Leonardo Music Journal
Issue 7
December 1997

112 pages
ISSN 0961-1215
E-ISSN 1531-4812

Machine Learning and Sound Design: A Case Study

pp.
49
55
Article PDF (706.76 KB)
Abstract

The author discusses the role of Machine Learning (ML) in sound design, focusing on the modeling of a particular aspect of human intelligence that is believed to play an important role in musical creativity: the Generalization of Perceptual Attributes (GPA). GPA is the process by which a listener tries to find common sound attributes when confronted with a series of sounds. The basics of GPA and ML are introduced in the context of ARTIST (ARTificial Intelligence Sound Tools), a prototype case-study system. ARTIST is a sound-design system that works in cooperation with the user, providing useful levels of automated reasoning to render synthesis tasks less laborious and to enable the user to explore alternatives when designing a certain sound.

Originally presented at the Seventh International Symposium on Electronic Art (ISEA 96), Rotterdam, The Netherlands, 16–20 September 1996.