Marking and deferring correction of misrecognition errors

• US 6,195,637 B1
• Filed: 03/25/1998
• Issued: 02/27/2001
• Est. Priority Date: 03/25/1998
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Ortega, Kerry A., Ballard, Barbara E.
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US09/048,504
• Time in Patent Office: 1,070 Days
• Field of Search: 704/235, 704/250, 704/205, 704/256
• US Class Current: 704/235
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method for correcting misrecognition errors comprises the steps of: dictating to a speech application; marking misrecognized words during the dictating step; and, after the dictating and marking steps, displaying and correcting the marked misrecognized words, whereby the correcting of the misrecognized words is deferred until after the dictating step is concluded and the dictating step is not significantly interrupted. The displaying and correcting step can be implemented by invoking a correction tool of the speech application, whereby the correcting of the misrecognized words trains the speech application.

Claims

1. A method for correcting misrecognition errors, comprising the steps of:

accepting speech dictation in a speech dictation session;

accepting a user command to mark misrecognized words in said speech dictation during said speech dictation session;

responsive to said user command to mark said misrecognized words, marking said misrecognized words during said speech dictation session, but deferring correction of said marked misrecognized words until after said speech dictation session;

concluding said speech dictation session; and

, displaying and correcting said marked misrecognized words subsequent to said speech dictation session,

whereby said correcting of said misrecognized words is deferred until after said speech dictation session is concluded and said speech dictation session is not significantly interrupted.

2. The method of claim 1, wherein said displaying and correcting step is implemented by invoking a correction tool of said speech application, whereby said correcting of said misrecognized words trains said speech application.

3. The method of claim 1, wherein said user command to mark misrecognized words in said speech dictation during said speech dictation session is implemented by activating a pointing tool.

4. The method of claim 3, wherein said user command to mark misrecognized words in said speech dictation during said speech dictation session is implemented by uttering voice commands.

5. The method of claim 1, wherein said user command to mark misrecognized words in said speech dictation during said speech dictation session is implemented by uttering voice commands.

6. The method of claim 1, wherein correcting said words is implemented by activating a pointing tool.

7. The method of claim 1, wherein correcting said words is implemented by uttering voice commands.

8. The method of claim 1, wherein said displaying and correcting step comprises the step of:

sequentially displaying each sentence with a marked word; and

,

displaying a list of user selectable words to substitute for said marked word.

9. The method of claim 8, wherein said displaying and correcting step further comprises the step of enabling users to enter a correction of said marked word by typing a word not on said list.

10. The method of claim 8, wherein said displaying and correcting step further comprises the step of enabling users to enter a correction of said marked word by uttering a word not on said list.

11. The method of claim 1, wherein said displaying and correcting step further comprises the step of enabling said user to select format corrections for said marked word in said sentence and for user selected text in said sentence.

12. The method of claim 8, wherein said displaying and correcting step further comprises the step of enabling said user to select format corrections for said marked word in said sentence and for user selected text in said sentence.

13. The method of claim 12, further comprising the step of generating a graphical user interface to implement said displaying and correcting step.

14. The method of claim 12, further comprising the step of generating respective graphical user interfaces for correcting text errors and format errors.

15. The method of claim 1, further wherein said displaying and correcting step is implemented by generating respective graphical user interfaces for correcting text errors and format errors.

16. A method for correcting misrecognition errors, comprising the steps of:

accepting speech dictation in a speech dictation session;

accepting a user command to mark misrecognized words in said speech dictation during said speech dictation session;

responsive to said user command to mark said misrecognized words, marking said misrecognized words during said speech dictation session, but deferring correction of said marked misrecognized words until after said speech dictation session;

after said speech dictation session, displaying and correcting said marked misrecognized words,

whereby said correcting of said misrecognized words is deferred until after said speech dictation session is concluded and said speech dictation session is not significantly interrupted.

17. The method of claim 16, wherein said displaying and correcting step is implemented by invoking a correction tool of said speech application, whereby said correcting of said misrecognized words trains said speech application.