Using a predefined passphrase to evaluate a speaker verification system

Abstract

This article presents a standardized and repeatable process used to evaluate the performance of a speaker verification system.Through the use of a common passphrase and a subset of extracted feature vectors that outperforms other combinations, thestudy limits the exposure to potential experimental flaws, while measuring true biometric performance more effectively thanexisting evaluation methodologies. After collecting a dataset of 33 participants, the researchers achieved a performance rate of99.8% for the 22 users who contributed at least 20 text-dependent samples. The primary focus of the research, however, was toillustrate a variety of testing techniques that can be used to efficiently analyze the performance of a speaker verification systemand advocate the use of a common passphrase in this process.