Voice-controlled light switches

• US 9,826,599 B2
• Filed: 12/28/2015
• Issued: 11/21/2017
• Est. Priority Date: 12/28/2015
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Banta, William Christopher
• Primary Examiner(s): Owens, Douglas W
• Assistant Examiner(s): Kaiser, Syed M
• Application Number:
  US14/980,392
• Publication Number:
  US 20170188437A1
• Time in Patent Office: 694 Days
• Field of Search: 315297
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• 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: H04L 12/282 based on user interaction within the home receiver circuitry for displaying additional information being controlled by a remote control apparatus H04N21/42204
• CPC Class Codes: H04L 12/2825 Reporting to a device located outside the home and the home network access arrangements H04L12/2856; for remote control or remote monitoring of applications H04L67/025; telephonic communication systems adapted for combination with telemetering systems H04M11/002
• CPC Class Codes: H04R 1/028 associated with devices performing functions other than acoustics, e.g. electric candles
• CPC Class Codes: H04R 1/406 microphones
• CPC Class Codes: H04R 2201/021 Transducers or their casings adapted for mounting in or to a wall or ceiling
• CPC Class Codes: H05B 47/12 by detecting audible sound
• CPC Class Codes: H05B 47/19 via wireless transmission

Abstract

This disclosure describes, in part, voice-controlled light switches that act as voice-controlled endpoints at which users may provide voice commands. These light switches may physically couple to a power source, as well as to one or more appliances. The light switches may include physical switches to selectively provide power to the appliances, either in a binary fashion (on or off) or along of spectrum of positions. In either instance, the appliances coupled to the light switches may include lights, electrical outlets, home appliances (e.g., dishwashers, washing machines, etc.), factory machinery, or any other device that receives electrical power.

Claims

1. An apparatus comprising:

one or more wires to couple to a power source and to at least one light;

a switch configured to toggle between at least an on position and an off position, the one or more wires providing power from the power source to the at least one light when the switch is in the on position and not providing power from the power source to the at least one light when the switch is in the off position;

a faceplate;

a first microphone located on a distal end of the switch;

a second microphone located at a first position of the faceplate, the first position being near the distal end of the switch when the switch is in the on position;

a third microphone located at a second position of the faceplate, the second position being near the distal end of the switch when the switch is in the off position;

a wireless network interface;

one or more processors;

one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform acts comprising;

receiving a first audio signal generated by at least one of the first microphone, the second microphone, or the third microphone;

performing speech recognition on the first audio signal;

determining that the first audio signal includes data representing at least one predefined word;

determining that the switch is in the off position;

performing beamforming on a second audio signal generated by the first microphone and on a third audio signal generated by the third microphone to generate one or more processed audio signals; and

sending, to a remote device and via the wireless network interface, the one or more processed audio signals.

2. The apparatus as recited in claim 1, the acts further comprising:

receiving, from the remote device, an instruction to turn on the at least one light; and

coupling the one or more wires to cause the one or more wires to provide power from the power source to the at least one light while the switch remains in the off position.

3. The apparatus as recited in claim 1, wherein the first position is located approximately at a middle of a horizontal dimension of the faceplate and the second position is located approximately at the middle of the horizontal dimension of the faceplate, and further comprising:

a fourth microphone located substantially horizontally in-line with the second microphone and towards a left side of the faceplate;

a fifth microphone located substantially horizontally in-line with the second microphone and towards a right side of the faceplate;

a sixth microphone located substantially horizontally in-line with the third microphone and towards the left side of the faceplate; and

a seventh microphone located substantially horizontally in-line with the third microphone and towards the right side of the faceplate.

4. The apparatus as recited in claim 3, the acts further comprising determining, prior to the sending, that a first line defined by the third microphone and the first microphone is more in-line with a user that stated the at least one predefined word than a second line defined by the sixth microphone and the first microphone and a third line defined by the seventh microphone and the first microphone.

5. An apparatus comprising:

one or more wires to couple to an alternating-current (AC) power source located within a building and to at least one power load;

a switch configured to move from at least a first position to a second position, when the switch is in the first position the AC power source is electrically coupled to the at least one power load and when the switch is in the second position the AC power source is decoupled from the at least one power load;

a faceplate;

a first microphone located proximate the faceplate configured to generate a first audio signal;

a second microphone located proximate the faceplate configured to generate a second audio signal;

one or more processors; and

one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform acts comprising;

performing beamforming on the first audio signal and the second audio signal to generate one or more processed audio signals; and

sending the one or more processed audio signals to a remote device configured to perform speech recognition on the one or more processed audio signals.

