Classical vs. biometric features in the 2013 speaker recognition evaluation in mobile environments

Mazaira Fernández, Luis Miguel and Álvarez Marquina, Agustin and Gómez Vilda, Pedro and Martínez Olalla, Rafael and Muñoz Mulas, Cristina (2013). Classical vs. biometric features in the 2013 speaker recognition evaluation in mobile environments. In: "I Jornadas Multidisciplinares de Usuarios de la Voz, el Habla y el Canto", 27-28 Jun 2013, Las Palmas de Gran Canaria, Spain. ISBN 84-695-8101-5. pp. 96-105.

Description

Title: Classical vs. biometric features in the 2013 speaker recognition evaluation in mobile environments
Author/s:
  • Mazaira Fernández, Luis Miguel
  • Álvarez Marquina, Agustin
  • Gómez Vilda, Pedro
  • Martínez Olalla, Rafael
  • Muñoz Mulas, Cristina
Item Type: Presentation at Congress or Conference (Unspecified)
Event Title: I Jornadas Multidisciplinares de Usuarios de la Voz, el Habla y el Canto
Event Dates: 27-28 Jun 2013
Event Location: Las Palmas de Gran Canaria, Spain
Title of Book: Libro de Actas de las I Jornadas Multidisciplinares de Usuarios de la Voz, el Habla y el Canto
Date: June 2013
ISBN: 84-695-8101-5
Volume: 1
Subjects:
Freetext Keywords: Speaker characterization; Speaker recognition; GMM-UBM; Source-tract separation; MOBIO database
Faculty: Facultad de Informática (UPM)
Department: Arquitectura y Tecnología de Sistemas Informáticos
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (233kB) | Preview

Abstract

MFCC coefficients extracted from the power spectral density of speech as a whole, seems to have become the de facto standard in the area of speaker recognition, as demonstrated by its use in almost all systems submitted to the 2013 Speaker Recognition Evaluation (SRE) in Mobile Environment [1], thus relegating to background this component of the recognition systems. However, in this article we will show that selecting the adequate speaker characterization system is as important as the selection of the classifier. To accomplish this we will compare the recognition rates achieved by different recognition systems that relies on the same classifier (GMM-UBM) but connected with different feature extraction systems (based on both classical and biometric parameters). As a result we will show that a gender dependent biometric parameterization with a simple recognition system based on GMM- UBM paradigm provides very competitive or even better recognition rates when compared to more complex classification systems based on classical features

More information

Item ID: 31141
DC Identifier: http://oa.upm.es/31141/
OAI Identifier: oai:oa.upm.es:31141
Official URL: http://jvhc2013.ulpgc.es/web4/index.php
Deposited by: Memoria Investigacion
Deposited on: 07 Oct 2014 16:15
Last Modified: 10 Feb 2015 18:30
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM