Authentication of users of self service channels

Abstract

An interactive voice response (IVR) system comprises a memory storing recorded segments of speech by individuals, and a processor configured to enrol individuals. The enrolment process may comprise retrieving one or more of said recorded segments of speech by an individual from said memory and using the retrieved segments to create a voice print for the individual. The suitability of the voice print for authenticating the individual in an IVR system is then tested. This may be done using segments of speech of a predetermined maximum duration such as three seconds or some other amount commensurate with the typical duration of a voice response in an IVR system. An individual may be enrolled as suitable for IVR authentication if the voice print passed the suitability test. Individuals may be authenticated using a voice print only if the voice print has passed the suitability test.

Description

FIELD OF THE INVENTION[0001]This invention relates generally to the field of authentication of individuals. In particular, the invention relates to the authentication of individuals using their voices.BACKGROUND OF THE INVENTION[0002]Large organizations, such as commercial organizations, financial institutions, government agencies or public safety organizations conduct communication sessions, also known as interactions, with individuals such as customers, suppliers and the like on a daily basis.[0003]Communication sessions between parties may involve exchanging sensitive information, for example any of financial data, transactions and personal medical data. Thus in communication sessions with individuals it may be necessary to authenticate the individual, e.g., ensure that the individual really is who he or she claims to be. Authentication may include checking that identification details provided by an individual match identification details held on record for that individual. Authe...

AI Technical Summary

Benefits of technology

The patent describes a system and method for verifying the identity of individuals using voice biometrics in self-service channels. The system automatically performs background checks on voice prints to ensure high accuracy of authentication. The level of accuracy is predetermined, and only those individuals for whom highly accurate authentication is possible are enrolled. The system uses speech segments of a predetermined maximum duration to test the suitability of a voice print for authentication. The system can also make use of the fact that some members of a population have voices that can be authenticated with only a short burst of speech. The authentication process involves retrieving previously recorded segments of speech and using them to create a voice print for the individual, which is then tested using segments of speech of a predetermined maximum duration. The enrollment is recorded in a database, and when an individual revisits the system, they can be authenticated using their voice print.

Problems solved by technology

Some speaker's voices may be extremely difficult to forge for biometric comparison purposes, since a myriad of qualities may be measured ranging from dialect and speaking style to pitch, spectral magnitudes, and format frequencies.

This requirement has hindered the take-up of voice print technology for user authentication.

Hitherto it has been considered that the use of voice prints, and particularly text-independent voice prints, is typically not suitable for authenticating users of self-service channels because, for example, only short bursts of speech e.g. in the range of 3-5 seconds may be obtained from the user, and experience has shown that the use of such short bursts of speech typically does not lead to adequate performance

Images