Methodology for voice enabling applications

• US 7,668,720 B2
• Filed: 02/22/2005
• Issued: 02/23/2010
• Est. Priority Date: 02/20/2004
• Status: Active Grant

• Current Assignee: Vangard Voice Systems, Inc.
• Original Assignee: Vangard Voice Systems, Inc.
• Inventors: Seifert, David H., Sherman, William F., Arthur, William J.
• Primary Examiner(s): Dorvil; Richemond
• Assistant Examiner(s): Saint Cyr; Leonard
• Application Number:
  US11/064,759
• Publication Number:
  US 20060167697A1
• Time in Patent Office: 1,827 Days
• Field of Search: 704/275
• US Class Current: 704/275
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 2015/228 of application context

Abstract

Methodology for voice-enabling an application minimizes code add-ons or code insertions. As an example, in applications used by a plurality of remote devices, the method may include dividing a master wordlist associated with the application into a plurality of wordlists respectively associated with the plurality of remote devices, and then converting the plurality of wordlists to a plurality of grammar lists respectively associated with the plurality of remote devices. Accordingly, the methodology voice enables applications with minimal alteration of the code of the applications.

Claims

1. A method for voice-enabling an application, comprising:

functionally associating the application with a speech object, the speech object comprises an association between an application element of the application and both (a) a word or language utterance and (b) a function call, by;

performing element inspection and object population by identifying the application element for voice enabling;

describing properties of the application element, and

placing the identification and description of the properties in the speech object;

configuring a recognizer system and an interpreter using a specific grammar definition language supporting semantic expressions that integrate the word or language utterance with a rule as to what action is to be taken upon recognition of the word or language utterance;

recognizing and processing the word utterance or language utterance by the recognizer system using the specific grammar definition language; and

mapping the word or language utterance by the interpreter using the specific grammar definition language into the function call that controls the application element in the application.

2. The method of claim 1 wherein the function call is communicated as data or action as specified by the application element.

3. The method of claim 1 wherein the grammar definition language associates words or language utterances with function call.