System and method for customizing speech recognition input and output

• US 7,860,717 B2
• Filed: 09/27/2004
• Issued: 12/28/2010
• Est. Priority Date: 09/25/2003
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Dictaphone Corporation (Microsoft Corporation)
• Inventors: Urhbach, Amy J., Santisteban, Ana, Frankel, Alan, Cote, William F., Carrier, Jill
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): Rider; Justin W
• Application Number:
  US10/951,291
• Publication Number:
  US 20050114122A1
• Time in Patent Office: 2,283 Days
• Field of Search: 704/270, 704275-276
• US Class Current: 704/276
• CPC Class Codes: G06F 40/103 Formatting, i.e. changing of presentation of documents automatic justification G06F40/189; automatic line break hyphenation G06F40/191
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models

Abstract

A system and method may be disclosed for facilitating the site-specific customization of automated speech recognition systems by providing a customization client for site-specific individuals to update and modify language model input files and post processor input files. In customizing the input files, the customization client may provide a graphical user interface for facilitating the inclusion of words specific to a particular site. The customization client may also be configured to provide the user with a series of formatting rules for controlling the appearance and format of a document transcribed by an automated speech recognition system.

Claims

1. A method for customizing input data for a language model in a speech recognition system, the language model having a predetermined data format for receiving words and/or phrases to be added to the language model, the method comprising:

providing a graphical user interface (GUI) that allows a user to specify a plurality of words and/or phrases in a first format independent of the predetermined data format of the language model; and

automatically converting the specified plurality of words and/or phrases in the first format, via at least one computer system, to language model input data in a second format compatible with the predetermined data format of the language model.

2. The method according to claim 1, wherein providing the GUI comprises formatting the plurality of words and/or phrases into flat files.

3. The method according to claim 1, wherein the automatically converting the specified plurality of words and/or phrases comprises normalizing the specified plurality of words and/or phrases for use by the language model.

4. The method according to claim 1, wherein the automatically converting the specified plurality of words and/or phrases comprises filtering the specified plurality of words and/or phrases for use by the language model.

5. The method according to claim 1, wherein providing the GUI comprises displaying words and/or phrases for possible selection by the user via the GUI.

6. The method according to claim 5, wherein the displaying the words and/or phrases comprises normalizing the words and/or phrases for display to the user.

7. The method according to claim 5, wherein the displaying the words and/or phrases comprises filtering the words and/or phrases for display to the user.

8. The method according to claim 1, wherein providing the GUI comprises importing words and/or phrases for possible selection by the user via the GUI.

9. The method according to claim 1, wherein providing the GUI comprises providing buttons representing predetermined options for the user to select via the GUI.

10. The method according to claim 1, further comprising adding the specified plurality of words and/or phrases to the language model using the language model input data in the second format.

11. A method for customizing input data for a post processor in a speech recognition system, the post processor having a predetermined data format for receiving formatting rules to be used in formatting text documents, the method comprising:

providing a graphical user interface (GUI) that allows a user to specify formatting rules in a first format independent of the predetermined data format of the post processor; and

automatically converting the specified formatting rules in the first format, via at least one computer system, to post processor input data in a second format compatible with the predetermined data format of the post processor.

12. The method according to claim 11, wherein providing the GUI comprises providing buttons representing predetermined options for the user to select via the GUI.

13. The method according to claim 11, further comprising configuring the post processor to format text documents in accordance with the specified formatting rules using the post processor input data in the second format.

14. A system for customizing input data for a language model in a speech recognition system, the language model having a predetermined data format for receiving words and/or phrases to be added to the language model, the system comprising at least one computer system configured to:

provide a graphical user interface (GUI) that allows a user to specify a plurality of words and/or phrases in a first format independent of the predetermined data format of the language model; and

automatically convert the specified plurality of words and/or phrases in the first format to language model input data in a second format compatible with the predetermined data format of the language model.

15. At least one computer-readable storage medium encoded with a plurality of computer-executable instructions that, when executed, perform a method for customizing input data for a language model in a speech recognition system, the language model having a predetermined data format for receiving words and/or phrases to be added to the language model, the method comprising:

providing a graphical user interface (GUI) that allows a user to specify a plurality of words and/or phrases in a first format independent of the predetermined data format of the language model; and

automatically converting the specified plurality of words and/or phrases in the first format to language model input data in a second format compatible with the predetermined data format of the language model.

16. A system for customizing input data for a post processor in a speech recognition system, the post processor having a predetermined data format for receiving formatting rules to be used in formatting text documents, the system comprising at least one computer system configured to:

provide a graphical user interface (GUI) that allows a user to specify formatting rules in a first format independent of the predetermined data format of the post processor; and

automatically convert the specified formatting rules in the first format to post processor input data in a second format compatible with the predetermined data format of the post processor.

17. At least one computer-readable storage medium encoded with a plurality of computer-executable instructions that, when executed, perform a method for customizing input data for a post processor in a speech recognition system, the post processor having a predetermined data format for receiving formatting rules to be used in formatting text documents, the method comprising:

providing a graphical user interface (GUI) that allows a user to specify formatting rules in a first format independent of the predetermined data format of the post processor; and

automatically converting the specified formatting rules in the first format to post processor input data in a second format compatible with the predetermined data format of the post processor.