Adaptive beam forming devices, methods, and systems

• US 9,451,362 B2
• Filed: 06/11/2014
• Issued: 09/20/2016
• Est. Priority Date: 06/11/2014
• Status: Active Grant

• Current Assignee: Ademco Inc. (Resideo Technologies, Inc.)
• Original Assignee: Honeywell International Inc.
• Inventors: Katuri, SrinivasaRao, Kolavennu, Soumitri N., Kulkarni, Amit
• Primary Examiner(s): Hang, Vu B
• Application Number:
  US14/301,938
• Publication Number:
  US 20150364136A1
• Time in Patent Office: 832 Days
• Field of Search: 704/226, 704/231, 704/233, 704/240, 704/246, 704/251, 704/270
• 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 15/22 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: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: G10L 2021/02166 Microphone arrays; Beamforming
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 21/0216 characterised by the method used for estimating noise
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: H04R 3/005 for combining the signals of two or more microphones specially adapted for hearing aids H04R25/407
• CPC Class Codes: H04R 3/02 for preventing acoustic reaction , i.e. acoustic oscillatory feedback specially adapted for hearing aids H04R25/453

Abstract

Devices, methods, systems, and computer-readable media for adaptive beam forming are described herein. One or more embodiments include a method for adaptive beam forming, comprising: receiving a voice command at a number of microphones, determining an instruction based on the received voice command, calculating a confidence level of the determined instruction, determining feedback based on the confidence level of the determined instruction, and altering a beam of the number of microphones based on the feedback.

Claims

1. A method for adaptive beam forming, comprising:

receiving a voice command at a number of microphones;

determining an instruction based on the received voice command;

calculating a confidence level of the determined instruction;

determining feedback based on the confidence level of the determined instruction, wherein determining feedback includes determining a location where the voice command originated;

altering a beam of the number of microphones based on the feedback, wherein altering the beam of the number of microphones includes focusing a beam angle and a beam width on the location where the voice command originated; and

determining to utilize the feedback for a different received voice command when the different received voice command has similar properties to the received voice command.

2. The method of claim 1, wherein the feedback includes information relating to optimizing a defined beam width and a defined beam direction.

3. The method of claim 1, wherein the confidence level includes a percentage that corresponds to a likelihood the determined instruction correctly corresponds to the received voice command.

4. The method of claim 1, wherein the feedback includes information relating to noise not relating to the received voice command.

5. The method of claim 1, wherein determining the instruction includes utilizing a predetermined vocabulary to determine the instruction of the received voice command.

6. The method of claim 1, wherein determining the instruction includes utilizing a number of acoustic models.

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

receive a voice command;

send the received voice command to a cloud computing network to determine a first instruction of the voice command;

receive feedback from the cloud computing network, wherein the feedback includes a location where the voice command originated;

alter a beam of a number of microphones based on the feedback to determine an altered voice command, wherein altering the beam of the number of microphones includes focusing a beam angle and a beam width on the location where the voice command originated;

send the altered voice command to the cloud computing network to determine a second instruction from the altered voice command; and

determine to utilize the feedback for a different received voice command when the different received voice command has similar properties to the received voice command.

8. The medium of claim 7, wherein the received voice command and altered voice command correspond to a number of executable instructions that when executed by a processor to perform a particular function.

9. The medium of claim 7, wherein the altered voice command is selected to perform a function corresponding to the second instruction.

10. The medium of claim 7, wherein the feedback includes a signal to noise ratio of the received voice command.

11. The medium of claim 7, wherein the feedback includes a quality of the received voice command.

12. The medium of claim 7, wherein instructions to alter the beam of a number of microphones includes altering a beam width and a beam direction.

13. A system, comprising:

an array of microphones to receive a number of voice commands from a plurality of beam directions and a plurality of beam widths;

a signal processor device to define a beam direction from the plurality of beam directions and a beam width from the plurality of beam widths, wherein the signal processor adjusts the defined beam direction and defined beam width based on a received feedback from a speech recognition device, wherein the feedback includes a location where the number of voice commands originated, and wherein the signal processor device determines to utilize the feedback for a different received voice command when the different received voice command has similar properties to the received voice command; and

the speech recognition device to analyze the received number of voice commands at the defined beam direction and defined beam width, wherein the speech recognition device sends feedback to the signal processor device.

14. The medium of claim 13, wherein the feedback includes parameters of the voice command from each of a plurality of beam angles.

15. The system of claim 13, wherein the signal processor includes:

an adaptive beam former;

a residual echo suppressor;

an adaptive noise canceller; and

an adaptive speech recognizer.

16. The system of claim 13, wherein signal processor device and the speech recognition device are utilized on a cloud computing network.

17. The system of claim 13, wherein the feedback includes an alternate beam angle from the plurality of beam angles and an alternate beam width from the plurality of beam widths to increase a signal to noise ratio of the received number of voice commands.

18. The system of claim 17, wherein the defined beam angle and the defined beam width are altered to the alternate beam angle and the alternate beam width.

19. The system of claim 17, wherein the speech recognition device includes a front end module to determine a signal to noise ratio and a back end module to determine the alternate beam width and the alternate beam width.