Acoustic environment recognizer for optimal speech processing

Patent metadata

Field	Value
Publication number	US-2018197558-A1
Application number	US-201815912230-A
Country	US
Kind code	A1
Filing date	Mar 5, 2018
Priority date	Oct 31, 2014
Publication date	Jul 12, 2018
Grant date	—

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:
selecting, if first metadata associated with ambient noise occurring in an acoustic environment corresponds to second metadata in a 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 a 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 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, if the first processing scheme is selected, the audio stream using the first processing scheme in order to suppress the ambient noise in the audio stream interfering with the audio signal, thereby enhancing the audio stream; and
processing, if the second processing scheme is selected, the audio stream using the second processing scheme in order to suppress the different ambient noise.

2 . The system of claim 1 , wherein the first set of operations further comprise obtaining, from visual content captured by a camera of a device of the user, the first metadata associated with the ambient noise.

3 . The system of claim 1 , wherein the second set of operations further comprise providing, after processing the audio stream, the audio stream to a destination.

4 . The system of claim 1 , wherein the first set of operations further comprise determining if the first metadata associated with the ambient noise occurring in the acoustic environment corresponds to the second metadata in the profile for the acoustic environment.

5 . The system of claim 1 , wherein the first set of operations further comprise estimating, if the first metadata associated with the ambient noise occurring in the acoustic environment does not correspond to the second metadata in the profile for the acoustic environment, what the acoustic environment is based on the first metadata.

6 . The system of claim 1 , wherein the first set of operations further comprise selecting the first processing scheme based on a location of the acoustic environment.

7 . The system of claim 1 , wherein the first set of operations further comprise selecting the first processing scheme based on a type of device providing the audio stream.

8 . The system of claim 1 , wherein the first set of operations further comprise obtaining, from sensor data, third metadata for refining acoustic parameters utilized in processing the audio stream to suppress the ambient noise in the audio stream.

9 . The system of claim 1 , wherein the second set of operations further comprise providing the audio stream enhanced by the processing to a speech recognition system.

10 . The system of claim 1 , wherein the first set of operations further comprise selecting the first processing scheme based on a device profile of a device providing the audio stream.

11 . The system of claim 1 , wherein the second set of operations further comprise utilizing a noise suppression algorithm, an echo-cancellation algorithm, a speech enhancement algorithm, or a combination thereof, to process the audio stream and to suppress the ambient noise.

12 . The system of claim 1 , wherein first set of operations further comprise updating the profile for the acoustic environment based on the first metadata.

13 . The system of claim 1 , wherein the first set of operations further comprise generating a new profile for the acoustic environment if the first metadata does not correspond to the second metadata.

14 . A method, comprising:
selecting, if first metadata associated with ambient noise occurring in an acoustic environment corresponds to second metadata in a 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 a user, wherein the selecting is performed by utilizing instructions from a first memory that are executed by a first hardware processor of an acoustic environment recognizer; 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 occurring in the acoustic environment; processing, if the first processing scheme is selected and 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, thereby enhancing the audio stream; and processing, if the second processing scheme is selected and by utilizing the instructions from the second memory that are executed by the second hardware processor of the speech signal enhancer, the audio stream using the second processing scheme in order to suppress the different ambient noise.

15 . The method of claim 14 , further comprising providing, after processing the audio stream, the audio stream to a destination.

16 . The method of claim 14 , further comprising updating the profile for the acoustic environment based on the first metadata.

17 . The method of claim 14 , further comprising obtaining, from sensor data, third metadata for refining acoustic parameters utilized in processing the audio stream to suppress the ambient noise in the audio stream.

18 . The method of claim 14 , 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 14 , further comprising utilizing a noise suppression algorithm, an echo-cancellation algorithm, a speech enhancement algorithm, or a combination thereof, to process the audio stream and to suppress the ambient noise.

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:
selecting, if first metadata associated with ambient noise occurring in an acoustic environment corresponds to second metadata in a 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 a 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 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 s

Assignees

• At & T Ip I Lp

Inventors

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

Classifications

• G10L21/0208

  Noise filtering · CPC title

• G10L21/028 Primary

  using properties of sound source · CPC title

• G10L21/0216

  characterised by the method used for estimating noise · CPC title

• G10L15/20

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

• G10L25/72

  for transmitting results of analysis · CPC title