Automated Partitioning of Tonal Music

Bryan Pardo and William P. Birmingham, The University of Michigan, USA

The work described in this paper provides a set of concise and efficient algorithms for context-free harmonic analysis of tonal music and provides a good first approximation of the harmonic structures in a typical piece of tonal music. HarmAn does this using a relative small set of rules, which do not require an understanding of the tonal context, nor any metrical information to perform the analysis. The results achieved by this system compare well to those achieved by much more complex systems.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.