Menu hierarchy skipping dialog for directed dialog speech recognition

• US 8,457,973 B2
• Filed: 03/04/2006
• Issued: 06/04/2013
• Est. Priority Date: 03/04/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Blanchard, Harry Edward
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US11/276,542
• Publication Number:
  US 20070208568A1
• Time in Patent Office: 2,649 Days
• Field of Search: 704/270, 704/275, 704/231, 704/257, 704/277, 704/270.1, 704/246, 379/88.01, 379/88.03, 379/88.04, 379 8805- 8809
• US Class Current: 704/275
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G09B 5/04 with audible presentation of the material to be studied sound recording or reproducing G11B
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 21/06 Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids G10L15/26 takes precedence
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A method and a processing device for managing an interactive speech recognition system is provided. Whether a voice input relates to expected input, at least partially, of any one of a group of menus different from a current menu is determined. If the voice input relates to the expected input, at least partially, of any one of the group of menus different from the current menu, skipping to the one of the group of menus is performed. The group of menus different from the current menu include menus at multiple hierarchical levels.

Claims

1. A method comprising:

determining, via a processor, whether a voice input relates to expected input of any one of a plurality of menus different from a current menu, wherein the plurality of menus different from the current menu comprises menus at a plurality of hierarchical levels;

when the voice input relates to the expected input skipping to the one of the plurality of menus; and

when the voice input does not relate to the expected input;

retrieving a dynamic record associated with a user, wherein the dynamic record comprises menu traversal tracks, backtracking, and an amount of time spent in a menu;

identifying the voice input as from one of an expert and a non-expert based on the dynamic record; and

when the voice input is from the non-expert, providing a tutorial describing how to skip to one of the plurality of menus.

2. The method of claim 1, further comprising:

using a single grammar with respect to all voice inputs for all menus in the plurality of menus.

3. The method of claim 1, further comprising:

informing the user what to say to cause a menu skip when the voice input relates to expected input of multiple menus in the plurality of menus.

4. The method of claim 1, wherein determining whether the voice input relates to the expected input further comprises:

recognizing one of a key phrase and a keyword in the voice input; and

matching the one of the key phrase and the keyword to the one of the plurality of menus different from the current menu.

5. The method of claim 4, wherein each of the plurality of menus has one of an associated key phrase and an associated keyword that is non-overlapping with respective key phrases and keywords of other menus in the plurality of menus.

6. The method of claim 1, wherein determining whether the voice input relates to expected input further comprises:

recognizing a portion of a key phrase associated with a menu other than the current menu; and

prompting the user for additional information.

7. The method of claim 1, wherein determining whether the voice input relates to expected input further comprises:

determining that the voice input comprises a conversational correction.

8. A system comprising:

a processor; and

a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform a method comprising;

determining whether a voice input relates to expected input of any one of a plurality of menus different from a current menu, wherein the plurality of menus different from the current menu comprises menus at a plurality of hierarchical levels;

when the voice input relates to the expected input skipping to the one of the plurality of menus different from the current menu; and

when the voice input does not relate to the expected input;

retrieving a dynamic record associated with a user, wherein the dynamic record comprises menu traversal tracks, backtracking, and an amount of time spent in a menu;

identifying the voice input as from one of an expert and a non-expert based on the dynamic record; and

when the voice input is from the non-expert providing a tutorial describing how to skip to one of the plurality of menus.

9. The system of claim 8, the computer-readable storage medium having additional instructions stored which result in the method further comprising:

using a single grammar with respect to all voice inputs for all menus in the plurality of menus.

10. The system of claim 8, wherein determining whether the voice input relates to expected input further comprises:

recognizing one of a key phrase and a keyword in the voice input; and

matching the one of the key phrase and the keyword to the one of the plurality of menus.

11. The system of claim 10, wherein:

each menu of the plurality of menus has one of an associated key phrase and a keyword that is non-overlapping with a respective one of a key phrase and a keyword of other menus of the plurality of menus.

12. The system of claim 8, wherein determining whether the voice input relates to expected input further comprises:

recognizing a portion of a key phrase associated with the one of the plurality of menus other than the current menu; and

prompting for additional information.

13. The system of claim 8, wherein determining whether the voice input relates to expected input further comprises:

determining that the voice input comprises a conversational correction.

14. A non-transitory computer-readable storage device having instructions stored to control a processor to perform a method comprising:

determining whether a voice input relates to expected input of any one of a plurality of menus different from a current menu, wherein the plurality of menus different from the current menu comprises menus at a plurality of hierarchical levels;

when the voice input relates to the expected input, skipping to the one of the plurality of menus; and

when the voice input does not relate to the expected input;

retrieving a dynamic record associated with a user, wherein the dynamic record comprises menu traversal tracks, backtracking, and an amount of time spent in a menu;

identifying the voice input as from one of an expert and a non-expert based on the dynamic record; and

when the voice input is from the non-expert, providing a tutorial to the non-expert describing how to skip to one of the plurality of menus.

15. The non-transitory computer-readable storage device of claim 14, the non-transitory computer-readable storage medium having additional instruction stored which result in the method further comprising:

using a single grammar with respect to the voice input for all menus in the plurality of menus.

16. The non-transitory computer-readable storage device of claim 14, wherein determining whether the voice input relates to expected input further comprises:

recognizing one of a key phrase and a keyword in the voice input; and

matching the one of the key phrase and the keyword to the one of the plurality of menus.

17. The non-transitory computer-readable storage device of claim 16, wherein

each menu of the plurality of menus has a respective associated one of a key phrase and a keyword that is non-overlapping with one of a respective key phrase and a keyword of other menus of the plurality of menus.

18. The non-transitory computer-readable storage device of claim 14, wherein determining whether the voice input relates to expected input further comprises:

recognizing a portion of a key phrase associated with the one of the plurality of menus other than the current menu; and

prompting for additional information.

19. The non-transitory computer-readable storage device of claim 14, wherein determining whether the voice input relates to expected input further comprises:

determining that the voice input comprises a conversational correction.

20. A processing device comprising:

means for determining, via a processor, whether a voice input relates to expected input, at least partially, of any one of a plurality of menus different from a current menu, wherein the plurality of menus different from the current menu comprises menus at a plurality of hierarchical levels;

means for skipping, when the voice input relates to the expected input, to the one of the plurality of menus different from the current; and

means for, when the voice input does not relate to the expected input;

retrieving a dynamic record associated with a user, wherein the dynamic record comprises menu traversal tracks, backtracking, and an amount of time spent in a menu;

identifying the voice input as one of an expert and a non-expert based on the dynamic record; and

when the voice input is from the non-expert, providing a tutorial to the non-expert describing how to skip to one of the plurality of menus.