SPEECH ENABLED MANAGEMENT SYSTEM

• US 20160055848A1
• Filed: 08/25/2014
• Published: 02/25/2016
• Est. Priority Date: 08/25/2014
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Meruva, Jayaprakash, Huseth, Steve, Chandra Acharya, Bhabesh, Kommoju, Sekhar, Reddy, Chandrakantha
• Granted Patent: US 9,786,276 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04N 23/63 by using electronic viewfinders
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A speech-enabled management system is described herein. One system includes a grammar building tool configured to create a set of grammar keys based on ontology analytics corresponding to data received from a digital video manager (DVM) server, a speech recognition engine configured to recognize a speech command from a set of grammar files, a command translator configured to translate the recognized speech command to an executable command, and a processor configured to execute the speech command based on a particular grammar key from the set of grammar keys.

Claims

1. A speech-enabled management system, comprising:

a grammar building tool configured to create a set of grammar keys based on ontology analytics corresponding to data received from a digital video manager (DVM) server;

a speech recognition engine configured to recognize a speech command from a set of grammar files;

a command translator configured to translate the recognized speech command to an executable command; and

a processor configured to execute the speech command based on a particular grammar key from the set of grammar keys.

2. The system of claim 1, further comprising a speech synthesizer configured to identify and select a pronunciation lexicon based on pronunciation phonemes associated with domain terms.

3. The system of claim 1, further comprising a control dialog manager configured to determine whether the speech command is applicable for a current context.

4. The system of claim 1, wherein the speech recognition engine is based on operator voice training profile or a speech pattern.

5. The system of claim 1, wherein the ontology analytics are based on ontological factors, including inferences and associations between two data elements.

6. The system of claim 1, wherein:

the set of grammar keys correspond to a particular project; and

the grammar building tool is configured to change the set of grammar keys based on a change to the particular project.

7. The system of claim 1, wherein the DVM server includes camera configuration data, location data, and system configuration data.

8. The system of claim 7, wherein the set of grammar keys is configured to:

correspond to a camera located within a particular area and control the camera in a sequential or mapping order; and

control a set of operations, wherein the set of operations include pan, tilt, zoom, start, stop, recording, clear, monitor, and tile features.

9. The system of claim 1, wherein the executed speech command is performed at a workstation that includes a surveillance monitor, video, console, or microphone.

10. A method for operating a speech-enabled management system, comprising:

creating a set of grammar keys from a plurality of grammar files;

identifying a speech command;

determining whether the speech command is applicable for a current context; and

upon determining the speech command is applicable for the current context;

translating a grammar key from the set of grammar keys based on the speech command; and

executing the speech command based on the translated grammar key.

11. The method of claim 10, wherein the method includes creating the set of grammar keys based on ontology analytics including a mapping table that associates a location to a particular camera.

12. The method of claim 11, wherein translating the grammar key includes mapping the speech command to the location and particular camera.

13. The method of claim 10, wherein the method includes identifying the speech command by deciphering the speech command from a plurality of pronunciation speech lexicons.

14. The method of claim 10, wherein executing the speech command includes commanding a particular camera, view, audit, recording, or operational task.

15. A speech-enabled management system, comprising:

a grammar building tool configured to create a set of grammar keys based on ontology analytics corresponding to a set of data received from a DVM server;

a speech recognition engine configured to recognize an applicable speech command within a current context from a set of grammar files;

a command translator configured to translate the applicable speech command to a recognized speech command; and

a processor configured to execute the speech command based on a particular grammar key from the set of grammar keys.

16. The system of claim 15, wherein the grammar building tool includes a plurality of grammar files associated with recognition grammar, features, and location.

17. The system of claim 15, wherein the speech synthesizer is configured to synthesize text to speech signals and transfer the speech signals to a speaker.

18. The system of claim 15, wherein the speech recognition engine is configured to identify the speech command based on phonology, morphology, syntax, semantics, and lexicon language aspects.

19. The system of claim 15, further comprising displaying camera views on surveillance monitors and automatically changing a number of camera tile views on the surveillance monitors based on a number of cameras.

20. The system of claim 15, wherein the ontology analytics includes a mapping table, wherein the camera mapping associates a location in key table with a camera or tile location in camera table.