Methods and systems for integration of speech into systems

• US 9,548,049 B2
• Filed: 02/19/2014
• Issued: 01/17/2017
• Est. Priority Date: 02/19/2014
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Sivaratri, Mahesh, Ambooken, Minni, McCullough, Sue, Bibby, David
• Primary Examiner(s): Yang, Qian
• Application Number:
  US14/184,327
• Publication Number:
  US 20150235640A1
• Time in Patent Office: 1,063 Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 21/10 Transforming into visible information

Abstract

A method of managing speech data in a system is provided. The method includes receiving speech data that is generated by a speech recognition module; searching data structures of a definition file for a speech tag based on the speech data, wherein the data structures define features of a display screen; and determining an action associated with the speech tag; and at least one of communicating data to an application of the system and generating display data based on the action.

Claims

1. A method of managing speech data in a system, comprising:

maintaining a definition datastore that stores in a tree structure a plurality of data structures that define features of a displayed interface, each data structure including a speech tag that comprises a string of characters that is associated with a name, a label, or a function of the feature;

receiving speech data that includes translated text that has been generated by a speech recognition module;

hierarchically searching, by a processor, the data structures of the tree structure for a speech tag that matches the text of the speech data, wherein the hierarchical searching comprises evaluating a state of the features associated with the data structures for visibility;

determining an action associated with the speech tag; and

at least one of communicating data to an application of the system and generating display data based on the action.

2. The method of claim 1, wherein the state is at least one of visible and invisible.

3. The method of claim 1, further comprising tracking the states of the features that are being displayed, and wherein the searching is based on the tracked states of the features.

4. The method of claim 1, updating a vocabulary of the speech recognition module based on the speech tag.

5. The method of claim 4, performing speech recognition techniques on a speech utterance based on the updated vocabulary.

6. The method of claim 1, wherein the generating the display data comprises generating data that is to be displayed in the display screen.

7. The method of claim 1, wherein the generating the display data comprises generating display data to display a new display screen.

8. The method of claim 1, wherein the generating the display data comprises generating display data to alter an appearance of a feature of the display screen.

9. The method of claim 1, wherein the feature of the display screen is a hidden feature.

10. The method of claim 1, wherein the feature of the display screen is a displayed feature.

11. A system for managing speech data in a computing system of an aircraft, comprising:

an information datastore that stores a definition file that is associated with an aircraft related application, wherein the definition file includes a tree structure including a plurality of data structures that define features of a displayed interface associated with the aircraft related application, each data structure including a speech tag that comprises a string of characters that is associated with a name, a label, or function of the feature; and

a computer module that receives speech data, that hierarchically searches, by a processor, the data structures of the tree structure for a speech tag that matches the text of the speech data, wherein the hierarchical search comprises evaluating a state of the features associated with the data structures for visibility, and that communicates data to the aircraft related application or generates display data based on an action associated with the speech tag.

12. The system of claim 11, wherein the state is a display state of visible or invisible.

13. The system of claim 11, wherein the computer module updates a vocabulary of a speech recognition module based on the state of features that are being displayed, and generates the speech data based on the vocabulary.

14. The system of claim 11, wherein the display data includes at least one of data to be displayed in the display screen, data to alter an appearance of a feature of the display screen, and data to display a new display screen.