n-gram-based approach to composer recognition

Downloads

Authors

  • Jacek WOŁKOWICZ Warsaw University of Technology, Institute of Radioelectronics; Dalhousie University, Faculty of Computer Science, Canada
  • Zbigniew KULKA Warsaw University of Technology, Institute of Radioelectronics
  • Vlado KEŠELJ Dalhousie University, Faculty of Computer Science, Canada

Abstract

This paper describes how tools provided by Natural Language Processing and Information Retrieval can be applied to music. A method of converting complex musical structure to features (n-grams) corresponding with words of text was introduced. Mutual correspondence between both representations was shown by demonstrating certain important regularities known from text processing, which may also be found in music. The problem of automatic composer attribution to which statistical analysis of n-gram profiles known from statistical NLP was applied served as a case study. A MIDI files corpus of piano pieces was chosen as the source of data.

Keywords:

composer recognition, music processing, music information retrieval (MIR), n-grams, MIDI