User sensing system and method for low power voice command activation in wireless communication systems

• US 9,196,262 B2
• Filed: 03/14/2013
• Issued: 11/24/2015
• Est. Priority Date: 03/14/2013
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Shen, Jian, Yang, Tongzeng
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US13/826,840
• Publication Number:
  US 20140278437A1
• Time in Patent Office: 985 Days
• Field of Search: 704/231, 704/233, 704/254, 704/275, 704/226, 704/214, 704/207, 704/227, 704/228, 455/570, 455/296, 370/406.08, 370/406.06, 370/388.04, 370/406.01, 370/88.01, 370/406.05, 370/88.03, 370/221.11, 381/56, 381/110
• US Class Current: 1/1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2025/786 Adaptive threshold
• CPC Class Codes: G10L 21/06 Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids G10L15/26 takes precedence
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: H04W 52/0254 detecting a user operation or a tactile contact or a motion of the device
• CPC Class Codes: Y02D 30/70 in wireless communication networks

Abstract

A method of activating voice control on a wireless device includes sampling signals from a plurality of sensors on the device, determining if the device is in a hands-on state by a user on the basis of the signal sampling, and enabling a voice activated detection (VAD) application on the device on the basis of the determination. A voice controlled apparatus in a wireless device includes a plurality of sensors arranged on the device, a microphone, a controller to sample signals from one or more of the plurality of sensors, a processor coupled to the controller, and a voice activated detection (VAD) application running on the processor coupled to the controller and the microphone.

Claims

1. A method of activating voice control on a wireless device, comprising:

sampling signals from a plurality of sensors on the device;

determining if the device is in a hands-on state by a user on the basis of the signal sampling; and

enabling a voice activated detection (VAD) application on the device on the basis of the determination.

2. The method of claim 1, wherein the sampling comprises periodically activating at least one of the plurality of the sensors in a duty cycle.

3. The method of claim 2, wherein the duty cycle comprises a first time period defining a time duration during which the sensors are activated and a second time period defining a repetition rate of the first time period, the duty cycle being a of the first time period to the second time period ratio less than 1.

4. The method of claim 3, wherein the duty cycle is equal to or less than 50% and greater than 0%.

5. The method of claim 1, wherein determining the hands-on state comprises comparing a level of the sampled signals to a threshold level, and activating the hands-on state when the sampled signals equal or exceed the threshold level.

6. The method of claim 5, wherein the threshold level is a reference level specified to distinguish the user'"'"'s hands-on contact with the device from non-contact with at least one sensor.

7. The method of claim 1, further comprising:

interpreting voice detected by the VAD application using an audio processor;

communicating by the device with a communications interface to obtain signals from a remote server based on the interpreted voice; and

halting the operation of the VAD application, audio processor and communication interface.

8. The method of claim 7, further wherein the halting takes place after a delay time based on detecting the device is found in a “

hands-off”

condition and the VAD does not detect voice.

9. The method of claim 8, wherein the delay time is greater than a specified number of seconds.

10. The method of claim 8, wherein halting comprises disabling at least one of the VAD, the audio processor and the communication interface to one of a standby and an off state.

11. The method of claim 8, wherein the delay time between samplings is dynamically variable.

12. A voice controlled apparatus included in a wireless device, comprising:

a plurality of sensors arranged on the device;

a microphone;

a controller to sample signals from at least one of the plurality of sensors;

a processor coupled to the controller; and

a voice activated detection (VAD) application running on the processor and coupled to the controller and the microphone.

13. The apparatus of claim 12, wherein the controller periodically activates at least one of the plurality of the sensors at a duty cycle for sampling output signals.

14. The apparatus of claim 13, wherein the duty cycle comprises a first time period defining a time duration during which the sensors are activated and a second time period defining a repetition rate of the first time period, the duty cycle being a ratio less than 1 of the first time period to the second time period.

15. The apparatus of claim 14, wherein the duty cycle is less than 50% and greater than 0%.

16. The apparatus of claim 12, wherein the controller compares a level of the sampled signals to a threshold level, and activates the hands-on state when the sampled signals equal or exceed the threshold level.

17. The apparatus of claim 16, wherein the threshold level is a reference level specified to distinguish the user'"'"'s hands-on contact from non-contact with at least one sensor e.

18. The apparatus of claim 12, further comprising:

an audio processor running the VAD application to interpret voice;

a communication interface coupled to the audio processor to obtain signals from a remote server based on the interpreted voice, wherein the controller halts operation of the VAD application, audio processor and communication interface for specified conditions after a delay time.

