Pachet, F., Papadopoulos, A. and Roy, P. Sampling Variations of Sequences for Structured Music Generation. Proceedings of the 18th International Society for Music Information Retrieval Conference, pages 23-27, Suzhou, China, October 2017 ISMIR.

Sony CSL authors: Fran├žois Pachet, Pierre Roy


Recently, machine-learning techniques have been success- fully used for the generation of complex artifacts such as music or text. However, these techniques are still unable to capture and generate artifacts that are convincingly struc- tured. In particular, musical sequences do not exhibit pat- tern structure, as typically found in human composed mu- sic. We present an approach to generate structured se- quences, based on a mechanism for sampling efficiently variations of musical sequences. Given an input sequence and a statistical model, this mechanism uses belief propa- gation to sample a set of sequences whose distance to the input sequence is approximately within specified bounds. This mechanism uses local fields to bias the generation. We show experimentally that sampled sequences are in- deed closely correlated to the standard musical similarity function defined by Mongeau and Sankoff. We then show how this mechanism can be used to implement composi- tion strategies that enforce arbitrary structure on a musical lead sheet generation problem. We illustrate our approach with a convincingly structured generated lead sheet in the style of the Beatles.

Keywords: Machine, Learning


[PDF] Adobe Acrobat PDF file

BibTeX entry

@INPROCEEDINGS { pachet:17d, ADDRESS="Suzhou, China", AUTHOR="Pachet, F. and Papadopoulos, A. and Roy, P.", BOOKTITLE="Proceedings of the 18th International Society for Music Information Retrieval Conference", MONTH="October", PAGES="23-27", PUBLISHER="ISMIR", TITLE="Sampling Variations of Sequences for Structured Music Generation", YEAR="2017", }