ISCA Archive Odyssey 2001
ISCA Archive Odyssey 2001

Integration and imputation methods for unreliable feature compensation in GMM based speaker verification

Andrzej Drygajlo, Mounir El-Maliki

This paper addresses the problem of text-independent speaker verification in the presence of unreliable (masked by noise) fea-tures. It presents and assesses several integration and imputa-tion approaches used for unreliable feature compensation in the framework of Gaussian mixture models (GMMs) of speakers. These approaches include marginalisation, bounded integra-tion, mean imputations, integrated speech-background model and Wiener filtering dependent on the most probable Gaussian component.