INTELLIGENT PLACEMENT OF APPLIANCE RESPONSE TO VOICE COMMAND

• US 20150032456A1
• Filed: 07/25/2013
• Published: 01/29/2015
• Est. Priority Date: 07/25/2013
• Status: Active Grant

• Current Assignee: Haier US Appliance Solutions, Inc. DBA GE Appliances (Haier Group Company)
• Original Assignee: General Electric Company
• Inventors: Wait, Keith Wesley
• Granted Patent: US 9,431,014 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G01S 5/18 using ultrasonic, sonic, or infrasonic waves
• CPC Class Codes: G01S 5/26 Position of receiver fixed by co-ordinating a plurality of position lines defined by path-difference measurements G01S5/28 takes precedence
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2021/02166 Microphone arrays; Beamforming
• 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

Abstract

Systems and methods for intelligent placement of appliance response to a voice command are provided. An exemplary system includes a plurality of appliances. An exemplary method includes connecting each of the plurality of appliances over a local area network and generating a location map providing a location of each of the plurality of appliances. The method includes receiving the human voice signal at a plurality of microphones respectively included in the plurality of appliances and determining an originating location of the human voice signal based at least in part on the location map. The method includes selecting one of the plurality of appliances to respond to the human voice signal based at least in part on the location map and the originating location.

Claims

1. A method for operating a system to respond to a human voice signal, the system comprising a plurality of appliances, the method comprising:

connecting each of the plurality of appliances over a local area network;

generating a location map providing a location of each of the plurality of appliances;

receiving the human voice signal at a plurality of microphones respectively included in the plurality of appliances;

determining an originating location of the human voice signal based at least in part on the location map; and

selecting one of the plurality of appliances to respond to the human voice signal based at least in part on the location map and the originating location.

2. The method of claim 1, wherein generating the location map providing the location of each of the plurality of appliances comprises:

emitting an audio signal from each of the plurality of appliances;

receiving each audio signal at each of the non-emitting appliances; and

generating the location map based on one or more characteristics associated with the received audio signals.

3. The method of claim 2, wherein generating the location map based on one or more characteristics associated with the received audio signals comprises:

determining, for each audio signal, a direction of arrival at each non-emitting appliance; and

generating the location map based on the plurality of directions of arrival for each audio signal.

4. The method of claim 3, wherein determining, for each audio signal, the direction of arrival at each non-emitting appliance comprises calculating the direction of arrival at each non-emitting appliance based on a time difference in reception between two microphones included in each non-emitting appliance, the two microphones having a known spatial configuration.

5. The method of claim 2, wherein generating the location map based on one or more characteristics associated with the received audio signals comprises:

determining, for each audio signal, a plurality of distances from emittance respectively associated with the plurality of non-emitting appliances, each distance from emittance for each non-emitting appliance being based on a time of arrival of the audio signal at such non-emitting appliance; and

generating the location map based on the plurality of distances from emittance for each audio signal.

6. The method of claim 5, further comprising synchronizing a plurality of clocks respectively included in the plurality of appliances prior to instructing each of the plurality of appliances to emit an audio signal.

7. The method of claim 1, further comprising selecting one of the plurality of appliances to serve as a network master, the network master performing data processing for the system.

8. The method of claim 1, wherein determining the originating location of the human voice signal based at least in part on the location map comprises:

determining, for each of the plurality of appliances, a direction of arrival of the human voice signal; and

determining the originating location based on the plurality of directions of arrival and the location map.

9. The method of claim 8, wherein the direction of arrival of the human voice signal is determined for each of the plurality of appliances based on a time difference in reception between two microphones included in each appliance, the two microphones having a known spatial configuration.

10. The method of claim 1, wherein determining the originating location of the human voice signal based at least in part on the location map comprises determining the originating location of the human voice signal based on the location map and a plurality of respective times of arrival of the human voice signal at the plurality of appliances.

11. The method of claim 1, wherein receiving the human voice signal at the plurality of microphones comprises respectively generating a plurality of recorded voice waveforms at the plurality of appliances, the method further comprising, after determining the originating location of the human voice signal, performing a beamforming technique with respect to the plurality of recorded voice waveforms to spatially filter the human voice signal.

12. The method of claim 1, wherein selecting one of the plurality of appliances to respond to the human voice signal based at least in part on the location map and the originating location comprises:

determining one or more functionalities required for an appropriate response; and

identifying the appliance that is capable of performing the one or more functionalities and is most proximate to the originating location.

13. A system for responding to a human voice signal, the system comprising:

a plurality of appliances in communication over a local area network, each of the plurality of appliances comprising a processor, a memory, a speaker, and at least one microphone;

wherein at least one of the plurality of appliances is configured to generate a location map based on a plurality of audio signals respectively transmitted by the plurality of appliances, the location map describing a position for each of the plurality of appliances.

14. The system of claim 13, wherein:

each of the plurality of appliances further comprises an internal clock;

the plurality of appliances are configured to synchronize their internal clocks; and

the at least one appliance is configured to generate the location map by performing operations, the operations comprising;

sequentially prompting each of the plurality of appliances to transmit one of the plurality of audio signals with its speaker, such that the plurality of audio signals are respectively transmitted by the plurality of appliances over time;

receiving, for each transmitted audio signal, a time of arrival of such audio signal at each of the non-transmitting appliances; and

determining the position for each of the plurality of appliances based on a comparison of the plurality of times of times of arrival for each of the plurality of audio signals.

15. The system of claim 13, wherein:

each appliance comprises two microphones having a known spatial arrangement; and

the at least one appliance is configured to generate the location map by performing operations, the operations comprising;

sequentially prompting each of the plurality of appliances to transmit one of the plurality of audio signals with its speaker, such that the plurality of audio signals are respectively transmitted by the plurality of appliances over time;

receiving, for each transmitted audio signal, a direction of arrival of such audio signal from each of the non-transmitting appliances; and

determining the position for each of the plurality of appliances based on a comparison of the plurality of directions of arrival for each of the plurality of audio signals.

16. The system of claim 13, wherein the microphones of the plurality of appliances collectively form an array for receiving the human voice signal.

17. The system of claim 16, wherein at least one of the plurality of appliances is configured to generate a beamformed voice signal by performing a beamforming technique with respect to a plurality of voice waveforms respectively collected by the plurality of microphones.

18. The system of claim 13, wherein:

one of the plurality of appliances is designated as a network master;

each of the plurality of appliances is configured to detect and receive the human voice signal and to record a time of arrival or a direction of arrival; and

the network master is configured to;

determine an originating location of the human voice signal based on the plurality of times of arrival or the plurality of directions of arrival; and

select one of the appliances to respond to the human voice signal based at least in part on the originating location.

19. The system of claim 18, wherein the network master is configured select one of the appliances to respond to the human voice signal based at least in part on the originating location by performing operations, the operations comprising:

obtaining one or more criteria required for an appropriate response;

determining which of the plurality of appliances that satisfy the one or more criteria is most proximate to the location of the origin.

20. A device for use in a system configured to respond to a human voice signal, the system comprising a plurality of appliances, the device comprising:

a processor;

a memory; and

a network interface for communicating with the system over a local area network;

wherein the device is configured to perform operations, the operations comprising;

determining a location map describing a location for each of the plurality of appliances based on a plurality of audio signals respectively transmitted by the plurality of appliances;

determining an originating location of the human voice signal based at least in part on the location map; and

selecting one of the appliances to respond to the human voice signal based at least in part on the location map and the originating location.