Bone conduction transducers for privacy

Patent metadata

Field	Value
Publication number	US-11501760-B2
Application number	US-202117525801-A
Country	US
Kind code	B2
Filing date	Nov 12, 2021
Priority date	Jun 21, 2019
Publication date	Nov 15, 2022
Grant date	Nov 15, 2022

Abstract

A method for routing audio content through an electronic device that is to be worn by a user. The method obtains a communication and determines whether the communication is private. In response to determining that the communication is private, the method drives a bone conduction transducer of the electronic device with an audio signal associated with the communication. In response to determining that the communication is not private, however, the method drives a speaker of the electronic device with the audio signal.

First claim

What is claimed is:

1. A method comprising:
obtaining image data captured by a camera of an electronic device that represents a scene within a field of view of the camera;
performing an object recognition algorithm upon the image data to identify an object within the scene;
obtaining an indication that output of an audio signal is desired;
in response to obtaining the indication, determining whether the audio signal is to be designated as private according to the object; and
driving a bone conduction transducer (BCT) of the electronic device with the audio signal when the audio signal is designated as private.

2. The method of claim 1 further comprising driving, at a first instance in time, a speaker of the electronic device with the audio signal,
wherein determining whether the audio signal is to be designated as private is at a second instance in time, after the first instance in time,
wherein driving the BCT with the audio signal comprises ceasing to drive the speaker with the audio signal.

3. The method of claim 1 , wherein driving the BCT with the audio signal is at a first instance in time, wherein the method further comprises
determining, at a second instance in time, after the first instance in time that the object is no longer within the scene according to the object recognition algorithm; and
in response to determining that the object is no longer within the scene,
ceasing to drive the BCT, and
beginning to drive a speaker of the electronic device with the audio signal.

4. The method of claim 1 , wherein the object comprises a person within the scene, wherein determining whether the audio signal is to be designated as private comprises determining that the person is within a threshold distance from the electronic device.

5. The method of claim 4 , wherein audio signal comprises audio content describing at least one of physical attributes and identification information of the person.

6. The method of claim 4 , wherein determining whether the audio signal is to be designated as private further comprises determining that the person in the scene is within the field of view of the camera for a threshold period of time.

7. The method of claim 1 , wherein the audio signal is a first audio signal, wherein the method further comprises
receiving a piece of sound program content;
extracting a first portion of the piece of sound program content as the first audio signal and a second portion of the piece of sound program content as a second audio signal; and
driving a speaker of the electronic device with the second audio signal while driving the BCT with the first audio signal.

8. The method of claim 7 , wherein the first audio signal includes speech and the second audio signal includes ambient sound content of the piece of sound program content.

9. A headset comprising:
a camera;
a bone conduction transducer (BCT);
a processor; and
memory having stored therein instructions which when executed by the processor cause the headset to:
obtain image data captured by the camera that represents a scene within a field of view of the camera;
perform an object recognition algorithm upon the image data to identify an object within the scene;
obtain an indication that output of an audio signal is desired;
in response to obtaining the indication, determine whether the audio signal is to be designated as private according to the object; and
drive the BCT with the audio signal when the audio signal is designated as private.

10. The headset of claim 9 further comprises a speaker, wherein the instructions further comprise instructions to drive, at a first instance in time, the speaker with the audio signal,
wherein the instructions to determine whether the audio signal is to be designated as private is at a second instance in time, after the first instance in time,
wherein the instructions to drive the BCT with the audio signal comprises instructions to cease driving the speaker with the audio signal.

11. The headset of claim 9 further comprises a speaker, wherein the instructions to drive the BCT with the audio signal is at a first instance in time, wherein the memory has further instructions to:
determine, at a second instance in time, after the first instance in time that the object is no longer within the scene according to the object recognition algorithm; and
in response to determining that the object is no longer within the scene,
cease to drive the BCT; and
begin to drive the speaker with the audio signal.

12. The headset of claim 9 , wherein the object comprises a person within the scene, wherein the instructions to determine whether the audio signal is to be designated as private comprises instructions to determine that the person is within a threshold distance from the electronic device.

13. The headset of claim 12 , wherein the audio signal comprises audio content describing at least one of physical attributes and identification information of the person.

14. The headset of claim 12 , wherein the instructions to determine whether the audio signal is to be designated as private further comprises instructions to determine that the person in the scene is within the field of view of the camera for a threshold period of time.

15. A non-transitory machine-readable medium having instructions which when executed by a processor of an electronic device obtain image data captured by a camera that represents a scene within a field of view of the camera;
perform an object recognition algorithm upon the image data to identify an object within the scene;
obtain an indication that output of an audio signal is desired;
in response to obtaining the indication, determine whether the audio signal is to be designated as private according to the object; and
drive a bone conduction transducer (BCT) of the electronic device with the audio signal when the audio signal is designated as private.

16. The non-transitory machine-readable medium of claim 15 further comprises instructions to drive, at a first instance in time, a speaker of the electronic device with the audio signal,
wherein the instructions to determine whether the audio signal is to be designated as private is at a second instance in time, after the first instance in time,
wherein the instructions to drive the BCT with the audio signal comprises instructions to cease driving the speaker with the audio signal.

17. The non-transitory machine-readable medium of claim 15 , wherein the instructions to drive the BCT with the audio signal is at a first instance in time, wherein the medium has further instructions to:
determine, at a second instance in time, after the first instance in time that the object is no longer within the scene according to the object recognition algorithm; and
in response to determining that the object is no longer within the scene,
cease to drive the BCT; and
begin to drive a speaker of the electronic device with the audio signal.

18. The non-transitory machine-readable medium of claim 15 , wherein the object comprises a person within the scene, wherein the instructions to determine whether the audio signal is to be designated as private comprises instructions to determine that the person is within a threshold distance from the electronic device.

19. The non-transitory machine-readable medium of claim 18 , wherein the audio signal comprises audio content describing at least one of physical attributes and identification information of the person.

20. The non-transitory machine-readable medium of claim 1

Assignees

• Apple Inc

Inventors

• Silfvast Robert D
• Evans Neal D
• Vitt Nikolas T
• Sheaffer Jonathan D

Classifications

• G10L2015/088

  Word spotting · CPC title

• G10L15/00

  Speech recognition (G10L17/00 takes precedence) · CPC title

• H04R2460/13

  Hearing devices using bone conduction transducers · CPC title

• H04R1/1091 Primary

  Details not provided for in groups H04R1/1008 - H04R1/1083 · CPC title

• G10L15/083 Primary

  Recognition networks (G10L15/142, G10L15/16 take precedence) · CPC title