Robust estimation, interpretation and assessment of likelihood ratios in forensic speaker recognition

Biblos-e Archivo/Manakin Repository

Show simple item record

dc.contributor.author González-Rodríguez, Joaquín
dc.contributor.author Drygajlo, Andrzej
dc.contributor.author Ramos, Daniel
dc.contributor.author García-Gomar, Marta
dc.contributor.author Ortega-García, Javier
dc.contributor.other UAM. Departamento de Ingeniería Informática es_ES
dc.date.accessioned 2015-02-06T17:05:35Z
dc.date.available 2015-02-06T17:05:35Z
dc.date.issued 2006-04
dc.identifier.citation Computer Speech & Language 20.2-3 (2006): 331-335 en_US
dc.identifier.issn 0885-2308 (print) en_US
dc.identifier.issn 1095-8363 (online) en_US
dc.identifier.uri http://hdl.handle.net/10486/663651
dc.description This is the author’s version of a work that was accepted for publication in Computer Speech & Language. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Computer Speech & Language,20, 2-3, (2005)] DOI: 10.1016/j.csl.2005.08.005 en_US
dc.description Proceedings of Odyssey 2004: The speaker and Language Recognition Workshop (Toledo, Spain) en_US
dc.description.abstract In this contribution, the Bayesian framework for interpretation of evidence when applied to forensic speaker recognition is introduced. Different aspects of the use of voice as evidence in the court are addressed, as well as the use by the forensic expert of the likelihood ratio as the right way to express the strength of the evidence. Details on computation procedures of likelihood ratios (LR) are given, along with the assessment tools and methods to validate the performance of these Bayesian forensic systems. However, due to the practical scarcity of suspect data and the mismatched conditions between traces and reference populations common in daily casework, significant errors appear in LR estimation if specific robust techniques are not applied. Original contributions for the robust estimation of likelihood ratios are fully described, including TDLRA (target dependent likelihood ratio alignment), oriented to guarantee the presumption of innocence of suspected but non-perpetrators speakers. These algorithms are assessed with extensive Switchboard experiments but moreover through blind LR-based submissions to both NFI-TNO 2003 Forensic SRE and NIST 2004 SRE, where the strength of the evidence was successfully provided for every questioned speech-suspect recording pair in the respective evaluations. en_US
dc.description.sponsorship This work was in part supported by the Spanish Ministry for Science and Technology under projects TIC2003-09068-C02-01 and TIC2003-08382-C05-01. en_US
dc.format.extent 45 págs. es_ES
dc.format.mimetype application/pdf en
dc.language.iso eng en
dc.publisher Elsevier BV
dc.relation.ispartof Computer Speech and Language en_US
dc.rights © 2005 Elsevier B.V. All rights reserved en_US
dc.subject.other Forensic Speaker Recognition en_US
dc.subject.other Evidence en_US
dc.subject.other Interpretation en_US
dc.subject.other Robust en_US
dc.subject.other Bayesian likelihood ratio en_US
dc.subject.other Tippett plots en_US
dc.title Robust estimation, interpretation and assessment of likelihood ratios in forensic speaker recognition en_US
dc.type article en
dc.type conferenceObject en
dc.subject.eciencia Informática es_ES
dc.subject.eciencia Telecomunicaciones es_ES
dc.relation.publisherversion http://dx.doi.org/10.1016/j.csl.2005.08.005
dc.identifier.doi 10.1016/j.csl.2005.08.005
dc.identifier.publicationfirstpage 331
dc.identifier.publicationissue 2-3
dc.identifier.publicationlastpage 335
dc.identifier.publicationvolume 20
dc.relation.eventdate May 31 - June 3, 2004 en_US
dc.relation.eventplace Toledo (Spain) en_US
dc.relation.eventtitle The Speaker and Language Recognition Workshop, ODYSSEY 2004 en_US
dc.type.version info:eu-repo/semantics/acceptedVersion en
dc.contributor.group Análisis y Tratamiento de Voz y Señales Biométricas (ING EPS-002) es_ES
dc.rights.cc Reconocimiento – NoComercial – SinObraDerivada es_ES
dc.rights.accessRights openAccess en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record