Feature Extraction Using Pitch Class Profile Information Entropy

  • Maximos A. Kaliakatsos-Papakostas
  • Michael G. Epitropakis
  • Michael N. Vrahatis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6726)


Computer aided musical analysis has led a research stream to explore the description of an entire musical piece by a single value. Combinations of such values, often called global features, have been used for several identification tasks on pieces with symbolic music representation. In this work we extend some ideas that estimate information entropy of sections of musical pieces, to utilize the Pitch Class Profile information entropy for global feature extraction. Two approaches are proposed and tested, the first approach considers musical sections as overlapping sliding onset windows, while the second one as non-overlapping fixed-length time windows.


Pitch Class Profile Information Entropy Global Features Composer Identification 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Madsen, S.T., Widmer, G.: Towards a computational model of melody identification in polyphonic music. In: Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007), Hyderabad, India. Morgan Kaufmann Publishers Inc, San Francisco (2007)Google Scholar
  2. 2.
    Hillewaere, R., Manderick, B., Conklin, D.: Global feature versus event models for folk song classification. In: Proceedings of the 10th International Society for Music Information Retrieval Conference (ISMIR 2009), Kobe, Japan, pp. 729–733 (2009)Google Scholar
  3. 3.
    Kaliakatsos-Papakostas, M.A., Epitropakis, M.G., Vrahatis, M.N.: Musical composer identification through probabilistic and feedforward neural networks. In: Di Chio, C., Brabazon, A., Di Caro, G.A., Ebner, M., Farooq, M., Fink, A., Grahl, J., Greenfield, G., Machado, P., O’Neill, M., Tarantino, E., Urquhart, N. (eds.) EvoApplications 2010. LNCS, vol. 6025, pp. 411–420. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  4. 4.
    Hillewaere, R., Manderick, B., Coklin, D.: Melodic models for polyphonic music classification. In: Proceedings of the 2nd International Workshop on Machine Learning and Music (MML 2009), held in conjunction with (ECML-PKDD 2009), Bled, Slovenia, pp. 19–24 (2009)Google Scholar
  5. 5.
    Kranenburg, P.V., Backer, E.: Musical style recognition - a quantitative approach. In: Parncutt, R., Kessler, A., Zimmer, F. (eds.) Proceedings of the Conference on Interdisciplinary Musicology (CIM 2004), Graz, Austria, pp. 1–10 (2004)Google Scholar
  6. 6.
    Kaliakatsos-Papakostas, M.A., Epitropakis, M.G., Vrahatis, M.N.: Weighted Markov Chain model for musical composer identification. In: Di Chio, C., Brabazon, A., Di Caro, G.A., Drechsler, R., Farooq, M., Grahl, J., Greenfield, G., Prins, C., Romero, J., Squillero, G., Tarantino, E., Tettamanzi, A.G.B., Urquhart, N., Uyar, A.Ş. (eds.) EvoApplications 2011, Part II. LNCS, vol. 6625, pp. 334–343. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  7. 7.
    Liu, Y.W.: Modeling music as markov chains: Composer identification,

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Maximos A. Kaliakatsos-Papakostas
    • 1
  • Michael G. Epitropakis
    • 1
  • Michael N. Vrahatis
    • 1
  1. 1.Computational Intelligence Laboratory (CI Lab), Department of MathematicsUniversity of PatrasGreece

Personalised recommendations