Method and apparatus for propagating corrections in speech recognition software

• US 6,314,397 B1
• Filed: 04/13/1999
• Issued: 11/06/2001
• Est. Priority Date: 04/13/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Lewis, James R., Ortega, Kerry, Ballard, Barbara
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US09/290,858
• Time in Patent Office: 938 Days
• Field of Search: 704/200, 704/270, 704/275, 704/235, 704/272, 704/251, 704/255, 704/256, 704/257, 704/246, 704/231, 704/243
• US Class Current: 704/235
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

In a computer system having a word processing application adapted for speech recognition, a method and system to propagate corrections in dictated text. in response to a first user command, a first error word is selected to be corrected from a word processing file containing dictated text. The error word is replaced by a correct word selected by a user. The system subsequently searches the dictated text contained in the document fie in response to another user command to locate a second or subsequent error word that is a close acoustic match to the first error word. The second or subsequent error word may then be replaced using a word selected from an alternate word list.

Claims

1. In a computer system having a word processing application adapted for speech recognition, a method to propagate corrections in dictated text comprising:

in response to a first user command, selecting a first error word to be corrected from the dictated text;

replacing said first error word with a correct word selected by the user; and

in response to a second user command, searching among remaining words in the dictated text for additional error words that have an acoustic model which is similar to an acoustic model associated with said first error word.

2. The method according to claim 1 further comprising the step of replacing said each additional error word in the dictated text with said correct word.

3. The method according to claim 1 further comprising locating said additional error words by text matching a word in the dictated text to an alternate word contained in an alternate word list for said first error word.

4. The method according to claim 1 further comprising locating said additional error words by text matching said first error word to a word in the dictated text.

5. The method according to claim 1 further comprising:

displaying an alternate word list when said first error word is selected; and

replacing said first error word with said correct word selected from said alternate word list.

6. The method according to claim 5 further comprising adding said correct word to said alternate word list and displaying said alternate word list when each of said additional error words is located.

7. In a computer system having a word processing application adapted for speech recognition, a system for propagating corrections in a word processing application document file comprising:

means responsive to a first user command for selecting a first error word to be corrected in said document file;

means for replacing said first error word in said document file with a correct word selected by a user;

means responsive to a second user command for searching remaining words in said document file for additional error words that have an acoustic model which is similar to an acoustic model associated with said first error word.

8. The system according to claim 7 further comprising means for replacing each of said additional error words in said document file with said correct word.

9. The system according to claim 7 further comprising means for locating each additional error word by text matching a word in said document file to an alternate word contained in an alternate word list for said first error word.

10. The system according to claim 7 further comprising means for locating each of said additional error words by text matching said first error word to a word in said document file.

11. The system according to claim 7 further comprising:

means for displaying an alternate word list when said first error word is selected; and

means for replacing said first error word with said correct word selected from said alternate word list.

12. The system according to claim 11 further comprising means for adding said correct word to said alternate word list and displaying said alternate word list when each of said additional error words is located.

13. A machine readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

storing in a memory a word processing application document file containing dictated text;

in response to a first user command, selecting a first error word to be corrected in said dictated text;

replacing said first error word with a correct word selected by a user; and

in response to a second user command, searching among remaining words in said dictated text for additional error words that have an acoustic model which is similar to an acoustic model associated with said first error word.