Disambiguation method and system for a voice activated directory assistance system

• US 7,013,280 B2
• Filed: 02/27/2001
• Issued: 03/14/2006
• Est. Priority Date: 02/27/2001
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Michelini, Vanessa V., Davis, Brent L., Ghasemi, Reza, Kong, Tracy, Hill, Susan M., Lauria, John r
• Primary Examiner(s): Young, W. R.
• Assistant Examiner(s): Vo, Huyen X.
• Application Number:
  US09/794,413
• Publication Number:
  US 20020120452A1
• Time in Patent Office: 1,841 Days
• Field of Search: 704/246, 704/251, 704/231, 704/275, 704/9, 704/270, 704/270.1, 706/20, 379/354, 379/213.01, 379/357.05, 379/88.03, 379/67.1, 700/90, 707/10, 707/4, 707/6
• US Class Current: 704/270
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation

Abstract

A method for correcting ambiguations in directory assistance systems includes the steps of receiving and processing a directory assistance request from a caller. If the processing results in an ambiguation of at least two names, audio information is provided to the caller. The audio information includes, at least in part, playback of an audio recording of at least one person included in the ambiguation. The audio playback helps the caller resolve the ambiguation. A voice activated directory assistance system having structure for resolving ambiguations is also disclosed.

Claims

1. A method for correcting ambiguations in directory assistance systems, comprising the steps of:

receiving and processing a voice directory assistance request from a caller;

performing speech recognition on the voice directory assistance request;

presenting audio information to said caller if the request results in an ambiguation of at least two names, said audio information comprising a serial presentation of audibly recorded alternative names, each name audibly recorded in a voice of a person named; and

receiving from said caller a selection of a name, thereby resolving said ambiguation.

2. The method of claim 1, wherein said audio information comprises the person stating their name.

3. The method of claim 1, wherein the audio information comprises a message from the person being named.

4. The method of claim 1, wherein the directory assistance systems comprise voice activated directory assistance systems.

5. The method of claim 1, wherein said audio information includes additional information for selecting between names in said ambiguation.

6. The method of claim 5, wherein said additional information comprises at least one of department information, location information, job description information, and personal information.

7. The method of claim 1, further comprising the step of connecting said caller to the phone line of the selected name.

8. A directory assistance system, comprising:

a searchable directory for storing directory information;

a database of audio recordings, each audio recording comprising a name of a person audibly recorded in a voice of a person named and corresponding to an entry in said searchable directory;

a query system for searching said directory for a particular entry based on received voice directory assistance requests;

a speech recognition system for converting the voice directory assistance requests into computer-processable queries for processing by said query system; and

a disambiguation system for retrieving and playing back selected ones of said audio recordings in said database responsive to said query system locating multiple entries during a directory search;

said disambiguation system serially presenting the selected audio recordings when multiples entries are located in response to a query from a caller seeking directory assistance to enable the caller to select a name.

9. The directory assistance system of claim 8, wherein each audio recording comprises a person stating their name.

10. The directory assistance system of claim 8, wherein said audio recordings comprise voice messages.

11. The directory assistance system of claim 8, wherein the directory assistance system is a voice activated directory assistance system.

12. The directory assistance system of claim 8, wherein said database of audio recordings further comprises additional information for selecting between names in an ambiguation.

13. The directory assistance system of claim 12, wherein said additional information comprises at least one of department information, location information, job description information, and personal information.

14. The directory assistance system of claim 8, further comprising structure for connecting a caller of the directory assistance system to a telephone associated with a located entry in said searchable directory.

15. A machine readable storage, having stored thereon a computer program for correcting ambiguations in a directory assistance system, said computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

receiving and processing a voice directory assistance request from a caller;

performing speech recognition on the voice directory assistance request;

presenting audio information to said caller if the request results in an ambiguation of at least two names, said audio information comprising a serial presentation of audibly recorded alternative names, each name audibly recorded in a voice of a person named; and

receiving from said caller a selection of a name, thereby resolving said ambiguation.

16. The machine readable storage of claim 15, wherein said audio information comprises the person stating their name.

17. The machine readable storage of claim 15, wherein the audio information comprises a message from the person being named.

18. The machine readable storage of claim 15, wherein the directory assistance system is a voice activated directory assistance system.

19. The machine readable storage of claim 15, wherein said audio information includes additional information for selecting between names in said ambiguation.

20. The machine readable storage of claim 19, wherein said additional information comprises at least one of department information, location information, job description information, and personal information.

21. The machine readable storage of claim 15, further comprising the step of connecting said caller to the phone line of the selected name.