Text formatter with intuitive customization

• US 9,697,834 B2
• Filed: 07/26/2012
• Issued: 07/04/2017
• Est. Priority Date: 07/26/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Kobal, Jeffrey S., Bisani, Maximilian, Divay, Olivier
• Primary Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US14/416,955
• Publication Number:
  US 20150262580A1
• Time in Patent Office: 1,804 Days
• CPC Class Codes: G06F 40/103 Formatting, i.e. changing of presentation of documents automatic justification G06F40/189; automatic line break hyphenation G06F40/191
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A computer implemented method and system of formatting text output from a speech recognition system is provided. The method includes determining if a user correction to a text output from a speech recognition system can be accomplished by changing a formatting setting associated with the speech recognition system. The formatting setting is changed based on an inferential indication that the change to the formatting setting is acceptable to the user and/or an explicit confirmation from the user that the change to the formatting setting is acceptable.

Claims

1. A computer implemented method of formatting text in a speech recognition system, the method comprising:

determining if a user correction to a text output from the speech recognition system can be accomplished by changing a formatting setting associated with the speech recognition system; and

changing the formatting setting based, at least in part, on an inferential indication that the change to the formatting setting is acceptable to the user and/or an explicit confirmation from the user that the change to the formatting setting is acceptable.

2. The method according to claim 1, wherein changing the formatting setting based on an explicit confirmation from the user includes:

providing via a user interface at least one option to the user to change the formatting setting; and

changing the formatting setting if the user accepts one or more of the options.

3. The method according to claim 2, the method further comprising:

prior to providing the at least one option to the user to change the formatting setting, testing each option to change to the formatting setting by;

formatting the text output with the change to the formatting setting incorporated to produce a candidate text;

comparing the user correction to the candidate text;

if the candidate text matches the user correction to the text output, provide the option to the user; and

if the candidate text does not match the user correction to the text output, do not provide the option to the user.

4. The method according to claim 1, wherein changing the formatting setting based on an inferential indication includes:

monitoring previously made corrections; and

changing the formatting setting based, at least in part, on the previously made corrections.

5. The method according to claim 1, wherein the formatting setting is associated with a spacing, a numbering, a spelling variation, a capitalization, an abbreviation, a contraction, a number, a unit of measure, a price, a date, a time, an address, an e-mail address, a web address, a phone number, masking of foul language, a legal citation, a dosage, a blood pressure and/or a vertebra number.

6. The method according to claim 1, wherein determining if a user correction to text output from the speech recognition system can be accommodated by changing a formatting setting associated with the speech recognition system includes:

using a formatting graph representing alternative formatted texts of a token sequence associated with the text output.

12. The system according to claim 1, wherein the adaptation component uses a formatting graph representing alternative formatted texts of the output in determining if a user correction to text output from the speech recognition system can be accommodated by changing a formatting setting associated with the speech recognition system.

7. A speech recognition system for outputting text based on a spoken utterance, the system comprising:

at least one processor configured to implement an adaptation component for;

determining if a user correction to text output from the speech recognition system can be accomplished by changing a formatting setting associated with the speech recognition system; and

changing the formatting setting based, at least in part, on an inferential indication that the change to the formatting setting is acceptable to the user and/or an explicit confirmation from the user that the change to the formatting setting is acceptable.

8. The system according to claim 7, further comprising:

a user interface for providing at least one option to the user to change the formatting setting, and upon which the user can provide explicit confirmation that one or more of the options to change the formatting setting is acceptable.

9. The system according to claim 8, wherein prior to providing the at least one option to the user to change the formatting setting, the adaptation component tests each option to change the formatting by:

formatting the text output, with the change to the formatting setting incorporated, to produce a candidate text;

if the candidate text matches the user correction to the text output, provide the option to the user; and

if the candidate text does not match the user correction to the text output, do not provide the option to the user.

10. The system according to claim 7, wherein the inferential indication is based, at least in part, on previous corrections to formatted text monitored by the adaptation component module.

11. The system according to claim 7, wherein the formatting setting is associated with a spacing, a numbering, a spelling variation, a capitalization, an abbreviation, a contraction, a number, a unit of measure, a price, a date, an address, an e-mail address, a web address, a phone number, masking of foul language, a legal citation, a dosage, a blood pressure and/or a vertebra number.

13. A computer implemented method of formatting text in a speech recognition system, the method comprising:

determining if a user correction to a text output from the speech recognition system can be accomplished by changing a formatting setting associated with the speech recognition system; and

changing the formatting setting associated with the speech recognition system based, at least in part, on the formatting of pre-existing text.

14. The method according to claim 13, wherein changing the formatting setting includes:

changing the formatting setting only after receiving explicit confirmation from a user that the change to the formatting setting is acceptable.

15. The method according to claim 14, wherein changing the formatting setting includes:

providing via a user interface at least one option to a user to change the formatting setting; and

changing the formatting setting if the user accepts one or more of the options.

16. The method according to claim 13, wherein the formatting setting is associated with a spacing, a numbering, a spelling variation, a capitalization, an abbreviation, a contraction, a number, a unit of measure, a price, a date, a time, an address, an e-mail address, a web address, a phone number, masking of foul language, a legal citation, a dosage, a blood pressure and/or a vertebra number.

17. A speech recognition system for outputting text based on a spoken utterance, the system comprising:

at least one processor configured to implement an adaptation component for;

determining if a user correction to text output from the speech recognition system can be accomplished by changing a formatting setting associated with the speech recognition system; and

changing the formatting setting associated with the speech recognition system based, at least in part, on the formatting of pre-existing text.

18. The system according to claim 17, wherein the adaptation component is further configured to change the formatting setting only after receiving explicit confirmation from a user that the change to the formatting setting is acceptable.

19. The system according to claim 18, further comprising:

a user interface for providing at least one option to a user to change the formatting setting, and upon which the user can provide explicit confirmation that one or more of the options to change the formatting setting is acceptable.

20. The system according to claim 17, wherein the formatting setting is associated with a spacing, a numbering, a spelling variation, a capitalization, an abbreviation, a contraction, a number, a unit of measure, a price, a date, an address, an e-mail address, a web address, a phone number, masking of foul language, a legal citation, a dosage, a blood pressure and/or a vertebra number.