8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

A Comparison of Session Variability Compensation Techniques for SVM-Based Speaker Recognition

Mitchell McLaren, Robbie Vogt, Brendan Baker, Sridha Sridharan

Queensland University of Technology, Australia

This paper compares two of the leading techniques for session variability compensation in the context of GMM mean super-vector SVM classifiers for speaker recognition: inter-session variability modelling and nuisance attribute projection. The former is incorporated in the GMM model training while the latter is employed as a modified SVM kernel. Results on both the NIST 2005 and 2006 corpora demonstrate the effectiveness of both techniques for reducing the effects of session variation. Further, system- and score-level fusion experiments show that the combination of the two methods provides improved performance.

Full Paper

Bibliographic reference.  McLaren, Mitchell / Vogt, Robbie / Baker, Brendan / Sridharan, Sridha (2007): "A comparison of session variability compensation techniques for SVM-based speaker recognition", In INTERSPEECH-2007, 790-793.