Method and system for buffering recognized words during speech recognition

• US 5,899,976 A
• Filed: 10/31/1996
• Issued: 05/04/1999
• Est. Priority Date: 10/31/1996
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Rozak, Michael J.
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Chawan, Vijay B.
• Application Number:
  US08/741,698
• Time in Patent Office: 915 Days
• Field of Search: 704/235, 704/260, 704/255, 704/240, 704/243, 704/247, 704/251, 704/252, 704/275, 704/276, 704/277, 704/200
• US Class Current: 704/270
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method and system for editing words that have been misrecognized. The system allows a speaker to specify a number of alternative words to be displayed in a correction window by resizing the correction window. The system also displays the words in the correction window in alphabetical order. A preferred system eliminates the possibility, when a misrecognized word is respoken, that the respoken utterance will be again recognized as the same misrecognized word. The system, when operating with a word processor, allows the speaker to specify the amount of speech that is buffered before transferring to the word processor.

Claims

1. A method in a dictation editing system for buffering recognized words before sending to an application program, the method comprising:

receiving from a speaker an indication of an amount of speech;

receiving utterances from the speaker;

recognizing the received utterances as recognized words;

displaying the recognized words in a dictation window;

in response to a request from the speaker to correct a displayed word,

displaying a list of alternative words for the word to correct; and

replacing the word to correct with an alternative word from the list; and

when the indicated amount of speech has been recognized and displayed, transferring to the application program system words displayed in the dictation window.

2. The method of claim 1 wherein the amount of speech is indicated to be a sentence.

3. The method of claim 1 wherein the amount of speech is indicated to be a paragraph.

4. The method of claim 1 wherein the amount of speech is indicated by resizing the dictation window.

5. The method of claim 1 wherein the step of recognizing uses continuous speech recognition.

6. The method of claim 1 wherein the step of recognizing uses discrete speech recognition.

7. The method of claim 1 wherein the application program is a word processor.

8. A method in a computer system for delaying transmission of words from a dictation editing system to a processing system so that a user can correct any words misrecognized, the method comprising:

receiving from the user an indication of an amount of recognized words;

receiving representations of words;

recognizing the received representations as recognized words;

displaying the recognized words;

correcting the displayed words as directed by the user; and

when the indicated amount of recognized words have been recognized and displayed, transferring to the processing system some of the displayed words.

9. The method of claim 8 wherein the received representations are spoken utterances.

10. The method of claim 8 wherein the amount of recognized words is indicated to be a sentence.

11. The method of claim 8 wherein the amount of recognized words is indicated to be a paragraph.

12. The method of claim 8 wherein the amount of recognized words is indicated by resizing a window in which the words are displayed.

13. The method of claim 8 wherein the step of recognizing uses continuous speech recognition.

14. The method of claim 8 wherein the step of recognizing uses discrete speech recognition.

15. A computer system for delayed transmission of words from a dictation editing system to a processing system so that a user can correct any words misrecognized by the dictation editing system, comprising:

means for receiving from the user an indication of an amount of recognized words;

means for receiving representations of words;

means for recognizing the received representations as recognized words;

means for displaying the recognized words;

means for correcting the displayed words as directed by the user; and

means for transferring to the processing system some of the displayed words when the indicated amount of recognized words have been recognized and displayed.

16. The computer system of claim 15 wherein the received representations are spoken utterances.

17. The computer system of claim 15 wherein the amount of recognized words is indicated to be a sentence.

18. The computer system of claim 15 wherein the amount of recognized words is indicated to be a paragraph.

19. The computer system of claim 15 wherein the amount of recognized words is indicated by resizing a window in which the words are displayed.

20. A computer-readable medium containing instructions for causing a computer system to delay transmission of words from a dictation editing system to a processing system so that a user can correct any words misrecognized, by:

receiving from the user an indication of an amount of recognized words;

receiving spoken utterances from the user;

recognizing the received spoken utterances as recognized words;

displaying the recognized words;

correcting the displayed words as directed by the user; and

when the indicated amount of recognized words have been recognized and displayed, transferring to the processing system a portion of the displayed words as corrected.

21. The computer-readable medium of claim 20 wherein the amount of recognized words is indicated to be a sentence.

22. The computer-readable medium of claim 20 wherein the amount of recognized words is indicated to be a paragraph.

23. The computer-readable medium of claim 20 wherein the amount of recognized words is indicated by resizing a window in which the words are displayed.

24. The computer-readable medium of claim 20 wherein the recognizing uses continuous speech recognition.

25. The computer-readable medium of claim 20 wherein the recognizing uses discrete speech recognition.