Optimization of the area under the ROC curve using neural network supervectors for text-dependent speaker verification

Mingote, V. (Universidad de Zaragoza) ; Miguel, A. (Universidad de Zaragoza) ; Ortega, A. (Universidad de Zaragoza) ; Lleida, E. (Universidad de Zaragoza)
Optimization of the area under the ROC curve using neural network supervectors for text-dependent speaker verification
Resumen: 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.
Idioma: Inglés
DOI: 10.1016/j.csl.2020.101078
Año: 2020
Publicado en: COMPUTER SPEECH AND LANGUAGE 63 (2020), 101078 [16 pp.]
ISSN: 0885-2308

Factor impacto JCR: 1.899 (2020)
Categ. JCR: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE rank: 95 / 139 = 0.683 (2020) - Q3 - T3
Factor impacto SCIMAGO: 0.452 - Software (Q2) - Human-Computer Interaction (Q2)

Financiación: info:eu-repo/grantAgreement/ES/DGA-FEDER/T36-17R
Financiación: info:eu-repo/grantAgreement/ES/MINECO/TIN2017-85854-C4-1-R
Tipo y forma: Article (PostPrint)
Área (Departamento): Área Teoría Señal y Comunicac. (Dpto. Ingeniería Electrón.Com.)

Creative Commons You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. You may not use the material for commercial purposes. If you remix, transform, or build upon the material, you may not distribute the modified material.


Exportado de SIDERAL (2025-01-15-15:06:03)


Visitas y descargas

Este artículo se encuentra en las siguientes colecciones:
Articles > Artículos por área > Teoría de la Señal y Comunicaciones



 Record created 2025-01-15, last modified 2025-01-15


Postprint:
 PDF
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)