Ricardo Paranhos Velloso Violato, Petr Schwarz, Joaquin Gonzalez-Rodriguez, Javier Franco-Pedroso, Pavel Matejka, J. Kosmala, B. Vesnicer, Dijana Petrovska-Delacrétaz, Z. Boulkcnafet, R. Zazo Candil, L. M. Mazaira Fernandez, Houssemeddine Khemiri, Elhocine Boutellaa, Elie Khoury, Gérard Chollet, Tiago de Freitas Pereira, Javier Gonzalez-Dominguez, M. Boulayemen, Rahim Saeidi, T. Cipr, Marcus de Assis Angeloni, Germán Bordel, Mikel Peñagarikano, Luis Javier Rodríguez-Fuentes, J. Zganec-Gros, Farid Harizi, Sébastien Marcel, Amparo Varona, D.A. van Leeuwen, Alberto Abad, Manuel Günther, Flávio Olmos Simões, A. Alvarez Marquina, M. Uliani Neto, L. El Shafey, Mireia Diez, P. Gómez Vilda, Messaoud Bengherabi, UAM. Departamento de Tecnología Electrónica y de las Comunicaciones, Análisis y Tratamiento de Voz y Señales Biométricas (ING EPS-002), IDIAP Research Institute, Alpineon d.o.o. (Alpineon d.o.o.), Biometric Recognition Group (Universidad Autonoma de Madrid) (ATVS), Fundação Centro de Pesquisa e Desenvolvimento em Telecomunicações, CPqD, Centre de Développement des Technologies Avancées (CDTA), Universidad Politécnica de Madrid (UPM), Universidad del Pais Vasco / Euskal Herriko Unibertsitatea [Espagne] (UPV/EHU), Spoken Language Systems Laboratory [Portugal] (L2F), Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa (INESC-ID), Instituto Superior Técnico, Universidade Técnica de Lisboa (IST)-Instituto de Engenharia de Sistemas e Computadores (INESC)-Instituto Superior Técnico, Universidade Técnica de Lisboa (IST)-Instituto de Engenharia de Sistemas e Computadores (INESC), Département Electronique et Physique (EPH), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux (SAMOVAR), Laboratoire Traitement et Communication de l'Information (LTCI), Télécom ParisTech-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS), Phonexia s. r. o. (Phonexia s. r. o.), Centre for Language Studies, Radboud university [Nijmegen], Department of Computer Graphics and Multimedia (DCGM FIT BUT), and Faculty of Information Technology de Brno
Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. E. Khoury , B. Vesnicer, J. Franco-Pedroso, R. Violato, Z. Boulkenafet, L.M. Mazaira Fernández, M. Díez, J. Kosmala, H. Khemiri, T. Cipr, R. Saeidi, M. Gunther, J. Zganec-Gros, R. Zazo Candil, F. Simöes, M. Bengherabi, A. Álvarez Marquina, M. Penagarikano, A. Abad, M. Boulayemen, P. Schwarz,, D. Van Leeuwen, J. González-Domínguez, M. Uliani Neto, E. Boutellaa, P. Gómez Vilda, A. Varona, D. Petrovska-Delacretaz, P. Matejka, J. González-Rodríguez, T. Pereira, F. Harizi, L. J. Rodríguez-Fuentes, L. El Shafey, M. Angeloni, G. Bordel, G. Chollet, S. Marcel, "The 2013 speaker recognition evaluation in mobile environment" in International Conference on Biometrics (ICB), Madrid (Spain), 2013, 1-8, This paper evaluates the performance of the twelve primary systems submitted to the evaluation on speaker verification in the context of a mobile environment using the MOBIO database. The mobile environment provides a challenging and realistic test-bed for current state-of-the-art speaker verification techniques. Results in terms of equal error rate (EER), half total error rate (HTER) and detection error trade-off (DET) confirm that the best performing systems are based on total variability modeling, and are the fusion of several sub-systems. Nevertheless, the good old UBM-GMM based systems are still competitive. The results also show that the use of additional data for training as well as gender-dependent features can be helpful., This evaluation was supported by the European Union under the project BEAT contract no. FP7-284989 , as well as the Swiss National Science Foundation under the LOBI project.