Statistical Models for Analysing and Generating Music

Topic Description

The generation of music, in a given style, from a corpus, remains an open problem. Tackling this challenge is a way to investigate the nature of creativity and gain an increased understanding of how music works. Statistical approaches have been developed which show a lot of promise, and have the advantage of flexibility compared to rule-based approaches.

In this project you will investigate how current approaches to music generation can be improved to increase stylistic success and be made more creative. Evaluation the outputs of music generation systems is critical, and will be a central part of the project.

One variant on this project would be to look at collaborative creativity between a person and machine. Or indeed, group creativity. We are happy to consider other variations on the theme!

Skills Required:

Software development skills

Knowledge of appropriate music theory

Knowledge of statistics/maths useful

Experience with experimental design useful

Background Reading:

T. Collins, R. Laney, A. Willis, and P. H. Garthwaite. Developing and evaluating computational models of musical style. Artificial Intelligence for Engineering Design, Analysis and Manufacturing 30(1):16-43, 2016.

Tom Collins. Improved methods for pattern discovery in music, with applications in automated stylistic composition. PhD thesis, Faculty of Mathematics, Computing and Technology, The Open University, 2011. Available at:

T. Collins, R. Laney, A. Willis, and P. H. Garthwaite. Chopin, mazurkas and Markov. Significance, 8(4):154-159, 2011.

T. Collins, J. Thurlow, R. Laney, A. Willis, and P. H. Garthwaite. A comparative evaluation of algorithms for discovering translational patterns in baroque keyboard works. In J. S. Downie and R. C.Veltkamp, editors, Proceedings of the 11th International Conference on Music Information Retrieval (ISMIR), pages 3-8, Utrecht, The Netherlands, 2010.

T. Collins, R. Laney, A. Willis, and P. H. Garthwaite. Using
discovered polyphonic patterns to filter computer-generated music. In Proceedings of the International Conference
on Computational Creativity (ICCC-X), pages 1-10, Lisbon, Portugal, 2010.

T. Collins, R. Laney, A. Willis, and P. H. Garthwaite. Modeling pattern importance in Chopin’s mazurkas. Music Perception, 28:387-414, 2011.

R. P. Whorley, G. A. Wiggins, C. Rhodes, and M. T. Pearce. Multiple viewpoint systems: Time complexity and the construction of domains for complex musical viewpoints in the harmonization problem. Journal of New Music
Research, 42(3):237-266, 2013.

R. P. Whorley. The Construction and Evaluation of Statistical Models of Melody and Harmony. PhD thesis, Department of Computing, Goldsmiths, University of London, UK,

R. P. Whorley and D. Conklin. Improved iterative random walk for four-part harmonization. In T.Collins, D. Meredith, and A. Volk, editors, Mathematics and Computation in Music 2015, LNAI 9110.

Report an error on this page