The 2013 speaker recognition evaluation in mobile environment
Elie Khoury
(1)
,
Bostjan Vesnicer
(2)
,
Javier Franco-Pedroso
(3)
,
Ricardo P.V. Violato
(4)
,
Zinelabidine Boulkenafet
(5)
,
Luis Miguel Mazaira Fernandez
(6)
,
Mireia Diez
(7)
,
Justina Kosmala
(8)
,
Houssemeddine Khemiri
(9, 10, 11, 12)
,
Tomas Cipr
(13)
,
Rahim Saedi
(14)
,
Manuel Gunther
(1)
,
Jerneja Zganec-Gros
(2)
,
Ruben Zazo Candil
(3)
,
Flávio Simoes
(4)
,
Messaoud Bengherabi
(5)
,
Augustin Alvarez Marquina
(6)
,
Mikel Penagarikano
(7)
,
Alberto Abad
(8)
,
Mehdi Boulaymen
(9)
,
Petr Schwarz
(13, 15)
,
David van Leeuwen
(14)
,
Javier Gonzalez-Dominguez
(3)
,
Mário Uliani Neto
(4)
,
Elhocine Boutellaa
(5)
,
Pedro Gomez Vilda
(6)
,
Amparo Varona
(7)
,
Dijana Petrovska-Delacrétaz
(9, 10, 12)
,
Pavel Matejka
(13, 15)
,
Joaquin Gonzalez-Rodriguez
(3)
,
Tiago de Freitas Pereira
(4)
,
Farid Harizi
(5)
,
Luis Javier Rodriguez-Fuentes
(7)
,
Laurent El Shafey
(1)
,
Marcus Angeloni
(4)
,
German Bordel
(7)
,
Gérard Chollet
(11)
,
Sébastien Marcel
(1)
1
IDIAP Research Institute
2 Alpineon d.o.o. (Alpineon d.o.o.)
3 ATVS - Biometric Recognition Group (Universidad Autonoma de Madrid)
4 Fundação Centro de Pesquisa e Desenvolvimento em Telecomunicações
5 CDTA - Centre de Développement des Technologies Avancées
6 UPM - Universidad Politécnica de Madrid
7 UPV / EHU - Universidad del País Vasco [Espainia] / Euskal Herriko Unibertsitatea [España] = University of the Basque Country [Spain] = Université du pays basque [Espagne]
8 L2F - Spoken Language Systems Laboratory [Portugal]
9 TSP - EPH - Département Electronique et Physique
10 SAMOVAR - Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux
11 LTCI - Laboratoire Traitement et Communication de l'Information
12 CNRS - Centre National de la Recherche Scientifique
13 Phonexia s. r. o. (Phonexia s. r. o.)
14 Centre for Language Studies
15 DCGM FIT BUT - Department of Computer Graphics and Multimedia
2 Alpineon d.o.o. (Alpineon d.o.o.)
3 ATVS - Biometric Recognition Group (Universidad Autonoma de Madrid)
4 Fundação Centro de Pesquisa e Desenvolvimento em Telecomunicações
5 CDTA - Centre de Développement des Technologies Avancées
6 UPM - Universidad Politécnica de Madrid
7 UPV / EHU - Universidad del País Vasco [Espainia] / Euskal Herriko Unibertsitatea [España] = University of the Basque Country [Spain] = Université du pays basque [Espagne]
8 L2F - Spoken Language Systems Laboratory [Portugal]
9 TSP - EPH - Département Electronique et Physique
10 SAMOVAR - Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux
11 LTCI - Laboratoire Traitement et Communication de l'Information
12 CNRS - Centre National de la Recherche Scientifique
13 Phonexia s. r. o. (Phonexia s. r. o.)
14 Centre for Language Studies
15 DCGM FIT BUT - Department of Computer Graphics and Multimedia
Gérard Chollet
- Fonction : Auteur
- PersonId : 176991
- IdHAL : gerard-chollet
- ORCID : 0000-0003-4245-146X
- IdRef : 078020824
Résumé
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