Apparatus and method for speech recognition data retrieval

• US 20060259302A1
• Filed: 05/13/2005
• Published: 11/16/2006
• Est. Priority Date: 05/13/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Rosen, Kenneth H., Lewis, Steven Hart
• Granted Patent: US 8,751,240 B2
• Time in Patent Office: Days
• US Class Current: 704/255
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

A combination and a method are provided. Automatic speech recognition is performed on a received utterance. A meaning of the utterance is determined based, at least in part, on the recognized speech. At least one query is formed based, at least in part, on the determined meaning of the utterance. The at least one query is sent to at least one searching mechanism to search for an address of at least one web page that satisfies the at least one query.

Claims

1. A method, comprising:

performing automatic speech recognition on a received utterance;

determining a meaning of the utterance based, at least in part, on the recognized speech;

forming at least one query based, at least in part, on the determined meaning of the utterance; and

sending the at least one query to at least one searching mechanism to search for an address of at least one web page that satisfies the query.

2. The method of claim 1, further comprising:

sending results of the at least one query to a party for display.

3. The method of claim 1, wherein the received utterance is from an ongoing call.

4. The method of claim 1, wherein performing automatic speech recognition on a received utterance further comprises:

creating text corresponding to the received utterance.

5. The method of claim 4, wherein determining a meaning of the utterance based, at least in part, on the recognized speech further comprises:

performing spoken language understanding analysis based, at least in part, on the created text to determine the meaning, and

creating an indication of the meaning.

6. The method of claim 5, further comprising:

forming the at least one query based, at least in part, on the indication of the meaning.

7. The method of claim 1, further comprising:

sending one of the at least one query to at least one other searching mechanism configured to search a local or remote data resource.

8. The method of claim 1, wherein the searching mechanism includes a knowledge base of web pages.

9. A combination comprising:

an automatic speech recognizer configured to receive an utterance and convert the utterance to text;

a spoken language understanding component configured to process the text and produce an indication of a meaning of the utterance based, at least in part, on the text; and

at least one search query component configured to process the indication of the meaning and, based at least in part on the indication of the meaning, produce at least one query for a corresponding searching entity that is configured to search for an address of at least one web site that satisfies the at least one query, each of the at least one search query component being further configured to send the at least one query to the corresponding searching entity.

10. The combination of claim 9, further comprising:

a first processing device including the automatic speech recognizer, the spoken language understanding component, and the search query component.

11. The combination of claim 9, further comprising:

a first processing device including the automatic speech recognizer; and

a second processing device including the spoken language understanding component and the search query component, wherein

the first processing device and the second processing device are configured to communicate with each other through a network.

12. The combination of claim 9, further comprising:

a first processing device including the automatic speech recognizer and the search query component; and

a second processing device including the spoken language understanding component, wherein

the first processing device and the second processing device are configured to communicate with each other through a network.

13. The combination of claim 9, further comprising:

a display device configured to display a result of a query performed by the corresponding searching entity.

14. The combination of claim 13, wherein the result of the query includes a link to a web page that satisfies the query.

15. The combination of claim 13, wherein the result of the query includes a description of a web page that satisfies the query.

16. The combination of claim 9, further comprising:

at least one other search query component configured to process the indication of the meaning and, based at least in part on the indication of the meaning, produce at least one query for a corresponding second searching entity to search for a local or remote data resource for information that satisfies the at least one query, each of the at least one other search query component being further configured to send the at least one query to the corresponding second searching entity.

17. A machine-readable medium having instructions for at least one processor recorded thereon, the machine-readable medium comprising:

instructions for performing automatic speech recognition on a received utterance;

instructions for determining a meaning of the utterance based, at least in part, on the recognized speech;

instructions for forming a query based, at least in part, on the determined meaning of the utterance; and

instructions for sending the query to a searching mechanism to search for an address of at least one web page that satisfies the query.

18. The machine-readable medium of claim 17, further comprising:

instructions for sending results of the query to a party for display

19. The machine-readable medium of claim 17, wherein the received utterance is from an ongoing call.

20. The machine-readable medium of claim 17, wherein the instructions for performing automatic speech recognition on a received utterance further comprise:

instructions for creating text corresponding to the received utterance.

21. The machine-readable medium of claim 17, wherein the instructions for determining a meaning of the utterance based, at least in part, on the recognized speech further comprise:

instructions for performing spoken language understanding analysis based, at least in part, on the created text to determine the meaning; and

creating an indication of the meaning.

22. The machine-readable medium of claim 21, further comprising:

instructions for forming the query based, at least in part, on the indication of the meaning.

23. The machine-readable medium of claim 17, wherein the searching mechanism includes a knowledge base of web pages.

24. The machine-readable medium of claim 17, further comprising:

instructions for forming a second query based, at least in part, on the indication of the meaning; and

instructions for sending the second query to a second searching mechanism to search a local or remote data resource for information that satisfies the second query.

25. A combination comprising:

means for converting a received utterance to text;

means for processing the text and, based at least in part on the text, producing an indication of a meaning of the utterance; and

means for processing the indication of the meaning of the utterance and, based at least in part on the indication of the meaning of the utterance, producing a query for a searching entity to search for an address of at least one web site that satisfies the query.

26. The combination of claim 25, further comprising:

means for sending the query to the searching entity via a network.

27. The combination of claim 25, further comprising:

means for receiving a result from the searching entity via the network; and

means for displaying the result to a party during an ongoing call, wherein the received utterance is from the ongoing call.

28. The combination of claim 25, further comprising:

means for automatically logging information related to searching activity.