Natural input of arbitrary text

• US 20070088549A1
• Filed: 10/14/2005
• Published: 04/19/2007
• Est. Priority Date: 10/14/2005
• Status: Abandoned Application

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Mowatt, David
• Application Number:
  US11/251,250
• Publication Number:
  US 20070088549A1
• Time in Patent Office: Days
• US Class Current: 704/243
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A method and system for enabling a speech recognition system to recognize entities having arbitrary text. The method includes identifying an entity having arbitrary text from a user and detecting that the entity has an identifiable pattern of characters. The speech recognition system prompts the user to assign an alternative natural phrase that corresponds with the entity. The alternative natural phrase is stored in a dictionary to thereby textually enter the entity upon capturing the corresponding natural phrase.

Claims

1. A computer-implemented method of enabling a speech recognition system to recognize entities that have arbitrary text, the method comprising:

identifying an entity having arbitrary text;

detecting that the entity has an identifiable pattern of characters;

prompting a user to assign an alternative natural phrase that corresponds with the entity; and

storing the alternative natural phrase that corresponds with the entity to thereby textually enter the entity upon later capturing of the corresponding alternative natural phrase.

2. The computer-implemented method of claim 1, wherein detecting that the entity has an identifiable pattern of characters comprises parsing and determining that the entity has a pattern of characters that coincide with characters used in an email alias.

3. The computer-implemented method of claim 1, wherein detecting that the entity has an identifiable pattern of characters comprises detecting that the entity has a statistically identifiable pattern of characters.

4. The computer-implemented method of claim 1, further comprising receiving notification from the user that dictated text was wrongly recognized prior to identifying that the entity has arbitrary text.

5. The computer-implemented method of claim 1, further comprising receiving an entity that is spelled by the user prior to identifying that the entity has arbitrary text.

6. The computer-implemented method of claim 1, wherein prompting the user to assign an alternative natural phrase that corresponds with the entity comprises suggesting at least one alternative natural phrase for the entity.

7. The computer-implemented method of claim 1, further comprising visually rendering a list of alternative interpretations of the captured alternative natural phrase after the entity is textually entered.

8. The computer-implemented method of claim 7, further comprising replacing the textually entered entity with a selected one of the list of visually rendering alternative interpretations.

9. The computer-implemented method of claim 1, further comprising determining that the alternative natural phrase being assigned to the entity having arbitrary text is also assigned to a second entity having arbitrary text.

10. The computer-implemented method of claim 9, further comprising prompting the user to reassign a different alternative natural phrase to the entity.

11. The computer-implemented method of claim 9, further comprising prompting the user to reassign a different alternative natural phrase to the second entity having arbitrary text.

12. A speech recognition system that recognizes entities that have arbitrary text, the system comprising:

a speech recognition engine configured to identify an entity having arbitrary text;

an entity detection subsystem configured to detect that the entity has an identifiable pattern of characters;

a natural phrase engine configured to prompt a user to assign an alternative natural phrase that corresponds with the entity; and

a dictionary configured to store the alternative natural phrase that corresponds with the entity.

13. The speech recognition system of claim 12, wherein the natural phrase engine is further configured to suggest at least one alternative natural phrase for the entity.

14. The speech recognition system of claim 12, further comprising a speech correction subsystem configured to visually render a list of alternative interpretations of the captured alternative natural phrase after the entity is textually entered.

15. The speech recognition system of claim 12, wherein the speech recognition engine is further configured to determine that the alternative natural phrase that corresponds with the entity is also assigned to a second entity.

16. The speech recognition system of claim 15, wherein the speech recognition engine is further configured to prompt the user to reassign a different alternative natural phrase to the entity having arbitrary text.

17. The speech recognition system of claim 12, wherein the speech recognition engine is further configured to:

capture the alternative natural phrase as spoken by the user;

access the dictionary; and

textually enter the entity having arbitrary text that corresponds with the captured alternative natural phrase.

18. A computer-implemented method for entering entities that have arbitrary text using a speech recognition system, the method comprising:

capturing an alternative natural phrase as spoken by a user;

accessing a dictionary to retrieve an entity having arbitrary text that corresponds with the captured alternative natural phrase; and

textually entering the entity having arbitrary text.

19. The computer-implemented method of claim 18, further comprising visually rendering a list of alternative interpretations of the captured alternative natural phrase after the entity is textually entered.

20. The computer-implemented method of claim 19, further comprising replacing the textually entered entity having arbitrary text with a selected one of the list of visually rendered alternative interpretations.