PERFORMING AUTOMATED VOICE OPERATIONS BASED ON SENSOR DATA REFLECTING SOUND VIBRATION CONDITIONS AND MOTION CONDITIONS

• US 20150179189A1
• Filed: 12/24/2013
• Published: 06/25/2015
• Est. Priority Date: 12/24/2013
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Dadu, Saurabh, Krishnamurthy, Lakshman, Shah, Saurin, Tharappel, Francis M., Kar, Swarnendu
• Granted Patent: US 9,620,116 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 25/84 for discriminating voice from noise

Abstract

Systems and methods may provide for determining a sound vibration condition of an ambient environment of a wearable device and determining a motion condition of the wearable device. In addition, one or more automated voice operations may be performed based at least in part on the sound vibration condition and the motion condition. In one example, two or more signals corresponding to the sound vibration condition and the motion condition may be combined.

Claims

1. A wearable device comprising:

an air-based microphone; and

logic, implemented at least partly in fixed-functionality hardware, to;

determine a sound vibration condition of an ambient environment of the wearable device based at least in part on a signal associated with the air-based microphone,

determine a motion condition of the wearable device, and

perform one or more automated voice operations based at least in part on the sound vibration condition and the motion condition.

2. The wearable device of claim 1, wherein the logic is to use a combination of two or more signals corresponding to the sound vibration condition and the motion condition to perform the one or more automated voice operations.

3. The wearable device of claim 1, further including an inertial sensor, wherein the motion condition is to be determined based at least in part on a signal associated with the inertial sensor.

4. The wearable device of claim 3, wherein at least one of the one or more automated voice operations is to include a voice activity detection operation.

5. The wearable device of claim 1, further including a bone conduction microphone, wherein the motion condition is to be determined based at least in part on a signal associated with the bone conduction microphone.

6. The wearable device of claim 5, wherein at least one of the one or more automated voice operations is to include one or more of a voice activity detection operation, a keyword detection operation, a speaker verification operation or a voice interaction operation.

7. A method comprising:

determining a sound vibration condition of an ambient environment of a wearable device;

determining a motion condition of the wearable device; and

performing one or more automated voice operations based at least in part on the sound vibration condition and the motion condition.

8. The method of claim 7, further including using a combination of two or more signals corresponding to the sound vibration condition and the motion condition to perform the one or more automated voice operations.

9. The method of claim 7, wherein the sound vibration condition is determined based at least in part on a signal associated with an air-based microphone of the wearable device.

10. The method of claim 7, wherein the motion condition is determined based at least in part on a signal associated with an inertial sensor of the wearable device and at least one of the one or more automated voice operations includes a voice activity detection operation.

11. The method of claim 7, wherein the motion condition is determined based at least in part on a signal associated with a bone conduction microphone of the wearable device, wherein at least one of the one or more automated voice operations includes one or more of a voice activity detection operation, a keyword detection operation, a speaker verification operation or a voice interaction operation.

12. At least one computer readable storage medium comprising a set of instructions which, if executed by a wearable device, cause the wearable device to:

determine a sound vibration condition of an ambient environment of the wearable device;

determine a motion condition of the wearable device; and

perform one or more automated voice operations based at least in part on the sound vibration condition and the motion condition.

13. The at least one computer readable storage medium of claim 12, wherein the instructions, if executed, cause the wearable device to use a combination of two or more signals corresponding to the sound vibration condition and the motion condition to perform the one or more automated voice operations.

14. The at least one computer readable storage medium of claim 12, wherein the sound vibration condition is to be determined based at least in part on a signal associated with an air-based microphone of the wearable device.

15. The at least one computer readable storage medium of claim 12, wherein the motion condition is to be determined based at least in part on a signal associated with an inertial sensor of the wearable device.

16. The at least one computer readable storage medium of claim 15, wherein at least one of the one or more automated voice operations is to include a voice activity detection operation.

17. The at least one computer readable storage medium of claim 12, wherein the motion condition is to be determined based at least in part on a signal associated with a bone conduction microphone of the wearable device.

18. The at least one computer readable storage medium of claim 17, wherein at least one of the one or more automated voice operations is to include one or more of a voice activity detection operation, a keyword detection operation, a speaker verification operation or a voice interaction operation.

19. An apparatus comprising:

logic, implemented at least partly in fixed-functionality hardware, to;

determine a sound vibration condition of an ambient environment of a wearable device,

determine a motion condition of the wearable device, and

perform one or more automated voice operations based at least in part on the sound vibration condition and the motion condition.

20. The apparatus of claim 19, wherein the logic is to use a combination of two or more signals corresponding to the sound vibration condition and the motion condition to perform the one or more automated voice operations.

21. The apparatus of claim 19, wherein the sound vibration condition is to be determined based at least in part on a signal associated with an air-based microphone of the wearable device.

22. The apparatus of claim 19, wherein the motion condition is to be determined based at least in part on a signal associated with an inertial sensor of the wearable device.

23. The apparatus of claim 22, wherein at least one of the one or more automated voice operations is to include a voice activity detection operation.

24. The apparatus of claim 19, wherein the motion condition is to be determined based at least in part on a signal associated with a bone conduction microphone of the wearable device.

25. The apparatus of claim 24, wherein at least one of the one or more automated voice operations is to include one or more of a voice activity detection operation, a keyword detection operation, a speaker verification operation or a voice interaction operation.