Method and system for automatically detecting morphemes in a task classification system using lattices

• US 8,200,491 B2
• Filed: 08/27/2011
• Issued: 06/12/2012
• Est. Priority Date: 11/05/1999
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Gorin, Allen Louis, Petrovska-Delacretaz, Dijana, Riccardi, Giuseppe, Wright, Jeremy Huntley
• Primary Examiner(s): AZAD, ABUL K
• Application Number:
  US13/219,659
• Publication Number:
  US 20110313769A1
• Time in Patent Office: 290 Days
• Field of Search: 704/275, 704251-257
• US Class Current: 704/254
• CPC Class Codes: G10L 15/08 Speech classification or search

Abstract

In an embodiment, a lattice of phone strings in an input communication of a user may be recognized, wherein the lattice may represent a distribution over the phone strings. Morphemes in the input communication of the user may be detected using the recognized lattice. Task-type classification decisions may be made based on the detected morphemes in the input communication of the user.

Claims

1. A method comprising:

receiving verbal speech and non-verbal speech from a user;

selecting verbal candidate morphemes from the verbal speech and non-verbal candidate morphemes from the non-verbal speech;

forming, via a processor, a first lattice, based, at least in part, on the verbal candidate morphemes and stored morphemes, and forming a second lattice based on the non-verbal candidate morphemes;

determining a task objective of the speech, based at least in part on the first lattice and the second lattice; and

routing the user according to the task objective.

2. The method of claim 1, further comprising:

determining a second task objective of the non-verbal speech, based at least in part on the non-verbal lattice; and

determining if one of the task objective and the second task objective has priority.

3. The method of claim 1, wherein the non-verbal speech comprises at least one of gestures, body movements, head movements, non-responses, text, keyboard entries, keypad entries, mouse clicks, DTMF codes, pointers, stylus, cable set-top box entries, graphical user interface entries, and touchscreen entries.

4. The method of claim 1, wherein the verbal candidate morphemes are expressed in multimodal form.

5. The method of claim 1, further comprising prompting the user to provide a feedback response.

6. The method of claim 5, wherein the feedback response comprises at least one of a confirmation with respect to the task objective and additional information with respect to the speech.

7. The method of claim 1, wherein the first lattice determines a salience measure associated with the task objective and the verbal candidate morphemes.

8. A system comprising:

a processor; and

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

receiving verbal speech and non-verbal speech from a user;

selecting verbal candidate morphemes from the verbal speech and non-verbal candidate morphemes from the non-verbal speech;

forming a first lattice based, at least in part, on the verbal candidate morphemes and stored morphemes, and forming a second lattice based on the non-verbal candidate morphemes;

determining a task objective of the speech, based at least in part on the first lattice and the second lattice; and

routing the user according to the task objective.

9. The system of claim 8, the instructions, when executed by the processor, cause the processor to perform a method further comprising:

determining a second task objective of the non-verbal speech, based at least in part on the non-verbal lattice; and

determining if one of the task objective and the second task objective has priority.

10. The system of claim 8, wherein the non-verbal speech comprises at least one of gestures, body movements, head movements, non-responses, text, keyboard entries, keypad entries, mouse clicks, DTMF codes, pointers, stylus, cable set-top box entries, graphical user interface entries, and touchscreen entries.

11. The system of claim 8, wherein the verbal candidate morphemes are expressed in multimodal form.

12. The system of claim 8, the instructions, when executed by the processor, cause the processor to perform a method further comprising prompting the user to provide a feedback response.

13. The system of claim 12, wherein the feedback response comprises at least one of a confirmation with respect to the task objective and additional information with respect to the speech.

14. The system of claim 8, wherein the first lattice determines a salience measure associated with the task objective and the verbal candidate morphemes.

15. A non-transitory computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to perform a method comprising:

receiving verbal speech and non-verbal speech from a user;

selecting verbal candidate morphemes from the verbal speech and non-verbal candidate morphemes from the non-verbal speech;

forming a first lattice based, at least in part, on the verbal candidate morphemes and stored morphemes, and forming a second lattice based on the non-verbal candidate morphemes;

determining a task objective of the speech, based at least in part on the first lattice and the second lattice; and

routing the user according to the task objective.

16. The non-transitory computer-readable storage medium of claim 15, the instructions, when executed by the computing device, cause the computing device to perform a method further comprising:

determining a second task objective of the non-verbal speech, based at least in part on the non-verbal lattice; and

determining if one of the task objective and the second task objective has priority.

17. The non-transitory computer-readable storage medium of claim 15, wherein the non-verbal speech comprises at least one of gestures, body movements, head movements, non-responses, text, keyboard entries, keypad entries, mouse clicks, DTMF codes, pointers, stylus, cable set-top box entries, graphical user interface entries, and touchscreen entries.

18. The non-transitory computer-readable storage medium of claim 15, wherein the verbal candidate morphemes are expressed in multimodal form.

19. The non-transitory computer-readable storage medium of claim 15, the instructions, when executed by the computing device, cause the computing device to perform a method further comprising prompting the user to provide a feedback response.

20. The non-transitory computer-readable storage medium of claim 19, wherein the feedback response comprises at least one of a confirmation with respect to the task objective and additional information with respect to the speech.