METHODS AND SYSTEMS FOR SPEECH ADAPTATION DATA

• US 20130325450A1
• Filed: 09/10/2012
• 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 10,431,235 B2
• Time in Patent Office: Days
• US Class Current: 704/201
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence

Abstract

Computationally implemented methods and systems include detecting speech data related to a speech-facilitated transaction, acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party, obtaining a destination of one or more of the adaptation data and the speech data, and transmitting one or more of the speech data and the adaptation data to the acquired destination. In addition to the foregoing, other aspects are described in the claims, drawings, and text.

Claims

1. A computationally-implemented method, comprising:

detecting speech data related to a speech-facilitated transaction;

acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party;

obtaining a destination of one or more of the adaptation data and the speech data.

transmitting one or more of the speech data and the adaptation data to the acquired destination.

9. The computationally-implemented method of claim 1, wherein said detecting speech data related to a speech-facilitated transaction comprises:

receiving the adaptation data; and

determining from the reception of the adaptation data that speech data related to a speech-facilitated transaction is being transferred.

11. The computationally-implemented method of claim 1, wherein said detecting speech data related to a speech-facilitated transaction comprises:

receiving a signal requesting initiation of one or more operations in preparation for a speech-facilitated transaction.

18. The computationally-implemented method of claim 1, wherein said detecting speech data related to a speech-facilitated transaction comprises:

detecting that a device is transmitting speech data; and

collecting data regarding the detected device that is transmitting speech data.

23. The computationally-implemented method of claim 1, wherein said detecting speech data related to a speech-facilitated transaction comprises:

receiving speech data comprising previously recorded speech by the particular party, and a timestamp corresponding to a time at which the speech data was recorded.

30. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring data comprising one or more words and corresponding pronunciations of the one or more words that is at least partly based on at least one speech interaction of the particular party, said at least one speech interaction of the particular party discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

35. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party that occurred that occurred at a different time and a different location than a speech interaction prior to a speech interaction that generated the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

36. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring at least a portion of adaptation data that is at least partly based on at least one speech interaction of the particular party that occurred prior to a speech interaction that generated the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

39. The computationally-implemented method of claim 36, wherein said acquiring at least a portion of adaptation data that is at least partly based on at least one speech interaction of the particular party that occurred prior to a speech interaction that generated the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party comprises:

receiving, from a communication network provider, adaptation data that is at least partly based on at least one speech interaction of the particular party that occurred prior to a speech interaction that generated the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

40. The computationally-implemented method of claim 39, wherein said receiving, from a communication network provider, adaptation data that is at least partly based on at least one speech interaction of the particular party that occurred prior to a speech interaction that generated the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party comprises:

receiving, from a communication network provider, adaptation data that is at least partly based on at least one speech interaction of the particular party that occurred prior to a speech interaction that generated the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party and previously transmitted to the communication network provider.

43. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring adaptation data in response to a detection of a particular condition, said adaptation data at least partly based on at least one speech interaction of the particular party that occurred prior to a speech interaction that generated the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

49. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring adaptation data from a further device, said adaptation data at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

50. The computationally-implemented method of claim 49, wherein said acquiring adaptation data from a further device, said adaptation data at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party comprises:

acquiring adaptation data from a further device, said adaptation data originating at the further device and at least partly based on least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

55. The computationally-implemented method of claim 49, wherein said acquiring adaptation data from a further device, said adaptation data at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party comprises:

acquiring adaptation data from a further device, said adaptation data received by the further device from the particular device, and said adaptation data at least partly based on least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

56. The computationally-implemented method of claim 49, wherein said acquiring adaptation data from a further device, said adaptation data at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party comprises:

acquiring adaptation data, from a further device, said adaptation data comprising instructions for modifying a pronunciation dictionary, and said adaptation data at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

61. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party with a particular type of device, said at least one speech interaction discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

62. The computationally-implemented method of claim 61, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party with a particular type of device, said at least one speech interaction discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party comprises:

acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party with the particular type of device that is a same type of device as a target device configured to receive the speech data, said at least one speech interaction discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

67. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party with the particular device, said at least one speech interaction is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party.

