Audio Signal Beam Forming

Patent metadata

Field	Value
Publication number	US-2016249134-A1
Application number	US-201414434375-A
Country	US
Kind code	A1
Filing date	May 8, 2014
Priority date	May 8, 2014
Publication date	Aug 25, 2016
Grant date	—

Abstract

Techniques for processing audio data are described. An example of a computing device includes a microphone array to generate audio data and a camera. The computing device is to receive video data from the camera and identify a beam forming target based, at least in part, on the video data. The computing device also includes a beam former to process the audio data to aim a beam of the microphone array at the beam forming target.

First claim

What is claimed is:

1 . A computing device, comprising:
a microphone array to receive and generate audio data; a camera, wherein the computing device is to receive video data from the camera and identify a beam forming target based, at least in part, on the video data; and a beam former to process the audio data to aim a beam of the microphone array at the beam forming target.

2 . The computing device of claim 1 , comprising a display to display the video data, the computing device to receive a user selection of the beam forming target from the displayed video data.

3 . The computing device of claim 2 , wherein the user selection is a selection of an object shown on the display.

4 . The computing device of claim 3 , comprising a motion tracker to track the object, wherein the beam former uses motion tracking information from the motion tracker to adjust the microphone array to keep the beam aimed at the beam forming target.

5 . The computing device of claim 3 , wherein the object is a person's face.

6 . The computing device of claim 5 , comprising a face detector, wherein the person's face is identified by the face detector and highlighted on the display.

7 . The computing device of claim 1 , wherein the beam forming target is automatically identified by the computing device based on the video data without receiving a selection of the beam forming target from the user.

8 . The computing device of claim 1 , comprising a face detector to detect a person's face in the video data, wherein the person's face is automatically identified by the computing device as the beam forming target.

9 . The computing device of claim 1 , comprising a face detector to detect a person's face in the video data and highlight the person's face on the display, wherein a user of the computing device can manually select the person's face as the beam forming target.

10 . The computing device of claim 1 , wherein the microphone array includes three or more microphones to generate two or more separate audio beams to be aimed at two or more beam forming targets.

11 . An apparatus, comprising:
logic to receive video data from a camera; logic to identify a beam forming target based, at least in part, on the video data; and logic to receive audio data from a microphone array and process the audio data to aim a beam of the microphone array at the beam forming target.

12 . The apparatus of claim 11 , comprising logic to display the video data and logic to receive a user selection of the beam forming target from the displayed video data, wherein the user selection is a selection of an object shown in the displayed video data.

13 . The apparatus of claim 12 , comprising logic to track the object and generate motion tracking information, wherein the logic to process the audio data uses the motion tracking information to keep the beam aimed at the beam forming target.

14 . The apparatus of claim 12 , wherein the object is a person's face, the apparatus comprising logic to automatically identify the person's face.

15 . The apparatus of claim 11 , comprising logic to detect a person's face in the video data, wherein the person's face is automatically selected by the computing device as the beam forming target.

16 . The apparatus of claim 11 , comprising logic to detect a person's face in the video data, highlight the person's face on the display, receive a user selection of the person's face, and, based on the user selection, specify the person's face as the beam forming target.

17 . A computer-readable medium, comprising instructions to direct a processor to:
receive video data; identify a beam forming target based, at least in part, on the video data; and receive audio data from a microphone array and process the audio data to aim a beam of the microphone array at the beam forming target.

18 . The computer-readable medium of claim 17 , comprising instructions to direct the processor to display the video data and receive a user selection of the beam forming target from the displayed video data, wherein the user selection is a selection of an object shown in the displayed video data.

19 . The computer-readable medium of claim 18 , comprising instructions to direct the processor to track the object and generate motion tracking information, wherein the instructions to direct the processor to process the audio data uses the motion tracking information to keep the beam aimed at the beam forming target.

20 . The computer-readable medium of claim 18 , wherein the object is a person's face.

21 . The computer-readable medium of claim 20 , comprising instructions to direct the processor to automatically identify the person's face.

22 . The computer-readable medium of claim 17 , comprising instructions to direct the processor to automatically identify the beam forming target based on the video data without receiving a selection of the beam forming target from the user.

23 . The computer-readable medium of claim 17 , comprising instructions to direct the processor to detect a person's face in the video data, wherein the person's face is automatically selected by the computing device as the beam forming target.

24 . The computer-readable medium of claim 17 , comprising instructions to direct the processor to detect a person's face in the video data, highlight the person's face on the display, receive a user selection of the person's face, and, based on the user selection, specify the person's face as the beam forming target.

25 . The computer-readable medium of claim 17 , wherein the instructions to direct the processor to process the audio data generates two or more separate audio beams to be aimed at two or more beam forming targets.

Assignees

• Wang Jian
• Wong Hong
• Uan-Zo-Li Alexander
• Liang Xiaoguo
• Jiang Huaping
• Intel Corp

Inventors

• Wang Jian
• Wong Hong
• Uan-Zo-Li Alexander
• Liang Xiaoguo
• Jiang Huaping

Classifications

• G06K9/00255

  Physics · mapped topic

• H04R3/005 Primary

  for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407) · CPC title

• H04R2430/23

  Direction finding using a sum-delay beam-former · CPC title

• G06T7/2033

  Physics · mapped topic

• H04R2410/01

  Noise reduction using microphones having different directional characteristics · CPC title