Personalized voice applications in an information assistance service

• US 20060023849A1
• Filed: 09/30/2004
• Published: 02/02/2006
• Est. Priority Date: 07/30/2004
• Status: Active Grant

• Current Assignee: Grape Technology Group Incorporated (KGB)
• Original Assignee: Grape Technology Group Incorporated (KGB)
• Inventors: Miller, John S., Timmins, Timothy A.
• Granted Patent: US 7,991,129 B2
• Time in Patent Office: Days
• US Class Current: 379/88.190
• CPC Class Codes: H04M 3/42068 where the identifier is used to access a profile
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

To personalize a voice information delivery service, e.g., directory assistance, a voice email service, stock quotation service and other information assistance services, a user is afforded an option to customize automated voices/speeches to deliver information to him/her. The automated voices/speeches may be customized for different services and functions, and/or in terms of urgency, context, etc. of the information to be voice-delivered. In an illustrative embodiment, the user'"'"'s voice preferences for voice information deliveries are recorded in a user profile, which are represented by sets of speech characterizing parameters, respectively, based on which a text-to-speech (TTS) engine reads given text information to the user in the corresponding preferred voices/speeches.

Claims

1. A method for providing a service for delivering information over a communications network, comprising:

maintaining a record identifiable by data representing a user, the record containing a plurality of voice preferences for delivering information in automated voice, the plurality of voice preferences being associated with different aspects of the service, respectively;

receiving a call from the user, along with the data, through the communications network, the call including a request for the service for delivering selected information;

determining an aspect of the service in response to the request;

retrieving the record based at least on the received data;

determining from the record a voice preference associated with the aspect of the service; and

generating an automated voice in accordance with the voice preference to deliver the selected information.

2. The method of claim 1, wherein the aspect of the service includes delivering the selected information in a particular context.

3. The method of claim 2, wherein the particular context concerns freshness of the selected information.

4. The method of claim 2, wherein the particular context concerns an urgency of delivering the selected information.

5. The method of claim 1 wherein the service includes an information assistance service.

6. The method of claim 1, wherein the aspect of the service includes a function of the service.

7. The method of claim 6, wherein the function includes a voice email service function.

8. The method of claim 7, wherein the aspect of the service includes delivering, in the automated voice, information concerning at least one email message having a particular status.

9. The method of claim 8, wherein the particular status is determined by obtaining a first time stamp associated with the at least one email message received in an email account, and comparing the first time stamp with a second time stamp, associated with a previous call by the user for the service.

10. The method of claim 8, wherein the particular status is determined by obtaining an identifier of the at least one email message, and comparing the identifier against a list of identifiers of email messages.

11. The method of claim 8, wherein the particular status concerns an urgency of the at least one email message.

12. The method of claim 6, wherein the function includes a stock quotation service function.

13. The method of claim 12, wherein the aspect of the service includes delivering, in the automated voice, information concerning a stock in a particular status.

14. The method of claim 13, wherein the particular status concerns a change in the stock'"'"'s price.

15. The method of claim 1, wherein the communications network includes a telephone network.

16. The method of claim 15, wherein the data representing the user includes an automatic number identifier (ANI) associated with the call.

17. The method of claim 1, wherein the data representing the user includes a voiceprint derived from an utterance of the user.

18. A method for providing a service for delivering information via voice media, comprising:

allowing a user to select a plurality of sets of parameters for characterizing automated voices to be used in the service, respectively, the plurality of sets of parameters being associated with respective ones of aspects of the service;

storing the plurality of sets of parameters which are identifiable by data representing the user;

receiving a communication from the user, the communication including a request involving an aspect of the service;

obtaining the data representing the user during the communication;

identifying the plurality of sets of parameters based at least on the data; and

in response to the request, delivering selected information to the user in an automated voice characterized by one of the plurality of sets of parameters which is associated with the aspect of the service.

19. The method of claim 18, wherein the automated voices are generated using a text-to-speech conversion mechanism.

20. The method of claim 18, wherein the set of parameters associated with the aspect of the service affects at least one of voice quality, intonation, accent, rhythm, pitch, gender of a voice, and tempo of a delivery of the selected information in the automated voice.

21. The method of claim 18, wherein the aspect of the service includes delivering the selected information in a particular context.

