Observatorio de I+D+i UPM

Memorias de investigación
Communications at congresses:
Glottal Source Cepstrum Coefficients Applied to NIST SRE 2010
Year:2010
Research Areas
  • Electronic technology and of the communications
Information
Abstract
Through the present paper, a novel feature set for speaker recognition based on glottal estimate information is presented. An iterative algorithm is used to derive the vocal tract and glottal source estimations from speech signal. In order to test the importance of glottal source information in speaker characterization, the novel feature set has been tested in the 2010 NIST Speaker Recognition Evaluation (NIST SRE10). The proposed system uses glottal estimate parameter templates and classical cepstral information to build a model for each speaker involved in the recognition process. ALIZE [1] open-source software has been used to create the GMM models for both background and target speakers. Compared to using mel-frequency cepstrum coefficients (MFCC), the misclassification rate for the NIST SRE 2010 reduced from 29.43% to 27.15% when glottal source features are used.
International
No
Congress
V Jornadas de Reconocimiento Biométrico de Personas JRBP10
960
Place
Huesca
Reviewers
Si
ISBN/ISSN
0000000000000
Start Date
02/09/2010
End Date
03/09/2010
From page
0
To page
0
Actas de las V Jornadas de Reconocimiento Biométrico de Personas JRBP10
Participants
  • Autor: Luis Miguel Mazaira Fernandez (UPM)
  • Participante: Cristina Muñoz Mulas (GIAPSI)
  • Autor: Agustin Alvarez Marquina (UPM)
  • Autor: Pedro Gomez Vilda (UPM)
  • Autor: Rafael Martinez Olalla (UPM)
Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Informática Aplicada al Procesado de Señal e Imagen
S2i 2020 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)