Voice biometrics systems and methods

• US 10,720,166 B2
• Filed: 04/09/2018
• Issued: 07/21/2020
• Est. Priority Date: 04/09/2018
• Status: Active Grant

• Current Assignee: Synaptics Incorporated
• Original Assignee: Synaptics Incorporated
• Inventors: Caldwell, Frederic
• Primary Examiner(s): Islam, Mohammad K
• Application Number:
  US15/948,976
• Publication Number:
  US 20190311722A1
• Time in Patent Office: 834 Days
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase

Abstract

Systems and methods for user authentication include a microphone generating a corresponding audio input signal, and a voice processing system operable to identify a pass phrase including human speech in the audio input signal, a voice authentication system operable to extract feature characteristics associated with the identified pass phrase, compare the extracted feature characteristics to user voice features, and determine a confidence level of a voice match. The voice authentication system receives a first acoustic code, compares the first acoustic code to a second acoustic code associated with the user, and determines whether the first acoustic code and second acoustic code match. A user is authenticated if the first acoustic code and second acoustic code match and the confidence level exceeds a threshold value. A user device is operable to prompt the user to speak the pass phrase, generate the acoustic code and output the acoustic code through a speaker.

Claims

1. A system comprising:

a microphone sensing sound and generating a corresponding audio input signal;

a voice processing system configured to identify a pass phrase in the audio input signal, wherein the pass phrase includes human speech;

a voice authentication system configured to extract feature characteristics associated with the identified pass phrase, compare the extracted feature characteristics to user voice features, and determine a confidence level of a voice match;

wherein the voice authentication system is further configured to receive a first acoustic code generated by a speaker of a user device while the user is voicing the pass phrase, the first acoustic code having a frequency inaudible to humans, compare the first acoustic code to a second acoustic code associated with the user, and determine whether the first acoustic code and second acoustic code match; and

wherein the user is authenticated if the first acoustic code and second acoustic code match and the confidence level exceeds a threshold value.

2. The system of claim 1 further comprising a user device comprising a voice authentication application, and wherein the voice authentication application is configured to prompt the user to speak the pass phrase.

3. The system of claim 2 wherein the user device further comprises a speaker;

and wherein the voice authentication application is further configured to generate an acoustic code and output the acoustic code through the speaker.

4. The system of claim 3 further comprising audio input processing components configured to extract an acoustic code signal having a frequency range outside of range of speech.

5. The system of claim 3 further comprising audio input processing components configured to extract a speech signal having a frequency range within a range of human speech.

6. The system of claim 2 wherein the user device is a mobile device.

7. The system of claim 1 further comprising an authentication server configured to generate and store the user voice features.

8. The system of claim 1 further comprising a voice interaction device comprising the microphone, voice processing system, and voice authentication system.

9. A method comprising:

receiving an audio input signal;

identifying a pass phrase in the audio input signal, wherein the pass phrase includes human speech;

extracting feature characteristics associated with the identified pass phrase;

comparing the extracted feature characteristics to user voice features;

determining a confidence level of a voice match;

receiving a first acoustic code generated by a speaker of a user device while the user is voicing the pass phrase, the first acoustic code having a frequency inaudible to humans;

comparing the first acoustic code to a second acoustic code associated with the user;

determining whether the first acoustic code and second acoustic code match; and

authenticating the user if the first acoustic code and second acoustic code match and the confidence level exceeds a threshold value.

10. The method of claim 9 further comprising prompting the user to speak the pass phrase.

11. The method of claim 10 further comprising generating the acoustic code and outputting the acoustic code through a speaker.

12. The method of claim 11 further comprising extracting an acoustic code signal from the audio input signal having a frequency range outside of range of speech.

13. The method of claim 11 further comprising extracting a speech signal from the audio input signal having a frequency range within a range of human speech.

14. The method of claim 10 wherein the user is prompted on a screen of a mobile device.

15. The method of claim 9 further generating and storing the user voice features.

16. The method of claim 9 wherein the method is performed by a voice interaction device comprising a microphone, a voice processing system, and a voice authentication system.

17. The method of claim 9 wherein the acoustic code is received in the audio input signal.

18. The method of claim 9 further comprising implementing a training process to generate the user voice features from a set of sample phrases.

19. The method of claim 9 further comprising synchronizing the first acoustic code and the second acoustic code through a server.

20. The method of claim 9 further comprising identifying a first direction of the user generating the pass phrase and a second direction of a user device generating the acoustic code and wherein authenticating the user further comprises comparing the first direction and second direction.