METHODS AND SYSTEMS FOR MANAGING ADAPTATION DATA

• US 20130325454A1
• Filed: 10/26/2012
• Published: 12/05/2013
• Est. Priority Date: 05/31/2012
• Status: Active Grant

• Current Assignee: Elwha LLC (Intellectual Ventures LLC)
• Original Assignee: Elwha LLC (Intellectual Ventures LLC)
• Inventors: Levien, Royce A., Lord, Richard T., Lord, Robert W., Malamud, Mark A.
• Granted Patent: US 9,899,040 B2
• Time in Patent Office: Days
• US Class Current: 704/201
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 99/00 Subject matter not provided for in other groups of this subclass

Abstract

Computationally implemented methods and systems include managing adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party, facilitating transmission of the adaptation data to a target device, in response to an indicator related to a speech-facilitated transaction of a particular party, wherein the adaptation data is correlated to at least one aspect of speech of the particular party, and determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction In addition to the foregoing, other aspects are described in the claims, drawings, and text.

Claims

1. A computationally-implemented method, comprising:

managing adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party;

facilitating transmission of the adaptation data to a target device, in response to an indicator related to a speech-facilitated transaction of a particular party, wherein the adaptation data is correlated to at least one aspect of speech of the particular party; and

determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction.

2. The computationally-implemented method of claim 1, wherein said managing adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party comprises:

managing adaptation data, wherein the adaptation data is correlated to at least one previous speech-facilitated transaction by the particular party.

6. The computationally-implemented method of claim 1, wherein said managing adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party comprises:

managing adaptation data comprising data linking pronunciation of one or more phonemes by the particular party to one or more concepts.

7. The computationally-implemented method of claim 1, wherein said managing adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party comprises:

obtaining a reference to a location of adaptation data; and

providing the location of the adaptation data at particular intervals.

8. The computationally-implemented method of claim 1, wherein said managing adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party comprises:

obtaining a reference to a location of adaptation data; and

providing the location of the adaptation data upon request.

11. The computationally-implemented method of claim 1, wherein said facilitating transmission of the adaptation data to a target device, in response to an indicator related to a speech-facilitated transaction of a particular party, wherein the adaptation data is correlated to at least one aspect of speech of the particular party comprises:

transmitting a pronunciation dictionary to a target device, in response to an indicator related to a speech-facilitated transaction of a particular party, wherein the adaptation data is correlated to at least one aspect of speech of the particular party.

12. The computationally-implemented method of claim 1, wherein said facilitating transmission of the adaptation data to a target device, in response to an indicator related to a speech-facilitated transaction of a particular party, wherein the adaptation data is correlated to at least one aspect of speech of the particular party comprises:

transmitting a set of instructions for replacing a word frequency table with a modified word frequency table that reflects the particular party'"'"'s word usage to a target device, in response to an indicator related to a speech-facilitated transaction of a particular party, wherein the adaptation data is correlated to at least one aspect of speech of the particular party.

14. The computationally-implemented method of claim 1, wherein said facilitating transmission of the adaptation data to a target device, in response to an indicator related to a speech-facilitated transaction of a particular party, wherein the adaptation data is correlated to at least one aspect of speech of the particular party comprises:

facilitating transmission of the adaptation data to a target device, in response to an indication that the particular party intends to conduct a speech-facilitated transaction, wherein the adaptation data is correlated to at least one aspect of speech of the particular party.

15. The computationally-implemented method of claim 14, wherein said facilitating transmission of the adaptation data to a target device, in response to an indication that the particular party intends to conduct a speech-facilitated transaction, wherein the adaptation data is correlated to at least one aspect of speech of the particular party comprises:

facilitating transmission of the adaptation data to a target device, in response to an indication received from the target device that the particular party intends to conduct a speech-facilitated transaction, wherein the adaptation data is correlated to at least one aspect of speech of the particular party.

17. The computationally-implemented method of claim 15, wherein said facilitating transmission of the adaptation data to a target device, in response to an indication received from the target device that the particular party intends to conduct a speech-facilitated transaction, wherein the adaptation data is correlated to at least one aspect of speech of the particular party comprises:

facilitating transmission of the adaptation data to a target device, in response to an indication that the particular party is speaking to the target device.

19. The computationally-implemented method of claim 14, wherein said facilitating transmission of the adaptation data to a target device, in response to an indication that the particular party intends to conduct a speech-facilitated transaction, wherein the adaptation data is correlated to at least one aspect of speech of the particular party comprises:

facilitating transmission of the adaptation data to a target device, in response to an indication received from a particular device associated with the particular party that the particular party intends to conduct a speech-facilitated transaction, wherein the adaptation data is correlated to at least one aspect of speech of the particular party.

