The discovery of new sounds can inspire creativity, and various approaches have been explored in that effort. One approach is the application of evolutionary algorithms to sound synthesis. The work presented here is related to those efforts and focuses on the properties of pattern-producing networks and neuroevolution. The authors chronicle a journey of concept development and implementation iterations. A discussion of a browser-based environment facilitating such explorations is followed by an account of a migration to a more flexible execution technology stack, using the Web Audio API. As a result of that process, the authors introduce a system consisting of a software library and a command-line utility that facilitates further investigations. Those products are intended to serve as tools for further explorations of the applicability of evolutionary algorithms to the synthesis and discovery of inspiring sounds.

Authors: Jónsson, Björn Þór; Erdem, Çagri; Glette, Kyrre
Affiliations: RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Norway; Department of Informatics, University of Oslo, Norway(See document for exact affiliation information.)
JAES Volume 72 Issue 4 pp. 257-266; April 2024
Publication Date: April 2, 2024 Import into BibTeX
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=22395

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD JAES72)   /jaes72/4/pg257.pdf

DOI: https://doi.org/10.17743/jaes.2022.0137

Start a discussion about this report!