Machine learning of symbolic compositional rules with genetic programming: dissonance treatment in Palestrina

Inden, B ORCID: https://orcid.org/0000-0001-6048-6856 and Anders, T, 2019. Machine learning of symbolic compositional rules with genetic programming: dissonance treatment in Palestrina. PeerJ Computer Science, 5: e244. ISSN 2376-5992

Preview

Text 1256087_Inden.pdf - Published version Download (2MB) | Preview

Abstract

We describe a method for automatically extracting symbolic compositional rules from music corpora. Resulting rules are expressed by a combination of logic and numeric relations, and they can therefore be studied by humans. These rules can also be used for algorithmic composition, where they can be combined with each other and with manually programmed rules. We chose genetic programming (GP) as our machine learning technique, because it is capable of learning formulas consisting of both logic and numeric relations. GP was never used for this purpose to our knowledge. We therefore investigate a well understood case in this study: dissonance treatment in Palestrina’s music. We label dissonances with a custom algorithm, automatically cluster melodic fragments with labelled dissonances into different dissonance categories (passing tone, suspension etc.) with the DBSCAN algorithm, and then learn rules describing the dissonance treatment of each category with GP. Learning is based on the requirement that rules must be broad enough to cover positive examples, but narrow enough to exclude negative examples. Dissonances from a given category are used as positive examples, while dissonances from other categories, melodic fragments without dissonances, purely random melodic fragments, and slight random transformations of positive examples, are used as negative examples.

Item Type:	Journal article
Publication Title:	PeerJ Computer Science
Creators:	Inden, B. and Anders, T.
Publisher:	PeerJ
Date:	2019
Volume:	5
ISSN:	2376-5992
Identifiers:	Number Type 10.7717/peerj-cs.244 DOI 1256087 Other
Rights:	Open access. Distributed under Creative Commons CC-BY 4.0.
Divisions:	Schools > School of Science and Technology
Record created by:	Linda Sullivan
Date Added:	16 Dec 2019 12:19
Last Modified:	16 Dec 2019 12:19
URI:	https://irep.ntu.ac.uk/id/eprint/38864

Actions (login required)

Edit View

Statistics

Views

Downloads