Key-independent classification of harmonic change in musical audio

Ernest Li, Juan Pablo Bello

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

Abstract

We introduce a novel method for describing the harmonic development of a musical signal by using only low-level audio features. Our approach uses Euclidean and phase distances in a Tonal Centroid space. Both measurements are taken between successive chroma partitions of a harmonically segmented signal, for each of three harmonic circles representing fifths, major thirds, and minor thirds. The resulting feature vector can be used to quantify a string of successive chord changes according to changes in chord quality and movement of the chordal root. We demonstrate that our feature set can provide both unique classification and accurate identification of harmonic changes, while resisting variations in orchestration and key.

Original languageEnglish (US)
Title of host publicationAudio Engineering Society - 123rd Audio Engineering Society Convention 2007
Pages1061-1068
Number of pages8
StatePublished - Dec 1 2007
Event123rd Audio Engineering Society Convention 2007 - New York, NY, United States
Duration: Oct 5 2007Oct 8 2007

Publication series

NameAudio Engineering Society - 123rd Audio Engineering Society Convention 2007
Volume2

Other

Other123rd Audio Engineering Society Convention 2007
CountryUnited States
CityNew York, NY
Period10/5/0710/8/07

    Fingerprint

ASJC Scopus subject areas

  • Modeling and Simulation
  • Acoustics and Ultrasonics

Cite this

Li, E., & Bello, J. P. (2007). Key-independent classification of harmonic change in musical audio. In Audio Engineering Society - 123rd Audio Engineering Society Convention 2007 (pp. 1061-1068). (Audio Engineering Society - 123rd Audio Engineering Society Convention 2007; Vol. 2).