High performance speaker verification using principal spectral components

The described system finds key application in physical entry control and control of access to privileged information. Verification is based on a fast and user-friendly protocol, consisting of two stages: 1. Primary verification using a fixed text phrase. 2. Secondary verification using a random 5-digit sequence. The features used in the verification algorithm are the Principal Spectral Components, derived from the spectrum of the speech signal. Verification experiments on a 40 speaker database give a true speaker rejection rate of less than 1% and an impostor acceptance rate of less than 0.1%.