Exploiting visual information for enhancing audio signals via source separation and beamforming

• US 10,402,651 B2
• Filed: 02/26/2018
• Issued: 09/03/2019
• Est. Priority Date: 06/11/2014
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Dimitriadis, Dimitrios, Bowen, Donald J., Ji, Lusheng, Schroeter, Horst J.
• Primary Examiner(s): Tsang, Fan S
• Assistant Examiner(s): Siegel, David
• Application Number:
  US15/905,442
• Publication Number:
  US 20180181812A1
• Time in Patent Office: 554 Days
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: G06V 20/35 Categorising the entire scene, e.g. birthday party or wedding scene
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: H04R 2430/20 Processing of the output signals of the acoustic transducers of an array for obtaining a desired directivity characteristic H04R2203/12 takes precedence
• CPC Class Codes: H04R 2460/07 Use of position data from wide-area or local-area positioning systems in hearing devices, e.g. program or information selection
• CPC Class Codes: H04R 5/04 Circuit arrangements, e.g. for selective connection of amplifier inputs/outputs to loudspeakers, for loudspeaker detection, or for adaptation of settings to personal preferences or hearing impairments combinations of amplifiers H03F3/68; stereophonic systems H04S

Abstract

A system for exploiting visual information for enhancing audio signals via source separation and beamforming is disclosed. The system may obtain visual content associated with an environment of a user, and may extract, from the visual content, metadata associated with the environment. The system may determine a location of the user based on the extracted metadata. Additionally, the system may load, based on the location, an audio profile corresponding to the location of the user. The system may also load a user profile of the user that includes audio data associated with the user. Furthermore, the system may cancel, based on the audio profile and user profile, noise from the environment of the user. Moreover, the system may include adjusting, based on the audio profile and user profile, an audio signal generated by the user so as to enhance the audio signal during a communications session of the user.

Claims

1. A system, comprising:

a memory that stores instructions;

a processor that executes the instructions to perform operations, the operations comprising;

extracting, from visual content, first metadata associated with an environment of a user, wherein the first metadata indicates information that identifies an interferer generating noise in the environment and information that identifies a location of the interferer;

determining a location of the user based on the first metadata;

cancelling, based on the first metadata, an audio profile loaded based on the location of the user, and a user profile comprising audio data associated with the user, the noise from the environment of the user; and

modifying, based on the audio profile and the user profile, an audio signal generated by the user so as to enhance the audio signal during a communications session of the user.

2. The system of claim 1, wherein the operations further comprise obtaining the visual content associated with the environment of the user.

3. The system of claim 1, wherein the operations further comprise extracting, from audio content obtained from the environment, second metadata associated with the environment.

4. The system of claim 3, wherein the operations further comprise determining the location of the user and the location of the interferer based on the second metadata.

5. The system of claim 1, wherein the operations further comprise cancelling the noise from the environment of the user by utilizing spatial filtering.

6. The system of claim 1, wherein the operations further comprise obtaining the audio profile and the user profile from a cloud-based application.

7. The system of claim 1, wherein the operations further comprise updating the audio profile and the user profile based on the visual content.

8. The system of claim 1, wherein the operations further comprise utilizing a beamformer to sample audio signals captured from the environment.

9. The system of claim 1, wherein the operations further comprise separating each source of a plurality of sources contributing to the noise from other sources of the plurality of sources.

10. The system of claim 1, wherein the operations further comprise separating each source of a plurality of sources contributing to the noise from the user.

11. The system of claim 1, wherein the operations further comprise utilizing the first metadata to increase a speed of a noise suppression algorithm utilized to cancel the noise.

12. The system of claim 1, wherein the operations further comprise transmitting a null in a direction of the interferer generating the noise in the environment.

13. A method, comprising:

extracting, from media content and by utilizing instructions from a memory that are executed by a processor, first metadata associated with an environment of a user, wherein the first metadata indicates information that identifies an interferer generating noise in the environment and information that identifies a location of the interferer;

determining a location of the user based on the first metadata;

cancelling, based on the first metadata, an audio profile loaded based on the location of the user, and a user profile comprising audio data associated with the user, the noise from the environment of the user; and

enhancing, based on the audio profile and the user profile, an audio signal generated by the user during a communications session of the user.

14. The method of claim 13, further comprising utilizing a microphone array to cancel the noise from the environment.

15. The method of claim 13, further comprising obtaining the media content associated with the environment of the user.

16. The method of claim 13, further comprising transmitting a null in a direction of the interferer generating the noise in the environment.

17. The method of claim 13, further comprising separating each source of a plurality of sources contributing to the noise from other sources of the plurality of sources.

18. The method of claim 13, further comprising utilizing the first metadata to increase an efficiency of a noise suppression algorithm utilized to cancel the noise.

19. The method of claim 13, further comprising updating the audio profile or the user profile based on the media content.

20. A non-transitory computer-readable device comprising instructions, which when executed by a processor, cause the processor to perform operations comprising:

extracting, from media content, first metadata associated with an environment of a user, wherein the first metadata indicates information that identifies a location of an interferer generating noise in the environment and information that identifies a type of the environment;

determining a location of the user based on the first metadata;

cancelling, based on the first metadata, an audio profile loaded based on the location of the user, and a user profile comprising audio data associated with the user, the noise from the environment of the user; and

adjusting, based on the audio profile and the user profile, an audio signal generated by the user so as to enhance the audio signal during a communications session of the user.