggink, J., Brown, G.J.: Instrument recognition in accompanied sonatas and concertos. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 217–220 (2004)Google Scholar
  9. 9.
    Emmerich, M., Beume, N., Naujoks, B.: An EMO algorithm using the hypervolume measure as selection criterion. In: Coello Coello, C.A., Hernández Aguirre, A., Zitzler, E. (eds.) EMO 2005. LNCS, vol. 3410, pp. 62–76. Springer, Heidelberg (2005). doi:10.1007/978-3-540-31880-4_5 CrossRefGoogle Scholar
  10. 10.
    Eronen, A.J., Klapuri, A.: Musical instrument recognition using cepstral coefficients and temporal features. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 753–756 (2000)Google Scholar
  11. 11.
    Essid, S., Richard, G., David, B.: Instrument recognition in polyphonic music based on automatic taxonomies. IEEE Trans. Audio Speech Lang. Process. 14(1), 68–80 (2006)CrossRefGoogle Scholar
  12. 12.
    Fuhrmann, F.: Automatic musical instrument recognition from polyphonic music audio signals. Ph.D. thesis, Universitat Pompeu Fabra (2012)Google Scholar
  13. 13.
    Gaikwad, S., Chitre, A.V., Dandawate, Y.H.: Classification of Indian classical instruments using spectral and principal component analysis based cepstrum features. In: Proceedings of the 2014 International Conference on Electronic Systems, Signal Processing and Computing Technologies (ICESC), pp. 276–279 (2014)Google Scholar
  14. 14.
    Goto, M., Hashiguchi, H., Nishimura, T., Oka, R.: RWC music database: Music genre database and musical instrument sound database. In: Proceedings of the 4th International Conference on Music Information Retrieval (ISMIR), pp. 229–230 (2003)Google Scholar
  15. 15.
    Gunasekaran, S., Revathy, K.: Fractal dimension analysis of audio signals for Indian musical instrument recognition. In: Proceedings of the International Conference on Audio, Language and Image Processing (ICALIP), pp. 257–261 (2008)Google Scholar
  16. 16.
    Guyon, I., Nikravesh, M., Gunn, S., Zadeh, L.A.: Feature Extraction: Foundations and Applications. Springer, Heidelberg (2006)CrossRefMATHGoogle Scholar
  17. 17.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer, New York (2009)CrossRefMATHGoogle Scholar
  18. 18.
    Heittola, T., Klapuri, A., Virtanen, T.: Musical instrument recognition in polyphonic audio using source-filter model for sound separation. In: Proceedings of the 10th International Society for Music Information Retrieval Conference (ISMIR), pp. 327–332 (2009)Google Scholar
  19. 19.
    Koduri, G.K., Miron, M., Serrà, J., Serra, X.: Computational approaches for the understanding of melody in carnatic music. In: Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR), pp. 263–268 (2011)Google Scholar
  20. 20.
    Lartillot, O., Toiviainen, P.: MIR in Matlab (II): A toolbox for musical feature extraction from audio. In: Proceedings of the 8th International Conference on Music Information Retrieval (ISMIR), pp. 127–130 (2007)Google Scholar
  21. 21.
    Lashari, S.A., Ibrahim, R., Senan, N.: Soft set theory for automatic classification of traditional pakistani musical instruments sounds. In: Proceedings of the International Conference on Computer Information Science (ICCIS), pp. 94–99 (2012)Google Scholar
  22. 22.
    Lidy, T., Silla Jr., C.N., Cornelis, O., Gouyon, F., Rauber, A., Kaestner, C.A.A., Koerich, A.L.: On the suitability of state-of-the-art music information retrieval methods for analyzing, categorizing and accessing non-Western and ethnic music collections. Signal Process. 90(4), 1032–1048 (2010)CrossRefMATHGoogle Scholar
  23. 23.
    Livshin, A., Rodet, X.: The significance of the non-harmonic “noise” versis the harmonic series for musical instrument recognition. In: Proceedings of the 7th International Conference on Music Information Retrieval (ISMIR), pp. 95–100 (2006)Google Scholar
  24. 24.
    McEnnis, D., McKay, C., Fujinaga, I.: jAudio: Additions and improvements. In: Proceedings of the 7th International Conference on Music Information Retrieval (ISMIR), pp. 385–386 (2006)Google Scholar
  25. 25.
    Mierswa, I., Morik, K.: Automatic feature extraction for classifying audio data. Mach. Learn. J. 58(2–3), 127–149 (2005)CrossRefMATHGoogle Scholar
  26. 26.
    Müller, M.: Information Retrieval for Music and Motion. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  27. 27.
    Müller, M., Ewert, S.: Chroma toolbox: MATLAB implementations for extracting variants of chroma-based audio features. In: Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR), pp. 215–220 (2011)Google Scholar
  28. 28.
    Newton, M., Smith, L.: A neurally inspired musical instrument classification system based upon the sound onset. J. Acoust. Soc. Am. 131(6), 4785–4798 (2012)CrossRefGoogle Scholar
  29. 29.
    Sandrock, T.: Multi-label feature selection with application to musical instrument recognition. Ph.D. thesis, Stellenbosch University (2013)Google Scholar
  30. 30.
    Srinivasamurthy, A., Holzapfel, A., Serra, X.: In search of automatic rhythm analysis methods for Turkish and Indian art music. J. New Music Res. 43, 94–114 (2014)CrossRefGoogle Scholar
  31. 31.
    Sturm, B.: Evaluating music emotion recognition: Lessons from music genre recognition? In: Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6 (2013)Google Scholar
  32. 32.
    Tzanetakis, G., Cook, P.: Musical genre classification of audio signals. IEEE Trans. Speech Audio Process. 10(5), 293–302 (2002)CrossRefGoogle Scholar
  33. 33.
    Vatolkin, I., Preuß, M., Rudolph, G., Eichhoff, M., Weihs, C.: Multi-objective evolutionary feature selection for instrument recognition in polyphonic audio mixtures. Soft Comput. Fusion Found. Methodologies Appl. 16(12), 2027–2047 (2012)Google Scholar
  34. 34.
    Vatolkin, I., Rudolph, G., Weihs, C.: Evaluation of album effect for feature selection in music genre recognition. In: Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR), pp. 169–175 (2015)Google Scholar
  35. 35.
    Zitzler, E., Thiele, L.: Multiobjective optimization using evolutionary algorithms - A comparative case study. In: Proceedings of the 5th International Conference on Parallel Problem Solving from Nature (PPSN), pp. 292–304 (1998)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Computer ScienceTU DortmundDortmundGermany

Personalised recommendations