8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


On Cohort Selection for Speaker Verification

Yaniv Zigel, Arnon Cohen

Ben-Gurion University, Israel

Speaker verification systems require some kind of background model to reliably perform the verification task. Several algorithms have been proposed for the selection of cohort models to form a background model. This paper proposes a new cohort selection method called the Close Impostor Clustering (CIC). The new method is shown to outperform several other methods in a text-dependent verification task. Several normalization methods are also compared. With three cohort models and the best score-normalization method, the CIC yielded an average Equal Error Rate (EER) of 0.8%, while the second best method (Maximally-Spread Close, MSC) yielded average EER of 1.1%.

Full Paper

Bibliographic reference.  Zigel, Yaniv / Cohen, Arnon (2003): "On cohort selection for speaker verification", In EUROSPEECH-2003, 2977-2980.