Method and interface for correcting speech recognition errors for character languages

• US 6,260,015 B1
• Filed: 09/03/1998
• Issued: 07/10/2001
• Est. Priority Date: 09/03/1998
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Gong, Oing, Lewis, James R., Wang, Huifang, VanBuskirk, Ronald
• Primary Examiner(s): Tsang, Fan
• Assistant Examiner(s): Opsasnick, Michael N.
• Application Number:
  US09/146,177
• Time in Patent Office: 1,041 Days
• Field of Search: 382/181, 382/182, 382/185, 382/187, 382/229, 704/235, 704/257, 704/276
• US Class Current: 704/257
• CPC Class Codes: G06V 10/987 with the intervention of an operator
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method for correcting errors of a speech recognition application in natural speech recognition of words or phrases represented by characters can include the steps of selecting a character corresponding to an incorrectly recognized spoken word or phrase and observing a list of alternative characters. The method also can include replacing the incorrect character with one of the alternative characters, if the alternative characters correctly represent the incorrectly recognized word or phrase. If none of the alternative characters in the list correctly represents the spoken word or phrase, the step of drawing some features of a character correctly representing the incorrectly recognized word or phrase by moving a cursor can be included. Also included in the method can be the step of updating the list of alternative characters responsive to the drawing step; and, repeating the replacing, drawing and updating steps until a character correctly representing the word or phrase is selected from the updated list. A graphical user interface can respond to keyboard, mouse and voice commands.

Claims

1. A method for correcting errors of a speech recognition application in natural speech recognition of words or phrases represented by characters, comprising the steps of:

selecting a character corresponding to an incorrectly recognized spoken word or phrase in a transcript of dictated text;

observing a list of alternative characters;

replacing said incorrect character in said transcript with one of said alternative characters, if said one of said alternative characters correctly represents said incorrectly recognized word or phrase; and

,

drawing at least some features of a character correctly representing said incorrectly recognized word or phrase in said transcript by moving a cursor, if none of said alternative characters in said list correctly represents said spoken word or phrase.

2. The method of claim 1, further comprising the step of updating said list of alternative characters responsive to said drawing step.

3. The method of claim 1, further comprising the steps of:

filtering a comprehensive list of said characters based on said drawing step;

regenerating said list of alternative characters based on said filtering step; and

,

repeating said observing and replacing steps.

4. The method of claim 3, further comprising the steps of:

repeating said drawing step if none of said alternative characters in said regenerated list correctly represents said spoken word or phrase; and

,

repeating said filtering, regenerating, observing and replacing steps.

5. The method of claim 1, wherein said drawing step comprises the steps of:

selecting at least one predrawn character feature from a list of said features; and

,

pasting said at least one selected feature into at least one of a plurality of predefined zones by which said characters are defined.

6. The method of claim 5, further comprising the step of updating said list of alternative characters responsive to said selecting and pasting steps.

7. The method of claim 5, further comprising the steps of:

filtering a comprehensive list of said characters based on said selecting and pasting steps;

regenerating said list of alternative characters based on said filtering step; and

,

repeating said observing and replacing steps.

8. The method of claim 7, further comprising the steps of:

repeating said selecting and pasting steps if none of said alternative characters in said regenerated list correctly represents said spoken word or phrase; and

,

repeating said filtering, regenerating, observing and replacing steps.

9. The method of claim 1, comprising the steps of:

displaying said list in a first part of a graphical user interface (GUI) of said speech recognition application; and

,

drawing said at least some features in a second part of said GUI.

10. The method of claim 9, further comprising the step of changing said cursor in appearance as said cursor is moved between said first and second parts of said GUI.

11. The method of claim 9, further comprising the step of automatically initiating said updating step when said cursor is moved out of said second part of said GUI.

12. The method of claim 1, wherein at least one of said steps of selecting, replacing, and drawing is initiated by a voice command.

13. A method for correcting errors of a speech recognition application in natural speech recognition of words or phrases represented by characters, comprising the steps of:

selecting a character corresponding to an incorrectly recognized spoken word or phrase in a transcript of dictated text;

observing a list of alternative characters;

replacing said incorrect character in said transcript with one of said alternative characters, if said one of said alternative characters correctly represents said incorrectly recognized word or phrase;

drawing at least some features of a character correctly representing said incorrectly recognized word or phrase in said transcript by moving a cursor, if none of said alternative characters in said list correctly represents said spoken word or phrase;

updating said list of alternative characters responsive to said drawing step; and

,

repeating said replacing, drawing and updating steps until a character correctly representing said word or phrase is selected from said updated list.

14. The method of claim 13, wherein said updating step comprises the steps of:

filtering a comprehensive list of said characters based on said drawing step; and

,

regenerating said list of alternative characters based on said filtering step.

15. The method of claim 14, wherein said drawing step comprises the steps of:

selecting at least one predrawn character feature from a list of said features; and

,

pasting said at least one selected feature into at least one of a plurality of predefined zones by which said characters are defined.

16. The method of claim 13, wherein said drawing step comprises the steps of:

selecting at least one predrawn character feature from a list of said features; and

,

pasting said at least one selected feature into at least one of a plurality of predefined zones by which said characters are defined.

17. The method of claim 13, comprising the steps of:

displaying said list in a first part of a graphical user interface (GUI) of said speech recognition application;

selecting said at least one predrawn character from a second part of said GUI; and

,

pasting said at least one feature into a third part of said GUI.

18. The method of claim 17, further comprising the step of changing said cursor in appearance at least within said third part of said GUI.

19. The method of claim 17, further comprising the step of automatically initiating said updating step when said cursor is moved out of said third part of said GUI.

20. The method of claim 13, wherein at least one of said steps of selecting, replacing, drawing, and updating is initiated by a voice command.

21. A graphical user interface (GUI) embodied in a programmed routine set of instructions for correcting errors of a speech recognition application in natural speech recognition of words or phrases represented by characters, said GUI comprising:

a first section for displaying a list of alternative characters for replacing incorrect characters in a transcript of dictated text;

a second section for drawing at least some features of a character correctly representing said incorrectly recognized word or phrase in said transcript by moving a cursor; and

,

means for providing a cursor with different appearances in said first and second sections respectively; and

,

means for initiating regeneration and redisplay of said list responsive to information drawn in said second section.

22. The GUI of claim 21, wherein said initiating means comprises an activatable icon displayed on said GUI.

23. The GUI of claim 21, wherein said initiating means is responsive to movement of said cursor out of said second section.

24. The GUI of claim 21, comprising a third section for displaying a list of character features which can be selected and pasted into said second section.

25. The GUI of claim 24, wherein said second section is divided into a plurality of zones into which said selected character features can be pasted.

26. The GUI of claim 25, wherein said initiating means comprises an activatable icon displayed on said GUI.

27. The GUI of claim 25, wherein said initiating means is responsive to movement of said cursor out of said second section.

28. The GUI of claim 21, responsive to voice commands, keyboard commands, mouse commands, pen commands, or pad commands.