Advertisement

Dimensionality Reduction in Harmonic Modeling for Music Information Retrieval

  • Tim Crawford
  • Jeremy Pickens
  • Geraint Wiggins
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3902)

Abstract

A 24-dimensional model for the ‘harmonic content’ of pieces of music has proved to be remarkably robust in the retrieval of polyphonic queries from a database of polyphonic music in the presence of quite significant noise and errors in either query or database document. We have further found that higher-order (1st- to 3rd-order) models tend to work better for music retrieval than 0th-order ones owing to the richer context they capture. However, there is a serious performance cost due to the large size of such models and the present paper reports on some attempts to reduce dimensionality while retaining the general robustness of the method. We find that some simple reduced-dimensionality models, if their parameter settings are carefully chosen, do indeed perform almost as well as the full 24-dimensional versions. Furthermore, in terms of recall in the top 1000 documents retrieved, we find that a 6-dimensional 2nd-order model gives even better performance than the full model. This represents a potential 64-times reduction in model size and search-time, making it a suitable candidate for filtering a large database as the first stage of a two-stage retrieval system.

Keywords

Dimensionality Reduction Retrieval Result Harmonic Modeling Partial Observation Music Information Retrieval 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Pickens, J., Crawford, T.: Harmonic models for polyphonic music retrieval. In: Proceedings of the ACM Conference in Information Knowledge and Management (CIKM), McLean, Virginia (November 2002)Google Scholar
  2. 2.
    Pickens, J., Bello, J.P., Monti, G., Crawford, T., Dovey, M., Sandler, M., Byrd, D.: Polyphonic score retrieval using polyphonic audio queries: A harmonic modeling approach. Journal of New Music Research 32, 223–226 (2003)CrossRefGoogle Scholar
  3. 3.
    Pickens, J., Bello, J.P., Monti, G., Crawford, T., Dovey, M., Sandler, M., Byrd, D.: Polyphonic score retrieval using polyphonic audio queries: A harmonic modeling approach. In: Proceedings of 3rd International Symposium in Music Information Retrieval (ISMIR), IRCAM, Paris, pp. 140–149 (2002)Google Scholar
  4. 4.
    Krumhansl, C.L., Shepard, R.N.: Quantification of the hierarchy of tonal functions within a diatonic context. Journal of Experimental Psychology: Human Perception and Performance 5, 579–594 (1979)Google Scholar
  5. 5.
    Krumhansl, C.: Cognitive Foundations of Musical Pitch. Oxford University Press, New York (1990)Google Scholar
  6. 6.
    Purwins, H., Blankertz, B., Obermayer, K.: A new method for tracking modulations in tonal music in audio data format. In: Amari, S., Giles, C., Gori, M., Piuri, V. (eds.) International Joint Conference on Neural Networks, IJCNN 2000, vol. 6, pp. 270–275 (2000), http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.859408
  7. 7.
    Shmulevich, I., Yli-Harja, O., Coyle, E., Povel, D., Lemström, K.: Perceptual issues in music pattern recognition — complexity of rhythm and key find. Computers in the Humanities 35, 23–35 (2001)CrossRefGoogle Scholar
  8. 8.
    Shmulevich, I., Yli-Harja, O., Coyle, E., Povel, D., Lemström, K.: Perceptual issues in music pattern recognition — complexity of rhythm and key find. In: Proceedings of the AISB 1999 Symposium on Musical Creativity, Florida (1999)Google Scholar
  9. 9.
    Rand, W., Birmingham, W.: Statistical analysis in music information retrieval. In: Proceedings of the 2nd International Symposium on Music Information Retrieval, Indiana University, Bloomington, Indiana, pp. 25–26 (2001)Google Scholar
  10. 10.
    Hoos, H.H., Renz, K., Görg, M.: Guido/mir — an experimental music information retrieval system based on guido music notation. In: Proceedings of the 2nd International Symposium on Music Information Retrieval, pp. 41–50. Indiana University, Bloomington, Indiana (2001)Google Scholar
  11. 11.
    Birmingham, W., Dannenberg, R.B., Wakefield, G.H., Bartsch, M., Bykowski, D., Mazzoni, D., Meek, C., Mellody, M., Rand, M.: Musart: Music retrieval via aural queries. In: Proceedings of the 2nd International Symposium on Music Information Retrieval, pp. 73–81. Indiana University, Bloomington, Indiana (2001)Google Scholar
  12. 12.
    Cleverdon, C.W., Mills, J., Keen, M.: Factors determining the performance of indexing systems; vol. 1, design. Technical report, ASLIB Cranfield Project, Cranfield University, Cranfield, UK (1966), http://hdl.handle.net/1826/861, http://hdl.handle.net/1826/862
  13. 13.
    Cleverdon, C.W., Keen, M.: Factors determining the performance of indexing systems; vol. 2, test results. Technical report, ASLIB Cranfield Project, Cranfield University, Cranfield, UK (1966), http://hdl.handle.net/1826/863
  14. 14.
    TREC: Text retrieval conference, http://trec.nist.gov/
  15. 15.
    Byrd, D., Crawford, T.: Problems of music information retrieval in the real world. Information Processing and Management 38, 249–272 (2002)CrossRefMATHGoogle Scholar
  16. 16.
    Pickens, J.: Harmonic Modeling for Polyphonic Music Retrieval. PhD thesis, University of Massachusetts at Amherst (2004)Google Scholar
  17. 17.
    Sisman, E.: Variations (2005) (accessed July 25, 2005) http://www.grovemusic.com
  18. 18.
    Bello, J.P., Pickens, J.: A robust mid-level representation for harmonic content in music signals. In: Proceedings of the 7th International Conference on Music Information Retrieval, ISMIR 2005, September 2005, Queen Mary College, University of London (2005)Google Scholar
  19. 19.
    Downie, J.S.: Evaluating a Simple Approach to Music Information Retrieval: Conceiving Melodic N-grams as Text. PhD thesis, University of Illinois at Urbana Champaign (1999)Google Scholar
  20. 20.
    Endres, D.M., Schindelin, J.E.: A new metric for probability distributions. IEEE Transactions on Information Theory 49, 1858–1860 (2003)MathSciNetCrossRefMATHGoogle Scholar
  21. 21.
    Center for Computer-Assisted Research in the Humanities, Stanford University (CCARH): Musedata collection of encoded scores, http://www.musedata.org
  22. 22.
    ECOLM: Electronic corpus of lute music, http://www.ecolm.org
  23. 23.
    Casey, M.A.: Acoustic lexemes for organizing internet audio. Contemporary Music Review (accepted for publication, 2005)Google Scholar
  24. 24.
    Pickens, J.: Classifier combination for capturing musical variation. In: Proceedings of the 7th International Conference on Music Information Retrieval, ISMIR 2005, September 2005, Queen Mary College, University of London (2005)Google Scholar
  25. 25.
    OMRAS: Online musical recognition and searching, http://www.omras.org

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tim Crawford
    • 1
  • Jeremy Pickens
    • 2
  • Geraint Wiggins
    • 1
  1. 1.Goldsmiths CollegeUniversity of London, Centre for Cognition, Computation and CultureUK
  2. 2.Department of Computer ScienceKing’s CollegeLondon

Personalised recommendations