DSpace Repository

Maximum likelihood Linear Programming Data Fusion for Speaker Recognition

Show simple item record

dc.contributor Universitat de Vic. Escola Politècnica Superior
dc.contributor Universitat de Vic. Grup de Recerca en Tecnologies Digitals
dc.contributor.author Monte-Moreno, Enric
dc.contributor.author Chetouani, Mohamed
dc.contributor.author Faundez-Zanuy, Marcos
dc.contributor.author Solé-Casals, Jordi
dc.date.accessioned 2013-02-13T09:00:04Z
dc.date.available 2013-02-13T09:00:04Z
dc.date.created 2009
dc.date.issued 2009
dc.identifier.citation MONTE-MORENO, Enric i altres . "Maximum likelihood linear programming data fusion for speaker recognition". A: Speech Communication, 2009, vol. 51, núm. 9, pàg. 820-830 ca_ES
dc.identifier.issn 0167-6393
dc.identifier.uri http://hdl.handle.net/10854/2075
dc.description.abstract Biometric system performance can be improved by means of data fusion. Several kinds of information can be fused in order to obtain a more accurate classification (identification or verification) of an input sample. In this paper we present a method for computing the weights in a weighted sum fusion for score combinations, by means of a likelihood model. The maximum likelihood estimation is set as a linear programming problem. The scores are derived from a GMM classifier working on a different feature extractor. Our experimental results assesed the robustness of the system in front a changes on time (different sessions) and robustness in front a change of microphone. The improvements obtained were significantly better (error bars of two standard deviations) than a uniform weighted sum or a uniform weighted product or the best single classifier. The proposed method scales computationaly with the number of scores to be fussioned as the simplex method for linear programming. ca_ES
dc.format application/pdf
dc.format.extent 19 p. ca_ES
dc.language.iso eng ca_ES
dc.publisher Elsevier ca_ES
dc.rights (c) 2009 Elsevier. Published article is available at: http://dx.doi.org/10.1016/j.specom.2008.05.009
dc.subject.other Veu, Processament de ca_ES
dc.title Maximum likelihood Linear Programming Data Fusion for Speaker Recognition ca_ES
dc.type info:eu-repo/semantics/article ca_ES
dc.identifier.doi https://doi.org/10.1016/j.specom.2008.05.009
dc.relation.publisherversion http://dx.doi.org/10.1016/j.specom.2008.05.009
dc.rights.accesRights info:eu-repo/semantics/openAccess ca_ES
dc.type.version info:eu-repo/acceptedVersion ca_ES
dc.indexacio Indexat a SCOPUS
dc.indexacio Indexat a WOS/JCR ca_ES

Files in this item

Show simple item record

Search RIUVic

Advanced Search