IP Library › Granted Patent US 10,832,702

Granted Patent B2

US 10,832,702 · App. 16/155,053 · Granted Nov 10, 2020

Robustness of speech processing system against ultrasound and dolphin attacks

Inventor: John Paul Lesso (Edinburgh, GB)

Assignee: Cirrus Logic, Inc.

G10L25/93 G10L21/02 G10L25/03 G10L25/48 G10L25/60 G10L25/18 G10L25/21 G10L2025/937

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 10,832,702
App. No.: 16/155,053
Granted: Nov 10, 2020
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

A method for improving the robustness of a speech processing system having at least one speech processing module comprises: receiving an input sound signal comprising audio and non-audio frequencies; separating the input sound signal into an audio band component and a non-audio band component; and identifying possible interference within the audio band from the non-audio band component. Based on such an identification, the operation of a downstream speech processing module is adjusted.

Claims (132)

1. A method for improving the robustness of a speech processing system having at least one speech processing module, the method comprising:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

comparing the audio band and non-audio band components;

measuring a signal power in the audio band component P a ;

measuring a signal power in the non-audio band component P b ; and

if (P a /P b )<threshold limit, flagging the quality of the input sound signal as unreliable for speech processing; and

adjusting operation of a downstream speech processing module based on said identification, wherein the step of adjusting comprises controlling the operation of a downstream speech processing module based on the flagged unreliable quality.

2. The method of claim 1 , wherein identifying possible interference within the audio band from the non-audio band component comprises determining whether a power level of the non-audio band component exceeds a threshold value and, if so, identifying possible interference within the audio band from the non-audio band component.

3. The method of claim 1 , wherein the step of separating comprises:

filtering the input sound signal to obtain an audio band component of the input sound signal; and

filtering the input sound signal to obtain a non-audio band component of the input sound signal.

4. The method of claim 1 , wherein the speech processing system is a voice biometrics system.

5. A method for improving the robustness of a speech processing system having at least one speech processing module, the method comprising:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

identifying possible interference within the audio band from the non-audio band component, wherein the step of identifying possible interference within the audio band from the non-audio band component comprises comparing the audio band and non-audio band components, and wherein the step of comparing comprises:

detecting an envelope of the non-audio band component;

detecting a level of correlation between the envelope of the non-audio band component and the audio band component; and

determining possible non-audio band interference within the audio band if the level of correlation exceeds a threshold value; and

adjusting operation of a downstream speech processing module based on said identification.

6. The method of claim 5 , wherein the step of adjusting comprises flagging a detection of possible non-audio band interference within the audio band to a downstream speech processing module.

7. The method of claim 5 , wherein the step of separating comprises:

filtering the input sound signal to obtain an audio band component of the input sound signal; and

filtering the input sound signal to obtain a non-audio band component of the input sound signal.

8. The method of claim 5 , wherein the speech processing system is a voice biometrics system.

9. A method for improving the robustness of a speech processing system having at least one speech processing module, the method comprising:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

simulating an effect of a non-linearity on the non-audio band component to provide a simulated non-linear signal;

detecting a level of correlation between the simulated non-linear signal and the audio band component; and

determining possible non-audio band interference within the audio band if the level of correlation exceeds a threshold value; and

adjusting operation of a downstream speech processing module based on said identification.

10. The method of claim 9 , wherein the step of separating comprises:

filtering the input sound signal to obtain an audio band component of the input sound signal; and

filtering the input sound signal to obtain a non-audio band component of the input sound signal.

11. The method of claim 9 , wherein the speech processing system is a voice biometrics system.

12. A method for improving the robustness of a speech processing system having at least one speech processing module, the method comprising:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

identifying possible interference within the audio band from the non-audio band component; and

adjusting operation of a downstream speech processing module based on said identification, wherein the step of adjusting comprises providing a compensated sound signal to a downstream speech processing module; and wherein the step of providing a compensated sound signal comprises:

subtracting a simulated non-linear signal from the audio band component to provide a compensated output signal; and

providing the compensated output signal to a downstream speech processing module.

13. The method of claim 12 , wherein the step of subtracting comprises:

applying the simulated non-linearity signal to a filter; and

subtracting the filtered simulated non-linearity signal from the audio band component of the input sound signal to provide a compensated output signal.

14. A method according to claim 13 , wherein the filter is an adaptive filter, and the method comprises adapting the adaptive filter such that the component of the filtered simulated non-linearity signal in the compensated output signal is minimised.

15. The method of claim 14 , wherein adapting the adaptive filter comprises adapting a gain of the filter.

16. The method of claim 14 , wherein adapting the adaptive filter comprises adapting filter coefficients of the filter.

17. The method of claim 12 , wherein the step of separating comprises:

filtering the input sound signal to obtain an audio band component of the input sound signal; and

filtering the input sound signal to obtain a non-audio band component of the input sound signal.

18. The method of claim 12 , wherein the speech processing system is a voice biometrics system.

19. A method for improving the robustness of a speech processing system having at least one speech processing module, the method comprising:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

adjusting operation of a downstream speech processing module based on said identification;

wherein the steps of comparing and adjusting comprise:

simulating an effect of a non-linearity on the non-audio band component to provide a simulated non-linear signal;

subtracting the simulated non-linear signal from the audio band component to provide a compensated output signal; and

providing the compensated output signal to a downstream speech processing module.

20. The method of claim 19 , wherein the step of simulating the effect of the non-linearity comprises providing the non-audio band component to an adaptive non-linearity module, and wherein the method comprises controlling the adaptive non-linearity module such that the component of the simulated non-linearity signal in the compensated output signal is minimised.

