Exploring Performance-Based Music Attributes for Stylometric Analysis

Music Information Retrieval (MIR) and modern data mining techniques are applied to identify style markers in midi music for stylometric analysis and author attribution. Over 100 attributes are extracted from a library of 2830 songs then mined using supervised learning data mining techniques. Two attributes are identified that provide high informational gain. These attributes are then used as style markers to predict authorship. Using these style markers the authors are able to correctly distinguish songs written by the Beatles from those that were not with a precision and accuracy of over 98 per cent. The identification of these style markers as well as the architecture for this research provides a foundation for future research in musical stylometry.

• Abdellghani Bellaachia
• Edward Jimenez

• Music Information Retrieval
• Music Data Mining
• Stylometry.

[1] H.Somers, "Stylometry and Authorship", School of Computer Science
University of Manchester (Online). Available:
http://personalpages.manchester.ac.uk/staff/harold.somers/LELA30922/
Authorship.ppt.
[2] A. Simoes, A. Louenco, and J. Joao Almeida, "Using Text Mining
Techniques for Classical Music Scores Analysis", University of Minho,
2007.
[3] V. Vara, (2005, Oct. 6) "Unraveling Music-s DNA," Wall Street Journal
Online (Online). Available:
http://online.wsj.com/public/article/SB112784146741053451-
FYfrFWfQ29np0rdqx33NDS8LtWM_20051105.html?mod=tff_article
[4] Midi Manufactures Association, "General MIDI 1, 2 and Lite
Specifications" (Online). Available:
http://www.midi.org/techspecs/gm.php.
[5] C. McKay, (2004, June) "Automatic Genre Classification of MIDI
Recordings", McGill University, Montreal.
[6] N Orio, "Music Retrieval: A tutorial and Review", Now Publishers Inc,
2006.
[7] Peter van Kranenburg, "Musical style recognition - a quantitative
approach", University of Utrecht, Netherlands, Proceedings of the
Conference on Interdisciplinary Musicology, 2004.
[8] E. Stamatatos, N. Fakotakis, and G. Kokkinakis, "Automatic Text
Categorization in Terms of Genre and Author", University of Patras,
Computational Linuistics, Dec. 2000.