Improving the performance of text-independent short duration SVM- and GMM-based speaker verification

In the task of automatic speaker verification (ASV) it is well known that the duration of the speech signals is an important factor in the ultimate accuracy of the system. This paper deals with some of the aspects of adapting systems to work with limited amounts of data. First we highlight the importance of a well-tuned speech detection front-end when working with short durations. We consider a well-established technique (GMM) as well as a recent development (SVM on GMM mean supervectors), showing their limitations and alternatives. In particular the benefit of eigenvoice modelling in the context of short duration tasks is highlighted. Finally experiments on standard NIST databases demonstrate fusion potential between the presented techniques and significant gains when compared to a single GMM.