Speech recognition system and method for employing the same

• US 7,831,429 B2
• Filed: 02/16/2007
• Issued: 11/09/2010
• Est. Priority Date: 08/19/1996
• Status: Expired due to Fees

• Current Assignee: Symbol Technologies, LLC (Zebra Technologies Corporation)
• Original Assignee: Symbol Technologies, Inc. (Zebra Technologies Corporation)
• Inventors: O'Hagan, Timothy P.
• Primary Examiner(s): Dorvil; Richemond
• Assistant Examiner(s): GODBOLD, DOUGLAS
• Application Number:
  US11/675,899
• Publication Number:
  US 20070150283A1
• Time in Patent Office: 1,362 Days
• Field of Search: 704/231, 704/270
• US Class Current: 704/270
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A speech recognition system that includes a host computer which is operative to communicate at least one graphical user interface (GUI) display file to a mobile terminal of the system. The mobile terminal includes a microphone for receiving speech input; wherein the at least one GUI display file is operative to be associated with at least one of a dictionary file and syntax file to facilitate speech recognition in connection with the at least one GUI display file.

Claims

1. A speech recognition system, comprising:

a host computer operative to communicate at least one graphical user interface (GUI) display file to a mobile terminal, wherein the GUI files have attached thereto a dictionary file having phonemes and syntax file having allowable patterns of words being content specific to the graphical user interface (GUI) display file and associated with a particular context state; and

the mobile terminal that displays one or more GUI pages associated with the received GUI files and receives speech input to assign a correct meaning to received input speech by

determining a current context state of the received input speech,

assigning one meaning to received input speech by utilizing the dictionary file and syntax file when the current context state is determined to be a first context state, and

assigning a different meaning to the same received input speech by utilizing the dictionary file and syntax file when the current context state is determined to be a second context.

2. The system of claim 1, the host computer transmits visual information to/from the mobile terminal via employment of one or more web pages using GUI files.

3. The system of claim 2, the GUI files are further associated with an HTML file.

4. The system of claim 1, wherein at least one of the dictionary file or the syntax file are stored in a memory of the host computer.

5. The system of claim 1, wherein at least one of the dictionary file or the syntax file are stored in a memory of the mobile terminal to facilitate recognition of speech input at the mobile terminal.

6. A mobile terminal having speech recognition capabilities, comprising:

an antenna for receiving one or more graphical user interface (GUI) files from a host computer, wherein the GUI files have attached thereto a dictionary file having phonemes and syntax file having allowable patterns of words being content specific to the graphical display file and associated with a particular context state;

a processor;

a memory to store the received one or more graphical user interface (GUI) files;

a display operatively coupled to the processor, the display adapted to display at least one GUI based on the received one or more graphical user interface (GUI) files;

a microphone for receiving speech input from a user; and

a speech recognition system for determining a current context state of interactive communication with the user and assigning a correct meaning to received input speech by

assigning one meaning to received input speech by utilizing the dictionary file and syntax file when the current context state is determined to be a first context state, and

assigning a different meaning to the same received speech by utilizing the dictionary file and syntax file when the current context state is determined to be a second context state.

7. The mobile terminal of claim 6, the speech recognition system further comprises an acoustic processing system that receives inputs from the microphone and converts a spoken utterance to a digital signal.

8. The mobile terminal of claim 6, further comprises an operator input device in the form of a virtual keypad that is part of the web page being displayed.

9. The mobile terminal of claim 6, further including a bar code reader to facilitate input of data.

10. A method for facilitating speech recognition associated with a graphical user interface (GUI), comprising the steps of

transmitting at least one graphical user interface (GUI) display file from a remote host computer to a mobile terminal, wherein the GUI files have attached thereto a dictionary file having phonemes and syntax file having allowable patterns of words being content specific to the graphical display file and associated with a particular context state;

receiving input speech commands at the mobile terminal wherein the commands are associated with at least one GUI associated with the received GUI files;

determining a current context state of interactive communications with the user; and

utilizing a speech recognition system to assign a correct meaning to received speech command by

assigning one meaning to received input speech command by utilizing the dictionary file and syntax file when the current context state is determined to be a first context state, and

assigning a different meaning to the same received input speech command by utilizing the dictionary file and syntax file when the current context state is determined to be a second context state.

11. The method of claim 10, the assigned meaning is transmitted to the remote host computer.

12. The method of claim 10, determining a current context state further comprises loading a new syntax file into the speech recognition system each time there is a change in the context state.

13. The method of claim 10, storing the at least one of a dictionary file or syntax file within the mobile terminal to facilitate speech recognition at the mobile terminal.

14. The method of claim 10, associating the at least one of a dictionary or syntax file with the displayed GUI further comprises limiting at least one of the dictionary or syntax files to a permutation of commands and data which could validly be input in connection with the displayed GUI.

15. The method of claim 10, further comprising transmitting the GUI file comprising a HTML file to display the GUI, and at least one of a dictionary file or a syntax file to the mobile terminal by a remote computer.

16. The method of claim 10, the input speech commands facilitate user identification.