Authentication of users of self service channels

• US 9,697,836 B1
• Filed: 12/30/2015
• Issued: 07/04/2017
• Est. Priority Date: 12/30/2015
• Status: Active Grant

• Current Assignee: Nice Ltd
• Original Assignee: Nice Ltd
• Inventors: Buzaglo, Amnon, Lewkowicz, Oren Yaakov, Weiss, Oren, Lousky, Avraham
• Primary Examiner(s): Guerra-Erazo, Edgar
• Application Number:
  US14/984,523
• Publication Number:
  US 20170194004A1
• Time in Patent Office: 552 Days
• Field of Search: 704236, 704246, 704247, 704270, 704275, 704277
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231

Abstract

An interactive voice response (IVR) system comprises a memory storing recorded segments of speech by individuals, and a processor configured to enroll individuals. The enrollment 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.

Claims

1. A self-service system enabling individuals to conduct transactions with third parties, the system comprising:

a memory storing recorded segments of speech by individuals,

a processor configured to enroll individuals by;

retrieving one or more of said recorded segments of speech by an individual from said memory and using the retrieved segments to create a text-independent voice print for the individual,

testing the suitability of the voice print for authenticating the individual in a self-service system using segments of speech of a predetermined maximum duration, and enrolling the individual as suitable for authentication if the voice print passed the suitability test; and

a processor configured to authenticate individuals using a voice print only if the voice print has passed the suitability test.

2. The system according to claim 1 wherein the processor configured to enroll individuals is further configured to determine a proportion of candidate individuals to be excluded from enrolment based on a predetermined a level of authentication accuracy.

3. A system according to claim 1 wherein the predetermined maximum duration is 5 seconds.

4. A system according to claim 1 wherein the predetermined maximum duration is 3 seconds.

5. A system according to claim 1 wherein the segments of speech used in the suitability tests are different from the previously recorded segments used to create the voice print.

6. A system according to claim 1 wherein said segments of speech of a predetermined maximum duration comprise segments of speech by the individual to be enrolled, and the processor is configured to perform said suitability testing by operations including determining whether those segments enable authentication of the individual.

7. A system according to claim 6 wherein the determination whether those segments enable authentication of the individual is used to derive a false acceptance rate (FAR).

8. A system according to claim 1 wherein said segments of speech of a predetermined maximum duration comprise segments of speech by one or more other individuals than the individual to be enrolled, and the processor is configured to perform said suitability testing by operations including whether those segments enable authentication of any of the other individuals.

9. A system according to claim 8 wherein the determination whether those segments enable authentication of any of the other individuals is used to determine a false rejection rate (FRR).

13. A method according to claim 9 wherein the predetermined maximum duration is 5 seconds.

10. A method of operating a self-service system comprising one or more memories and one or more processors to provide services to customers, the method comprising enrolling a customer to use the system by:

retrieving one or more recorded segments of speech by the customer from a first memory and

using a processor;

creating a voice print for the customer using the retrieved segments,

testing the suitability of the voice print for authenticating the customer in a self-service system using segments of speech of a predetermined maximum duration, and enrolling the customer as suitable for authentication by voice print if the voice print passed the suitability test;

the method further comprising, using a processor;

authenticating the customer using the voice print only if the voice print has passed the suitability test.

11. A method according to claim 10 wherein the authentication comprises prompting the customer using a pre-recorded or automatically generated word or phrase to utter a phrase.

12. A method according to claim 11 wherein the authentication further comprises capturing the utterance or a part of the utterance and comparing the captured utterance to the voice print to authenticate the customer.

14. A method according to claim 10 wherein the predetermined maximum duration is 3 seconds.

15. A method according to claim 10 wherein the segments of speech used in the suitability tests are different from the previously recorded segments used to create the voice print.

16. A method according to claim 10 wherein said segments of speech of a predetermined maximum duration comprise segments of speech by the customer to be enrolled and further comprising performing said suitability testing by operations including determining whether those segments enable authentication of the customer.

17. A method according to claim 16 wherein the determination whether those segments enable authentication of the individual is used to derive a false acceptance rate (FAR).

18. A method according to claim 10 wherein said segments of speech of a predetermined maximum duration comprise segments of speech by one or more other individuals than the customer to be enrolled, and further comprising performing said suitability testing by operations including determining whether those segments enable authentication of any of the other individuals.

19. A method according to claim 18 wherein the determination whether those segments enable authentication of any of the other individuals is used to determine a false rejection rate (FRR).

20. A method of enrolling an individual for authentication by voice biometrics to use a self-service system, the method comprising:

retrieving from a memory one or more recorded segments of speech by the individual and, using one or more processors;

creating a text independent voice print for the individual using the retrieved segments of speech,

testing the suitability of the text independent voice print to authenticate the individual, if the voice print passes the suitability test tagging the individual in a memory storing details of individuals as enrolled, and

if the voice print fails the suitability test tagging the individual as disqualified from authentication by voice biometrics in said memory storing details of individuals.