148265 20250115160155.0 doi 10.1016/j.csl.2020.101078 sideral 117139 ART-2020-117139 eng Mingote, V. Universidad de Zaragoza (orcid)0000-0002-3505-0249 Optimization of the area under the ROC curve using neural network supervectors for text-dependent speaker verification 2020 This paper explores two techniques to improve the performance of text-dependent speaker verification systems based on deep neural networks. Firstly, we propose a general alignment mechanism to keep the temporal structure of each phrase and obtain a supervector with the speaker and phrase information, since both are relevant for a text-dependent verification. As we show, it is possible to use different alignment techniques to replace the global average pooling providing significant gains in performance. Moreover, we also present a novel Back-end approach to train a neural network for detection tasks by optimizing the Area Under the Curve (AUC) as an alternative to the usual triplet loss function, so the system is end-to-end, with a cost function close to our desired measure of performance. As we can see in the experimental section, this approach improves the system performance, since our triplet neural network based on an approximation of the AUC (aAUC) learns how to discriminate between pairs of examples from the same identity and pairs of different identities. The different alignment techniques to produce supervectors in addition to the new Back-end approach were tested on the RSR2015-Part I and RSR2015-Part II database for text-dependent speaker verification, providing competitive results compared to similar size networks using the global average pooling to extract supervectors and using a simple Back-end or triplet loss training. Access copy available to the general public Unrestricted info:eu-repo/grantAgreement/ES/DGA-FEDER/T36-17R info:eu-repo/grantAgreement/ES/MINECO/TIN2017-85854-C4-1-R info:eu-repo/semantics/openAccess by-nc-nd http://creativecommons.org/licenses/by-nc-nd/3.0/es/ 1.899 2020 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE 95 / 139 = 0.683 2020 Q3 T3 0.452 2020 Software 2020 Q2 Human-Computer Interaction 2020 Q2 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Miguel, A. Universidad de Zaragoza (orcid)0000-0001-5803-4316 Ortega, A. Universidad de Zaragoza (orcid)0000-0002-3886-7748 Lleida, E. Universidad de Zaragoza (orcid)0000-0001-9137-4013 5008 800 Universidad de Zaragoza Dpto. Ingeniería Electrón.Com. Área Teoría Señal y Comunicac. 63 (2020), 101078 [16 pp.] Comput. speech lang. COMPUTER SPEECH AND LANGUAGE 0885-2308 558778 http://zaguan.unizar.es/record/148265/files/texto_completo.pdf Postprint 2455349 http://zaguan.unizar.es/record/148265/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:148265 articulos driver 2025-01-15-15:06:03 ARTICLE