METHOD AND APPARATUS FOR ADJUSTING DETECTION THRESHOLD FOR ACTIVATING VOICE ASSISTANT FUNCTION

• US 20150081296A1
• Filed: 09/17/2013
• Published: 03/19/2015
• Est. Priority Date: 09/17/2013
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Lee, Minsub, Kim, Taesu, Hwang, Kyu Woong, Jin, Minho
• Granted Patent: US 9,240,182 B2
• Time in Patent Office: Days
• US Class Current: 704/239
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 25/48 specially adapted for particular use

Abstract

A method for activating a voice assistant function in a mobile device is disclosed. The method includes receiving an input sound stream by a sound sensor and determining a context of the mobile device. The method may determine the context based on the input sound stream. For determining the context, the method may also obtain data indicative of the context of the mobile device from at least one of an acceleration sensor, a location sensor, an illumination sensor, a proximity sensor, a clock unit, and a calendar unit in the mobile device. In this method, a threshold for activating the voice assistant function is adjusted based on the context. The method detects a target keyword from the input sound stream based on the adjusted threshold. If the target keyword is detected, the method activates the voice assistant function.

Claims

1. A method for activating a voice assistant function in a mobile device, the method comprising:

receiving an input sound stream by a sound sensor;

determining a context of the mobile device;

adjusting a threshold for activating the voice assistant function based on the context;

detecting a target keyword from the input sound stream based on the adjusted threshold; and

activating the voice assistant function if the target keyword is detected.

2. The method of claim 1, wherein determining the context of the mobile device comprises identifying the context of the mobile device based on the input sound stream.

3. The method of claim 1, wherein determining the context of the mobile device comprises:

obtaining data indicative of the context of the mobile device from at least one of an acceleration sensor, a location sensor, an illumination sensor, a proximity sensor, a clock unit, and a calendar unit in the mobile device; and

identifying the context of the mobile device based on the data.

4. The method of claim 1, wherein determining the context of the mobile device comprises:

obtaining data indicative of the context of the mobile device from at least one of an acceleration sensor and a location sensor in the mobile device; and

identifying the context of the mobile device as being in a vehicle based on the input sound stream and the data.

5. The method of claim 1, wherein determining the context of the mobile device comprises:

obtaining data indicative of the context of the mobile device from at least one of an illumination sensor and a proximity sensor in the mobile device; and

identifying the context of the mobile device as being within a container based on the input sound stream and the data.

6. The method of claim 1, wherein determining the context of the mobile device comprises:

obtaining status information of the mobile device; and

identifying the context of the mobile device based on the status information.

7. The method of claim 6, wherein the status information indicates a change in an operational status of a processor in the mobile device from an idle state to an active state.

8. The method of claim 7, wherein the operational status of the processor changes from the idle state to the active state in response to receiving an electronic message.

9. The method of claim 7, wherein the operational status of the processor changes from the idle state to the active state in response to an alarm event in the mobile device.

10. The method of claim 1, further comprising setting the threshold to a predetermined threshold when a predetermined period of time elapses after adjusting the threshold.

11. The method of claim 1, wherein adjusting the threshold comprises adjusting the threshold based on a likelihood of using the voice assistant function in the context of the mobile device.

12. The method of claim 11, wherein the likelihood is high if the context indicates that the mobile device is in a vehicle.

13. The method of claim 11, wherein the likelihood is low if the context is indicative of a sleeping context.

14. The method of claim 1, wherein detecting the target keyword from the input sound stream comprises:

calculating a degree of similarity between the input sound stream and a sound model of the target keyword;

comparing the degree of similarity with the threshold; and

detecting the target keyword from the input sound stream if the degree of similarity exceeds the threshold.

15. A mobile device for activating a voice assistant function, comprising:

a sound sensor configured to receive an input sound stream;

a threshold adjustment unit configured to adjust a threshold for activating the voice assistant function by determining a context of the mobile device; and

a voice activation unit configured to activate the voice assistant function if a target keyword is detected from the input sound stream based on the adjusted threshold.

16. The mobile device of claim 15, wherein the threshold adjustment unit comprises a context inference unit configured to identify the context of the mobile device based on the input sound stream.

17. The mobile device of claim 15, wherein the threshold adjustment unit comprises a context determination unit configured to obtain data indicative of the context of the mobile device from at least one of an acceleration sensor, a location sensor, an illumination sensor, a proximity sensor, a clock unit, and a calendar unit in the mobile device, and identify the context of the mobile device based on the data.

18. The mobile device of claim 15, wherein the threshold adjustment unit comprises a context determination unit configured to obtain data indicative of the context of the mobile device from at least one of an acceleration sensor and a location sensor in the mobile device, and identify the context of the mobile device as being in a vehicle based on the input sound stream and the data.

19. The mobile device of claim 15, wherein the threshold adjustment unit comprises a context determination unit configured to obtain data indicative of the context of the mobile device from at least one of an illumination sensor and a proximity sensor in the mobile device, and identify the context of the mobile device as being within a container based on the input sound stream and the data.

20. The mobile device of claim 15, wherein the threshold adjustment unit comprises a context determination unit configured to obtain status information of the mobile device and identify the context of the mobile device based on the status information.

