Acoustic environment recognizer for optimal speech processing

• US 9,911,430 B2
• Filed: 11/28/2016
• Issued: 03/06/2018
• Est. Priority Date: 10/31/2014
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group), Kia Corp.
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Schroeter, Horst J., Bowen, Donald J., Dimitriadis, Dimitrios B., Ji, Lusheng
• Primary Examiner(s): JACKSON, JAKIEDA R
• Application Number:
  US15/362,372
• Publication Number:
  US 20170076736A1
• Time in Patent Office: 463 Days
• Field of Search: 704233, 704226
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 21/0216 characterised by the method used for estimating noise
• CPC Class Codes: G10L 21/028 using properties of sound source
• CPC Class Codes: G10L 25/72 for transmitting results of analysis

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.

Claims

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;

obtaining, from visual content captured by a camera of a device of a user, first metadata associated with ambient noise occurring in an acoustic environment in which the user is located;

determining if the first metadata associated with the ambient noise corresponds to second metadata in a profile for the acoustic environment;

selecting, based on the first metadata and the visual content, and if the first metadata associated with the ambient noise corresponds to the second metadata in the profile for the acoustic environment, a first processing scheme, wherein the first processing scheme suppresses the ambient noise from an audio stream including an audio signal associated with the user;

selecting, if the first metadata associated with the ambient noise does not correspond to the second metadata in the profile for the acoustic environment, a second processing scheme, wherein the second processing scheme suppresses different ambient noise that has a correlation to the ambient noise occurring in the acoustic environment;

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 the audio stream using the first processing scheme in order to suppress the ambient noise in the audio stream interfering with the audio signal associated with the user, thereby enhancing the audio stream; and

providing, after processing the audio stream using the first processing scheme, the audio stream to a destination.

2. The system of claim 1, wherein the first set of operations further comprises receiving, at the first hardware processor of the acoustic environment recognizer, the audio stream including the audio signal associated with the user.

3. The system of claim 1, wherein the first set of operations further comprises obtaining orientation data from a sensor of the device of the user.

4. The system of claim 3, wherein the first set of operations further comprises selecting the first processing scheme based on the orientation data.

5. The system of claim 1, wherein the first set of operations further comprises obtaining, from acoustic data obtained from an acoustic sensor of the device, third metadata associated with the ambient noise.

6. The system of claim 1, wherein the first set of operations further comprises selecting the first processing scheme based on a device type of the device.

7. The system of claim 1, wherein the first set of operations further comprises selecting the first processing scheme based on a location corresponding to the acoustic environment.

8. The system of claim 1, wherein the first set of operations further comprises identifying a type of the acoustic environment based on the first metadata.

9. The system of claim 8, wherein the first set of operations further comprise selecting the first processing scheme based on the type of the acoustic environment.

10. The system of claim 1, wherein the second set of operations further comprise enhancing the audio stream by utilizing a device profile associated with the device of the user.

11. The system of claim 1, wherein the second set of operations further comprise enhancing the audio stream by utilizing a user profile associated with the user.

12. The system of claim 1, wherein the first set of operations further comprise determining a voice characteristic of the user.

13. A method, comprising:

extracting, from visual content captured by a camera of a device of a user, first metadata associated with ambient noise occurring in an acoustic environment in which the user is located, wherein the extracting is performed by utilizing instructions from a first memory that are executed by a first hardware processor of an acoustic environment recognizer;

determining if the first metadata associated with the ambient noise corresponds to second metadata in a profile for the acoustic environment;

selecting, based on the first metadata and the visual content and if the first metadata associated with the ambient noise corresponds to the second metadata in the profile for the acoustic environment, a first processing scheme, wherein the first processing scheme suppresses the ambient noise from an audio stream including an audio signal associated with the user;

selecting, if the first metadata associated with the ambient noise does not correspond to the second metadata in the profile for the acoustic environment, a second processing scheme, wherein the second processing scheme suppresses different ambient noise that has a correlation to the ambient noise occurring in the acoustic environment;

processing, by utilizing instructions from a second memory that are executed by a second hardware processor of a speech signal enhancer, the audio stream using the first processing scheme in order to suppress the ambient noise in the audio stream interfering with the audio signal associated with the user, thereby enhancing the audio stream; and

transmitting, after processing the audio stream using the first processing scheme, the audio stream to a destination.

14. The method of claim 13, further comprising receiving, at the first hardware processor of the acoustic environment recognizer, the audio stream including the audio signal associated with the user.

15. The method of claim 13, further comprising obtaining orientation data from a sensor of the device of the user.

16. The method of claim 13, further comprising generating a new profile for the acoustic environment.

17. The method of claim 13, further comprising enhancing the audio stream based on a time at which the audio stream is received.

18. The method of claim 13, further comprising identifying a type of the acoustic environment based on the first metadata.

19. The method of claim 18, further comprising selecting the first processing scheme based on the type of the acoustic environment.

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:

obtaining, from visual content captured by a camera of a device of a user, first metadata associated with ambient noise occurring in an acoustic environment in which the user is located;

determining if the first metadata associated with the ambient noise corresponds to second metadata in a profile for the acoustic environment;

selecting, based on the first metadata and the visual content and if the first metadata associated with the ambient noise corresponds to the second metadata in the profile for the acoustic environment, a first processing scheme, wherein the first processing scheme suppresses the ambient noise from an audio stream including an audio signal associated with the user;

selecting, if the first metadata associated with the ambient noise does not correspond to the second metadata in the profile for the acoustic environment, a second processing scheme, wherein the second processing scheme suppresses different ambient noise that has a correlation to the ambient noise occurring in the acoustic environment;

wherein the computer-readable device comprises a second set of instructions, which when executed by a second hardware processor of a speech signal enhancer, cause the second hardware processor to perform a second set of operations comprising;

processing the audio stream using the processing scheme in order to suppress the ambient noise in the audio stream interfering with the audio signal associated with the user, thereby enhancing the audio stream; and

transmitting, after processing the audio stream using the processing scheme, the audio stream to a destination.