Personalized system for providing improved understandability of received speech

• US 20020095292A1
• Filed: 01/18/2001
• Published: 07/18/2002
• Est. Priority Date: 01/18/2001
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Mittal, Parul A., Dubey, Pradeep Kumar
• Granted Patent: US 6,823,312 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: G10L 21/06 Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids G10L15/26 takes precedence

Abstract

The present invention provides a method and system for providing improved understandability of received speech characterized in that it includes:

input interface means for capturing received speech signals connected to a speech recognition means for identifying the contents of the received speech connected to one input of a data processing means for performing improvement in understandability,

a user profile storage means connected to another input of said data processing means for providing user specific improvement data, and

an output generation means connected to the output of said data processing means to produce personalized output based on an individual'"'"'s needs.

The instant invention also provides a configured computer program product for carrying out the above method.

Claims

1. A personalized system for providing a service for improving understandability of received speech in accordance with user specific needs characterized in that it includes:

input interface means for capturing received speech signals connected to a speech recognition or speech signal analysis means for identifying the contents of the received speech connected to one input of a data processing means for performing improvement in understandability,

a user profile storage means connected to another input of said data processing means for providing user specific improvement data, and

an output generation means connected to the output of said data processing means to produce personalized output based on an individual'"'"'s needs.

2. The system as claimed in claim 1, wherein said personalized system is online.

3. The system as claimed in claim 1, wherein said speech recognition means is any known speech recognition means.

4. The system as claimed in claim 1, wherein said data processing means is a computing system.

5. The system as claimed in claim 1, wherein said data processing means is a server system in a client server environment.

6. The system as claimed in claim 1, wherein said data processing means is a self-learning system using artificial intelligence or expert system techniques, which improves its performance based on feedback from the users over a period of time and also dynamically updates the users current profiles.

7. The system as claimed in claim 1 wherein said speech recognition means, speech signal analysis means, data processing means and output generation means individually or collectively improve performance automatically with time, use, improvement in technology, enhancement in design or changes in user profile and provides the improved service without the need to make any changes to the user equipment.

8. The system as claimed in claim 1, wherein said output generation means is a means for generating speech from the electrical signal received from said data processing means

9. The system as claimed in claim 1, wherein said output generation means is a display means for generating visual output for the user

10. The system as claimed in claim 1, wherein said output generation means is a vibro-tactile de vice for generating output for the user in tactile form.

11. The system as claimed in claim 1 further includes means for the user to register with said system.

12. The system as claimed in claim 1, wherein said data processing means includes means to perform the understandability improvement with reference to the context of the received speech.

13. The system as claimed in claim 1, wherein said data processing means includes means to translate the received speech from one language to another.

14. The system as claimed in claim 1, wherein said data processing means includes means for computing the data partially on the client and partially on the server.

15. The system as claimed in claim 1, wherein said data processing means includes the means for the user to specify or modify the stored individual profile.

16. The system as claimed in claim 1, wherein the user identifies himself by a userid at the beginning of each transaction.

17. The system as claimed in claim 1, wherein said data processing means includes a default profile means in the absence of specific user profiles.

18. The system as claimed in claim 1 wherein the system allows the user to specify a usage environment or conversation context at the beginning of each transaction.

19. The system as claimed in claim 1, wherein data processing means includes use of a specified context to limit the vocabulary for speech recognition and enhance system performance.

20. The system as claimed in claim 1, wherein the data processing means includes means for sending advertisement to the user in between or after the outputs.

21. The system as claimed in claim 1, wherein said input interface means and/or output generation means are speech enabled wireless application protocol devices.

22. The system as claimed in claim 1, wherein said output generation means supports a graphical display interface.

23. A system as claimed in claim 1 wherein said input interface is a microphone of a regular telephone device, land line or mobile and the output generation means is a speaker of said phone device, the speaker is meant only for single user and the microphone is meant for the user'"'"'s surroundings.

24. The system as claimed in claim 1, wherein said output generation means is a speaker of a telephone device, which could be plugged in the user'"'"'s ears using a wire or wireless medium namely, Bluetooth.

