METHOD AND APPARATUS FOR PERFORMING FUNCTION BY SPEECH INPUT

• US 20150302856A1
• Filed: 08/22/2014
• Published: 10/22/2015
• Est. Priority Date: 04/17/2014
• Status: Abandoned Application

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Kim, Taesu, Jin, Minho, Cho, Juncheol
• Application Number:
  US14/466,580
• Publication Number:
  US 20150302856A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/48 specially adapted for particular use
• CPC Class Codes: H04M 1/724 User interfaces specially adapted for cordless or mobile telephones
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00

Abstract

A method for performing a function in an electronic device is disclosed. The method may include receiving an input sound stream including a speech command indicative of the function and identifying the function from the speech command in the input sound stream. Further, the method may determine a security level associated with the speech command. It may be verified whether the input sound stream is indicative of a user authorized to perform the function based on the security level. In response to verifying that the input sound stream is indicative of the user, the function may be performed.

Claims

1. A method for performing a function in an electronic device, the method comprising:

receiving an input sound stream including a speech command indicative of the function;

identifying the function from the speech command in the input sound stream;

determining a security level associated with the speech command;

verifying whether the input sound stream is indicative of a user authorized to perform the function based on the security level; and

performing the function in response to verifying that the input sound stream is indicative of the user.

2. The method of claim 1, wherein the function is associated with the security level among a plurality of predetermined security levels.

3. The method of claim 2, wherein the plurality of predetermined security levels are assigned to a plurality of functions, and

wherein at least one of the plurality of predetermined security levels is adjusted in response to a change in a device security level.

4. The method of claim 1, wherein verifying whether the input sound stream is indicative of the user comprises verifying whether the speech command in the input sound stream is indicative of the user.

5. The method of claim 4, wherein verifying whether the speech command in the input sound stream is indicative of the user comprises:

determining a verification score for the speech command based on a speaker model associated with the user; and

verifying whether the speech command is indicative of the user based on the verification score for the speech command and a verification threshold associated with the security level.

6. The method of claim 1, wherein verifying whether the input sound stream is indicative of the user comprises:

receiving a verification keyword from a speaker of the speech command; and

verifying whether the verification keyword is indicative of the user.

7. The method of claim 6, wherein verifying whether the verification keyword is indicative of the user comprises:

determining a keyword score for the verification keyword; and

verifying whether the verification keyword is indicative of the user based on the keyword score and a keyword detection threshold.

8. The method of claim 6, wherein verifying whether the verification keyword is indicative of the user comprises:

determining a verification score for the verification keyword based on a speaker model associated with the verification keyword; and

verifying whether the verification keyword is indicative of the user based on the verification score for the verification keyword and a verification threshold associated with the verification keyword.

9. The method of claim 1, wherein receiving the input sound stream comprises receiving an activation keyword for activating a speech recognition application adapted to identify the function from the speech command, and

wherein the method further comprises:

verifying whether the activation keyword is indicative of an authorized user of the speech recognition application; and

activating the speech recognition application in response to verifying that the activation keyword is indicative of the authorized user of the speech recognition application.

10. The method of claim 1, wherein receiving the input sound stream comprises:

receiving an activation keyword for activating a speech recognition application adapted to identify the function from the speech command; and

detecting the activation keyword from the input sound stream to activate the speech recognition application, and

wherein verifying whether the input sound stream is indicative of the user comprises verifying whether at least one of the activation keyword and the speech command in the input sound stream is indicative of the user.

11. An electronic device for performing a function, comprising:

a sound sensor configured to receive an input sound stream including a speech command indicative of the function;

a speech recognition unit configured to identify the function from the speech command in the input sound stream;

a security management unit configured to verify whether the input sound stream is indicative of a user authorized to perform the function based on a security level associated with the speech command; and

a function control unit configured to perform the function in response to verifying that the input sound stream is indicative of the user.

12. The electronic device of claim 11, wherein the function is associated with the security level among a plurality of predetermined security levels.

13. The electronic device of claim 12, wherein the plurality of predetermined security levels are assigned to a plurality of functions, and

wherein at least one of the plurality of predetermined security levels is adjusted in response to a change in a device security level.

14. The electronic device of claim 11, wherein the security management unit is configured to verify whether the speech command in the input sound stream is indicative of the user.

15. The electronic device of claim 14, further comprising a verification score determining unit configured to determine a verification score for the speech command based on a speaker model associated with the user,

wherein the security management unit is configured to verify whether the speech command is indicative of the user based on the verification score for the speech command and a verification threshold associated with the security level.

16. The electronic device of claim 11, wherein the sound sensor is further configured to receive a verification keyword from a speaker of the speech command, and

wherein the security management unit is configured to verify whether the verification keyword is indicative of the user.

17. The electronic device of claim 16, wherein the speech recognition unit is further configured to:

determine a keyword score for the verification keyword; and

verify whether the verification keyword is indicative of the user based on the keyword score and a keyword detection threshold.

18. The electronic device of claim 16, further comprising a verification score determining unit configured to determine a verification score for the verification keyword based on a speaker model associated with the verification keyword,

wherein the security management unit is configured to verify whether the verification keyword is indicative of the user based on the verification score for the verification keyword and a verification threshold associated with the verification keyword.

19. The electronic device of claim 11, wherein the sound sensor is further configured to receive an activation keyword for activating the speech recognition unit adapted to identify the function from the speech command, and

wherein the electronic device further comprises a voice activation unit configured to:

verify whether the activation keyword is indicative of an authorized user of the speech recognition unit; and

activate the speech recognition unit in response to verifying that the activation keyword is indicative of the authorized user of the speech recognition unit.

20. The electronic device of claim 11, wherein the sound sensor is further configured to receive an activation keyword for activating the speech recognition unit adapted to identify the function from the speech command, and

wherein the electronic device further comprises a voice activation unit configured to detect the activation keyword to activate the speech recognition unit, and

wherein the security management unit is configured to verify whether at least one of the activation keyword and the speech command is indicative of the user.

21. An electronic device for performing a function, comprising:

means for receiving an input sound stream including a speech command indicative of the function;

means for identifying the function from the speech command in the input sound stream;

means for verifying whether the input sound stream is indicative of a user authorized to perform the function based on a security level associated with the speech command; and

means for performing the function in response to verifying that the input sound stream is indicative of the user.

22. The electronic device of claim 21, wherein a plurality of predetermined security levels are assigned to a plurality of functions, the plurality of predetermined security levels including the security level associated with the speech command, and the plurality of functions including the function identified from the speech command, and

wherein at least one of the plurality of predetermined security levels is adjusted in response to a change in a device security level.

23. The electronic device of claim 21, wherein the means for verifying whether the input sound stream is indicative of the user is configured to verify whether the speech command in the input sound stream is indicative of the user.

24. The electronic device of claim 23, further comprising means for determining a verification score for the speech command based on a speaker model associated with the user,

wherein the means for verifying whether the input sound stream is indicative of the user is configured to verify whether the speech command is indicative of the user based on the verification score for the speech command and a verification threshold associated with the security level.

25. The electronic device of claim 21, wherein the means for receiving the input sound stream is further configured to receive a verification keyword from a speaker of the speech command, and

wherein the means for verifying whether the input sound stream is indicative of the user is configured to verify whether the verification keyword is indicative of the user.

26. A non-transitory computer-readable storage medium comprising instructions for performing a function, the instructions causing a processor of an electronic device to perform the operations of:

receiving an input sound stream including a speech command indicative of the function;

identifying the function from the speech command in the input sound stream;

determining a security level associated with the speech command;

verifying whether the input sound stream is indicative of a user authorized to perform the function based on the security level; and

performing the function in response to verifying that the input sound stream is indicative of the user.

27. The medium of claim 26, wherein a plurality of predetermined security levels are assigned to a plurality of functions, the plurality of predetermined security levels including the security level associated with the speech command, and the plurality of functions including the function identified from the speech command, and

wherein at least one of the plurality of predetermined security levels is adjusted in response to a change in a device security level.

28. The medium of claim 26, wherein verifying whether the input sound stream is indicative of the user comprises verifying whether the speech command in the input sound stream is indicative of the user.

29. The medium of claim 28, wherein verifying whether the speech command in the input sound stream is indicative of the user comprises:

determining a verification score for the speech command based on a speaker model associated with the user; and

verifying whether the speech command is indicative of the user based on the verification score for the speech command and a verification threshold associated with the security level.

30. The medium of claim 26, wherein verifying whether the input sound stream is indicative of the user comprises:

receiving a verification keyword from a speaker of the speech command; and

verifying whether the verification keyword is indicative of the user.