System and method for voice authentication

• US 10,503,469 B2
• Filed: 12/12/2017
• Issued: 12/10/2019
• Est. Priority Date: 12/19/2012
• Status: Active Grant

• Current Assignee: Visa International Service Association (Visa, Inc.)
• Original Assignee: Visa International Service Association (Visa, Inc.)
• Inventors: Rutherford, Robert, Hua, Julian
• Primary Examiner(s): Serrou, Abdelali
• Application Number:
  US15/839,699
• Publication Number:
  US 20180113675A1
• Time in Patent Office: 728 Days
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06Q 20/20 Point-of-sale [POS] network systems
• CPC Class Codes: G06Q 20/326 Payment applications installed on the mobile devices
• CPC Class Codes: G06Q 20/3272 using an audio code
• CPC Class Codes: G06Q 20/40145 Biometric identity checks
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

Embodiments of the invention provide for secure voice authentication through a communication device or access device. Certain embodiments allow for providing a word string to a communication device or authentication device. The communication or authentication device plays a supplemental signal that is unique to a transaction. The communication device or authentication device concurrently records an audio segment originating from the user and the supplemental signal. The audio segment is an attempt by the user to vocally reproduce the word string. The communication device or authentication device sends the concurrently recorded audio segment and supplemental signal, to a computer, where the computer authenticates the user.

Claims

1. A method for enrolling a user in an authentication system and conducting a transaction, the method comprising:

receiving, by a device, a user request to enroll in the authentication system;

prompting, by the device, a word string to be repeated by a user;

recording, by the device, a first audio segment originating from the user while the user attempts to vocally reproduce the prompted word string;

sending, by the device, the first audio segment to a server computer, wherein the server computer generates a voice profile for the user including the first audio segment, wherein the server computer stores the generated voice profile;

playing, by the device, a supplemental signal that is inaudible and that is unique to the transaction and that was provided to the device by the server computer;

concurrently recording, by the device, a third audio segment originating from the user, and the supplemental signal to form a second audio segment; and

sending, by the device, the second audio segment to the server computer, wherein the server computer authenticates the user by determining that the third audio segment matches the first audio segment in the voice profile, and that the supplemental signal in the second audio segment matches the supplemental signal provided by the server computer.

2. The method of claim 1, wherein the prompted word string is a first displayed word string, and wherein the third audio segment originates from the user while the user attempts to vocally reproduce a second displayed word string.

3. The method of claim 1, wherein the server computer updates the voice profile for the user based on a result of the authentication.

4. The method of claim 1, further comprising filtering the first audio segment originating from the user to remove background noises from the first audio segment.

5. A device, comprising:

a processor; and

a non-transitory computer-readable storage medium, comprising code executable by the processor, for performing a method for enrolling a user in an authentication system and conducting a transaction, the method comprising;

receiving a user request;

prompting a word string to be repeated by a user;

recording a first audio segment originating from the user while the user attempts to vocally reproduce the prompted word string; and

sending the first audio segment to a server computer, wherein the server computer generates a voice profile for the user based on the first audio segment, wherein the server computer stores the generated voice profile;

playing a supplemental signal that is inaudible and that is unique to the transaction and that was provided to the device by the server computer;

concurrently recording a third audio segment originating from the user, and the supplemental signal to form a second audio segment; and

sending the second audio segment to the server computer, wherein the server computer authenticates the user by determining that the third audio segment matches the first audio segment in the voice profile, and that the supplemental signal in the second audio segment matches the supplemental signal provided by the server computer.

6. The device of claim 5, wherein the prompted word string is a first displayed word string, and wherein the third audio segment originates from the user while the user attempts to vocally reproduce a second displayed word string.

7. The device of claim 5, wherein the server computer updates the voice profile for the user based on a result of the authentication.

8. The device of claim 5, wherein the method further comprises filtering the first audio segment originating from the user to remove background noises from the first audio segment.

9. A method for enrolling a user in an authentication system and conducting a transaction, the method comprising:

receiving, by a server computer, a first audio segment originating from a user while the user attempts to vocally reproduce a word string;

generating, by the server computer, a voice profile for the user including the first audio segment;

storing, by the server computer, the generated voice profile;

providing, by the server computer to a device, a supplemental signal that is inaudible and is unique to the transaction, wherein the supplemental signal is subsequently played by the device and the device concurrently records a third audio segment, received from the user, and the supplemental signal to form a second audio segment;

receiving, by the server computer and from the device, the second audio segment comprising the third audio segment and the supplemental signal; and

authenticating, by the server computer, the user for the transaction by matching the third audio segment with the first audio segment, and matching the supplemental signal in the second audio segment with the supplemental signal provided by the server computer.

10. The method of claim 9, wherein the word string is displayed to the user via the device in response to the device receiving a user request.

11. The method of claim 10, wherein the prompted word string is a first displayed word string, and wherein the third audio segment originates from the user while the user attempts to vocally reproduce a second displayed word string.

12. The method of claim 9, further comprising updating, by the server computer, the voice profile for the user based on a result of the authentication.

13. A server computer, comprising:

a processor; and

a non-transitory computer-readable storage medium, comprising code executable by the processor, for performing a method for enrolling a user in an authentication system and conducting a transaction, the method comprising;

receiving, from a device, a first audio segment originating from a user;

generating a voice profile for the user based on the first audio segment;

storing the generated voice profile;

providing, to the device, a supplemental signal that is inaudible and that is unique to the transaction, wherein the supplemental signal is subsequently played by the device and the device concurrently records a third audio segment, received from the user, and the supplemental signal to form a second audio segment;

receiving, from the device, the second audio segment comprising the third audio segment originating from the user and the supplemental signal; and

authenticating the user for the transaction by matching the third audio segment with the first audio segment, and matching the supplemental signal in the second audio segment with the supplemental signal provided by the server computer.

14. The server computer of claim 13, wherein a word string is displayed to the user via the device in response to the device receiving a user request.

15. The server computer of claim 14, wherein the prompted word string is a first displayed word string, and wherein the third audio segment originates from the user while the user attempts to vocally reproduce a second displayed word string.

16. The server computer of claim 13, wherein the method further comprises updating, by the server computer, the voice profile for the user based on a result of the authentication.