Acoustic environment recognizer for optimal speech processing

Patent metadata

Field	Value
Publication number	US-9530408-B2
Application number	US-201414530066-A
Country	US
Kind code	B2
Filing date	Oct 31, 2014
Priority date	Oct 31, 2014
Publication date	Dec 27, 2016
Grant date	Dec 27, 2016

Abstract

A system for providing an acoustic environment recognizer for optimal speech processing is disclosed. In particular, the system may utilize metadata obtained from various acoustic environments to assist in suppressing ambient noise interfering with a desired audio signal. In order to do so, the system may receive an audio stream including an audio signal associated with a user and including ambient noise obtained from an acoustic environment of the user. The system may obtain first metadata associated with the ambient noise, and may determine if the first metadata corresponds to second metadata in a profile for the acoustic environment. If the first metadata corresponds to the second metadata, the system may select a processing scheme for suppressing the ambient noise from the audio stream, and process the audio stream using the processing scheme. Once the audio stream is processed, the system may provide the audio stream to a destination.

First claim

We claim:

1. A system, comprising:
a first memory that stores a first set of instructions;
a first hardware processor of an acoustic environment recognizer that executes the first set of instructions to perform a first set of operations, the first set of operations comprising:
receiving, at the first hardware processor of the acoustic environment recognizer, an audio stream including an audio signal associated with a user and including ambient noise obtained from an acoustic environment in which the user is located;
obtaining, from visual content captured by a camera of a device of the user and from orientation data obtained from a sensor of the device of the user, first metadata associated with the ambient noise in the acoustic environment, wherein the visual content is obtained from the camera by the first hardware processor of the acoustic environment recognizer, wherein the orientation data corresponds with an orientation of the device of the user;
determining if the first metadata associated with the ambient noise corresponds to second metadata in a profile for the acoustic environment;
selecting, by utilizing the first hardware processor and if the first metadata is determined to correspond to the second metadata, a processing scheme for suppressing the ambient noise from the audio stream, wherein the processing scheme is selected based on the profile, the visual content, and the orientation data;

a second memory that stores a second set of instructions; and
a second hardware processor of a speech signal enhancer that executes the second set of instructions to perform a second set of operations, the second set of operations comprising:
processing, at the second hardware processor of the speech signal enhancer, the audio stream using the processing scheme in order to suppress the ambient noise in the audio stream; and
providing, after processing the audio stream using the processing scheme, the audio stream to a destination.

2. The system of claim 1 , wherein the first set of operations further comprises selecting, if the first metadata is determined to not correspond to the second metadata, a different processing scheme for suppressing different ambient noise that has a correlation to the ambient noise obtained from the acoustic environment in which the user is located.

3. The system of claim 2 , wherein the second set of operations further comprises processing the audio stream using the different processing for suppressing different ambient noise that has the correlation to the ambient noise obtained from the acoustic environment in which the user is located.

4. The system of claim 1 , wherein the first set of operations further comprises obtaining third metadata associated with the ambient noise in the acoustic environment from a different sensor of the device of the user.

5. The system of claim 1 , wherein the first set of operations further comprises updating, if the first metadata is determined to correspond to the second metadata, the profile for the acoustic environment based on the first metadata.

6. The system of claim 1 , wherein the first set of operations further comprises generating, if the first metadata is determined to not correspond to the second metadata, a new profile for the acoustic environment.

7. The system of claim 1 , wherein the second set of operations further comprises utilizing a device profile associated with the device of the user to enhance a quality of the audio stream.

8. The system of claim 1 , wherein the second set of operations further comprises utilizing a user profile including a speech characteristic of the user to enhance a quality of the audio stream.

9. The system of claim 1 , wherein the second set of operations further comprises enhancing the audio stream based on a time at which the audio stream was received.

10. A method, comprising:
receiving, at a first hardware processor of an acoustic environment recognizer, an audio stream including an audio signal associated with a user and including ambient noise obtained from an acoustic environment in which the user is located;
obtaining, from visual content captured by a camera of a device of the user and from orientation data obtained from a sensor of the device of the user, first metadata associated with the ambient noise in the acoustic environment, wherein the visual content is obtained from the camera by the first hardware processor of the acoustic environment recognizer, wherein the orientation data corresponds with an orientation of the device of the user;
determining, by utilizing instructions from memory that are executed by the first hardware processor, if the first metadata associated with the ambient noise corresponds to second metadata in a profile for the acoustic environment;
selecting, by utilizing the first hardware processor and if the first metadata is determined to correspond to the second metadata, a processing scheme for suppressing the ambient noise from the audio stream, wherein the processing scheme is selected based on the profile, the visual content, and the orientation data;
processing, at a second hardware processor of a speech signal enhancer, the audio stream using the processing scheme in order to suppress the ambient noise in the audio stream; and
providing, after processing the audio stream using the processing scheme, the audio stream to a destination.

11. The method of claim 10 , further comprising selecting, if the first metadata is determined to not correspond to the second metadata, a different processing scheme for suppressing different ambient noise that has a correlation to the ambient noise obtained from the acoustic environment in which the user is located.

12. The method of claim 11 , further comprising processing the audio stream using the different processing for suppressing different ambient noise that has the correlation to the ambient noise obtained from the acoustic environment in which the user is located.

13. The method of claim 10 , further comprising obtaining third metadata associated with the ambient noise in the acoustic environment from a different sensor of the device of the user.

14. The method of claim 10 , further comprising updating, if the first metadata is determined to correspond to the second metadata, the profile for the acoustic environment based on the first metadata.

15. The method of claim 10 , further comprising generating, if the first metadata is determined to not correspond to the second metadata, a new profile for the acoustic environment.

16. The method of claim 10 , further comprising utilizing a device profile associated with the device of the user to enhance a quality of the audio stream.

17. The method of claim 10 , further comprising enhancing the audio stream based on a time at which the audio stream was received.

18. The method of claim 10 , further comprising utilizing a user profile including a speech characteristic of the user to enhance a quality of the audio stream.

19. The method of claim 10 , further comprising deleting an existing device profile for the device associated with the user when the user upgrades the device, and further comprising creating a new device profile for a new device associated with the user.

20. A computer-readable device comprising a first set of instructions, which when executed by a first hardware processor of an acoustic environment recognizer, cause the first hardware processor to perform a first set of operations comprising:
receiving, at the first hardware processor of the acoustic environmen

Assignees

• At & T Ip I Lp

Inventors

• Schroeter Horst J
• Bowen Donald J
• Dimitriadis Dimitrios B
• Ji Lusheng

Classifications

• G10L15/20 Primary

  Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence) · CPC title

• G10L21/0208

  Noise filtering · CPC title

• G10L21/0216

  characterised by the method used for estimating noise · CPC title

• G10L21/028 Primary

  using properties of sound source · CPC title

• G10L25/72

  for transmitting results of analysis · CPC title