Genre classification of music by tonal harmony

Issue title: Machine Learning and Music

Guest editors: Darrell Conklinx, Christina Anagnostopoulouy and Rafael Ramirezz

Article type: Research Article

Authors: Pérez-Sancho, Carlos^{a; *} | Rizo, David^a | Iñesta, José M.^a | de León, Pedro J. Ponce^a | Kersten, Stefan^b | Ramirez, Rafael^b

Affiliations: [a] Departamento de Lenguajes y Sistemas Informáticos, Universidad de Alicante, Alicante, Spain | [b] Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain | [x] City University London, London, UK | [y] University of Athens, Athens, Greece | [z] Universitat Pompeu Fabra, Baralona, Spain

Correspondence: [*] Corresponding author: Carlos Pérez-Sancho, Apartado de correos 99, E-03080 Alicante, Spain. Tel.: +34 965 37 72; Fax: +34 965 90 93 26; E-mail: cperez@dlsi.ua.es.

Abstract: In this paper we present a genre classification framework for audio music based on a symbolic classification system. Audio signals are transformed into a symbolic representation of harmony using a chord transcription algorithm, based on the computation of harmonic pitch class profiles. Then, language models built from a ground truth of chord progressions for each genre are used to perform classification. We show that chord progressions are a suitable feature to represent musical genre, as they capture the harmonic rules relevant in each musical period or style. Finally, results using both pure symbolic information and chords transcribed from audio-from-MIDI are compared, in order to evaluate the effects of the transcription process in this task.

DOI: 10.3233/IDA-2010-0437

Journal: Intelligent Data Analysis, vol. 14, no. 5, pp. 533-545, 2010