21. The mobile device of claim 20, wherein the status information indicates a change in an operational status of a processor in the mobile device from an idle state to an active state.

22. The mobile device of claim 21, wherein the operational status of the processor changes from the idle state to the active state in response to receiving an electronic message.

23. The mobile device of claim 21, wherein the operational status of the processor changes from the idle state to the active state in response to an alarm event in the mobile device.

24. The mobile device of claim 15, wherein the threshold adjustment unit is further configured to set the threshold to a predetermined threshold when a predetermined period of time elapses after adjusting the threshold.

25. The mobile device of claim 15, wherein the threshold adjustment unit is further configured to adjust the threshold based on a likelihood of using the voice assistant function in the context of the mobile device.

26. The mobile device of claim 25, wherein the likelihood is high if the context indicates that the mobile device is in a vehicle.

27. The mobile device of claim 25, wherein the likelihood is low if the context is indicative of a sleeping context.

28. The mobile device of claim 15, wherein the voice activation unit is further configured to calculate a degree of similarity between the input sound stream and a sound model of the target keyword, compare the degree of similarity with the threshold, and detect the target keyword from the input sound stream if the degree of similarity exceeds the threshold.

29. A mobile device for activating a voice assistant function, comprising:

means for receiving an input sound stream;

means for adjusting a threshold for activating the voice assistant function by determining a context of the mobile device; and

means for activating the voice assistant function if a target keyword is detected from the input sound stream based on the adjusted threshold.

30. The mobile device of claim 29, wherein the means for adjusting the threshold comprises means for identifying the context of the mobile device based on the input sound stream.

31. The mobile device of claim 29, wherein the means for adjusting the threshold comprises means for obtaining data indicative of the context of the mobile device from at least one of an acceleration sensor, a location sensor, an illumination sensor, a proximity sensor, a clock unit, and a calendar unit in the mobile device, and identifying the context of the mobile device based on the data.

32. The mobile device of claim 29, wherein the means for adjusting the threshold comprises means for obtaining data indicative of the context of the mobile device from at least one of an acceleration sensor and a location sensor in the mobile device, and identifying the context of the mobile device as being in a vehicle based on the input sound stream and the data.

33. The mobile device of claim 29, wherein the means for adjusting the threshold comprises means for obtaining status information of the mobile device and identifying the context of the mobile device based on the status information.

34. The mobile device of claim 33, wherein the status information indicates a change in an operational status of a processor in the mobile device from an idle state to an active state.

35. The mobile device of claim 34, wherein the operational status of the processor changes from the idle state to the active state in response to receiving an electronic message.

36. The mobile device of claim 34, wherein the operational status of the processor changes from the idle state to the active state in response to an alarm event in the mobile device.

37. The mobile device of claim 29, wherein the means for adjusting the threshold is configured to set the threshold to a predetermined threshold when a predetermined period of time elapses after adjusting the threshold.

38. The mobile device of claim 29, wherein the means for adjusting the threshold is configured to adjust the threshold based on a likelihood of using the voice assistant function in the context of the mobile device.

39. The mobile device of claim 38, wherein the likelihood is high if the context indicates that the mobile device is in a vehicle.

40. A non-transitory computer-readable storage medium comprising instructions for activating a voice assistant function in a mobile device, the instructions causing a processor of the mobile device to perform the operations of:

receiving an input sound stream by a sound sensor;

determining a context of the mobile device;

adjusting a threshold for activating the voice assistant function based on the context;

detecting a target keyword from the input sound stream based on the adjusted threshold; and

activating the voice assistant function if the target keyword is detected.

41. The medium of claim 40, wherein determining the context of the mobile device comprises identifying the context of the mobile device based on the input sound stream.

42. The medium of claim 40, wherein determining the context of the mobile device comprises:

obtaining data indicative of the context of the mobile device from at least one of an acceleration sensor, a location sensor, an illumination sensor, a proximity sensor, a clock unit, and a calendar unit in the mobile device; and

identifying the context of the mobile device based on the data.

43. The medium of claim 40, wherein determining the context of the mobile device comprises:

obtaining data indicative of the context of the mobile device from at least one of an acceleration sensor and a location sensor in the mobile device; and

identifying the context of the mobile device as being in a vehicle based on the input sound stream and the data.

44. The medium of claim 40, wherein determining the context of the mobile device comprises:

obtaining status information of the mobile device; and

identifying the context of the mobile device based on the status information.

45. The medium of claim 44, wherein the status information indicates a change in an operational status of the processor of the mobile device from an idle state to an active state.

46. The medium of claim 45, wherein the operational status of the processor changes from the idle state to the active state in response to receiving an electronic message.

47. The medium of claim 45, wherein the operational status of the processor changes from the idle state to the active state in response to an alarm event in the mobile device.

48. The medium of claim 40, wherein the operations further comprise setting the threshold to a predetermined threshold when a predetermined period of time elapses after adjusting the threshold.

49. The medium of claim 40, wherein adjusting the threshold comprises adjusting the threshold based on a likelihood of using the voice assistant function in the context of the mobile device.

50. The medium of claim 49, wherein the likelihood is high if the context indicates that the mobile device is in a vehicle.