SPEAKER VERIFICATION SYSTEM AND PROCESS

摘要

An individual's speech sample, obtained for the purpose of speaker verification, is used to create a "protected" model of the speech. The protected model, which is stored in a database in association with a personal identifier for that individu al, is arranged so that the characteristics of the individual's speech cannot be ascert ained from the protected model, without access to an encryption key or other secured information stored in the system. (Fig. 1)