6. The apparatus as recited in claim 5, further comprising:

a wireless network interface;

and wherein the sending comprises sending the one or more processed audio signals using the wireless network interface.

7. The apparatus as recited in claim 5,

wherein the acts further comprise performing speech recognition on at least one of the first audio signal, the second audio signal, or the one or more processed audio signals to at least one of identity data representing a predefined utterance or identify data representing a voice command related to the at least one power load or another power load.

8. The apparatus as recited in claim 5, further comprising:

a third microphone located on the switch configured to generate a third audio signal;

and wherein the acts further comprise;

performing speech recognition on at least one of the first audio signal, the second audio signal, or the one or more processed audio signals; and

identifying data representing a predefined utterance;

and wherein the sending comprises sending the one or more processed audio signals to the remote device at least partly in response to the identifying.

9. The apparatus as recited in claim 5, wherein the first microphone is located at a third position proximate the faceplate that is nearer the switch when the switch is in the first position and the second microphone is located at a fourth position proximate the faceplate that is nearer the switch when the switch is in the second position, and further comprising:

a third microphone located on the switch configured to generate a third audio signal;

and wherein the acts further comprise;

determining that the switch is in the first position;

selecting the first audio signal generated by the first microphone for at least one of processing or sending at least partly in response to determining that the switch is in the first position;

determining that the switch is in the second position; and

selecting the second audio signal generated by the second microphone for at least one of processing or sending at least partly in response to determining that the switch is in the second position.

10. The apparatus as recited in claim 5, wherein the first microphone and the second microphone are located substantially horizontally in-line with one another proximate the faceplate.

11. The apparatus as recited in claim 5, further comprising a button that is selectable to cause at least one of the first microphone to generate the first audio signal or the second microphone to generate the second audio signal.

12. The apparatus as recited in claim 5, wherein the switch comprises a toggle switch, a rocker switch, a dimmer switch, or a time-delay switch.

13. The apparatus as recited in claim 5, wherein the at least one power load comprises a light, an electrical outlet, or a home appliance.

15. The method as recited in claim 13, wherein the selecting the first audio signal and the second audio signal for processing comprises sending the first audio signal and the second audio signal to a remote device without sending the third audio signal to the remote device.

16. The method as recited in claim 13, wherein the selecting the first audio signal and the second audio signal for processing comprises performing beamforming on the first audio signal and the second audio signal to generate one or more processed audio signals, and further comprising at least one of sending the one or more processed audio signals to a remote device or performing speech recognition on the one or more processed audio signals.

17. The method as recited in claim 13, further comprising:

performing speech recognition on at least one of the first audio signal, the second audio signal, or the third audio signal; and

determining that the at least one of the first audio signal, the second audio signal, or the third audio signal includes data representing a predefined utterance;

and wherein the selecting the first audio signal and the second audio signal for processing is further based at least in part on the determining that the at least one of the first audio signal, the second audio signal, or the third audio signal includes the data representing the predefined utterance.

18. The method as recited in claim 13, further comprising:

determining that the physical switch resides in a second position; and

at least partly in response to determining that the physical switch resides in the second position, selecting at least the first audio signal and the third audio signal for processing.

19. The method as recited in claim 13, further comprising:

receiving a fourth audio signal generated by a fourth microphone, the fourth microphone residing substantially horizontally in-line with the second microphone;

determining that a first line defined by the second microphone and the first microphone points closer to a source of audio than does a second line defined by the fourth microphone and the first microphone;

and wherein the selecting the first audio signal and the second audio signal for processing is further based at least in part on the determining that the first line points closer to the source of audio than does the second line.

20. The method as recited in claim 13, wherein:

the receiving the first audio signal comprises receiving the first audio signal generated by the first microphone residing on a physical switch of a light switch;

the receiving the second audio signal comprises receiving the second audio signal generated by the second microphone residing on a top portion of a faceplate of the light switch; and

the receiving the third audio signal comprises receiving the third audio signal generated by the third microphone residing on a bottom portion of the faceplate of the light switch.

14. A method comprising:

receiving a first audio signal generated by a first microphone residing on a physical switch;

receiving a second audio signal generated by a second microphone;

receiving a third audio signal generated by a third microphone;

determining that the physical switch resides in a first position; and

at least partly based on the physical switch residing in the first position, selecting at least the first audio signal and the second audio signal for processing.