20. The computationally-implemented method of claim 1, wherein said facilitating transmission of the adaptation data to a target device, in response to an indicator related to a speech-facilitated transaction of a particular party, wherein the adaptation data is correlated to at least one aspect of speech of the particular party comprises:

transmitting first adaptation data correlated to a first aspect of speech of the particular party to the target device; and

transmitting second adaptation data correlated to a second aspect of speech of the particular party to the target device, prior to completion of the speech-facilitated transaction of the particular party.

21. The computationally-implemented method of claim 20, wherein said transmitting first adaptation data correlated to a first aspect of speech of the particular party to the target device comprises:

transmitting first adaptation data correlated to an accent of the particular party to the target device.

27. The computationally-implemented method of claim 20, wherein said transmitting first adaptation data correlated to a first aspect of speech of the particular party to the target device comprises:

transmitting first adaptation data based on previous speech-facilitated transactions by members of a group having at least one trait in common with the particular party.

28. The computationally-implemented method of claim 27, wherein said transmitting first adaptation data based on previous speech-facilitated transactions by members of a group having at least one trait in common with the particular party comprises:

transmitting first adaptation data based on previous speech-facilitated transactions by members of a group originating from a same geographic area as the particular party.

29. The computationally-implemented method of claim 20, wherein said transmitting second adaptation data correlated to a second aspect of speech of the particular party to the target device, prior to completion of the speech-facilitated transaction of the particular party comprises:

transmitting second adaptation data correlated to a second aspect of speech of the particular party to the target device, prior to completion of the speech-facilitated transaction of the particular party, in response to a request from the target device.

34. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

determining not to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction.

36. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

determining whether to update the adaptation data, said determination at least partly based on a result of a beginning portion of the speech-facilitated transaction.

37. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

determining whether to update the adaptation data, wherein the speech-facilitated transaction comprises a first sentence and a second sentence, and said determination occurs after the first sentence and prior to the second sentence.

38. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

determining whether to update the adaptation data, said determination made prior to completion of the speech-facilitated transaction.

39. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

determining whether to update the adaptation data, said determination made after at least one word is spoken in the speech-facilitated transaction.

40. The computationally-implemented method of claim 39, wherein said determining whether to update the adaptation data, said determination made after at least one word is spoken in the speech-facilitated transaction comprises:

determining whether to update the adaptation data, said determination occurring prior to a particular word being spoken in the speech facilitated transaction.

41. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

receiving a result of at least a portion of the speech-facilitated transaction; and

determining whether to update the adaptation data, said determination at least partly based on the received result.

43. The computationally-implemented method of claim 41, wherein said receiving a result of at least a portion of the speech-facilitated transaction comprises:

receiving a result of at least a portion of the speech-facilitated transaction from the particular party.

44. The computationally-implemented method of claim 43, wherein said receiving a result of at least a portion of the speech-facilitated transaction from the particular party comprises:

receiving a result of at least a portion of the speech-facilitated transaction from the particular party interacting with a particular device configured to manage the adaptation data.

46. The computationally-implemented method of claim 43, wherein said receiving a result of at least a portion of the speech-facilitated transaction from the particular party interacting with a particular device configured to manage the adaptation data comprises:

receiving a result of at least a portion of the speech-facilitated transaction from the particular party providing feedback to the particular device after an end of the speech-facilitated transaction.

47. The computationally-implemented method of claim 41, wherein said receiving a result of at least a portion of the speech-facilitated transaction comprises:

receiving an indication that the at least a portion of the speech-facilitated transaction was unsuccessful.

48. The computationally-implemented method of claim 47, wherein said receiving an indication that the at least a portion of the speech-facilitated transaction was unsuccessful comprises:

receiving an indication that the at least a portion of the speech facilitated transaction was not successfully interpreted by the target device.

49. The computationally-implemented method of claim 41, wherein said receiving a result of at least a portion of the speech-facilitated transaction comprises:

receiving an indication that the target device has determined that the at least a portion of the speech-facilitated transaction was unsuccessful.

51. The computationally-implemented method of claim 49, wherein said receiving a result of at least a portion of the speech-facilitated transaction comprises:

receiving an indication that the target device interpreted the at least a portion of the speech-facilitated transaction with a confidence rate below a particular threshold.

55. The computationally-implemented method of claim 41, wherein said receiving a result of at least a portion of the speech-facilitated transaction comprises:

receiving a result of at least a portion of the speech-facilitated transaction, said result comprising a pronunciation of one or more words spoken by the particular party during the speech-facilitated transaction.

57. The computationally-implemented method of claim 41, wherein said receiving a result of at least a portion of the speech-facilitated transaction comprises:

receiving a result of at least a portion of the speech-facilitated transaction, said result comprising a table of one or more words interpreted during the speech-facilitated transaction and a pronunciation of the one or more interpreted words by the particular party.

58. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

receiving a result of the at least a portion of the speech-facilitated transaction;

updating the adaptation data based on the result of the at least a portion of the speech-facilitated transaction; and

transmitting updated adaptation data to the target device prior to completion of the speech-facilitated transaction.

59. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

receiving a result of the at least a portion of the speech-facilitated transaction; and

updating the adaptation data based on the result of the at least a portion of the speech-facilitated transaction.

61. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

receiving update data from a further device regarding updating the adaptation data; and

updating the adaptation data based on the received update data.

62. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

receiving a result of the at least a portion of the speech-facilitated transaction;

transmitting the result of the at least a portion of the speech-facilitated transaction to a further location; and

receiving, from the further location, update data comprising an indication of whether to update the adaptation data.

63. The computationally-implemented method of claim 62, wherein said transmitting the result of the at least a portion of the speech-facilitated transaction to a further location comprises:

transmitting the result of the at least a portion of the speech-facilitated transaction to a further location at which the adaptation data is also stored.

64. The computationally-implemented method of claim 62, wherein said receiving, from the further location, update data comprising an indication of whether to update the adaptation data comprises:

receiving, from the further location, update data further comprising instructions for updating the adaptation data.

66. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

receiving a result of the at least a portion of the speech-facilitated transaction, wherein the result indicates that the speech-facilitated transaction is moving too quickly for speech to be fully processed; and

facilitating presentation of a visual or audible indicator to the particular party that indicates for the particular party to slow down the speech-facilitated transaction.

67. The computationally-implemented method of claim 1, wherein said determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction comprises:

receiving a result of a first portion of the speech-facilitated transaction;

updating the adaptation data at least partly based on the result of the first portion of the speech-facilitated transaction; and

transmitting updated adaptation data to the target device, said updated adaptation data configured to be applied by the target device prior to completion of a second portion of the speech-facilitated transaction.

68. The computationally-implemented method of claim 67, wherein said updating the adaptation data at least partly based on the result of the first portion of the speech-facilitated transaction comprises:

changing an algorithm of the adaptation data at least partly based on the result of the first portion of the speech-facilitated transaction.

69. The computationally-implemented method of claim 68, wherein said changing an algorithm of the adaptation data at least partly based on the result of the first portion of the speech-facilitated transaction comprises:

modifying at least one parameter of at least one algorithm of the adaptation data at least partly based on the result of the first portion of the speech-facilitated transaction.

71. The computationally-implemented method of claim 67, wherein said updating the adaptation data at least partly based on the result of the first portion of the speech-facilitated transaction comprises:

modifying a pronunciation dictionary that is part of the adaptation data, said modifying at least partly based on the result of the first portion of the speech-facilitated transaction.

72. The computationally-implemented method of claim 71, wherein said modifying a pronunciation dictionary that is part of the adaptation data, said modifying at least partly based on the result of the first portion of the speech-facilitated transaction comprises:

adding one or more words to the pronunciation dictionary that is part of the adaptation data, said modifying at least partly based on the result of the first portion of the speech-facilitated transaction.

74. The computationally-implemented method of claim 71, wherein said modifying a pronunciation dictionary that is part of the adaptation data, said modifying at least partly based on the result of the first portion of the speech-facilitated transaction comprises:

substituting, in the adaptation data, a new pronunciation dictionary for a previous pronunciation dictionary that was part of the adaptation data and previously applied in interpreting the first portion of the speech-facilitated transaction.

75. The computationally-implemented method of claim 67, wherein said updating the adaptation data at least partly based on the result of the first portion of the speech-facilitated transaction comprises:

modifying a path of a path selection algorithm of the adaptation data, said modifying at least partly based on the result of the first portion of the speech-facilitated transaction.

3. (canceled)

4. (canceled)

5. (canceled)

9. (canceled)

10. (canceled)

13. (canceled)

16. (canceled)

18. (canceled)

22. (canceled)

23. (canceled)

24. (canceled)

25. (canceled)

26. (canceled)

30. (canceled)

31. (canceled)

32. (canceled)

33. (canceled)

35. (canceled)

42. (canceled)

45. (canceled)

50. (canceled)

52. (canceled)

53. (canceled)

54. (canceled)

56. (canceled)

60. (canceled)

65. (canceled)

70. (canceled)

73. (canceled)

76. (canceled)

77. (canceled)

78. (canceled)

79. (canceled)

80. (canceled)

81. (canceled)

82. A computationally-implemented system, comprising

means for managing adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party;

means for facilitating transmission of the adaptation data to a target device, in response to an indicator related to a speech-facilitated transaction of a particular party, wherein the adaptation data is correlated to at least one aspect of speech of the particular party;

means for determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction.

83-161. -161. (canceled)

162. A device defined by a computational language comprising:

one or more interchained physical machines ordered for managing adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party;

one or more interchained physical machines ordered for facilitating transmission of the adaptation data to a target device, in response to an indicator related to a speech-facilitated transaction of a particular party, wherein the adaptation data is correlated to at least one aspect of speech of the particular party; and

one or more interchained physical machines ordered for determining whether to update the adaptation data, said determination at least partly based on a result of at least a portion of the speech-facilitated transaction.