21. The method of claim 19 , wherein the step of separating comprises:

filtering the input sound signal to obtain an audio band component of the input sound signal; and

filtering the input sound signal to obtain a non-audio band component of the input sound signal.

22. The method of claim 19 , wherein the speech processing system is a voice biometrics system.

23. A method for improving the robustness of a speech processing system having at least one speech processing module, the method comprising:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

identifying possible interference within the audio band from the non-audio band component;

adjusting operation of a downstream speech processing module based on said identification; and

measuring a signal power in the non-audio band component P b , wherein the method is responsive to the step of measuring the signal power, such that:

if the measured signal power level P b is below a threshold level X, the method comprises flagging the input sound signal as free of non-audio band interference, and

if the measured signal power level P b is above a threshold level X, the method performs the step of identifying possible interference within the audio band from the non-audio band component.

24. The method of claim 23 , wherein the step of separating comprises:

filtering the input sound signal to obtain an audio band component of the input sound signal; and

filtering the input sound signal to obtain a non-audio band component of the input sound signal.

25. The method of claim 23 , wherein the speech processing system is a voice biometrics system.

26. A system for improving the robustness of a speech processing system having at least one speech processing module, the system comprising an input for receiving an input sound signal comprising audio and non-audio frequencies; and a filter for separating a non-audio band component from the input sound signal, and the system being configured for:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

comparing the audio band and non-audio band components;

measuring a signal power in the audio band component P a ;

measuring a signal power in the non-audio band component P b ; and

if (P a /P b )<threshold limit, flagging the quality of the input sound signal as unreliable for speech processing; and

adjusting operation of a downstream speech processing module based on said identification, wherein the step of adjusting comprises controlling operation of a downstream speech processing module based on the flagged unreliable quality.

27. A system for improving the robustness of a speech processing system having at least one speech processing module, the system comprising an input for receiving an input sound signal comprising audio and non-audio frequencies; and a filter for separating a non-audio band component from the input sound signal, and the system being configured for:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

detecting an envelope of the non-audio band component;

detecting a level of correlation between the envelope of the non-audio band component and the audio band component; and

determining possible non-audio band interference within the audio band if the level of correlation exceeds a threshold value; and

adjusting operation of a downstream speech processing module based on said identification.

28. A system for improving the robustness of a speech processing system having at least one speech processing module, the system comprising an input for receiving an input sound signal comprising audio and non-audio frequencies; and a filter for separating a non-audio band component from the input sound signal, and the system being configured for:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

simulating an effect of a non-linearity on the non-audio band component to provide a simulated non-linear signal;

detecting a level of correlation between the simulated non-linear signal and the audio band component; and

determining possible non-audio band interference within the audio band if the level of correlation exceeds a threshold value; and

adjusting operation of a downstream speech processing module based on said identification.

29. A system for improving the robustness of a speech processing system having at least one speech processing module, the system comprising an input for receiving an input sound signal comprising audio and non-audio frequencies; and a filter for separating a non-audio band component from the input sound signal, and the system being configured for:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

identifying possible interference within the audio band from the non-audio band component; and

subtracting a simulated non-linear signal from the audio band component to provide a compensated output signal; and

providing the compensated output signal to a downstream speech processing module.

30. A system for improving the robustness of a speech processing system having at least one speech processing module, the system comprising an input for receiving an input sound signal comprising audio and non-audio frequencies; and a filter for separating a non-audio band component from the input sound signal, and the system being configured for:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

adjusting operation of a downstream speech processing module based on said identification;

wherein the steps of comparing and adjusting comprise:

simulating an effect of a non-linearity on the non-audio band component to provide a simulated non-linear signal;

subtracting the simulated non-linear signal from the audio band component to provide a compensated output signal; and

providing the compensated output signal to a downstream speech processing module.

31. A system for improving the robustness of a speech processing system having at least one speech processing module, the system comprising an input for receiving an input sound signal comprising audio and non-audio frequencies; and a filter for separating a non-audio band component from the input sound signal, and the system being configured for:

receiving an input sound signal comprising audio and non-audio frequencies;

separating the input sound signal into an audio band component and a non-audio band component;

identifying possible interference within the audio band from the non-audio band component;

adjusting operation of a downstream speech processing module based on said identification; and

measuring a signal power in the non-audio band component P b , wherein the method is responsive to the step of measuring the signal power, such that:

if the measured signal power level P b is below a threshold level X, the method comprises flagging the input sound signal as free of non-audio band interference, and

if the measured signal power level P b is above a threshold level X, the method performs the step of identifying possible interference within the audio band from the non-audio band component.

32. A non-transitory computer readable storage medium having computer-executable instructions stored thereon that, when executed by processor circuitry, cause the processor circuitry to perform a method according to claim 1 .

Assignments (2)

ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 3, 2020

From: CIRRUS LOGIC INTERNATIONAL SEMICONDUCTOR LTD.

To: CIRRUS LOGIC, INC.

Reel/Frame 053681/0884 →

ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 9, 2018

From: LESSO, JOHN PAUL

To: CIRRUS LOGIC INTERNATIONAL SEMICONDUCTOR LTD.

Reel/Frame 047105/0463 →

Priority Claims (1)

GB 1801874.7 · Feb 6, 2018 · national

Continuity (2)

Provisional Application 62571944 · Oct 13, 2017

Related Publication 20190115046A1 · Apr 18, 2019