Method and apparatus for controlling access to applications having different security levels

Patent metadata

Field	Value
Publication number	US-9343068-B2
Application number	US-201314028139-A
Country	US
Kind code	B2
Filing date	Sep 16, 2013
Priority date	Sep 16, 2013
Publication date	May 17, 2016
Grant date	May 17, 2016

Abstract

A method for controlling access to a plurality of applications in an electronic device includes receiving a voice command from a speaker for accessing a target application among the plurality of applications, and verifying whether the voice command is indicative of a user authorized to access the applications based on a speaker model of the authorized user. In this method, each application is associated with a security level having a threshold value. The method further includes updating the speaker model with the voice command if the voice command is verified to be indicative of the user, and adjusting at least one of the threshold values based on the updated speaker model.

First claim

What is claimed:

1. A method for controlling access to a plurality of applications in an electronic device, the method comprising:
receiving a voice command from a speaker for accessing a target application among the plurality of applications, at least two of the plurality of applications associated with different security levels having different threshold values;
controlling access to one or more of the plurality of applications by verifying whether the voice command is indicative of an authorized user based on a speaker model of the authorized user; and
in response to verifying that the voice command is indicative of the authorized user, updating the speaker model based on the voice command and adjusting at least one of the threshold values based on the updated speaker model.

2. The method of claim 1 , further comprising:
receiving a new voice command for accessing a new target application among the plurality of applications; and
verifying whether the new voice command is indicative of the authorized user based on the updated speaker model.

3. The method of claim 1 , wherein verifying whether the voice command is indicative of the authorized user comprises:
determining a confidence value of the voice command based on the speaker model; and
accessing the target application if the confidence value of the voice command exceeds a threshold value for a security level of the target application.

4. The method of claim 3 , wherein updating the speaker model comprises:
weighting the voice command in proportion to the confidence value of the voice command; and
updating the speaker model based on the weighted voice command.

5. The method of claim 1 , wherein the speaker model comprises statistical data of at least one sound feature extracted from a plurality of sound samples of the authorized user.

6. The method of claim 5 , wherein updating the speaker model comprises updating the statistical data with at least one sound feature extracted from the voice command.

7. The method of claim 1 , wherein adjusting the at least one of the threshold values comprises:
determining a confidence value for each of at least one sound sample associated with a security level selected from security levels of the plurality of applications based on the updated speaker model; and
adjusting the threshold value of the selected security level to a new threshold value based on the confidence value.

8. The method of claim 7 , wherein the threshold value of the selected security level is adjusted to a lowest confidence value among the confidence values for the at least one sound sample.

9. The method of claim 7 , wherein the selected security level is the security level associated with the target application.

10. The method of claim 7 , wherein the selected security level is determined based on a confidence value of the voice command.

11. The method of claim 1 , wherein adjusting the at least one of the threshold values comprises:
determining confidence values for a plurality of sound samples based on the updated speaker model; and
adjusting the threshold values to new threshold values based on the confidence values.

12. The method of claim 11 , wherein adjusting the threshold values comprises:
determining a lowest confidence value and a highest confidence value among the confidence values;
partitioning a difference between the lowest and highest confidence values into a plurality of ranges associated with security levels of the plurality of applications, wherein each of the plurality of ranges includes a lower limit; and
assigning the lower limits as the new threshold values for the security levels.

13. The method of claim 1 , wherein each of the plurality of applications is associated with a security level having a threshold value, and wherein each of the security levels is associated with a set of sound samples having a confidence value greater than the threshold value for the security level.

14. The method of claim 13 , further comprising adding the voice command to one of the sets of sound samples for a security level selected based on a confidence value of the voice command.

15. The method of claim 1 , further comprising if the voice command is not verified to be indicative of the authorized user, authenticating the voice command to be indicative of the authorized user based on an input from the speaker.

16. The method of claim 15 , wherein the input from the speaker includes at least one of an image of a face, a fingerprint, a personal identification number, or an additional voice command.

17. An electronic device for controlling access to a plurality of applications, the electronic device comprising:
a sound sensor configured to receive a voice command from a speaker for accessing a target application among the plurality of applications;
a storage unit configured to store the plurality of applications, a plurality of security levels, a plurality of threshold values, and a speaker model of an authorized user, at least two of the plurality of applications associated with a different security levels of the plurality of security levels, the different security levels having different threshold values of the plurality of threshold values;
a speaker verification unit configured to control access to one or more of the plurality of applications by verifying whether the voice command is indicative of the authorized user based on the speaker model of the authorized user; and
a database updating unit configured to update the speaker model based on the voice command in response to verifying that the voice command is indicative of the authorized user and to adjust at least one of the threshold values based on the updated speaker model.

18. The electronic device of claim 17 , wherein:
the sound sensor is further configured to receive a new voice command for accessing a new target application among the plurality of applications, and
the speaker verification unit is further configured to verify whether the new voice command is indicative of the authorized user based on the updated speaker model.

19. The electronic device of claim 17 , wherein the speaker verification unit is further configured to determine a confidence value of the voice command based on the speaker model and to access the target application if the confidence value of the voice command exceeds the threshold value for the security level of the target application.

20. The electronic device of claim 19 , wherein the database updating unit is further configured to weight the voice command in proportion to the confidence value of the voice command and to update the speaker model based on the weighted voice command.

21. The electronic device of claim 17 , wherein the speaker model comprises statistical data of at least one sound feature extracted from a plurality of sound samples of the authorized user.

22. The electronic device of claim 21 , wherein the database updating unit is further configured to update the statistical data with at least one sound feature extracted from the voice command.

23. The electronic device of claim 17 , wherein the database updating unit is further configured to determine a confidence value for each of at least one sound sample associated with a security level selected from the security levels based on the updated speaker model and to adjust the threshold value of the selected security level to a new threshold value based on the confidence value.

24. The electronic

Assignees

• Qualcomm Inc

Inventors

• Yun Sungrack
• Kim Taesu
• Cho Jun-Cheol
• Park Min-Kyu
• Hwang Kyu Woong

Classifications

• G10L17/26

  Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices · CPC title

• G10L17/04

  Training, enrolment or model building · CPC title

• G10L17/24

  the user being prompted to utter a password or a predefined phrase · CPC title

• H04L63/0861

  using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231) · CPC title

• G10L17/005

  Physics · mapped topic