METHOD AND SYSTEM FOR PROVIDING A VOICE INTERFACE

• US 20100114944A1
• Filed: 10/31/2008
• Published: 05/06/2010
• Est. Priority Date: 10/31/2008
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Wu, Tao, Polifroni, Joseph H., Kiss, Imre, Adler, Mark R.
• Granted Patent: US 9,978,365 B2
• Time in Patent Office: Days
• US Class Current: 707/770
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

Methods and systems for providing a voice interface are disclosed. A classifier voice interface of a user terminal may receive a query, may parse the query to identify an attribute, and may process the query to select a first domain-specific voice interface of a plurality of domain-specific voice interface based on the attribute, wherein each of the domain-specific voice interface comprises specialized information to process queries of different types. The classifier voice interface may further instruct the first domain-specific voice interface to process the query.

Claims

1. A method comprising:

receiving a query;

parsing the query to identify an attribute;

processing the query to select a first domain-specific voice interface of a plurality of domain-specific voice interfaces based on the attribute, wherein each of the domain-specific voice interfaces comprises specialized information to process queries of different types; and

instructing the first domain-specific voice interface to process the query.

2. The method of claim 1, further comprising receiving a vocal input to activate a classifier.

3. The method of claim 2, wherein the vocal input corresponds to an identity assigned to the classifier.

4. The method of claim 1, wherein the first domain-specific voice interface is selected by identifying keywords in the query.

5. The method of claim 1, wherein the first domain-specific voice interface is selected by natural language processing of the query.

6. The method of claim 5, wherein the natural language processing applies domain knowledge to process the query.

7. The method of claim 5, wherein the natural language processing applies grammar to process the query.

8. The method of claim 5, wherein the natural language processing applies statistical models to process the query.

9. The method of claim 5, wherein the natural language processing applies user data to process the query.

10. The method of claim 1, wherein the first domain-specific voice interface is selected by communicating the query to the first domain-specific voice interface for interpreting the query to confirm that selection of the first domain-specific voice interface is appropriate.

11. The method of claim 1, wherein the first domain-specific voice interface is selected based on each of the plurality of domain-specific voice interface interpreting the query to generate a response score and selecting a highest response score.

12. The method of claim 1, further comprising identifying context information corresponding to the query, wherein the first domain-specific voice interface is selected based on the context information.

13. The method of claim 12, wherein the context information comprises user preferences.

14. One or more computer readable media storing computer-executable instructions which, when executed by a processor, cause the processor to perform a method comprising:

receiving a query;

parsing the query to identify an attribute;

processing the query to select a first domain-specific voice interface of a plurality of domain-specific voice interfaces based on the attribute, wherein each of the domain-specific voice interfaces comprises specialized information to process queries of different types; and

instructing the first domain-specific voice interface to process the query.

15. The one or more computer readable media of claim 14, storing further computer-executable instructions which, when executed by the processor, cause the processor to perform a method comprising receiving a vocal input to activate a classifier.

16. The one or more computer readable media of claim 14, storing further computer-executable instructions which, when executed by the processor, cause the processor to perform a method comprising identifying context information corresponding to the query, wherein the first domain-specific voice interface is selected based on the context information.

17. An apparatus comprising:

a processor configured to;

receive a query;

parse the query to identify an attribute;

process the query to select a first domain-specific voice interface of a plurality of domain-specific voice interfaces based on the attribute, wherein each of the domain-specific voice interfaces comprises specialized information to process queries of different types; and

instruct the first domain-specific voice interface to process the query.

18. The apparatus of claim 17, further comprising a memory configured to store computer readable instructions, and wherein the processor is configured to execute the computer readable instructions.

19. An apparatus comprising:

means for receiving a query;

means for parsing the query to identify an attribute;

means for processing the query to select a first domain-specific voice interface of a plurality of domain-specific voice interfaces based on the attribute, wherein each of the domain-specific voice interfaces comprises specialized information to process queries of different types; and

means for instructing the first domain-specific voice interface to process the query.

20. A method comprising:

receiving an attribute;

applying a scoring function to generate a utility score for each of a plurality of query response templates based on the attribute;

selecting at least one of the plurality of query response templates based on the utility scores; and

audibly outputting a query response generated from the at least one query response template.

21. The method of claim 20, wherein the attribute is one of a plurality of attributes.

22. The method of claim 21, further comprising ranking the plurality of attributes based on user preferences to assign a respective weight to each of the plurality of attributes.

23. The method of claim 22, wherein the attributes are weighted based on context information.

24. The method of claim 20, further comprising prompting a user to input a subsequent query.

25. The method of claim 20, further comprising identifying an in-domain action corresponding to a first utility score.

26. The method of claim 25, further comprising performing the in-domain action.

27. The method of claim 25, further comprising identifying a cross-domain action associated with the in-domain action.

28. The method of claim 27, further comprising handing over processing to a domain-specific voice interface to perform the cross-domain action.

29. The method of claim 28, further comprising receiving a result of the cross-domain action from the domain-specific voice interface.

30. One or more computer readable media storing computer-executable instructions which, when executed by a processor, cause the processor to perform a method comprising:

receiving an attribute;

applying a scoring function to generate a utility score for each of a plurality of query response templates based on the attribute;

selecting at least one of the plurality of query response templates based on the utility scores; and

audibly outputting a query response generated from the at least one query response template.

31. The one or more computer readable media of claim 30, storing further computer-executable instructions which, when executed by the processor, cause the processor to perform a method comprising ranking the attribute relative to a plurality of attributes based on user preferences to assign a respective weight to each of the plurality of attributes.

32. The one or more computer readable media of claim 30, storing further computer-executable instructions which, when executed by the processor, cause the processor to perform a method comprising prompting a user to input a subsequent query.

33. The one or more computer readable media of claim 30, storing further computer-executable instructions which, when executed by the processor, cause the processor to perform a method comprising identifying an in-domain action corresponding to a first utility score.

34. The one or more computer readable media of claim 33, storing further computer-executable instructions which, when executed by the processor, cause the processor to perform a method comprising performing the in-domain action.

35. The one or more computer readable media of claim 33, storing further computer-executable instructions which, when executed by the processor, cause the processor to perform a method comprising identifying a cross-domain action associated with the in-domain action.

36. The one or more computer readable media of claim 35, storing further computer-executable instructions which, when executed by the processor, cause the processor to perform a method comprising handing over processing to a domain-specific voice interface to perform the cross-domain action.

37. The one or more computer readable media of claim 36, storing further computer-executable instructions which, when executed by the processor, cause the processor to perform a method comprising receiving a result of the cross-domain action from the domain-specific voice interface.

38. An apparatus comprising:

a processor configured to;

receive an attribute;

apply a scoring function to generate a utility score for each of a plurality of query response templates based on the attribute;

select at least one of the plurality of query response templates based on the utility scores; and

audibly output a query response generated from the at least one query response template.

39. The apparatus of claim 38, further comprising a memory configured to store computer readable instructions, and wherein the processor is configured to execute the computer readable instructions.

40. An apparatus comprising:

means for receiving an attribute;

means for applying a scoring function to generate a utility score for each of a plurality of query response templates based on the attribute;

means for selecting at least one of the plurality of query response templates based on the utility scores; and

means for audibly outputting a query response generated from the at least one query response template.