22. The method of claim 21 wherein the particular context concerns freshness of the selected information.

23. The method of claim 21, wherein the particular context concerns an urgency of delivering the selected information.

24. The method of claim 18 wherein the service includes an information assistance service.

25. The method of claim 18, wherein the aspect of the service includes a function of the service.

26. The method of claim 25, wherein the function includes a voice email service function.

27. The method of claim 25, wherein the function includes a stock quotation service function.

28. The method of claim 18, wherein the communication includes a telephonic communication.

29. The method of claim 28, wherein the data representing the user includes an ANI associated with the telephonic communication.

30. The method of claim 18, wherein the data representing the user includes a voiceprint derived from an utterance of the user.

31. A system for providing a service for delivering information over a communications network, comprising:

storage for maintaining a record identifiable by data representing a user, the record containing a plurality of voice preferences for delivering information in automated voice, the plurality of voice preferences being associated with different aspects of the service, respectively;

an interface for receiving a call from the user, along with the data, through the communications network, the call including a request for the service for delivering selected information, an aspect of the service being determined in response to the request, the record being retrieved based at least on the received data;

a processor programmed to determine from the record a voice preference associated with the aspect of the service; and

a server for generating an automated voice in accordance with the voice preference to deliver the selected information.

32. The system of claim 31, wherein the aspect of the service includes delivering the selected information in a particular context.

33. The system of claim 32, wherein the particular context concerns freshness of the selected information.

34. The system of claim 32, wherein the particular context concerns an urgency of delivering the selected information.

35. The system of claim 31 wherein the service includes an information assistance service.

36. The system of claim 31, wherein the aspect of the service includes a function of the service.

37. The system of claim 36, wherein the function includes a voice email service function.

38. The system of claim 37, wherein the aspect of the service includes delivering, in the automated voice, information concerning at least one email message having a particular status.

39. The system of claim 38, wherein the particular status is determined by obtaining a first time stamp associated with the at least one email message received in an email account, and comparing the first time stamp with a second time stamp, associated with a previous call by the user for the service.

40. The system of claim 38, wherein the particular status is determined by obtaining an identifier of the at least one email message, and comparing the identifier against a list of identifiers of email messages.

41. The system of claim 38, wherein the particular status concerns an urgency of the at least one email message.

42. The system of claim 36, wherein the function includes a stock quotation service function.

43. The system of claim 42, wherein the aspect of the service includes delivering, in the automated voice, information concerning a stock in a particular status.

44. The system of claim 43, wherein the particular status concerns a change in the stock'"'"'s price.

45. The system of claim 31, wherein the communications network includes a telephone network.

46. The system of claim 45, wherein the data representing the user includes an ANI associated with the call.

47. The system of claim 31, wherein the data representing the user includes a voiceprint derived from an utterance of the user.

48. A system for providing a service for delivering information via voice media, comprising:

a mechanism for allowing a user to select a plurality of sets of parameters for characterizing automated voices to be used in the service, respectively, the plurality of sets of parameters being associated with respective ones of aspects of the service;

storage for storing the plurality of sets of parameters which are identifiable by data representing the user;

an interface for receiving a communication from the user, the communication including a request involving an aspect of the service, the data representing the user being obtained during the communication;

a processor programmed to identify the plurality of sets of parameters based at least on the data; and

a server responsive to the request for delivering selected information to the user in an automated voice characterized by one of the plurality of sets of parameters which is associated with the aspect of the service.

49. The system of claim 48, wherein the automated voices are generated using a text-to-speech conversion mechanism.

50. The system of claim 48, wherein the set of parameters associated with the aspect of the service affects at least one of voice quality, intonation, accent, rhythm, pitch, gender of a voice, and tempo of a delivery of the selected information in the automated voice.

51. The system of claim 48, wherein the aspect of the service includes delivering the selected information in a particular context.

52. The system of claim 51 wherein the particular context concerns freshness of the selected information.

53. The system of claim 51, wherein the particular context concerns an urgency of delivering the selected information.

54. The system of claim 48 wherein the service includes an information assistance service.

55. The system of claim 48, wherein the aspect of the service includes a function of the service.

56. The system of claim 55, wherein the function includes a voice email service function.

57. The system of claim 55, wherein the function includes a stock quotation service function.

58. The system of claim 48, wherein the communication includes a telephonic communication.

59. The system of claim 58, wherein the data representing the user includes an ANI associated with the telephonic communication.

60. The system of claim 48, wherein the data representing the user includes a voiceprint derived from an utterance of the user.