System and method for verifying the identity of a user by voiceprint analysis

• US 9,313,307 B2
• Filed: 03/04/2010
• Issued: 04/12/2016
• Est. Priority Date: 09/01/2005
• Status: Active Grant

• Current Assignee: Xtone Incorporated
• Original Assignee: Xtone Incorporated
• Inventors: Dhawan, Vishal, Price, Timothy M., Sindhwani, Manoj
• Primary Examiner(s): ZENATI, AMAL S
• Application Number:
  US12/717,854
• Publication Number:
  US 20100158207A1
• Time in Patent Office: 2,231 Days
• Field of Search: 379/88.14, 379/88.21, 704/258, 704270-275, 704/246
• US Class Current: 1/1
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: H04M 1/2478 Telephone terminals specially adapted for non-voice services, e.g. email, internet access centralized arrangements where telephones services are combined H04M7/0024; for recording text messages H04M3/5322; for accessing Internet H04M3/4938
• CPC Class Codes: H04M 1/2535 adapted for voice communication over an Internet Protocol [IP] network Voice over Internet Protocol (VoIP) network equipment and services H04M7/006; implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP] H04L69/16
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A distributed voice application execution environment system conducts a voiceprint analysis when a user initially begins to interact with the system. If the system is able to identify the user through a voiceprint analysis, the system immediately begins to interact with the user utilizing voice applications which have been customized for that user.

Claims

1. A method of interacting with a user of a distributed voice application execution system, comprising:

receiving spoken input from an individual using a local device, wherein the spoken input is received by one of a voice application and a voice applications agent that is resident, at least in part, on the local device;

conducting a voiceprint analysis on the received spoken input in an attempt to identify the individual, wherein the result of the analysis is the identification of a first user'"'"'s identity, and a first confidence value that indicates the likelihood that the individual who provided the spoken input is the first user;

performing a first voice application for the individual that is configured to perform a function for the individual other than identifying the individual when the first confidence value is below a first threshold value, which indicates that the voiceprint analysis was unable to identify the individual to a high degree of confidence, wherein the first voice application is performed by a voice applications agent that is resident, at least in part, on the local device, and wherein performing the first voice application comprises receiving additional spoken input from the individual; and

conducting a second voiceprint analysis using the additional spoken input when the first voice application is performed in an attempt to verify that the individual is the first user, wherein the result of the second analysis includes a second confidence value that indicates the likelihood that the individual who provided the additional spoken input is the first user.

2. The method of claim 1, wherein the first voice application that is performed by the voice applications agent is a generic voice application.

3. The method of claim 1, wherein if the second confidence value is above the first threshold value, which indicates that the second voiceprint analysis was able identify the individual to a high degree of confidence, the method further comprises performing a second voice application for the individual, wherein the second voice application is one which has been customized for the first user.

4. The method of claim 3, wherein if the second confidence value is above a second threshold value which is higher than the first threshold value, performing a second voice application for the individual comprises performing a voice application that utilizes the first user'"'"'s confidential information.

5. The method of claim 3, wherein if the second confidence value is above a second threshold value which is higher than the first threshold value, performing a second voice application for the individual comprises performing a voice application that provides the individual with functionality customized for the first user.

6. The method of claim 1, further comprising performing a second voice application for the individual that is configured to perform a function for the individual other than identifying the individual when the first confidence value is above the first threshold value, wherein the second voice application is a voice application that has been customized for the first user.

7. The method of claim 6, wherein performing the second voice application comprises receiving supplementary spoken input from the individual, and wherein the method further comprises conducting a second voiceprint analysis using the supplementary spoken input in an attempt to verify that the individual is the first user, and wherein the result of the second voiceprint analysis includes a second confidence value that indicates the likelihood that the individual who provided the supplementary spoken input is the first user.

8. The method of claim 7, wherein if the second confidence value is above a second threshold value which is higher than the first threshold value, the method further comprises performing a third voice application for the individual, wherein the third voice application is one which utilizes the first user'"'"'s confidential information.

9. The method of claim 7, wherein if the second confidence value is above a second threshold value which is higher than the first threshold value, the method further comprises performing a third voice application for the individual, wherein the third voice application provides the individual with functionality reserved for the first user.

10. The method of claim 1, wherein if the first confidence value is above the first threshold value, the method further comprises performing a second voice application for the individual which has been customized for the first user, and which utilizes the first user'"'"'s confidential information.

11. The method of claim 1, wherein if the first confidence value is above the first threshold value, the method further comprises performing a second voice application for the individual which has been customized for the first user and which provides the individual with functionality reserved for the first user.

20. The method of claim 3, wherein the second voice application is configured to perform the same function as the first voice application.

12. A non-transitory computer readable medium having instructions stored thereon, which when executed by one or more processors of a local device and/or one or more processors of at least one computer server in communication with the local device, cause the local device and/or the at least one computer server to perform a method of interacting with a user of a distributed voice application execution system, the method comprising:

receiving spoken input from an individual using a local device, wherein the spoken input is received by one of a voice application and a voice applications agent that is resident, at least in part, on the local device;

conducting a voiceprint analysis on the received spoken input in an attempt to identify the individual, wherein the result of the analysis is the identification of a first user'"'"'s identity, and a first confidence value that indicates the likelihood that the individual who provided the spoken input is the first user;

performing a first voice application for the individual that is configured to perform a function for the individual other than identifying the individual when the first confidence value is below a first threshold value, which indicates that the voiceprint analysis was unable to identify the individual to a high degree of confidence, wherein the first voice application is performed by a voice applications agent that is resident, at least in part, on the local device, and wherein performing the first voice application comprises receiving additional spoken input from the individual; and

conducting a second voiceprint analysis using the additional spoken input when the first voice application is performed in an attempt to verify that the individual is the first user, wherein the result of the second analysis includes a second confidence value that indicates the likelihood that the individual who provided the additional spoken input is the first user.

13. The non-transitory computer readable medium of claim 12, wherein the first voice application that is performed by the voice applications agent is a generic voice application.

14. The non-transitory computer readable medium of claim 12, wherein if the second confidence value is above the first threshold value, which indicates that the second voiceprint analysis was able to identify the individual to a high degree of confidence, the method further comprises performing a second voice application for the individual, wherein the second voice application is one which has been customized for the first user.

15. The non-transitory computer readable medium of claim 14, wherein if the second confidence value is above a second threshold value which is higher than the first threshold value, performing a second voice application for the individual comprises performing a voice application that utilizes the first user'"'"'s confidential information.

16. The non-transitory computer readable medium of claim 14, wherein if the second confidence value is above a second threshold value which is higher than the first threshold value, performing a second voice application for the individual comprises performing a voice application that provides the individual with functionality customized for the first user.

17. The non-transitory computer readable medium of claim 12, wherein the method further comprises performing a second voice application for the individual that is configured to perform a function for the individual other than identifying the individual when the first confidence value is above the first threshold value, wherein the second voice application that is performed is a voice application that has been customized for the first user.

18. The non-transitory computer readable medium of claim 12, wherein the method further comprises performing a second voice application for the individual that is configured to perform a function for the individual other than identifying the individual when the first confidence value is above the first threshold value, wherein the second voice application that is performed is one which has been customized for the first user, and which utilizes the first user'"'"'s confidential information.

19. The non-transitory computer readable medium of claim 12, wherein the method further comprises performing a second voice application for the individual that is configured to perform a function for the individual other than identifying the individual when the first confidence value is above the first threshold value, the second voice application that is performed is one which has been customized for the first user and which provides the individual with functionality reserved for the first user.

21. The system of claim 14, wherein the second voice application is configured to perform the same function as the first voice application.