Cross recurrence quantification for cover song identification

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Serrà Julià, Joanca
• dc.contributor.author Serra, Xavierca
• dc.contributor.author Andrzejak, Ralph Gregorca
• dc.contributor.other Universitat Pompeu Fabraca
• dc.date.accessioned 2012-02-09T09:47:48Z
• dc.date.available 2012-02-09T09:47:48Z
• dc.date.issued 2009ca
• dc.description.abstract There is growing evidence that nonlinear time series analysis techniques can be used to successfully characterize, classify, or process signals derived from realworld dynamics even though these are not necessarily deterministic and stationary. In the present study we proceed in this direction by addressing an important problem our modern society is facing, the automatic classification of digital information. In particular, we address the automatic identification of cover songs, i.e. alternative renditions of a previously recorded musical piece. For this purpose we here propose a recurrence quantification analysis measure that allows tracking potentially curved and disrupted traces in cross recurrence plots. We apply this measure to cross recurrence /nplots constructed from the state space representation of musical descriptor time series extracted from the raw audio signal. We show that our method identifies cover songs with a higher accuracy as compared to previously published techniques. Beyond the particular application proposed here, we discuss how our approach can be useful for the characterization of a variety of signals from different scientific disciplines. We study coupled Rössler dynamics with stochastically modulated mean frequencies as one concrete example to illustrate this point.en
• dc.description.sponsorship This research has been partially funded by the EU-IP project PHAROS IST-2006-045035 and by the BFU2007-61710 Spanish Ministry of Education and Science grant.en
• dc.format.mimetype application/pdfca
• dc.identifier.citation Serra J, Serra X, Andrzejak R G. Cross recurrence quantification for cover song identification. New Journal of Physics. 2009; 11(093017). DOI 10.1088/1367-2630/11/9/093017ca
• dc.identifier.doi http://dx.doi.org/10.1088/1367-2630/11/9/093017
• dc.identifier.issn 11367-2630ca
• dc.identifier.uri http://hdl.handle.net/10230/16206
• dc.language.iso engca
• dc.publisher Institute of Physics (IOP)ca
• dc.relation.ispartof New Journal of Physics. 2009;11(093017)
• dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/045035
• dc.relation.projectID info:eu-repo/grantAgreement/ES/2PN/BFU2007-61710
• dc.rights © IOP Publishing Ltd and Deutsche Physikalische Gesellschaft. The published version of the article is available at http://iopscience.iop.org/1367-2630/11/9/093017/ca
• dc.rights.accessRights info:eu-repo/semantics/openAccessen
• dc.subject.other Música -- Informàticaca
• dc.subject.other So -- Tractament per ordinadorca
• dc.subject.other Sèries temporals -- Anàlisica
• dc.title Cross recurrence quantification for cover song identificationca
• dc.type info:eu-repo/semantics/articleca
• dc.type.version info:eu-repo/semantics/acceptedVersionen