Creating a voice response grammar from a user grammar

• US 7,634,412 B2
• Filed: 12/11/2003
• Issued: 12/15/2009
• Est. Priority Date: 12/11/2003
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Watson, Thomas J., Schumacher, Daniel Mark, Burkhart, Michael John, Bodin, William Kress, Eisenhauer, Daniel G.
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): Rider; Justin W
• Application Number:
  US10/733,941
• Publication Number:
  US 20050131702A1
• Time in Patent Office: 2,196 Days
• Field of Search: None
• US Class Current: 704/275
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/487 Arrangements for providing information services, e.g. recorded voice services or time announcements
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/567 Multimedia conference systems

Abstract

Methods, systems, and products are disclosed for creating a voice response grammar in a voice response server that include identifying a user for a presentation, the user having a user grammar, the user grammar including one or more user grammar elements and storing a multiplicity of user grammar elements for the user in a voice response grammar on a voice response server. In typical embodiments, identifying a user for a presentation includes creating a data structure representing a presentation and listing in the data structure at least one user identification. In typical embodiments, each grammar element includes an identifier of a structural element, a key phrase for invoking a presentation action, and a presentation action identifier representing a presentation action.

Claims

1. A method for creating a voice response grammar in a voice response server, the method comprising:

i. identifying a user for a presentation, the user having a user grammar, the user grammar including one or more user grammar elements for a content type, each user grammar element including an identifier of a structural element, a key phrase for invoking a presentation action, and a presentation action identifier representing a presentation action;

ii. identifying presentation documents for the presentation, each presentation document having a content type, wherein the content type indicates a format of the presentation document;

iii. selecting user grammar elements according to the content type of the identified presentation documents; and

iv. storing a multiplicity of user grammar elements for the user in a voice response grammar on a voice response server, including storing the selected user grammar elements in the voice response grammar.

2. The method of claim 1 wherein identifying a user for a presentation comprises:

creating a data structure representing a presentation; and

listing in the data structure at least one user identification.

3. The method of claim 1 wherein the user grammar comprises a multiplicity of user grammar elements, the method further comprising:

identifying presentation documents for the presentation, the presentation documents including structured documents having structural element identifiers; and

selecting user grammar elements in dependence upon the structural element identifiers;

wherein storing a multiplicity of user grammar elements for the user in a voice response grammar on a voice response server includes storing the selected user grammar elements in the voice response grammar.

4. The method of claim 1 wherein the user grammar comprises a multiplicity of user grammar elements, the method further comprising:

identifying presentation documents for the presentation, each presentation document having a presentation grammar including presentation action identifiers; and

selecting user grammar elements in dependence upon the presentation action identifiers;

wherein storing a multiplicity of user grammar elements for the user in a voice response grammar on a voice response server includes storing the selected user grammar elements in the voice response grammar.

5. The method of claim 1 further comprising creating a presentation document, including:

creating, in dependence upon an original document, a structured document comprising one or more structural elements;

classifying a structural element of the structured document according to a presentation attribute; and

creating a presentation grammar for the structured document, wherein the presentation grammar for the structured document includes grammar elements each of which includes an identifier for at least one structural element of the structured document.

6. The method of claim 5 wherein classifying a structural element comprises:

identifying a presentation attribute for the structural element;

identifying a classification identifier in dependence upon the presentation attribute; and

inserting the classification identifier in association with the structural element in the structured document.

7. The method of claim 5 wherein creating a presentation grammar for the structured document comprises:

identifying the content type of the original document;

selecting, in dependence upon the content type, a full presentation grammar from among a multiplicity of full presentation grammars; and

filtering the full presentation grammar into a presentation grammar for the structured document in dependence upon the structural elements of the structured document.