Method and system for proofreading and correcting dictated text

• US 20030200093A1
• Filed: 06/11/2003
• Published: 10/23/2003
• Est. Priority Date: 06/11/1999
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Keller, Arthur, Hanson, Gary R., Lewis, James R., Ortega, Kerry A., Ballard, Barbara E., Vanbuskirk, Ronald E.
• Granted Patent: US 6,760,700 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method of proofreading and correcting dictated text contained in an electronic document can include selecting proofreading criteria for identifying textual errors contained in the electronic document; playing back each word contained in the electronic document; and, marking as a textual error each played back word in nonconformity with at least one of the proofreading criteria.

Claims

1. A method for proofreading and correcting user dictated text contained in an electronic document, comprising the steps of:

selecting proofreading criteria for identifying textual errors contained in dictated text in said electronic document;

audibly playing back each word contained in said dictated text in said electronic document, said step of audibly playing back each word further comprising sequentially highlighting each said word contained in said electronic document, visually displaying each said sequentially highlighted word in a user interface separate from a user interface used to display said electronic document, providing user voice audio playback using user voice data corresponding to each said highlighted word in said electronic document in coordination with said visually displaying step, generating text-to-speech audio playback for each said highlighted word in said electronic document not having corresponding user voice data, and providing said text-to-speech audio playback in coordination with said visually displaying step; and

during said audible playback, marking as a textual error each said played back word in nonconformity with at least one of said proofreading criteria, wherein said marking step comprises automatically marking as a textual error each said replayed word inconsistent with said proofreading criteria.

2. The method of claim 1, wherein said selecting step comprises the steps of:

specifying a low confidence word threshold below which any word will be identified as a textual error;

enabling homonym and confusable word criteria whereby any homonym and confusable word will be identified as a textual error; and

specifying a word grade level above which any word will be identified as a textual error.

3. The method of claim 1, wherein said selecting step comprises the steps of:

generating a grammar rules check list for reference by a grammar checker; and

enabling grammar checking whereby any word or phrase inconsistent with said grammar rules will be identified as a textual error.

4. The method of claim 1, wherein said displaying step further comprises:

visually displaying immediately before said visually displayed highlighted word at least one word preceding said highlighted word in said electronic document; and

visually displaying immediately after said visually displayed highlighted word at least one word succeeding said highlighted word in said electronic document.

5. The method of claim 1, wherein said marking step further comprises manually marking as a textual error each said replayed word suspected of violating at least one of said proofreading criteria, said manually marking step occurring concurrently to said automatic marking step.

6. The method of claim 1, further comprising the step of editing each said marked textual error identified in said marking step.

7. The method of claim 6, wherein said editing step comprises:

reviewing each said marked textual error identified in said marking step;

accepting user specified changes to each marked textual error reviewed in said reviewing step; and

unmarking each marked textual error corrected by said user in said accepting step.

8. The method of claim 7, wherein said reviewing step comprises the steps of:

highlighting each said word in said electronic document corresponding to said marked textual error marked in said marking step; and

displaying an explanation for each said marked textual error in a user interface.

9. The method of claim 7, wherein said reviewing step comprises the steps of:

suggesting a recommended change to said marked textual error;

displaying said recommended change in said user interface; and

accepting a user specified preference to substitute said recommended change for said marked textual error.

10. The method of claim 7, further comprising the step of unmarking each said marked textual error corresponding to a user command to unmark said marked textual error.

11. An electronic system for proofreading and correcting dictated text in an electronic document, wherein said electronic system comprises:

a proofreading tool for identifying and correcting textual errors in dictated text in said electronic document, said proofreading tool comprising an automated marking tool for automatically identifying and marking textual errors contained in said dictated text which exceed thresholds specified in said proofreading criteria, a mark processor for editing said marked textual errors identified by said marking tool, and a playback system for playing back said dictated text, wherein said playback system further comprises a highlighter for sequentially distinguishing each word contained in said dictated text, means for providing user voice audio playback for said distinguished words having corresponding user voice data, and a text-to-speech generator for producing audio playback for distinguished words not having corresponding user voice data required by said user voice audio playback means;

a proofreading options interface for storing proofreading criteria for use with said proofreading tool; and

a control panel for interacting with said proofreading tool.

12. The electronic system for proofreading and correcting dictated text in an electronic document according to claim 11, further comprising a voice command processor for controlling said proofreading options user interface.

13. The electronic system for proofreading and correcting dictated text according to claim 11, wherein said marking tool further comprises a manual marking tool for marking textual errors, whereby said manual marking tool can operate concurrent to said automated marking tool.

14. The electronic system for proofreading and correcting dictated text according to claim 11, wherein said marking tool further comprises a grammar checker for identifying grammatical errors contained in said electronic document.

15. The electronic system for proofreading and correcting dictated text according to claim 11, wherein said mark processor comprises:

a highlighter for sequentially distinguishing each word contained in said dictated text identified and marked as a textual error by said marking tool;

an explanation engine having explanations for each said textual error;

messaging means for transmitting said explanations to said control panel; and

means for editing said textual error.