25. The system as claimed in claim 1, wherein said output generation means is a display panel on a watch strap connected to the phone device through a wire or wireless medium.

26. The system as claimed in claim 1 wherein said input interface means captures the speech from the users environment and provides a feedback to the user after improving understandability.

27. The system as claimed in claim 1, wherein said output generation means automatically tracks the conversational context using already known techniques and multimedia devices.

28. The system as claimed in claim 1, wherein the input interface receives speech input from more than one source and provides improved understandability for all the received speech signals in accordance with the user profile.

29. The system as claimed in claim 1 further comprising pricing mechanism which is based on the quality of service and on fixed amount per unit time of use or variable amount per time of use or down payment for certain period of use or combination of down payment and pay per use or combination of down payment and unit time of use including period for free use.

30. A personalized method for providing a service for improving understandability of received speech in accordance with user specific needs characterized in that it includes:

capturing received speech signals,

identifying the contents of said received speech through speech recognition or speech signal analysis,

processing the data for performing improvement in understandability,

providing user specific improvement data by a user profile storage, and

generating personalized output based on an individual'"'"'s needs.

31. The method as claimed in claim 30, wherein said method is executed online.

32. The method as claimed in claim 30, wherein speech recognition is by any known speech recognition methods.

33. The method as claimed in claim 30, wherein said processing of data is done by computation.

34. The method as claimed in claim 30, wherein said processing of data is done by a server in a client server environment.

35. The method as claimed in claim 30, wherein said processing of data is done by a self-learning using artificial intelligence or expert method technique, which improves its performance based on feedback from the users over a period of time and also dynamically updates the user'"'"'s current profiles.

36. The method as claimed in claim 30, wherein said speech recognition, speech signal analysis, data processing and output generation individually or collectively improve performance automatically with time, use, improvement in technology, enhancement in design o r changes in user profile and provides the improved service without the need to make any changes to the user equipment.

37. The method as claimed in claim 30, wherein said generation of personalized output is by generating speech from the electrical signal received from said processing of data.

38. The method as claimed in claim 30, wherein said generation of personalized output is displayed for generating visual output for the user.

39. The method as claimed in claim 30, wherein said generation of personalized output is in a vibro-tactile form for generating output for the user in tactile form.

40. The method as claimed in claim 30 further includes registering of the user with said method.

41. The method as claimed in claim 30, wherein said processing of data includes performing the understandability improvement with reference to the context of the received speech.

42. The method as claimed in claim 30, wherein said processing of data includes translation of the received speech from one language to another.

43. The method as claimed in claim 30, wherein said processing of data includes computing the data partially on the client and partially on the server.

44. The method as claimed in claim 30, wherein said processing of data includes specifying or modifying the stored individual profile for the user.

45. The method as claimed in claim 30, wherein the user identifies himself by a userid at the beginning of each transaction.

46. The method as claimed in claim 30, wherein said processing of data includes a default profile in the absence of specific user profiles.

47. The method as claimed in claim 30, wherein the method allows the user to specify a usage environment or conversation context at the beginning of each transaction.

48. The method as claimed in claim 30, wherein said processing of data includes use of a specified context to limit the vocabulary for speech recognition and enhance system performance.

49. The method as claimed in claim 30, wherein said processing of data includes sending advertisement to the user in between or after the outputs.

50. The method as claimed in claim 30, wherein said capturing of received speech signals and/or generation of personalized output is by use of speech enabled wireless application protocol methods.

51. The method as claimed in claim 30, wherein said generation of personalized output supports a graphical display interface.

52. The method as claimed in claim 30 wherein received speech signals are captured through a microphone of a regular telephone device, land line or mobile and the output is generated through a speaker of said phone device, the speaker is meant only for single user and the microphone is meant for the user'"'"'s surroundings.

53. The method as claimed in claim 30, wherein said generation of personalized output is through a speaker of a telephone device, which could be plugged in the user'"'"'s ears using a wire or wireless medium namely, Bluetooth.

54. The method as claimed in claim 30, wherein said generation of personalized output is through a display panel on a watch strap connected to the phone device through a wire or wireless medium.

55. The method as claimed in claim 30 includes capturing the speech from the user'"'"'s environment and providing a feedback to the user after improving understandability.

