A sequential pattern mining approach to design taxonomies for hierarchical music genre recognition

In this paper, music genre taxonomies are used to design hierarchical classifiers that perform better than flat classifiers. More precisely, a novel method based on sequential pattern mining techniques is proposed for the extraction of relevant characteristics that enable to propose a vector represe...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Pattern analysis and applications : PAA 2018-05, Vol.21 (2), p.363-380
Hauptverfasser:	Iloga, Sylvain, Romain, Olivier, Tchuenté, Maurice
Format:	Artikel
Sprache:	eng
Schlagworte:	Classifiers Cluster analysis Clustering Computer Science Data mining Engineering Sciences Genre Music Pattern analysis Pattern Recognition Performance evaluation Representations Signal and Image processing Taxonomy Theoretical Advances
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!