Graph-Based Mutations for Music Generation

Maziar Kanani, Seán O’Leary, James McDermott

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Our study aims to compare the effects of direct mutation and graph-based mutation on representations of music domain. We focus on short tunes from the Irish folk tradition, represented as integer sequences, and use a graph-based representation based on Pathway Assembly (a directed acyclic graph) and the Sequitur algorithm. We define multiple mutation operators to work directly on the sequences or on the graphs, hypothesizing that graph-based mutations will tend to preserve the pattern used per tune, while direct mutation of sequences will tend to destroy patterns, resulting in new generated tunes that are more complex. We perform experiments on a corpus of tunes and apply the mutation operators many times consecutively to analyze their effects.

Original languageEnglish
Title of host publicationGECCO 2023 Companion - Proceedings of the 2023 Genetic and Evolutionary Computation Conference Companion
PublisherAssociation for Computing Machinery (ACM)
Pages1916-1919
Number of pages4
ISBN (Electronic)9798400701207
DOIs
Publication statusPublished - 15 Jul 2023
Event2023 Genetic and Evolutionary Computation Conference Companion, GECCO 2023 Companion - Lisbon, Portugal
Duration: 15 Jul 202319 Jul 2023

Publication series

NameGECCO 2023 Companion - Proceedings of the 2023 Genetic and Evolutionary Computation Conference Companion

Conference

Conference2023 Genetic and Evolutionary Computation Conference Companion, GECCO 2023 Companion
Country/TerritoryPortugal
CityLisbon
Period15/07/2319/07/23

Keywords

  • genetic algorithm
  • genetic programming
  • graph-based mutation
  • music generation
  • Pathway Assembly
  • Sequitur

Fingerprint

Dive into the research topics of 'Graph-Based Mutations for Music Generation'. Together they form a unique fingerprint.

Cite this