56. The method as claimed in claim 30, wherein said generation of personalized output includes automatic tracking of the conversational context using already known techniques and multimedia devices.

57. The method as claimed in claim 30, wherein the speech input is received from more than one source and improved understandability for all the received speech signals is provided in accordance with the user profile.

58. The method as claimed in claim 30 further comprising pricing, which is based on the quality of service and on fixed amount per unit time of use or variable amount per time of use or down payment for certain period of use or combination of down payment and pay per use or combination of down payment and unit time of use including period for free use.

60. The computer program product as claimed in claim 59, wherein said personalized computer program product is online.

61. The computer program product as claimed in claim 59, wherein speech recognition is performed by computer readable program code devices using any known speech recognition techniques.

62. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for processing of data is a computing system.

63. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for processing of data is a server system in a client server environment.

64. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for processing of data is a self-learning system using artificial intelligence or expert method technique, which improves its performance based on feedback from the users over a period of time and also dynamically updates the user'"'"'s current profiles.

65. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for speech recognition, speech signal analysis means, data processing and output generation individually or collectively improve performance automatically with time, use, improvement in technology, enhancement in design or changes in user profile and provides the improved service without the need to make any changes to the user equipment.

66. The computer program product as claimed in claim 59, wherein said computer readable program code means for generating output is configured to generate personalized output for the user in display form.

67. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for generating output is configured for generating personalized output for the user in vibro-tactile form.

68. The computer program product as claimed in claim 59 further includes computer readable program code means configured for the user to register with said computer program product.

69. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for processing of data performs the understandability improvement with reference to the context of the received speech.

70. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for processing of data translates the received speech from one language to another.

71. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for processing of data computes the data partially on the client and partially on the server.

72. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for processing of data specifies or modifies the stored individual profile for the user.

73. The computer program product as claimed in claim 59, wherein the user identifies himself by a userid at the beginning of each transaction.

74. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for processing of data includes a default profile in the absence of specific user profiles.

75. The computer program product as claimed in claim 59, wherein the computer program product allows the user to specify a usage environment or conversation context at the beginning of each transaction.

76. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for processing of data uses a specified context to limit the vocabulary for speech recognition and enhance system performance.

77. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for processing of data sends advertisement to the user in between or after the outputs.

78. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for capturing received speech signals and/or generation of personalized output is by use of speech enabled wireless application protocol methods.

79. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for generating personalized output supports a graphical display interface.

80. The computer program product as claimed in claim 59 wherein said computer readable program code means configured for capturing received speech signals is a microphone of a regular telephone device, land line or mobile and the computer readable program code means configured for generating output is a speaker of said phone device, the speaker is meant only for single user and the microphone is meant for the user'"'"'s surroundings.

81. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for generating personalized output is through a speaker of a telephone device, which could be plugged in the user'"'"'s ears using a wire or wireless medium namely, Bluetooth.

82. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for generating personalized output is through a display panel on a watch strap connected to the phone device through a wire or wireless medium.

83. The computer program product as claimed in claim 59, wherein said computer readable program code means configured for generating personalized output includes tracking conversational text automatically using already known techniques and multimedia devices.

84. The computer program product as claimed in claim 59, wherein the computer readable program code means configured for capturing received speech signals receives speech input from more than one source and provides improved understandability for all the received speech signals in accordance with the user profile.

85. The computer program product as claimed in claim 59 further comprising computer readable program code means configured for pricing, which is based on the quality of service and on fixed amount per unit time of use or variable amount per time of use or down payment for certain period of use or combination of down payment and pay per use or combination of down payment and unit time of use including period for free use.

59. A personalized computer program product comprising computer readable program code stored on computer readable storage medium embodied therein for providing a service for improving understandability of received speech in accordance with user specific needs comprising:

computer readable program code means configured for capturing received speech signals,

computer readable program code means configured for identifying the contents of said received speech through speech recognition or speech signal analysis,

computer readable program code means configured for processing the data for performing improvement in understandability,

computer readable program code means configured for providing user specific improvement data by a user profile storage, and

computer readable program code means configured for generating personalized output based on an individual'"'"'s needs.