Title :

Relevance of musical features for cadence detection

Author(s) :

Bigo, Louis [Auteur]
Algomus
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Feisthauer, Laurent [Auteur]
Algomus
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Giraud, Mathieu [Auteur]
Algomus
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Leve, Florence [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Algomus
Modélisation, Information et Systèmes - UR UPJV 4290 [MIS]

Conference title :

International Society for Music Information Retrieval Conference (ISMIR 2018)

City :

Paris

Country :

France

Start date of the conference :

2018

English keyword(s) :

Music information retrieval
Cadence
Classification
Harmony
Voice leading

HAL domain(s) :

Sciences de l'Homme et Société/Musique, musicologie et arts de la scène
Informatique [cs]/Son [cs.SD]

English abstract : [en]

Cadences, as breaths in music, are felt by the listener or studied by the theorist by combining harmony, melody, texture and possibly other musical aspects. We formalize and discuss the significance of 44 cadential features, ...
Show more >Cadences, as breaths in music, are felt by the listener or studied by the theorist by combining harmony, melody, texture and possibly other musical aspects. We formalize and discuss the significance of 44 cadential features, correlated with the occurrence of cadences in scores. These features describe properties at the arrival beat of a cadence and its surroundings, but also at other onsets heuristically identified to pinpoint chords preparing the cadence. The representation of each beat of the score as a vector of cadential features makes it possible to reformulate cadence detection as a classification task. An SVM classifier was run on two corpora from Bach and Haydn totaling 162 perfect authentic cadences and 70 half cadences. In these corpora, the classifier correctly identified more than 75% of perfect authentic cadences and 50% of half cadences, with low false positive rates. The experiment results are consistent with common knowledge that classification is more complex for half cadences than for authentic cadences.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

European Project :

Médiations visuelles, Culture numérique et Création (ERDF, Région Hauts-de-France)

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL