METHOD AND APPARATUS FOR ACTIVATING APPLICATION BY SPEECH INPUT

• US 20150302855A1
• Filed: 04/21/2014
• Published: 10/22/2015
• Est. Priority Date: 04/21/2014
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Kim, Taesu, Lee, Minsub
• Granted Patent: US 10,770,075 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/08 Speech classification or search
• 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 2015/223 Execution procedure of a spoken command

Abstract

A method, which is performed in an electronic device, for activating a target application is disclosed. The method may include receiving an input sound stream including an activation keyword for activating the target application and a speech command indicative of a function of the target application. The method may also detect the activation keyword from the input sound stream. If the activation keyword is detected, a portion of the input sound stream including at least a portion of the speech command may be buffered in a buffer memory. In addition, in response to detecting the activation keyword, the target application may be activated to perform the function of the target application.

Claims

1. A method, performed in an electronic device, for activating a target application, the method comprising:

receiving an input sound stream including an activation keyword for activating the target application and a speech command indicative of a function of the target application;

detecting the activation keyword from the input sound stream;

buffering, in a buffer memory, a portion of the input sound stream including at least a portion of the speech command in response to detecting the activation keyword; and

activating the target application in response to detecting the activation keyword to perform the function of the target application.

2. The method of claim 1, wherein detecting the activation keyword comprises detecting the activation keyword from a portion of the activation keyword in the input sound stream, and

wherein buffering the portion of the input sound stream comprises buffering the portion of the input sound stream in response to detecting the activation keyword from the portion of the activation keyword.

3. The method of claim 1, further comprising detecting an end of the activation keyword in the input sound stream,

wherein buffering the portion of the input sound stream comprises buffering the portion of the input sound stream in response to detecting the end of the activation keyword.

4. The method of claim 1, further comprising detecting a beginning of the speech command in the input sound stream,

wherein buffering the portion of the input sound stream comprises buffering the portion of the input sound stream in response to detecting the beginning of the speech command.

5. The method of claim 1, wherein activating the target application comprises verifying whether to activate the target application based on the buffered portion of the input sound stream.

6. The method of claim 5, wherein verifying whether to activate the target application comprises determining whether the buffered portion of the input sound stream includes speech.

7. The method of claim 6, wherein verifying whether to activate the target application further comprises determining whether the speech in the buffered portion of the input sound stream is indicative of a speaker of the activation keyword.

8. The method of claim 5, wherein verifying whether to activate the target application comprises determining whether a signal-to-noise ratio (SNR) of the buffered portion of the input sound stream exceeds a predetermined threshold value.

9. The method of claim 5, wherein verifying whether to activate the target application comprises determining whether the buffered portion of the input sound stream includes a predetermined revocation command indicative of revoking the activation keyword.

10. The method of claim 5, wherein detecting the activation keyword comprises detecting the activation keyword from a portion of the activation keyword in the input sound stream, and

wherein activating the target application comprises:

loading the target application in response to detecting the activation keyword from the portion of the activation keyword; and

launching the target application in response to verifying activation of the target application.

11. The method of claim 1, wherein activating the target application comprises:

recognizing the speech command from the buffered portion of the input sound stream; and

performing the function of the target application in response to the speech command.

12. An electronic device for activating a target application, comprising:

a sound sensor configured to receive an input sound stream including an activation keyword for activating the target application and a speech command indicative of a function of the target application;

a voice activation unit configured to detect the activation keyword from the input sound stream and activate the target application in response to detecting the activation keyword to perform the function of the target application; and

a buffer memory configured to store a portion of the input sound stream including at least a portion of the speech command in response to detecting the activation keyword.

13. The electronic device of claim 12, wherein the voice activation unit is further configured to detect the activation keyword from a portion of the activation keyword in the input sound stream, and

wherein the buffer memory is further configured to store the portion of the input sound stream in response to detecting the activation keyword from the portion of the activation keyword.

14. The electronic device of claim 12, wherein the voice activation unit is further configured to detect an end of the activation keyword in the input sound stream, and

wherein the buffer memory is further configured to store the portion of the input sound stream in response to detecting the end of the activation keyword.

15. The electronic device of claim 12, wherein the voice activation unit is further configured to detect a beginning of the speech command in the input sound stream, and

wherein the buffer memory is further configured to store the portion of the input sound stream in response to detecting the beginning of the speech command.

16. The electronic device of claim 12, wherein the voice activation unit is further configured to verify whether to activate the target application based on the stored portion of the input sound stream.

17. The electronic device of claim 16, wherein the voice activation unit is further configured to determine whether the stored portion of the input sound stream includes speech.

18. The electronic device of claim 17, wherein the voice activation unit is further configured to determine whether the speech in the stored portion of the input sound stream is indicative of a speaker of the activation keyword.

19. The electronic device of claim 16, wherein the voice activation unit is further configured to determine whether an SNR of the stored portion of the input sound stream exceeds a predetermined threshold value.

20. The electronic device of claim 16, wherein the voice activation unit is further configured to determine whether the stored portion of the input sound stream includes a predetermined revocation command indicative of revoking the activation keyword.

21. The electronic device of claim 16, wherein the voice activation unit is further configured to:

detect the activation keyword from a portion of the activation keyword in the input sound stream;

load the target application in response to detecting the activation keyword from the portion of the activation keyword; and

launch the target application in response to verifying activation of the target application.

22. The electronic device of claim 12, wherein the target application recognizes the speech command from the stored portion of the input sound stream and performs the function of the target application in response to the speech command.

23. A non-transitory computer-readable storage medium comprising instructions for activating a target application, the instructions causing a processor of an electronic device to perform the operations of:

receiving an input sound stream including an activation keyword for activating the target application and a speech command indicative of a function of the target application;

detecting the activation keyword from the input sound stream;

buffering, in a buffer memory, a portion of the input sound stream including at least a portion of the speech command in response to detecting the activation keyword; and

activating the target application in response to detecting the activation keyword to perform the function of the target application.

24. The medium of claim 23, wherein detecting the activation keyword comprises detecting the activation keyword from a portion of the activation keyword in the input sound stream, and

wherein buffering the portion of the input sound stream comprises buffering the portion of the input sound stream in response to detecting the activation keyword from the portion of the activation keyword.

25. The medium of claim 23, wherein activating the target application comprises verifying whether to activate the target application based on the buffered portion of the input sound stream.

26. The medium of claim 25, wherein detecting the activation keyword comprises detecting the activation keyword from a portion of the activation keyword in the input sound stream, and

wherein activating the target application comprises:

loading the target application in response to detecting the activation keyword from the portion of the activation keyword; and

launching the target application in response to verifying activation of the target application.

27. An electronic device for activating a target application, comprising:

means for receiving an input sound stream including an activation keyword for activating the target application and a speech command indicative of a function of the target application;

means for detecting the activation keyword from the input sound stream and activating the target application in response to detecting the activation keyword to perform the function of the target application;

means for storing a portion of the input sound stream including at least a portion of the speech command in response to detecting the activation keyword.

28. The electronic device of claim 27, wherein the means for detecting the activation keyword and activating the target application is configured to detect the activation keyword from a portion of the activation keyword in the input sound stream, and

wherein the means for storing the portion of the input sound stream is configured to store the portion of the input sound stream in response to detecting the activation keyword from the portion of the activation keyword.

29. The electronic device of claim 27, wherein the means for detecting the activation keyword and activating the target application is configured to verify whether to activate the target application based on the stored portion of the input sound stream.

30. The electronic device of claim 29, wherein the means for detecting the activation keyword and activating the target application is further configured to:

detect the activation keyword from a portion of the activation keyword in the input sound stream;

load the target application in response to detecting the activation keyword from the portion of the activation keyword; and

launch the target application in response to verifying activation of the target application.