Clustering-based genre prediction on music data

ABSTRACT

In this work, we study the problem of genre prediction on music data. The prediction is based on a genre map, which is constructed from clustering training music data. We make use of a novel algorithm which captures the structural distances from music data and achieves a high clustering accuracy. Preliminary experiments are conducted and discussed.

REFERENCES

• 1: S. R. Alten, Audio in Media, Thomson Wadsworth, Belmont, CA, 7th edn., 2005.
• 2: J. J Aucouturier and R. Pachet, 'Representing musical genre: A state of the art', Journal of New Music Research, 32, 83--93, (2003).
• 3: J. Han and M. Kamber, Data Mining, Morgan Kaufmann, San Francisco, CA, 2nd edn., 2006.
• 4: George Mitri , Alexandra L. Uitdenbogerd , Vic Ciesielski, Automatic music classification problems, Proceedings of the 27th Australasian conference on Computer science, p.315-322, January 01, 2004, Dunedin, New Zealand
• 5: J. Reed and C. H. Lee, 'A study on music genre classification based on universal acoustic models', in In Proceedings the 7th International Conference on Music Information Retrieval, pp. 89--94, (2006).
• 6: N. Scaringella, G. Zoia, and D. Mlynek, 'Automatic genre classification of music content: a survey', IEEE Signal Processing Magazine, 23, 133--141, (2006).
• 7: E. Slim, R. Gael, and D. Bertrand, 'Instrument recognition in polyphonic music based on automatic taxonomies', in IEEE '06: Transactions on Speech and Audio Processing, pp. 68--80, Piscataway, NJ, USA, (2006). IEEE Signal Processing Society.