METHOD AND SYSTEM FOR PROMPT CONSTRUCTION FOR SELECTION FROM A LIST OF ACOUSTICALLY CONFUSABLE ITEMS IN SPOKEN DIALOG SYSTEMS

• US 20080281598A1
• Filed: 05/09/2007
• Published: 11/13/2008
• Est. Priority Date: 05/09/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Goel, Vaibhava, Eide, Ellen Marie, Stewart, Osamuyimen T., Gopinath, Ramesh
• Granted Patent: US 8,909,528 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method (and system) of determining confusable list items and resolving this confusion in a spoken dialog system includes receiving user input, processing the user input and determining if a list of items needs to be played back to the user, retrieving the list to be played back to the user, identifying acoustic confusions between items on the list, changing the items on the list as necessary to remove the acoustic confusions, and playing unambiguous list items back to the user.

Claims

1. A method of determining a confusable list item in a spoken dialog system, said method comprising:

receiving user input;

processing said user input and determining if a list of items needs to be played back to the user;

retrieving said list to be played back to the user;

identifying acoustic confusions between items on said list;

changing said items on said list as necessary to remove said acoustic confusions; and

playing unambiguous list items back to the user.

2. The method according to claim 1, wherein if said items on said list are confusable, constructing a prompt to allow an unambiguous presentation of said items.

3. The method according to claim 1, wherein a measure of confusability is determined based on phonetic contents and orthography of said items.

4. The method according to claim 3, wherein said measure of confusability is customized to a playback system to resolve confusions specific to the playback system.

5. The method according to claim 1, further comprising reviewing commonly occurring recognition errors in previous calls.

6. The method according to claim 2, wherein said constructing a prompt comprises determining minimal features that distinguish items including the acoustic confusions.

7. The method according to claim 6, wherein the minimal features depend on a type of acoustic confusion.

8. The method according to claim 6, wherein said constructing a prompt considers a number of said items that are considered confusable.