Automatic characterisation of musical style

Martin D Westhead, Alan Smaill

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This paper describes a system for automatically characterising musical style using motifs. Motifs are patterns of rhythms or pitches common to more than one piece of music in a style. The Style Analysis with Motifs (SAM) system uses an original classification technique and is able to learn to distinguish between different styles with a success rate of over 95%. It is suggested that since motifs can be used to automatically discriminate between different styles effectively, they may be very important in the way humans achieve the task.
Original languageEnglish
Title of host publicationMusic Education: An Artificial Intelligence Approach
Subtitle of host publicationProceedings of a Workshop held as part of AI-ED 93, World Conference on Artificial Intelligence in Education, Edinburgh, Scotland, 25 August 1993
Number of pages14
Publication statusPublished - 1994

Cite this