Selective passive voice authentication

• US 10,013,983 B1
• Filed: 08/02/2016
• Issued: 07/03/2018
• Est. Priority Date: 09/19/2014
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Johnson, Zakery Layne, Fernandez, Gabriel Carlos
• Primary Examiner(s): McFadden, Susan
• Application Number:
  US15/226,375
• Time in Patent Office: 700 Days
• Field of Search: 704273
• CPC Class Codes: G06Q 20/40145 Biometric identity checks
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04L 63/0428 wherein the data content is protected, e.g. by encrypting or encapsulating the payload
• CPC Class Codes: H04L 63/083 using passwords cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226
• 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
• CPC Class Codes: H04L 63/102 Entity profiles
• CPC Class Codes: H04W 12/06 Authentication
• CPC Class Codes: H04W 12/062 Pre-authentication
• CPC Class Codes: H04W 12/08 Access security

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for authenticating a user using a voice biometric program are described. In some embodiments, first voice data from a user device is received. The first voice data can include audio data of a user speaking a first voice command, and the system can determine that the first voice command includes a voice command for which voice recognition can be performed. In response, the system can initiate a passive authentication scheme for selectively enabling access to secure data in response to the first voice command. The passive authentication scheme can provide the first voice data for voice recognition and receive an indication that the user is authenticated based on the voice recognition and, in response, allow access to a back-end system.

Claims

1. A computer-implemented method executed by at least one processor, the method comprising:

receiving, by the at least one processor, first voice data from a user device, the first voice data comprising audio data of a user speaking a first voice command; and

determining, by the at least one processor, that the first voice command comprises a voice command for which voice recognition can be performed and, in response, initiating a passive authentication scheme for selectively enabling access to secure data in response to the first voice command, the passive authentication scheme comprising;

providing, by the at least one processor, the first voice data for voice recognition, and

receiving, by the at least one processor, an indication that the user is authenticated based on the voice recognition and, in response, allowing access to a back-end system.

2. The method of claim 1, wherein determining that the first voice command comprises a voice command for which voice recognition can be performed comprises:

determining that the first voice command is included in a set of voice commands for which voice recognition can be performed; and

determining that a voice profile that is specific to the first voice command and the user is usable for voice authentication of the user.

3. The method of claim 2, wherein the set of voice commands comprises at least one voice command in a superset of voice commands, the superset of voice commands comprising voice commands that can be executed.

4. The method of claim 1, wherein allowing access to the back-end system comprises providing secure data for display to the user, the secure data being selected for display based on the first voice command.

5. The method of claim 1, further comprising:

receiving, by the at least one processor, second voice data from the user device, the second voice data comprising audio data of the user speaking a second voice command; and

determining, by the at least one processor, that the second voice command comprises a voice command for which voice recognition is not to be performed and, in response, initiating an active authentication scheme for selectively enabling access to secure data in response to authentication data received during the active authentication scheme.

6. The method of claim 5, wherein the active authentication scheme comprises:

providing, by the at least one processor, an authentication interface for display on the user device, the authentication interface enabling user input of the authentication data;

receiving, by the at least one processor, the authentication data; and

selectively enabling access to the back-end system based on the authentication data.

7. The method of claim 5, wherein determining that the second voice command comprises a voice command for which voice recognition is not to be performed comprises:

determining that the second voice command is included in a set of voice commands for which voice recognition can be performed; and

determining that a voice profile that is specific to the second voice command and the user is not usable for voice authentication of the user.

8. The method of claim 1, further comprising displaying a message on the user device indicating that the first voice command can be used for voice authentication of the user.

9. The method of claim 8, wherein displaying the message is performed in response to determining that a voice profile that is specific to the first voice command and the user is usable for voice authentication of the user.

10. A system comprising:

a data store for storing data; and

at least one processor configured to interact with the data store, the at least one processor being further configured to execute computer-readable instructions to perform operations comprising;

receiving first voice data from a user device, the first voice data comprising audio data of a user speaking a first voice command; and

determining that the first voice command comprises a voice command for which voice recognition can be performed and, in response, initiating a passive authentication scheme for selectively enabling access to secure data in response to the first voice command, the passive authentication scheme comprising;

providing the first voice data for voice recognition, and

receiving an indication that the user is authenticated based on the voice recognition and, in response, allowing access to a back-end system.

11. The system of claim 10, wherein determining that the first voice command comprises a voice command for which voice recognition can be performed comprises:

determining that the first voice command is included in a set of voice commands for which voice recognition can be performed; and

determining that a voice profile that is specific to the first voice command and the user is usable for voice authentication of the user.

12. The system of claim 11, wherein the set of voice commands comprises at least one voice command in a superset of voice commands, the superset of voice commands comprising voice commands that can be executed.

13. The system of claim 10, wherein allowing access to the back-end system comprises providing secure data for display to the user, the secure data being selected for display based on the first voice command.

14. The system of claim 10, wherein operations further comprise:

receiving second voice data from the user device, the second voice data comprising audio data of the user speaking a second voice command; and

determining that the second voice command comprises a voice command for which voice recognition is not to be performed and, in response, initiating an active authentication scheme for selectively enabling access to secure data in response to authentication data received during the active authentication scheme.

15. The system of claim 14, wherein the active authentication scheme comprises:

providing an authentication interface for display on the user device, the authentication interface enabling user input of the authentication data;

receiving the authentication data; and

selectively enabling communication between the user device and the back-end system based on the authentication data.

16. The system of claim 14, wherein determining that the second voice command comprises a voice command for which voice recognition is not to be performed comprises:

determining that the second voice command is included in a set of voice commands for which voice recognition can be performed; and

determining that a voice profile that is specific to the second voice command and the user is not usable for voice authentication of the user.

17. The system of claim 10, wherein operations further comprise displaying a message on the user device indicating that the first voice command can be used for voice authentication of the user, wherein displaying the message is performed in response to determining that a voice profile that is specific to the first voice command and the user is usable for voice authentication of the user.

18. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

receiving first voice data from a user device, the first voice data comprising audio data of a user speaking a first voice command; and

determining that the first voice command comprises a voice command for which voice recognition can be performed and, in response, initiating a passive authentication scheme for selectively enabling access to secure data in response to the first voice command, the passive authentication scheme comprising;

providing the first voice data for voice recognition; and

receiving an indication that the user is authenticated based on the voice recognition and, in response, allowing access to a back-end system.

19. The non-transitory computer-readable medium of claim 18, wherein determining that the first voice command comprises a voice command for which voice recognition can be performed comprises:

determining that the first voice command is included in a set of voice commands for which voice recognition can be performed; and

determining that a voice profile that is specific to the first voice command and the user is usable for voice authentication of the user, wherein the set of voice commands comprises at least one voice command in a superset of voice commands, the superset of voice commands comprising voice commands that can be executed.

20. The non-transitory computer-readable medium of claim 18, wherein the operations further comprise:

receiving second voice data from the user device, the second voice data comprising audio data of the user speaking a second voice command; and

determining that the second voice command comprises a voice command for which voice recognition is not to be performed and, in response, initiating an active authentication scheme for selectively enabling access to secure data in response to authentication data received during the active authentication scheme,

wherein determining that the second voice command comprises a voice command for which voice recognition is not to be performed comprises;

determining that the second voice command is included in a set of voice commands for which voice recognition can be performed; and

determining that a voice profile that is specific to the second voice command and the user is not usable for voice authentication of the user,

wherein the active authentication scheme comprises;

providing an authentication interface for display on the user device, the authentication interface enabling user input of the authentication data;

receiving the authentication data; and

selectively allowing access to the back-end system based on the authentication data.