Techniques and apparatus for audio isolation in video processing

1. An apparatus, comprising:

a digital display;

a processor circuit; and

an audio isolation component operative on the processor circuit to:

identify a selected position on the digital display during presentation of a video on the digital display, the video comprising a video stream and multiple audio streams, the multiple audio streams comprising audio recorded by an array of microphones prior to the presentation;

determine, based on the selected position, an angular displacement relative to a lens of a camera used to record the video; and

generate an audio beam centered at the angular displacement from at least one of the multiple audio streams based upon the selected position.

2. The apparatus of claim 1 , the audio isolation component operative on the processor circuit to identify the selected position by determining a position on the digital display corresponding to manual touchscreen input, input by an electronic indicating device, input by directed eye movement, gesture based input, or voice command input.

3. The apparatus of claim 1 , the array of microphones comprising a linear array or a two dimensional array.

4. The apparatus of claim 1 , the audio isolation component operative on the processor circuit to:

receive audio metadata that includes spatial indicia of microphones used to record the two or more audio streams; and

generate the audio beam by applying a beam forming function to the audio metadata.

5. The apparatus of claim 4 , the audio isolation component operative on the processor circuit to:

receive camera metadata including a field of view of a camera that recorded the video; and

determine the angular displacement of the selected position based upon X-Y display coordinates and the field of view.

6. The apparatus of claim 4 , the audio isolation component operative on the processor circuit to:

receive depth information for a visual element associated with the selected position; and

determine the angular displacement based upon the depth information associated with the visual element.

7. The apparatus of claim 1 , the audio isolation component operative on the processor circuit to determine X-Y coordinates of the selected position by tracking eye movement of a user proximate the display.

8. The apparatus of claim 1 , the audio isolation component operative on the processor circuit to provide signals to output audio from the audio beam.

9. The apparatus of claim 1 , the audio isolation component operative on the processor circuit to:

identify the selected position during recording of the video;

save the generated audio beam; and

discard audio from at least one other of the multiple audio streams.

10. The apparatus of claim 1 , the audio isolation component operative on the processor circuit to route the audio beam for output at one or more speakers of a set of multichannel speakers such that the audio beam is output based upon the spatial position of the one or more speakers.

11. The apparatus of claim 1 , the audio isolation component operative on the processor circuit to save the audio beam as an audio file having a format that converts the two or more audio streams into a recording represented by the audio beam.

12. The apparatus of claim 1 comprising a set of speakers to output audio from the audio beam.

13. A computer implemented method, comprising:

identifying a selected position on a display during presentation of a video, the video comprising a video stream and multiple audio streams, the multiple audio streams comprising audio recorded by an array of microphones prior to the presentation;

determining, based on the selected position, an angular displacement relative to a lens of a camera used to record the video; and

generating an audio beam centered at the angular displacement from at least one of the multiple audio streams based upon the selected position.

14. The computer implemented method of claim 13 , comprising identifying the selected position by determining a position on the display corresponding to manual touchscreen input, input by an electronic indicating device, input by directed eye movement, gesture based input, or voice command input.

15. The computer implemented method of claim 13 , the array of microphones that comprising a linear array or a two dimensional array.

16. The computer implemented method of claim 13 comprising:

receiving audio metadata that includes spatial indicia of microphones used to record the two or more audio streams; and

generating the audio beam by applying a beam forming function to the audio metadata.

17. The computer implemented method of claim 16 , comprising:

receiving camera metadata including a field of view of a camera that recorded the video; and

determining the angular displacement of the selected position based upon X-Y display coordinates and the field of view.

18. The computer implemented method of claim 16 , comprising:

receiving depth information for a visual element associated with the selected position; and

determining the angular displacement based upon the depth information associated with the visual element.

19. The computer implemented method of claim 13 , comprising:

providing signals to output audio from the audio beam.

20. The computer implemented method of claim 13 , comprising:

identifying the selected position during recording of the video;

saving the generated audio beam; and

designating for discard audio from at least one other of the multiple audio streams.

21. The computer implemented method of claim 13 , comprising routing the audio beam for output at one or more speakers of a set of multichannel speakers such that the audio beam is output based upon the spatial position of the one or more speakers.

22. The computer implemented method of claim 13 , comprising saving the audio beam as an audio file having a format that converts the two or more audio streams into a recording represented by the audio beam.

23. At least one non-transitory computer-readable storage medium comprising instructions that, when executed by a processor of a system, cause the system to:

identify a selected position on a digital display during presentation of a video, the video comprising a video stream and multiple audio streams, the multiple audio streams comprising audio recorded by an array of microphones prior to the presentation;

determining, based on the selected position, an angular displacement relative to a lens of a camera used to record the video; and

generate an audio beam centered at the angular displacement from at least one of the multiple audio streams based upon the selected position.

24. The at least one computer-readable storage medium of claim 23 , comprising instructions that, when executed, cause a system to identify the selected position by determining a position on the display corresponding to manual touchscreen input, input by an electronic indicating device, input by directed eye movement, gesture based input, or voice command input.

25. The at least one computer-readable storage medium of claim 23 , comprising instructions that, when executed, cause a system to:

receive audio metadata that includes spatial indicia of microphones used to record the two or more audio streams; and

generate the audio beam by applying a beam forming function to the audio metadata.

26. The at least one computer-readable storage medium of claim 25 , comprising instructions that, when executed, cause a system to:

receive camera metadata including a field of view of a camera that recorded the video; and

determine the angular displacement of the selected position based upon X-Y display coordinates and the field of view.

27. The at least one computer-readable storage medium of claim 25 , comprising instructions that, when executed, cause a system to:

receive depth information for a visual element associated with the selected position; and

determine the angular displacement based upon the depth information associated with the visual element.

28. The at least one computer-readable storage medium of claim 23 , comprising instructions that, when executed, cause a system to provide signals to output audio from the audio beam.

29. The at least one computer-readable storage medium of claim 23 , comprising instructions that, when executed, cause a system to:

identify the selected position during recording of the video;

save the generated audio beam; and

discard audio from at least one other of the audio streams.

30. The at least one computer-readable storage medium of claim 23 , comprising instructions that, when executed, cause a system to route the audio beam for output at one or more speakers of a set of multichannel speakers such that the audio beam is output based upon the spatial position of the one or more speakers.