Method and system for providing texts for voice requests

• US 20010037198A1
• Filed: 01/31/2001
• Published: 11/01/2001
• Est. Priority Date: 02/01/2000
• Status: Abandoned Application

• Current Assignee: Intovoice Corporation
• Original Assignee: Into Voice Corporation
• Inventors: Chen, I-Cheng
• Application Number:
  US09/775,044
• Publication Number:
  US 20010037198A1
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Methods and systems for providing texts for voice requests are disclosed. According to one embodiment, an audio signal is received from a caller. The audio signal is speech-recognized to produce a spoken text that contains one or more key words referring to a piece of information interesting to the caller. The key words are processed with a local search data set to formulate an identifier linking to the information that may be locally or remotely obtainable. As a result, a caller is relieved from an otherwise strict requirement that the caller has to speak every single word of an identifier of a piece of information.

Claims

1. A method for matching a spoken text, the method comprising:

receiving the spoken text from a voice recognition system that converts a voice signal to the spoken text;

looking up for one or more words that match the spoken text, wherein the one or more words are derived from an identifier of a piece of information provided from a server is coupled over a data network; and

retrieving the information either from the server or a local database with respect to the identifier as a query to the server or the database.

2. The method of

claim 1

, wherein the server is remotely located and provides the information upon receiving a request including the identifier.

3. The method of

claim 2

further comprising:

generating the request to include the identifier; and

sending out the request over the data network.

4. The method of

claim 3

, wherein the data network includes one of (i) the Internet, (ii) the Intranet, (iii) a wireless network, and (iv) a network of a private and a public network.

5. The method of

claim 4

, wherein the voice signal is received from a voice network and input to the voice recognition system.

6. The method of

claim 5

, wherein the voice network includes one or more of a public switched telephone network (PSTN) and a wireless network.

7. The method of

claim 3

, wherein the looking up for one or more words comprises:

receiving the identifier from the server, wherein the identifier contains more than one words;

extracting one or more key words from the identifier; and

archiving the one or more key words in a local searching data set, wherein the local searching data set is remotely separated from the server.

8. The method of

claim 7

, wherein the extracting of the one or more key words from the identifier comprises discarding generic words from the identifier, wherein the generic words can be included in other identifiers.

9. The method of

claim 7

, wherein the extracting of the one or more key words from the identifier further comprises:

computing a histogram of the identifier; and

identifying the generic words and the key words.

10. The method of

claim 1

, wherein the retrieving of the information comprises obtaining the information from the local database if the local database archives a copy of the information, otherwise from the server.

11. A method for matching a spoken text, the method comprising:

receiving a plurality of identifiers, each of the identifiers indicating a piece of information;

identifying generic words and key words from the identifiers; and

organizing the keywords in a structure that can facilitate matching of the spoken text to one of the keywords.

12. The method of

claim 11

further comprising storing the structure in a local database.

13. The method of

claim 12

, wherein the structure is based on a data structure designated from searching through with respect to a query.

14. The method of

claim 13

, wherein the structure is a tree structure, each node of the tree structure being one of the keywords and associated with one or more of the key words that are collectively from one of the identifiers.

15. The method of

claim 11

, wherein each of the identifiers contains one or more words and is selected from a group consisting of a title, a filename, a symbol, an IP address and a short article.

16. The method of

claim 15

, wherein the identifiers are supplied from a server providing information, each of pieces of the information being identified by one of the identifiers.

17. The method of

claim 16

, wherein the server is remotely located over a data network, and the identifiers are provided over the data network.

18. The method of

claim 11

, wherein the identifying of the generic words and the key words comprises:

computing a statistic measurement of the identifiers;

wherein the statistic measurement indicating how often each of the generic words and the key words has respectively occurred in the identifiers; and

classifying the generic words and the key words from the statistic measurement.

19. The method of

claim 18

, wherein the computing of the statistic measurement of the identifiers is computing a histogram of the identifiers.

20. The method of

claim 19

, wherein the classifying of the generic words and the key words comprises:

identifying any marginal words from the identifiers with respect to the histogram;

performing an linguistic analysis of the marginal words to group the marginal words with either the generic words or the key words.

21. A product including computer instructions to be executed in a computing device, the product comprising:

program code for receiving the spoken text from a voice recognition system that converts a voice signal to the spoken text;

program code for looking up for one or more words that match the spoken text, wherein the one or more words are derived from an identifier of a piece of information provided from a server is coupled over a data network; and

program code for retrieving the information either from the server or a local database with respect to the identifier as a query to the server or the database.

22. The product of

claim 21

, wherein the server is remotely located and provides the information upon receiving a request including the identifier.

23. The product of

claim 22

further comprising:

program code for generating the request to include the identifier; and

program code for sending out the request over the data network.

24. The product of

claim 23

, wherein the data network includes one of (i) the Internet, (ii) the Intranet, (iii) a wireless network, and (iv) a network of a private and a public network.

25. The product of

claim 24

, wherein the voice signal is received from a voice network and input to the voice recognition system.

26. The product of

claim 25

, wherein the voice network includes one or more of a public switched telephone network (PSTN) and a wireless network.

27. The product of

claim 23

, wherein the program code for looking up for one or more words comprises:

program code for receiving the identifier from the server, wherein the identifier contains more than one words;

program code for extracting one or more key words from the identifier; and

program code for archiving the one or more key words in a local searching data set, wherein the local searching data set is remotely separated from the server.

28. The product of

claim 27

, wherein the program code for extracting the one or more key words from the identifier comprises discarding generic words from the identifier, wherein the generic words can be included in other identifiers.

29. The product of

claim 27

, wherein the program code for extracting the one or more key words from the identifier further comprises:

program code for computing a histogram of the identifier; and

program code for identifying the generic words and the key words.

30. The product of

claim 21

, wherein the program code for retrieving the information comprises program code for obtaining the information from the local database if the local database archives a copy of the information, otherwise from the server.

31. A product including computer instructions to be executed in a computing device, the product comprising:

program code for receiving a plurality of identifiers, each of the identifiers indicating a piece of information;

program code for identifying generic words and key words from the identifiers; and

program code for organizing the keywords in a structure that can facilitate matching of the spoken text to one of the keywords.

32. The product of

claim 31

further comprising program code for storing the structure in a local database.

33. The product of

claim 32

, wherein the structure is based on a data structure designated from searching through with respect to a query.

34. The product of

claim 33

, wherein the structure is a tree structure, each node of the tree structure being one of the keywords and associated with one or more of the key words that are collectively from one of the identifiers.

35. The product of

claim 31

, wherein each of the identifiers contains one or more words and is selected from a group consisting of a title, a filename, a symbol, an IP address and a short article.

36. The product of

claim 35

, wherein the identifiers are supplied from a server providing information, each of pieces of the information being identified by one of the identifiers.

37. The product of

claim 36

, wherein the server is remotely located over a data network, and the identifiers are provided over the data network.

38. The product of

claim 31

, wherein the program code for identifying of the generic words and the key words comprises:

program code for computing a statistic measurement of the identifiers;

wherein the statistic measurement indicating how often each of the generic words and the key words has respectively occurred in the identifiers; and

program code for classifying the generic words and the key words from the statistic measurement.

39. The product of

claim 38

, wherein the program code for computing the statistic measurement of the identifiers is computing a histogram of the identifiers.

40. The product of

claim 39

, wherein the program code for classifying the generic words and the key words comprises:

program code for identifying any marginal words from the identifiers with respect to the histogram;

program code for performing an linguistic analysis of the marginal words to group the marginal words with either the generic words or the key words.