Evolving the process of a virtual composer

  • Csaba Sulyok
  • Andrew McPherson
  • Christopher Harte
Article

DOI: 10.1007/s11047-016-9561-6

Cite this article as:
Sulyok, C., McPherson, A. & Harte, C. Nat Comput (2016). doi:10.1007/s11047-016-9561-6

Abstract

In this paper we present a genetic programming system that evolves the music composition process rather than the musical product. We model the composition process using a Turing-complete virtual register machine, which renders musical pieces. These are evaluated using a series of fitness tests, which judge their statistical similarity against a corpus of Bach keyboard exercises. We explore the space of parameters for the system, looking specifically at population size, single-versus multi-track pieces and virtual machine instruction set design. Results demonstrate that the methodology succeeds in creating pieces of music that converge towards the properties of the chosen corpus. The output pieces exhibit certain musical qualities (repetition and variation) not specifically targeted by our fitness tests, emerging solely based on the statistical similarities.

Keywords

Evolutionary algorithms Music generation Music evaluation Corpus-based similarity tests 

Copyright information

© Springer Science+Business Media Dordrecht 2016

Authors and Affiliations

  • Csaba Sulyok
    • 1
  • Andrew McPherson
    • 1
  • Christopher Harte
    • 2
  1. 1.Queen Mary University of LondonLondonUK
  2. 2.Melodient Ltd.LeedsUK

Personalised recommendations