Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-9710
For citation please use:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLykartsis, Athanasios-
dc.contributor.authorLerch, Alexander-
dc.date.accessioned2020-02-21T15:56:47Z-
dc.date.available2020-02-21T15:56:47Z-
dc.date.issued2015-
dc.identifier.issn2413-6700-
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/10816-
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-9710-
dc.description.abstractIn this paper we present beat histogram features for multiple level rhythm description and evaluate them in a musical genre classification task. Audio features pertaining to various musical content categories and their related novelty functions are extracted as a basis for the creation of beat histograms. The proposed features capture not only amplitude, but also tonal and general spectral changes in the signal, aiming to represent as much rhythmic information as possible. The most and least informative features are identified through feature selection methods and are then tested using Support Vector Machines on five genre datasets concerning classification accuracy against a baseline feature set. Results show that the presented features provide comparable classification accuracy with respect to other genre classification approaches using periodicity histograms and display a performance close to that of much more elaborate up-to-date approaches for rhythm description. The use of bar boundary annotations for the texture frames has provided an improvement for the dance-oriented Ballroom dataset. The comparably small number of descriptors and the possibility of evaluating the influence of specific signal components to the general rhythmic content encourage the further use of the method in rhythm description tasks.en
dc.language.isoenen
dc.relation.ispartof10.14279/depositonce-9530-
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subject.ddc780 Musikde
dc.subject.otherbeat histogramen
dc.subject.othermusicen
dc.subject.othergenre classificationen
dc.subject.otherrhythmen
dc.titleBeat histogram features for rhythm-based musical genre classification using multiple novelty functionsen
dc.typeConference Objecten
tub.accessrights.dnbfreeen
tub.publisher.universityorinstitutionTechnische Universität Berlinen
dc.identifier.eissn2413-6689-
dc.type.versionpublishedVersionen
dcterms.bibliographicCitation.editorSvensson, Peter-
dcterms.bibliographicCitation.editorKristiansen, Ulf-
dcterms.bibliographicCitation.proceedingstitleProceedings of the 18th International Conference on Digital Audio Effectsen
dcterms.bibliographicCitation.originalpublisherplace[Trondheim]en
dcterms.bibliographicCitation.originalpublishernameNorwegian University of Science and Technology, Department of Music and Department of Electronics and Telecommunicationsen
Appears in Collections:FG Audiokommunikation » Publications

Files in This Item:
lykartsis_lerch_2015.pdf
Format: Adobe PDF | Size: 191 kB
DownloadShow Preview
Thumbnail

Item Export Bar

Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.