FAR-FIELD SPEECH RECOGNITION SYSTEMS AND METHODS

• US 20150194152A1
• Filed: 01/09/2014
• Published: 07/09/2015
• Est. Priority Date: 01/09/2014
• Status: Active Grant

• Current Assignee: Ademco Inc. (Resideo Technologies, Inc.)
• Original Assignee: Honeywell International Inc.
• Inventors: Katuri, SrinivasaRao, Kulkarni, Amit
• Granted Patent: US 9,443,516 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• 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 2021/02166 Microphone arrays; Beamforming
• CPC Class Codes: G10L 21/0208 Noise filtering

Abstract

A method for far-field speech recognition can include determining a location for a plurality of sound recognition devices, communicatively coupling each of the plurality of sound recognition devices, adjusting a sound reception for the plurality of sound recognition devices to receive a voice command from a particular direction, and sending instructions to a device based on the voice command.

Claims

1. A method for far-field speech recognition, comprising:

determining a location for a plurality of sound recognition device

communicatively coupling each of the plurality of sound recognition devices;

adjusting a sound reception for the plurality of sound recognition devices to receive a voice command from a particular direction; and

sending instructions to a device based on the voice command.

2. The method of claim 1, wherein determining the location for the plurality of sound recognition devices includes determining a location of a number of appliances with embedded speech recognition devices.

3. The method of claim 1, wherein determining the location for a plurality of sound recognition devices includes determining a location for each of the plurality of sound recognition devices to capture sound from a particular area.

4. The method of claim 1, wherein adjusting the sound reception for the plurality of sound recognition devices includes performing adaptive spatial signal processing of the sound recognition devices.

5. The method of claim 1, comprising placing the plurality of sound recognition devices in an array based on the determined locations.

6. The method of claim 1, wherein sending instructions to the device includes sending instructions to a device that is at a remote location from a location of the received voice command.

7. The method of claim 1, wherein sending instructions to the device includes sending the received voice command from a first room of a building to a device in a second room of the building,

8. A non-transitory computer readable medium, comprising instructions to:

receive a voice command from a user located at a first position;

adjust a sound reception to enhance aspects of the voice command;

identify the user based on the received voice command;

determine a device that relates to the voice command, and

send instructions to the device located at a second position, wherein the instructions are based on the voice command.

9. The medium of claim 8, wherein the voice command includes a description for changing a setting of the device.

10. The medium of claim 8, wherein the instructions to adjust a sound reception includes instructions to adapt the sound reception to remove background noise not related to the voice command

11. The medium of claim 8, comprising instructions to send the voice command to a cloud based computing device.

12. The medium of claim 8, wherein the first position is a remote location from the second position,

13. The medium of claim 8, wherein the instructions to identify the user includes instructions to determine an authorization level of the user.

14. The medium of claim 13, wherein the instructions to determine an authorization level includes instructions to determine if the user is authorized to change a number of settings of the device.

15. A system, comprising:

a plurality of communicatively coupled sound recognition devices placed in an array to receive sound within an area, wherein the plurality of sound recognition devices are communicatively coupled to a computing hub;

a number of devices communicatively coupled to the computing hub; and

the computing hub including instructions to;

receive a number of voice commands from the plurality of sound recognition devices;

identify a user based on the received number of voice commands;

determine a device from the number of devices that relates to the voice command; and

send instructions to the determined device to change a number of settings on the determined device, wherein the instructions are based on the voice command.

16. The system of claim 15, wherein the number of devices include a number of devices coupled to corresponding computing devices.

17. The system of claim 15, wherein the plurality of sound recognition devices are in a first location, the number of devices are in a second location, and the computing hub is in a third location.

18. The system of claim 17, wherein the plurality of sound recognition devices are coupled to a corresponding wireless radio to send the voice command to the computing hub.

19. The system of claim 15, wherein the computing hub utilizes a cloud computing network to process received voice commands.

20. The system of claim 15, wherein the instructions to identify the user includes instructions to determine a portion of the number of devices, wherein the portion of the number of devices are devices that the user has access to alter settings.