Acoustic transfer function personalization using sound scene analysis and beamforming

1. A method comprising:

detecting, via a microphone array of a wearable device, sounds from one or more sound sources in a local area of the wearable device;

estimating acoustic transfer functions associated with the sounds;

estimating a direction of arrival (DoA) of a sound source in the one or more sound sources;

calculating a first confidence level for the direction of arrival estimate;

tracking a movement of the sound source;

calculating a second confidence level for the movement of the sound source; and

updating, in response to the movement of the sound source, the acoustic transfer functions based in part on the first confidence level and the second confidence level.

2. The method of claim 1 , further comprising classifying the sound source based on a classification library.

3. The method of claim 1 , further comprising isolating a signal from the sound source from other sound sources in the local area of the wearable device.

4. The method of claim 2 , further comprising calculating a third confidence level for the classifying, and a fourth confidence level for a beamforming process.

5. The method of claim 4 , further comprising updating the acoustic transfer functions based on at least one of the third confidence level or the fourth confidence level.

6. The method of claim 1 , wherein the tracking comprises:

storing values for the number and locations of the one or more sound sources over time; and

detecting a change in at least one of the number or the locations.

7. The method of claim 1 , further comprising:

updating sound filters based in part on the updated acoustic transfer functions; and

presenting audio content based on the updated sound filters.

8. An audio system comprising:

a microphone array configured to detect sounds from one or more sound sources in a local area of the audio system; and

a controller configured to:

detect, via a microphone array of a wearable device, sounds from one or more sound sources in a local area of the wearable device;

estimate acoustic transfer functions associated with the sounds;

estimate a direction of arrival (DoA) of a sound source in the one or more sound sources;

calculate a first confidence level for the direction of arrival estimate;

track a movement of the sound source;

calculate a second confidence level for the movement of the sound source; and

update, in response to the movement of the sound source, the acoustic transfer functions based in part on the first confidence level and the second confidence level.

9. The audio system of claim 8 , wherein the controller is further configured to classify the sound source based on a classification library.

10. The audio system of claim 8 , wherein the controller is further configured to isolate a signal from the sound source from other sound sources in the local area of the wearable device.

11. The audio system of claim 9 , wherein the controller is further configured to calculate third confidence level for the classifying, and a fourth confidence level for a beamforming process.

12. The audio system of claim 11 , wherein the controller is further configured to update the acoustic transfer functions based on at least one of the third confidence level or the fourth confidence level.

13. The audio system of claim 8 , wherein the tracking of the movement comprises:

storing values for the number and locations of the one or more sound sources over time; and

detecting a change in at least one of the number or the locations.

14. The audio system of claim 8 , wherein the controller is further configured to:

update sound filters based in part on the updated acoustic transfer functions; and

present audio content based on the updated sound filters.

15. The audio system of claim 8 , wherein the controller is further configured to generate a notification of the movement of the sound source.

16. A non-transitory computer-readable storage medium comprising instructions executable by a processor, the instructions when executed causing the processor to perform actions comprising:

detecting, via a microphone array of a wearable device, sounds from one or more sound sources in a local area of the wearable device;

estimating acoustic transfer functions associated with the sounds;

estimating a direction of arrival (DoA) of a sound source in the one or more sound sources;

calculating a first confidence level for the direction of arrival estimate;

tracking a movement of the sound source;

calculating a second confidence level for the movement of the sound source; and

updating, in response to the movement of the sound source, the acoustic transfer functions based in part on the first confidence level and the second confidence level.

17. The non-transitory computer-readable storage medium of claim 16 , the actions further comprising classifying the sound source based on a classification library.

18. The non-transitory computer-readable storage medium of claim 17 , the actions further comprising calculating a third confidence level for the classifying, and a fourth confidence level for a beamforming process.

19. The non-transitory computer-readable storage medium of claim 17 , the actions further comprising:

updating sound filters based in part on the updated acoustic transfer functions; and

presenting audio content based on the updated sound filters.

20. The non-transitory computer-readable storage medium of claim 16 , the actions further comprising isolating a signal from the sound source from other sound sources in the local area of the wearable device.