16. The electronic system for proofreading and correcting dictated text according to claim 15, wherein said mark processor further comprises:

a suggestion engine having suggested corrections to each textual error; and

messaging means for transmitting said suggested corrections to said control panel.

17. The electronic system for proofreading and correcting dictated text according to claim 11, wherein said proofreading options interface comprises:

a low confidence word control for specifying a low confidence word threshold below which any word will be identified as a textual error;

a homonyms and confusable words switch for enabling the marking of homonyms and confusable words; and

a word grade level control for specifying a word grade level above which any word will be identified as a textual error.

18. The electronic system for proofreading and correcting dictated text according to claim 11, wherein said proofreading options interface comprises:

a grammar rules control interface containing grammar rules for reference by a grammar checker; and

a grammar rules switch for enabling marking of words or phrases inconsistent with said grammar rules by said grammar checker.

19. The electronic system for proofreading and correcting dictated text according to claim 11, wherein said control panel comprises:

a mark problems view for controlling said marking tool; and

a work with marks view for controlling said mark processor.

20. The electronic system for proofreading and correcting dictated text according to claim 19, wherein said mark problems view comprises:

a playback speed control for prescribing a rate of playback by said playback system;

a pause button for accepting a command to pause said playback of said dictated text;

a mark button for accepting a user command to manually mark said displayed word as a textual error;

first message transmitting means for transmitting said mark command to said marking tool;

second message transmitting means for transmitting said prescribed rate and said pause command to said playback system;

message receiving means for receiving each word played back by said playback system; and

a current-word text box for displaying each word received by said message receiving means.

21. The electronic system for proofreading and correcting dictated text according to claim 19, wherein said work with marks view comprises:

message receiving means for receiving data from said mark processor; and

a status line for displaying an explanation generated by an explanation engine and received by said message receiving means.

22. An electronic system for proofreading and correcting dictated text according to claim 21, wherein said work with marks view further comprises:

a suggestion panel for displaying a suggested correction generated by a suggestion engine and received by said message receiving means;

a suggestion button for accepting a user specified preference to substitute said suggested correction for said marked textual error; and

,

third message transmitting means for transmitting said substitution preference to said mark processor.

23. A computer apparatus programmed with a routine set of instructions stored in a fixed medium, said computer apparatus comprising:

means for selecting proofreading criteria for identifying textual errors contained in dictated text in said electronic document;

means for audibly playing back each word contained in said dictated text in said electronic document, said means for audibly playing back each word further comprising means for sequentially highlighting each said word contained in said electronic document, means for visually displaying each said sequentially highlighted word in a user interface separate from a-user interface used to display said electronic document, means for providing user voice audio playback using user voice data corresponding to each said highlighted word in said electronic document in coordination with said visually displaying means, means for generating text-to-speech audio playback for each said highlighted word in said electronic document not having corresponding user voice data, and means for providing said text-to-speech audio playback in coordination with said visually displaying means; and

means for marking as a textual error each said played back word in nonconformity with at least one of said proofreading criteria while audibly playing back each word contained in said dictated text in said electronic document, wherein said marking means comprises means for automatically marking as a textual error each said replayed word inconsistent with said proofreading criteria.

24. The computer apparatus of claim 23, wherein said selecting means comprise:

means for specifying a low confidence word threshold below which any word will be identified as a textual error;

means for enabling homonym and confusable word criteria whereby any homonym and confusable word will be identified as a textual error; and

means for specifying a word grade level above which any word will be identified as a textual error.

25. The computer apparatus of claim 23, wherein said selecting means comprise:

means for generating a grammar rules check list for reference by a grammar checker; and

means for enabling grammar checking whereby any word or phrase inconsistent with said grammar rules will be identified as a textual error.

26. The computer apparatus of claim 23, wherein said displaying means further comprise:

means for visually displaying immediately before said visually displayed highlighted word at least one word preceding said highlighted word in said electronic document; and

means for visually displaying immediately after said visually displayed highlighted word at least one word succeeding said highlighted word in said electronic document.

27. The computer apparatus of claim 23, wherein said marking means comprise means for manually marking as a textual error each said replayed word suspected of violating at least one of said proofreading criteria, wherein said means for manually marking textual errors are operative concurrently with said means for automatically marking textual errors.

28. The computer apparatus of claim 23, further comprising means for editing each said marked textual error identified by said marking means.

29. The computer apparatus of claim 28, wherein said editing means comprise:

means for reviewing each said marked textual error identified by said marking means;

means for accepting user specified changes to each marked textual error reviewed by said reviewing means; and

means for unmarking each marked textual error corrected by said user using said accepting means.

30. The computer apparatus of claim 29, wherein said reviewing means comprise:

means for highlighting each said word in said electronic document corresponding to said marked textual error marked by said marking means; and

means for displaying an explanation for each said marked textual error in a user interface.

31. The computer apparatus according to claim 29, wherein said reviewing means further comprise:

means for suggesting a recommended change to said marked textual error;

means for displaying said recommended change in said user interface; and

means for accepting a user specified preference to substitute said recommended change for said marked textual error.

32. The computer apparatus according to claim 29, further comprising unmarking means for unmarking each said marked textual error corresponding to a user command to unmark said marked textual error.