SYSTEM AND METHOD FOR IMPROVING NAME DIALER PERFORMANCE

• US 20100042414A1
• Filed: 09/12/2008
• Published: 02/18/2010
• Est. Priority Date: 08/18/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Pearsall, Susan Helen, Czahor, Michael T. III, Dudi, Ramkishore, Lewis, Steven Hart
• Granted Patent: US 8,762,153 B2
• Time in Patent Office: Days
• US Class Current: 704/270.100
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Disclosed herein are systems, methods, and computer readable-media for improving name dialer performance. The method includes receiving a speech query for a name in a directory of names, retrieving matches to the query, if the matches are uniquely spelled homophones or near-homophones, identifying information that is unique to all retrieved matches, and presenting a spoken disambiguation statement to a user that incorporates the identified unique information. Identifying information can include multiple pieces of unique information if necessary to completely disambiguate the matches. A hierarchy can establish priority of multiple pieces of unique information for use in the spoken disambiguation statement.

Claims

1. A method of improving name dialer performance, the method comprising:

receiving a speech query for a name in a directory of names;

retrieving matches to the query;

if the matches are uniquely spelled homophones or near-homophones, identifying information that is unique to all retrieved matches; and

presenting a spoken disambiguation statement to a user that incorporates the identified unique information.

2. The method of claim 1, wherein identifying information includes multiple pieces of unique information if necessary to completely disambiguate the retrieved matches.

3. The method of claim 2, wherein a hierarchy establishes priority of multiple pieces of unique information for use in the spoken disambiguation statement.

4. The method of claim 1, wherein a threshold is used to determine near-homophones.

5. The method of claim 1, the method further comprising:

receiving a confirmation of one of the retrieved matches; and

connecting a caller to the confirmed match.

6. The method of claim 1, wherein information unique to all retrieved matches is customized.

7. The method of claim 1, the method further comprising:

receiving a request from a user for further disambiguation information;

presenting further spoken disambiguation information to the user.

8. A system for improving name dialer performance, the system comprising:

a module configured to receive a speech query for a name in a directory of names;

a module configured to retrieve matches to the query;

if the matches are uniquely spelled homophones or near-homophones, a module configured to identify information that is unique to all retrieved matches; and

a module configured to present a spoken disambiguation statement to a user that incorporates the identified unique information.

9. The system of claim 8, wherein identifying information includes multiple pieces of unique information if necessary to completely disambiguate the retrieved matches.

10. The system of claim 9, wherein a hierarchy establishes priority of multiple pieces of unique information for use in the spoken disambiguation statement.

11. The system of claim 8, wherein a threshold is used to determine near-homophones.

12. The system of claim 8, the system further comprising:

a module configured to receive a confirmation of one of the retrieved matches; and

a module configured to connect a caller to the confirmed match.

13. The system of claim 8, wherein information unique to all retrieved matches is customized.

14. The system of claim 8, the system further comprising:

a module configured to receive a request from a user for further disambiguation information;

a module configured to present further spoken disambiguation information to the user.

15. A computer-readable medium storing a computer program having instructions for improving name dialer performance, the instructions comprising:

receiving a speech query for a name in a directory of names;

retrieving matches to the query;

if the matches are uniquely spelled homophones or near-homophones, identifying information that is unique to all retrieved matches; and

presenting a spoken disambiguation statement to a user that incorporates the identified unique information.

16. The computer-readable medium of claim 15, wherein identifying information includes multiple pieces of unique information if necessary to completely disambiguate the retrieved matches.

17. The computer-readable medium of claim 16, wherein a hierarchy establishes priority of multiple pieces of unique information for use in the spoken disambiguation statement.

18. The computer-readable medium of claim 15, wherein a threshold is used to determine near-homophones.

19. The computer-readable medium of claim 15, the instructions further comprising:

receiving a confirmation of one of the retrieved matches; and

connecting a caller to the confirmed match.

20. The computer-readable medium of claim 15, the instructions further comprising:

receiving a request from a user for further disambiguation information;

presenting further spoken disambiguation information to the user.