Skip to Main Content
A new method that improves the accuracy of text dependent speaker verification systems is presented in this paper. The new method exploits a set of novel speech features derived from a principal component analysis of pitch synchronous voiced speech segments. We use the term principal pitch components (PPCs) or optimal pitch bases (OPBs) to denote the new feature set. Utterance distances computed from these new PPC features are only weakly correlated with utterance distances computed from cepstral features. A distance measure that combines both, cepstral and PPC features provides a discriminative power that cannot be achieved with cepstral features alone. By augmenting the feature space of a cepstral baseline system with PPC features we are able to reduce the equal error probability of incorrect customer rejection versus incorrect impostor acceptance by over 10% beyond the discriminative limit of the cepstral analysis.