This project developed psychology-inspired techniques for algorithmic generation of music. The project was funded by an Australian Research Council (ARC) Discovery grant. It included statistical analysis of musical score data to ascertain the validity of perceptual theories of implication, prediction, and expectation in musical structures. This lead to sets of ‘rules’ for algorithmic composition. Analysis also revealed appropriate parameter values for those rules that seemed pertinent. Based on these rules we built algorithmic music systems that generated music based on composer-controlled parameters that effect note-level decisions. These generative models were tests with audiences through online surveys and critical review. The findings of the project were published in academic publications in the fields of computer music and music cognition. Creative works that utilised these techniques were performed and exhibited around the world.

Project Team

  • Prof. Andrew R. Brown (Griffith University)
  • Dr. Robert Davidson (University of Queensland)
  • Dr. Toby Gifford (Griffith University)
  • Prof. Eugene Narmour (Pennsylvania University)
  • Prof. Geraint Wiggins (Goldsmiths, University of London)
  • Prof. David Temperly (Eastman School of Music, Rochester)

Figure 1: An implementation of musical rules, shown as computer code and generated notational outcome.


Associate Publications:

  • Brown, A. R., Gifford, T., & Davidson, R. (Accepted 10 October 2013). Psychology-Inspired Techniques for Generative Melodies. Computer Music Journal.
  • Brown, A. R. & Gifford, T. (2013), Prediction and Proactivity in Real-Time Interactive Music Systems, in Musical Metacreation: Papers from the 2013 AIIDE Workshop, AAAI Press, United States.
  • Brown, A. R., Gifford, T., & Davidson, R. (2013). Amplifying Compositional Intelligence: Creating with a psychologically-inspired generative music system. In Proceedings of the International Computer Music Conference, Perth: ICMA, pp. 257-360.
  • Brown, A. R. (2012). Creative Partnerships with Technology: How creativity is enhanced through interactions with generative computational systems. Proceedings of the Eighth Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. Presented at the 1st International Workshop on Musical Metacreation, Stanford, CA: AA      AI.
  • Jones, D., Brown, A. R., & d’ Inverno, M. (2012). “The Extended Composer: Creative reflection and extension with generative tools.” In, J. McCormack & M. d’ Inverno (Eds.) Computers and Creativity (pp. 175–203). London: Springer.
  • Brown, A. R. and Gifford, T. (2010). Interrogating Statistical Models of Music Perception. International Conference on Music Perception and Cognition (pp.715-717). Seattle, Washington: ICMPA.
  • Brown, A. R., Gifford, T., Narmour, E., & Davidson, R. (2009). Generation in Context: An Exploratory Method for Musical Enquiry. The Second International Conference on Music Communication Science (pp.7-10). Sydney: HCSNet.

Associated Create Works:

  • Brown, A. R. (2013) Connections – A real-time generative audio visual installation, selected as part of the [d]Generate exhibition, curated by Gordon Moyes. Gympie Regional Gallery, Australia. 18 June – 10 August 2013.
  • Brown A. R., and Gifford, T. and Davidson, R. (2013) Entanglement, a work for piano, percussion and live electronics. Presented at ICMC 2013, Perth, 15 August 2013.
  • Brown, A. R. (2013) Solo live coding performance of the original work Multiple Beginnings. Live Code Festival, Karlsruhe, Germany, 19 April 2013.
  • Brown, A. R. (2012) Solo live coding performance of Improvised Interactions. Re-new Digital Arts Festival, Copenhagen, Denmark, 20 November 2012.
Smart Music Research