KIT | KIT-Bibliothek | Impressum | Datenschutz

Melodic segmentation: evaluating the performance of algorithms and musical experts

Hoethker, Karin; Thom, Belinda; Spevak, Christian


We review several segmentation algorithms, qualitatively
highlighting their strengths and weaknesses. We also
provide a detailed quantitative evaluation of two existing
approaches, Temperley's Grouper and Cambouropoulos' Local
Boundary Detection Model. In order to facilitate the comparison
of an algorithm's performance with human behavior, we compiled a
corpus of melodic excerpts in different musical styles and
collected individual segmentations from 19 musicians. We then
empirically assessed the algorithms' performance by observing
how well they can predict both the musicians' segmentations and
data taken from the Essen folk song collection.

Open Access Logo

Volltext §
DOI: 10.5445/IR/20982002
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Logik, Komplexität und Deduktionssysteme (ILKD)
Publikationstyp Buch
Publikationsjahr 2002
Sprache Englisch
Identifikator urn:nbn:de:swb:90-AAA209820029
KITopen-ID: 20982002
Erscheinungsvermerk Karlsruhe 2002. (Interner Bericht. Fakultät für Informatik, Universität Karlsruhe. 2002,3.)
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page