Welcome to the UPF Digital Repository

Cross-collection evaluation for music classification tasks

Show simple item record

dc.contributor.author Bogdanov, Dmitry
dc.contributor.author Porter, Alastair
dc.contributor.author Herrera Boyer, Perfecto
dc.contributor.author Serra, Xavier
dc.date.accessioned 2017-10-23T09:13:52Z
dc.date.available 2017-10-23T09:13:52Z
dc.date.issued 2016
dc.identifier.citation Bogdanov D, Porter A, Herrera P, Serra X. Cross-collection evaluation for music classification tasks. In: Devaney J, Mandel MI, Turnbull D, Tzanetakis G, editors. ISMIR 2016. Proceedings of the 17th International Society for Music Information Retrieval Conference; 2016 Aug 7-11; New York City (NY). [Canada]: ISMIR; 2016. p. 379-85.
dc.identifier.uri http://hdl.handle.net/10230/33061
dc.description Comunicació presentada a la 17th International Society for Music Information Retrieval Conference (ISMIR 2016), celebrada els dies 7 a 11 d'agost de 2016 a Nova York, EUA.
dc.description.abstract Many studies in music classification are concerned with obtaining the highest possible cross-validation result. However, some studies have noted that cross-validation may be prone to biases and that additional evaluations based on independent out-of-sample data are desirable. In this paper we present a methodology and software tools for cross-collection evaluation for music classification tasks. The tools allow users to conduct large-scale evaluations of classifier models trained within the AcousticBrainz platform, given an independent source of ground-truth annotations, and its mapping with the classes used for model training. To demonstrate the application of this methodology we evaluate five models trained on genre datasets commonly used by researchers for genre classification, and use collaborative tags from Last.fm as an independent source of ground truth. We study a number of evaluation strategies using our tools on validation sets from 240,000 to 1,740,000 music recordings and discuss the results.
dc.description.sponsorship This research has received funding from the European Unions Horizon 2020 research and innovation programme under grant agreement No 688382.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher International Society for Music Information Retrieval (ISMIR)
dc.relation.ispartof Devaney J, Mandel MI, Turnbull D, Tzanetakis G, editors. ISMIR 2016. Proceedings of the 17th International Society for Music Information Retrieval Conference; 2016 Aug 7-11; New York City (NY). [Canada]: ISMIR; 2016. p. 379-85.
dc.rights © Dmitry Bogdanov, Alastair Porter, Perfecto Herrera, Xavier Serra. Licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Attribution: Dmitry Bogdanov, Alastair Porter, Perfecto Herrera, Xavier Serra. “Cross-collection evaluation for music classification tasks”, 17th International Society for Music Information Retrieval Conference, 2016.
dc.rights.uri http://creativecommons.org/licenses/by/4.0/
dc.subject.other Música -- Anàlisi
dc.title Cross-collection evaluation for music classification tasks
dc.type info:eu-repo/semantics/conferenceObject
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/688382
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion


This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

Compliant to Partaking