Synthesis and display of speech commands method and system

• US 9,495,965 B2
• Filed: 09/19/2014
• Issued: 11/15/2016
• Est. Priority Date: 09/20/2013
• Status: Active Grant

• Current Assignee: Cambium Assessment, Inc.
• Original Assignee: American Institutes For Research
• Inventors: Dvorak, Joseph
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US14/491,655
• Publication Number:
  US 20150088526A1
• Time in Patent Office: 788 Days
• Field of Search: 704/275, 704/270.1, 715/728
• US Class Current: 1/1
• CPC Class Codes: G10L 15/28 Constructional details of speech recognition systems
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A construction and display of speech commands system that allows a user to simply read what is on an application that involves visual elements with which the user interacts, and in doing so, gives the appropriate commands to the speech recognition system for the task at hand. The construction and display of speech commands system may include a speech recognition system, a grammar builder module, and a speech enablement module. The construction and display of speech commands system may automatically generate a speech enabled application from generated speech grammar.

Claims

1. A construction and display of speech commands system comprising:

a speech recognition system;

a centralized server;

a grammar builder module, wherein the grammar builder module parses content of an application to generate speech grammar; and

a speech enablement module, wherein the speech enablement module processes grammar rules to modify said content into generated speech commands, conforming to said grammar rules, and providing the generated speech commands to the speech recognition system;

wherein the construction and display of speech commands system is configured to generate a speech enabled application from said generated speech grammar; and

wherein the speech recognition system, centralized server, grammar builder module, speech enablement module are integrated with each other.

2. The construction and display of speech commands system of claim 1 wherein the application is a web page.

3. The construction and display of speech commands system of claim 1 wherein the generated speech grammar and speech enabled application is stored in a flat file.

4. The construction and display of speech commands system of claim 1 wherein the generated speech grammar and speech enabled application is stored in a repository.

5. The construction and display of speech commands system of claim 1 wherein the system comprises a speech recognition performance module, wherein said speech recognition performance module modifies the generated speech commands based on a speech recognition performance ratio.

6. A construction and display of speech commands system, comprising:

a speech recognition system;

a centralized server;

a grammar builder module, wherein the grammar builder module parses content of an application to generate speech grammar;

wherein the speech recognition system, centralized server, grammar builder module, speech enablement module are integrated with each other;

a speech enablement module, wherein the speech enablement module is configured to process grammar rules to modify said content into generated speech commands, conforming to said grammar rules, and providing the generated speech commands to the speech recognition system;

a speech recognition performance module, wherein said speech recognition performance module modifies the generated speech commands based on a speech recognition performance ratio, wherein the speech recognition performance ratio is based on a number of utterances correctly recognized to a total number of utterances; and

wherein the construction and display of speech commands system is configured to generate a speech enabled application from said generated speech grammar.

7. A construction and display of speech commands method comprising:

parsing content of an application to generate speech grammar via a grammar builder module;

processing grammar rules to modify said content into generated speech commands conforming to said grammar rules via a speech enablement module, wherein the speech enablement module provides the generated speech commands to a speech recognition engine; and

generating a speech enabled application from said generated speech grammar; and

commands.

8. The construction and display of speech commands method of claim 7 wherein the application is a web page.

9. The construction and display of speech commands method of claim 7 wherein the generated speech grammar and speech enabled application is stored in a flat file.

10. The construction and display of speech commands method of claim 7 wherein the generated speech grammar and speech enabled application is stored in a repository.

11. The construction and display of speech commands method of claim 7 comprising modifying the generated speech commands based on a speech recognition performance ratio.

12. The construction and display of speech commands method of claim 11 wherein the speech recognition performance ratio is based on a number of utterances correctly recognized to a total number of utterances.