Constrained automatic speech recognition for more reliable speech-to-text conversion

• US 20070266100A1
• Filed: 04/18/2006
• Published: 11/15/2007
• Est. Priority Date: 04/18/2006
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Pirzada, Shamim
• Granted Patent: US 7,929,672 B2
• Time in Patent Office: Days
• US Class Current: 709/206
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]

Abstract

A device and method are provided which preferably establish cross-modal communications and allow telephony users and text-based users, such as Instant Messaging (IM) users, to communicate with each other. The device may include a processor that receives a text message preferably comprising a query, a keyword, and one or more responses to the query. The processor preferably generates a vocabulary containing the one or more responses provided in the text message. The method preferably includes receiving a text message comprising a query, a keyword, and one or more responses to the query. The method may further include converting the text message into an audible message, sending the audible message to a telephony user, receiving an audible response from the telephony user, and generating text from the audible response. The method may further include generating a vocabulary comprising the one or more responses provided in the text message.

Claims

1. A network device, comprising:

a processor adapted to receive a text message comprising a query, a keyword, and one or more responses to the query;

a speech synthesizer adapted to convert the text message into an audible message; and

a speech recognizer adapted to receive an audible response and generate text from the audible response.

2. The network device of claim 1, wherein the processor is further adapted to generate a vocabulary comprising the one or more responses provided in the text message.

3. The network device of claim 2, wherein the speech recognizer is further adapted to compare the audible response with the one or more responses in the vocabulary.

4. The network device of claim 3, wherein the speech recognizer is further adapted to generate the text from the audible response when the comparison yields a match among the one or more responses in the vocabulary.

5. The network device of claim 2, wherein contents of the vocabulary change according to the one or more responses provided in the received text message.

6. The network device of claim 1, further comprising:

a keyword spotter adapted to recognize the keyword provided in the received text message.

7. The network device of claim 6, wherein the processor is further adapted to generate a vocabulary comprising words occurring after the recognized keyword.

8. The network device of claim 7, wherein the processor is further adapted to generate a vocabulary ignoring words occurring before the recognized keyword.

9. The network device of claim 1, further comprising:

an interface adapted to receive a request for connection from a telephony user.

10. The network device of claim 9, wherein the processor is adapted to notify a text-based user that the request for connection was received.

11. The network device of claim 10, wherein the processor is further adapted to process the request for connection according to instructions from the text-based user.

12. The network device of claim 1, wherein the text message is received from an instant messaging (IM) user.

13. A method, comprising:

receiving a text message comprising a query, a keyword, and one or more responses to the query;

converting the text message into an audible message;

audibly sending the audible message to a telephony user;

receiving an audible response from the telephony user; and

generating text from the audible response.

14. The method of claim 13, further comprising:

generating a vocabulary comprising the one or more responses provided in the received text message.

15. The method of claim 14, further comprising:

comparing the audible response from the telephony user to the one or more responses in the generated vocabulary.

16. The method of claim 15, further comprising:

generating text corresponding to the audible response when the comparison yields a match among the one or more responses in the generated vocabulary.

17. The method of claim 13, further comprising:

recognizing the keyword provided in the received text message.

18. The method of claim 17, further comprising:

generating a vocabulary comprising words occurring after the recognized keyword.

19. The method of claim 17, further comprising:

generating a vocabulary ignoring words occurring before the recognized keyword.

20. The method of claim 13, further comprising:

receiving from the telephony user a request for connection with a text-based user; and

notifying the text-based user of the request for connection received from the telephony user.

21. The method of claim 20, further comprising:

transferring the telephony user to a voicemail account of the text-based user when the text-based user declines the request for connection.

22. The method of claim 20, further comprising:

notifying the telephony user that the text-based user will communicate with the telephony user using text messaging.

23. A network device, comprising:

means for receiving a text message comprising a query, a keyword, and one or more responses to the query;

means for converting the text message into an audible message;

means for audibly sending the audible message to a telephony user;

means for receiving an audible response from the telephony user; and

means for generating text from the audible response.

24. The network device of claim 23, further comprising:

means for generating a vocabulary comprising the one or more responses provided in the received text message.

25. The network device of claim 23, further comprising:

means for comparing the audible response from the telephony user to the one or more responses in the generated vocabulary.

26. The network device of claim 23, further comprising:

means for recognizing the keyword provided in the text message.

27. The network device of claim 26, further comprising:

means for generating a vocabulary comprising words occurring after the recognized keyword.

28. The network device of claim 26, further comprising:

means for generating a vocabulary ignoring words occurring before the recognized keyword.

29. The network device of claim 23, further comprising:

means for receiving from the telephony user a request for connection with a text-based user; and

means for notifying the text-based user of the request for connection received from the telephony user.

30. The network device of claim 29, further comprising:

means for transferring the telephony user to a voicemail account of the text-based user.

31. The network device of claim 29, further comprising:

means for notifying the telephony user that the text-based user will communicate with the telephony user using text messaging.

32. An article of computer-readable medium containing instructions that, when executed, cause a computer to:

receive a text message comprising a query, a keyword, and one or more responses to the query;

convert the text message into an audible message; and

receive an audible response and generate text from the audible response.

33. The article of claim 32, further comprising instructions that, when executed, cause the computer to generate a vocabulary comprising the one or more responses provided in the text message.

34. The article of claim 33, wherein the instructions that, when executed, cause the computer to compare the audible response with the one or more responses in the vocabulary.

35. The article of claim 34, wherein the instructions that, when executed, cause the computer to generate the text corresponding to the audible response when the comparison yields a match among the one or more responses in the vocabulary.

36. The article of claim 32, wherein the instructions that, when executed, further cause the computer to recognize the keyword provided in the received text message.

37. The article of claim 36, further comprising instructions that, when executed, cause the computer to generate a vocabulary comprising words occurring after the recognized keyword.

38. The article of claim 36, further comprising instructions that, when executed, cause the computer to generate a vocabulary ignoring words occurring before the recognized keyword.

39. The article of claim 32, further comprising instructions that, when executed, cause the computer to receive a request for connection from a telephony user.

40. The article of claim 39, further comprising instructions that, when executed, cause the computer to notify a text-based user that the request for connection was received.

41. The article of claim 40, further comprising instructions that, when executed, cause the computer to process the request for connection according to instructions from the text-based user.