Methods and systems for ambient system control

• US 10,565,862 B2
• Filed: 11/27/2012
• Issued: 02/18/2020
• Est. Priority Date: 11/27/2012
• Status: Active Grant

• Current Assignee: Comcast Cable Communications LLC (Comcast Corporation)
• Original Assignee: Comcast Cable Communications LLC (Comcast Corporation)
• Inventors: Chen, Michael
• Primary Examiner(s): Holloway, III, Edwin C
• Application Number:
  US13/686,080
• Publication Number:
  US 20140146644A1
• Time in Patent Office: 2,639 Days
• Field of Search: 367197, 370328, 713300, 713310, 713323, 381 91, 381122
• CPC Class Codes: G08C 17/02 using a radio link
• CPC Class Codes: G08C 23/04 using light waves, e.g. infrared
• 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 15/28 Constructional details of speech recognition systems
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems

Abstract

Provided are methods and systems for ambient system control, comprising multiple detection devices with varying levels of detection capability. The methods and systems contemplate the use of both voice and gesture commands, as well as other inputs, for system control.

Claims

1. A method comprising:

detecting, by a first detection device, a first audio signal generated by a user;

determining that the first audio signal comprises an activation indication;

sending, from the first detection device to a second detection device proximate to the user, based on the activation indication, an activation signal, wherein the activation signal causes the second detection device to activate;

detecting, by the second detection device, a second audio signal generated by the user;

determining that the second audio signal indicates a command; and

causing the command to be executed.

2. The method of claim 1, wherein the first detection device is configured for lower fidelity audio signal detection relative to the second detection device.

3. The method of claim 1, further comprising, based on the activation signal:

determining that the second detection device is proximate to the user; and

causing the second detection device to exit a lower power mode.

4. The method of claim 1, further comprising, based on the activation signal, causing one or more of a microphone, a motion sensor, or a camera associated with the second detection device to activate.

5. The method of claim 1, wherein the first detection device is powered by a continuous power source, and wherein the second detection device is powered by battery power.

6. The method of claim 1, wherein at least one of the first detection device or the second detection device comprises a plurality of devices.

7. The method of claim 1, wherein the second detection device comprises one or more of a remote control, a smartphone, a microphone, a camera, or a portable computer.

8. The method of claim 1, wherein one or more of the first detection device, the second detection device, or a computing device are configured to determine that the second audio signal indicates the command.

9. The method of claim 1, wherein causing the command to be executed comprises sending the command to a target device, wherein the target device executes the command.

10. The method of claim 9, wherein the target device comprises one or more of a TV, a DVR, a set top box, a radio, a thermostat, a light source, a security system, the first detection device, or the second detection device.

11. The method of claim 1, wherein causing the command to be executed comprises sending the command to a plurality of target devices.

12. The method of claim 1, wherein the second detection device has less available power than the first detection device, and wherein the second detection device is physically closer to the user than the first detection device.

13. A method comprising:

detecting, by a first detection device, a first portion of an audio signal generated by a user;

determining that the first portion of the audio signal comprises an activation indication;

sending, from the first detection device to a second detection device, based on the activation indication, an activation signal, wherein the activation signal causes the second detection device to activate;

detecting, by the second detection device, a second portion of the audio signal generated by the user;

determining, based on the second portion of the audio signal, a command;

determining, by the second detection device, that the command is associated with a target device; and

sending, to the target device, the command.

14. The method of claim 13, wherein the command comprises one or more of an activation command or an action command.

15. The method of claim 13, wherein the first detection device is configured for lower audio signal detection relative to the econd detection device.

16. The method of claim 13, wherein determining, based on the second portion of the audio signal, the command comprises:

determining, based on a time-based subdivision of the second portion of the audio signal, recognized phonemes within the second portion of the audio signal;

determining, based on the recognized phonemes, word phrases; and

determining the command by comparing the word phrases to one or more action commands.

17. The method of claim 13, further comprising executing, by the target device, the command.

18. The method of claim 13, wherein the target device comprises one or more of a TV, a DVR, a set top box, a radio, a thermostat, a light source, a security system, the first detection device, or the second detection device.

19. The method of claim 13, wherein the second detection device has less available power than the first detection device, and wherein the second detection device is physically closer to the user than the first detection device.

20. A method comprising:

detecting, by a first detection device, a first portion of an audio signal generated by a user;

determining that the first portion of the audio signal comprises an activation indication;

sending, from the first detection device to a second detection device, based on the activation indication, an activation signal, wherein the activation signal causes the second detection device to activate;

detecting, by the second detection device, a second portion of the audio signal generated by the user;

sending, by the second detection device, to a computing device, the second portion of the audio signal;

determining, by the computing device, that the second portion of the audio signal comprises a command; and

sending, to a target device, the command.

21. The method of claim 20, wherein the first detection device is configured for lower audio fidelity audio signal detection relative to the second detection device.

22. The method of claim 20, wherein the command comprises one or more of an activation command or an action command.

23. The method of claim 20, wherein determining that the second portion of the audio signal comprises the command comprises determining, based on a time-based subdivision of the second portion of the audio signal, one or more phonemes.

24. The method of claim 23, further comprising determining, based on the one or more phonemes, one or more word phrases;

and

comparing the one or more word phrases to one or more action commands.

25. The method of claim 20, wherein determining, by the computing device, that the second portion of the audio signal comprises the command comprises:

determining, based on a time-based subdivision of the second portion of the audio signal, recognized phonemes within the audio signal;

determining, based on the recognized phonemes, word phrases; and

determining the command by comparing the word phrases to one or more action commands.

26. The method of claim 20, further comprising, executing, by the target device, the command.

27. The method of claim 20, wherein the target device comprises one or more of a TV, a DVR, a set top box, a radio, a thermostat, a light source, a security system, the first detection device, or the second detection device.

28. The method of claim 20, wherein the second detection device has less available power than the first detection device, and wherein the second detection device is physically closer to the user than the first detection device.