Comparative Analysis of Content-Based and Context-Based Similarity on Musical Data

  • C. Boletsis
  • A. Gratsani
  • D. Chasanidou
  • I. Karydis
  • K. Kermanidis
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 364)

Abstract

Similarity measurement between two musical pieces is a hard problem. Humans perceive such similarity by employing a large amount of contextually semantic information. Commonly used content-based me-thodologies rely on information that includes little or no semantic information, and thus are reaching a performance “upper bound”. Recent research pertaining to contextual information assigned as free-form text (tags) in social networking services has indicated tags to be highly effective in improving the accuracy of music similarity. In this paper, we perform a large scale (20k real music data) similarity measurement using mainstream content and context methodologies. In addition, we test the accuracy of the examined methodologies against not only objective metadata but real-life user listening data as well. Experimental results illustrate the conditionally substantial gains of the context-based methodologies and a not so close match these methods with the real user listening data similarity.

References

  1. 1.
    Apple: iTunes - Everything you need to be entertained, http://www.apple.com/itunes/
  2. 2.
    Aucouturier, J.J., Pachet, F.: Music similarity measures: What’s the use? In: Proc. International Symposium on Music Information Retrieval, pp. 157–1638 (2003)Google Scholar
  3. 3.
    Aucouturier, J.J., Pachet, F.: Improving timbre similarity: How high is the sky? Journal of Negative Results in Speech and Audio Sciences 1 (2004)Google Scholar
  4. 4.
    Baumann, S., Hummel, O.: Using cultural metadata for artist recommendations. In: International Conference on Proc. Web Delivering of Music (2003)Google Scholar
  5. 5.
    Berenzweig, A., Logan, B., Ellis, D.P.W., Whitman, B.P.W.: A large-scale evaluation of acoustic and subjective music-similarity measures. Computer Music Journal 28, 63–76 (2004)CrossRefGoogle Scholar
  6. 6.
    Byrd, D.: Organization and searching of musical information, course syllabus (2008), http://www.informatics.indiana.edu/donbyrd/Teach/I545Site-Spring08/SyllabusI545.html
  7. 7.
    Dumais, S.T., Furnas, G.W., Landauer, T.K., Deerwester, S.: Using latent semantic analysis to improve information retrieval. In: Proc. Conference on Human Factors in Computing, pp. 281–285 (1988)Google Scholar
  8. 8.
    Karydis, I., Laopodis, V.: Web 2.0 cultural networking. In: Proc. Pan-Hellenic Conference in Informatics (2009)Google Scholar
  9. 9.
    Karydis, I., Nanopoulos, A.: Audio-to-tag mapping: A novel approach for music similarity computation. In: Proc. IEEE International Conference on Multimedia & Expo (2011)Google Scholar
  10. 10.
    Knees, P., Pampalk, E., Widmer, G.: Artist classification with web-based data. In: Proc. International Symposium on Music Information Retrieval, pp. 517–524 (2004)Google Scholar
  11. 11.
    Kontaki, M., Karydis, I., Manolopoulos, Y.: Content-based information retrieval in streaming music. In: Proc. Pan-Hellenic Conference in Informatics, pp. 249–259 (2007)Google Scholar
  12. 12.
    Lamere, P.: Social tagging and music information retrieval. Journal of New Music Research 37, 101–114 (2008)CrossRefGoogle Scholar
  13. 13.
    Last.fm: Listen to internet radio and the largest music catalogue online, http://www.last.fm
  14. 14.
    Levy, M., Sandler, M.: Learning latent semantic models for music from social tags. Journal of New Music Research 37(2), 137–150 (2008)CrossRefGoogle Scholar
  15. 15.
    Levy, M., Sandler, M.: Music information retrieval using social tags and audio. IEEE Transactions on Multimedia 11, 383–395 (2009)CrossRefGoogle Scholar
  16. 16.
    Logan, B., Ellis, D.P.W., Berenzweig, A.: Toward evaluation techniques for music similarity. In: Proc. International Conference on Multimedia & Expo 2003 (2003)Google Scholar
  17. 17.
    McEnnis, D., McKay, C., Fujinaga, I.: jAudio: A feature extraction library. In: Proc. International Conference on Music Information Retrieval (2005)Google Scholar
  18. 18.
    McEnnis, D., McKay, C., Fujinaga, I.: jAudio: Additions and improvements. In: Proc. International Conference on Music Information Retrieval, p. 385 (2006)Google Scholar
  19. 19.
    McFee, B., Barrington, L., Lanckriet, G.: Learning similarity from collaborative filters. In: International Society of Music Information Retrieval Conference, pp. 345–350 (2010)Google Scholar
  20. 20.
    MIREX: Music Information Retrieval Evaluation eXchangeGoogle Scholar
  21. 21.
    Mitrovic, D., Zeppelzauer, M., Breiteneder, C.: Features for content-based audio retrieval. In: Advances in Computers: Improving the Web, vol. 78, pp. 71–150. Elsevier, Amsterdam (2010)CrossRefGoogle Scholar
  22. 22.
    Pampalk, E.: Audio-based music similarity and retrieval: Combining a spectral similarity model with information extracted from fluctuation patterns. In: Proc. International Symposium on Music Information Retrieval (2006)Google Scholar
  23. 23.
    Pampalk, E.: Computational Models of Music Similarity and their Application in Music Information Retrieval. Ph.D. thesis, Vienna University of Technology, Vienna, Austria (2006)Google Scholar
  24. 24.
    Pampalk, E., Dixon, S., Widmer, G.: On the evaluation of perceptual similarity measures for music. In: Proc. International Conference on Digital Audio Effects, pp. 7–12 (2003)Google Scholar
  25. 25.
    Pampalk, E.: MA Toolbox, http://www.pampalk.at/ma/
  26. 26.
    Porter, M.F.: The porter stemming algorithm, http://tartarus.org/~martin/PorterStemmer/
  27. 27.
    Slaney, M., Weinberger, K., White, W.: Learning a metric for music similarity. In: Proc. International Conference on Music Information Retrieval, pp. 313–318 (2008)Google Scholar
  28. 28.
    Wang, D., Li, T., Ogihara, M.: Are tags better than audio? The effect of joint use of tags and audio content features for artistic style clustering. In: Proc. International Society for Music Information Retrieval, pp. 57–62 (2010)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2011

Authors and Affiliations

  • C. Boletsis
    • 1
  • A. Gratsani
    • 1
  • D. Chasanidou
    • 1
  • I. Karydis
    • 1
  • K. Kermanidis
    • 1
  1. 1.Dept. of InformaticsIonian UniversityKerkyraGreece

Personalised recommendations