Speech recognition using loosely coupled components

• US 9,666,190 B2
• Filed: 07/25/2016
• Issued: 05/30/2017
• Est. Priority Date: 06/13/2011
• Status: Active Grant

• Current Assignee: 3M Health Information Systems (3M Company)
• Original Assignee: MModal IP LLC (3M Company)
• Inventors: Koll, Detlef, Finke, Michael
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US15/218,492
• Publication Number:
  US 20160336011A1
• Time in Patent Office: 309 Days
• Field of Search: 704231, 704246, 704247, 704251, 704252
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/228 of application context

Abstract

An automatic speech recognition system includes an audio capture component, a speech recognition processing component, and a result processing component which are distributed among two or more logical devices and/or two or more physical devices. In particular, the audio capture component may be located on a different logical device and/or physical device from the result processing component. For example, the audio capture component may be on a computer connected to a microphone into which a user speaks, while the result processing component may be on a terminal server which receives speech recognition results from a speech recognition processing server.

Claims

1. A system comprising:

an audio capture component, the audio capture component comprising means for capturing a first audio signal representing first speech of a user to produce a first captured audio signal;

a speech recognition processing component comprising means for performing automatic speech recognition on the first captured audio signal to produce first speech recognition results;

a first result processing component, the first result processing component comprising first means for processing the first speech recognition results to produce first result output;

a second result processing component, the second result processing component comprising second means for processing the first speech recognition results to produce second result output;

a context sharing component comprising means for identifying a first one of the first and second result processing components as being associated with a first context of the user at a first time, the context sharing component further comprising;

means for receiving credentials from the user;

means for identifying, based on the credentials, a list of at least one result processing component authorized for use on behalf of the user at the first time;

means for determining that the at least one result processing component in the list is associated with the context of the user at the first time; and

means for identifying a location of the at least one result processing component associated with the context of the user at the first time; and

speech recognition result provision means for providing, via a method selected based on the identified location, the first speech recognition results to the identified first one of the first and second result processing components.

2. The system of claim 1, wherein:

the audio capture component further comprises means for capturing a second audio signal representing second speech of the user to produce a second captured audio signal;

the speech recognition processing component further comprises means for performing automatic speech recognition on the second captured audio signal to produce second speech recognition results;

the context sharing component further comprises means for identifying a second one of the first and second result processing components as being associated with a second context of the user at a second time, wherein the second one of the first and second result processing components differs from the first one of the first and second result processing components; and

wherein the speech recognition result provision means further comprises means for providing the second speech recognition results to the identified second one of the first and second result processing components.

3. The system of claim 1, wherein the credentials comprise a username and password of the user.

4. A computer-implemented method for use with a system:

wherein the system comprises;

an audio capture component;

a speech recognition processing component;

a first result processing component;

a second result processing component;

a context sharing component; and

speech recognition result provision means;

wherein the method comprises;

(A) using the audio capture component to capture a first audio signal representing first speech of a user to produce a first captured audio signal;

(B) using the speech recognition processing component to perform automatic speech recognition on the first captured audio signal to produce first speech recognition results;

(C) using the first result processing component to process the first speech recognition results to produce first result output;

(D) using second result processing component to process the first speech recognition results to produce second result output;

(E) using the context sharing component to identify a first one of the first and second result processing components as being associated with a first context of the user at a first time, wherein using the context sharing component to identify further comprises;

receiving credentials from the user;

identifying, based on the credentials, a list of at least one result processing component authorized for use on behalf of the user at the first time;

determining that the at least one result processing component in the list is associated with the context of the user at the first time; and

identifying a location of the at least one result processing component associated with the context of the user at the first time; and

(F) using the speech recognition result provision means to provide, via a method selected based on the identified location, the first speech recognition results to the identified first one of the first and second result processing components.

5. The method of claim 4, further comprising:

(G) using the audio capture component to capture a second audio signal representing second speech of the user to produce a second captured audio signal;

(H) using the speech recognition processing component to perform automatic speech recognition on the second captured audio signal to produce second speech recognition results;

(I) using the context sharing component to identify a second one of the first and second result processing components as being associated with a second context of the user at a second time, wherein the second one of the first and second result processing components differs from the first one of the first and second result processing components; and

(J) using the speech recognition result provision means to provide the second speech recognition results to the identified second one of the first and second result processing components.

6. The method of claim 4, wherein the credentials comprise a username and password of the user.