19. The apparatus of claim 18, wherein the specified conditions comprise at least the absence of signals from any of the sensors corresponding to a hands-off state of the wireless device and an absence of detected sound.

20. The apparatus of claim 19, wherein the delay time is greater than a specified number of seconds.

21. The apparatus of claim 18, wherein the halting operation comprises disabling the VAD to one of a standby and an off state.

22. The apparatus of claim 18, wherein the delay time between samplings is dynamically variable.

23. A voice command control apparatus included in a device, comprising:

means for sensing arranged on one or more surfaces of the device;

means for detecting sound;

means for controlling coupled to the sensing means for sampling signals from one or more of the plurality of sensing means;

means for processing at least one of the sampled signals; and

means for voice detection and interpretation.

24. The apparatus of claim 23, wherein the means for sensing comprises periodically activating and sampling response signals in a duty cycle from at least one of the sensing means.

25. The apparatus of claim 24, wherein the duty cycle comprises a first time period defining a time duration during which the sensing means are activated and a second time period defining a repetition rate of the first time period, the duty cycle being a ratio less than 1 of the first time period to the second time period.

26. The apparatus of claim 25, wherein the duty cycle is equal to or less than 50% and greater than 0%.

27. The apparatus of claim 24, wherein the means for sensing determines a hands-on state by a user comprises comparing a level of the signals detected by the sensing means to a threshold level, and activating the hands-on state when the detected signals equal or exceed the threshold level.

28. The apparatus of claim 27, wherein the threshold level is a reference level specified to distinguish between the user'"'"'s hands-on contact and non-contact with the device of each sensing means.

29. The apparatus of claim 23, further comprising:

means to interpret voice detected by the sound detecting means;

means to communicate with a remote server to obtain signals based on the interpreted voice; and

means to halt the operation of the sound detection means, voice interpretation means and communication means.

30. The apparatus of claim 29, wherein the means to halt stops the operations after a delay time based on detecting the device is determined to be in a “

hands-off”

condition and the voice interpreting means does not detect voice.

31. The apparatus of claim 30, wherein the delay time is greater than a specified number of seconds.

32. The apparatus of claim 30, wherein halting comprises disabling at least one of the voice interpreting means, the audio processing means and the communication means to one of a standby and an off state.

33. The apparatus of claim 30, wherein the delay time between samplings is dynamically variable.

34. A non-transitory computer readable media including instructions which when executed by a processor cause the processor to perform the following steps:

sampling signals from a plurality of sensors on the device;

determining if the device is in a hands-on state by a user on the basis of the signal sampling; and

enabling a voice activated detection (VAD) application on the device on the basis of the determination.

35. The non-transitory computer readable media of claim 34, wherein instructions for sampling comprises code for periodically activating at least one of the plurality of sensors in a duty cycle.

36. The non-transitory computer readable media of claim 35, wherein the duty cycle comprises a first time period defining a time duration during which the sensors are activated and a second time period defining a repetition rate of the first time period, the duty cycle being a ratio of the first time period to the second time period less than 1.

37. The non-transitory computer-readable medium of claim 36, wherein the duty cycle is equal to or less than 50% and greater than 0%.

38. The non-transitory computer-readable medium of claim 34, wherein determining the hands-on state comprises comparing a level of the sampled signals to a threshold level, and activating the hands-on state when the sampled signals equal or exceed the threshold level.

39. The non-transitory computer-readable medium of claim 38, wherein the threshold level is a reference level specified to distinguish the user'"'"'s hands-on contact with the device from non-contact with at least one sensor.

40. The non-transitory computer-readable medium of claim 34, the instruction further comprising code for:

interpreting voice detected by the VAD application using an audio processor;

communicating with a communications interface to obtain signals from a remote server based on the interpreted voice; and

halting the operation of the VAD application, audio processor and communication interface.

41. The non-transitory computer-readable medium of claim 40, the instruction further comprising code for:

halting the operations after a delay time based on detecting the device is found in a “

hands-off”

condition and the VAD does not detect voice.

42. The non-transitory computer-readable medium of claim 40, wherein instructions for halting operations comprises code for disabling at least one of the VAD, the audio processor and the communication interface to one of a standby and an off state.

43. The non-transitory computer-readable medium of claim 40, wherein the delay time between samplings is dynamically variable.