Speech Recognition Using Loosely Coupled Components

Patent metadata

Field	Value
Publication number	US-2016336011-A1
Application number	US-201615218492-A
Country	US
Kind code	A1
Filing date	Jul 25, 2016
Priority date	Jun 13, 2011
Publication date	Nov 17, 2016
Grant date	—

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.

First claim

What is claimed is:

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

Assignees

• Mmodal Ip Llc

Inventors

• Koll Detlef
• Finke Michael

Classifications

• G10L2015/228

  of application context · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/30 Primary

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title