Global Expectation-Violation as Fitness Function in Evolutionary Composition

Authors:
Tim Murray Browne;Charles Fox
Affiliations:
Computing Laboratory, University of Oxford,;Adaptive Behaviour Research Group, University of Sheffield,
Venue:
EvoWorkshops '09 Proceedings of the EvoWorkshops 2009 on Applications of Evolutionary Computing: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG
Year:
2009

Citing 6
Cited 1

Machine models of music

Machine models of music
Music and computer composition

Communications of the ACM
Bayesian computation in recurrent neural circuits

Neural Computation
Blues for Gary: Design Abstractions for a Jazz Improvisation Assistant

Electronic Notes in Theoretical Computer Science (ENTCS)
Scaffolding for interactively evolving novel drum tracks for existing songs

Evo'08 Proceedings of the 2008 conference on Applications of evolutionary computing
Open problems in evolutionary music and art

EC'05 Proceedings of the 3rd European conference on Applications of Evolutionary Computing

AI methods in algorithmic composition: a comprehensive survey

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

Previous approaches to Common Practice Period style automated composition --- such as Markov models and Context-Free Grammars (CFGs) --- do not well characterise global, context-sensitive structure of musical tension and release. Using local musical expectation violation as a measure of tension, we show how global tension structure may be extracted from a source composition and used in a fitness function. We demonstrate the use of such a fitness function in an evolutionary algorithm for a highly constrained task of composition from pre-determined musical fragments. Evaluation shows an automated composition to be effectively indistinguishable from a similarly constrained composition by an experienced composer.