Abstract: A system and method enrolls a speaker with an enrollment utterance and authenticates a user with a biometric analysis of an authentication utterance, without the need for a PIN (Personal Identification Number). During authentication, the system uses the same authentication utterance to identify who a speaker claims to be with speaker recognition, and verify whether is the speaker is actually the claimed person. Thus, it is not necessary for the speaker to identify biometric data using a PIN. The biometric analysis includes a neural tree network to determine unique aspects of the authentication utterances for comparison to the enrollment authentication. The biometric analysis leverages a statistical analysis using Hidden Markov Models to before authorizing the speaker.

Abstract: A system and method for authentication a user's identity via biometrics is disclosed. The system includes client software, an authentication server, and an independent biometric services server. Data associated with the biometric samples provided by a user are stored in the biometric services server and the user is assigned a unique identifier. The authentication server stores biometric templates consisting of information regarding the biometric samples and type of samples, e.g. voice, retina scans, fingerprints, DNA, etc. The authentication server also stores at least one pointer to the biometrics services server providing a link between the biometric samples stored in the biometric services server and the user's biometric template(s). Identity authentication is accomplished by a series of steps including querying the user for an identifier and analyzing a biometric sample provided by the user with the biometric samples stored in the biometric services server.