Using timing information in speaker verification

Abstract

This paper presents an analysis of temporal information as a feature for use in speaker verification systems. The relevance of temporal information in a speaker’s utterances is investigated, both with regard to improving the robustness of modern speaker verification systems and to detecting and deflecting recording attacks. It is shown that the use of timing information provides useful additional information that can be used to enhance the performance of verification systems, and that intra-speaker variability of typical tokens is sufficient (in comparison with typical noise-induced variability) to support the detection of recordings.