Moulieras, S. and Pachet, F. Maximum entropy models for generation of expressive music. arXiv:1610.03606, October 2016. https://arxiv.org/abs/1610.03606

Sony CSL authors: Simon Moulieras, Fran├žois Pachet

Abstract

In the context of contemporary monophonic music, expression can be seen as the difference between a musical performance and its symbolic representation, i.e. a musical score. In this paper, we show how Maximum Entropy (MaxEnt) models can be used to generate musical expression in order to mimic a human performance. As a training corpus, we had a professional pianist play about 150 melodies of jazz, pop, and latin jazz. The results show a good predictive power, validating the choice of our model. Additionally, we set up a listening test whose results reveal that on average, people significantly prefer the melodies generated by the MaxEnt model than the ones without any expression, or with fully random expression. Furthermore, in some cases, MaxEnt melodies are almost as popular as the human performed ones.

Keywords: Artificial, Intelligence

Downloads

[PDF] Adobe Acrobat PDF file

BibTeX entry

@TECHREPORT { moulieras:16a, AUTHOR="Moulieras, S. and Pachet, F.", INSTITUTION="arXiv:1610.03606", MONTH="October", NOTE="https://arxiv.org/abs/1610.03606", TITLE="Maximum entropy models for generation of expressive music", YEAR="2016", }