ODYSSEY 2004 - The Speaker and Language Recognition Workshop

May 31 - June 3, 2004
Toledo, Spain

Glottal Modeling and Closed-Phase Analysis for Speaker Recognition

Raymond E. Slyh, Eric G. Hansen, Timothy R. Anderson

Air Force Research Laboratory, Human Effectiveness Directorate, Wright-Patterson AFB Ohio, USA

This paper concerns the application of glottal models and closed-phase analysis to the problem of speaker recognition. A glottal model based on one originally proposed by Fujisaki and Ljungqvist was used in conjunction with closed-phase analysis to yield features for a speaker recognition system used in the NIST 2003 Speaker Recognition Evaluation. Scores from the system based on the glottal model features were combined with scores from a system using formant center frequencies and bandwidths and F0 (FMBWF0), yielding significant improvement over the FMBWF0 system alone. The combination of the glottal model and FMBWF0 scores was in turn combined with the scores from a standard MFCC system to yield improvement beyond that of the MFCC system alone.

Full Paper

Bibliographic reference.  Slyh, Raymond E. / Hansen, Eric G. / Anderson, Timothy R. (2004): "Glottal modeling and closed-phase analysis for speaker recognition", In ODYS-2004, 315-322.