By Bob L. Sturm, Oded Ben-Tal, Úna Monaghan, Nick Collins, Dorien Herremans, Elaine Chew, Gaëtan Hadjeres, Emmanuel Deruty, and François Pachet.
Journal of New Music Research 48(1), 36–55 (2019). First published online in 2018. DOI: 10.1080/09298215.2018.1515233.
Read the accepted manuscript (PDF) · Publisher version
About the paper
The authors worked with musicians to create pieces using machine learning and presented the results in a public concert. They used the experience to ask what makes these tools useful to musicians and how that should guide future research.
Abstract
Research applying machine learning to music modeling and generation typically proposes model architectures, training methods and datasets, and gauges system performance using quantitative measures like sequence likelihoods and/or qualitative listening tests. Rarely does such work explicitly question and analyse its usefulness for and impact on real-world practitioners, and then build on those outcomes to inform the development and application of machine learning. This article attempts to do these things for machine learning applied to music creation. Together with practitioners, we develop and use several applications of machine learning for music creation, and present a public concert of the results. We reflect on the entire experience to arrive at several ways of advancing these and similar applications of machine learning to music creation.
Related work
One of the case studies combines melodies generated by folk-rnn with harmonizations from DeepBach.