68. The computationally-implemented method of claim 67, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party with the particular device, said at least one speech interaction is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the particular device associated with the particular party comprises:

acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party with a cellular telephone device, said at least one speech interaction is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the cellular telephone device associated with the particular party.

69. The computationally-implemented method of claim 68, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party with a cellular telephone device, said at least one speech interaction is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on the cellular telephone device associated with the particular party comprises:

acquiring adaptation data that is at least partly based on at least one telephone conversation carried out using the cellular telephone device, said at least one telephone conversation is different than speech that is part of the detected speech data, wherein at least a portion of the adaptation data has been stored on the cellular telephone device associated with the particular party.

71. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party that used one or more same utterances as speech used in the detected speech data, said one or more same utterances spoken to a different device than a target device to which the detected speech data is directed.

77. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring a location of one or more instructions for modifying one or more portions of a speech recognition component of a target device, said instructions at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party.

79. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data is stored on the particular device associated with the particular party.

80. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data is temporarily stored on the particular device associated with the particular party until it is deposited at a remote server.

81. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring adaptation data that is at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data was transmitted from a first device to a second device using the particular device associated with the particular party as a conduit configured to facilitate the transmission.

83. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

acquiring adaptation data from a remote location, said adaptation data at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data was transmitted to the remote location from the particular device associated with the particular party.

84. The computationally-implemented method of claim 1, wherein said acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party comprises:

receiving adaptation data that is at least partly based on at least one speech interaction of the particular party that is discrete from the detected speech data; and

adding further data to the received adaptation data.

86. The computationally-implemented method of claim 84, wherein said adding further data to the received adaptation data comprises:

adding header data identifying an entity that received the adaptation data.

88. The computationally-implemented method of claim 1, wherein said obtaining a destination of one or more of the adaptation data and the speech data comprises:

receiving data regarding a target device configured to process the speech data.

89. The computationally-implemented method of claim 88, wherein said receiving data regarding a target device configured to process the speech data comprises:

receiving data comprising an address of a target device configured to process the speech data.

91. The computationally-implemented method of claim 1, wherein said obtaining a destination of one or more of the adaptation data and the speech data comprises:

determining a location of a target device that is a destination of one or more of the adaptation data and the speech data.

92. The computationally-implemented method of claim 91, wherein said determining a location of a target device that is a destination of one or more of the adaptation data and the speech data comprises:

determining a location on a network of a target device that is a destination of one or more of the adaptation data and the speech data.

95. The computationally-implemented method of claim 1, wherein said obtaining a destination of one or more of the adaptation data and the speech data comprises:

determining a program component that is configured to perform processing on one or more of the adaptation data and the speech data.

96. The computationally-implemented method of claim 1, wherein said obtaining a destination of one or more of the adaptation data and the speech data comprises:

determining a program component that is a destination of one or more of the adaptation data and the speech data.

97. The computationally-implemented method of claim 96, wherein said determining a program component that is a destination of one or more of the adaptation data and the speech data comprises:

selecting between an operating system component and an application component as a destination of one or more of the adaptation data and the speech data.

98. The computationally-implemented method of claim 1, wherein said obtaining a destination of one or more of the adaptation data and the speech data comprises:

acquiring data regarding one or more other devices configured to process detected speech data; and

determining a destination of the detected speech data based on the data regarding one or more other devices configured to process detected speech data.

99. The computationally-implemented method of claim 98, wherein said acquiring data regarding one or more other devices configured to process detected speech data comprises:

detecting one or more other devices configured to process detected speech data.

103. The computationally-implemented method of claim 98, wherein said acquiring data regarding one or more other devices configured to process detected speech data comprises:

detecting one or more other devices configured to process detected speech data;

transmitting a signal to the one or more other devices requesting data regarding a capability of the one or more other devices configured to process detected speech data; and

receiving data regarding the capability of the one or more other devices configured to process detected speech data.

104. The computationally-implemented method of claim 98, wherein said acquiring data regarding one or more other devices configured to process detected speech data comprises:

detecting one or more other devices configured to process detected speech data; and

receiving data regarding a capability of the detected one or more other devices configured to process detected speech data.

105. The computationally-implemented method of claim 104, wherein said receiving data regarding a capability of the detected one or more other devices configured to process detected speech data comprises:

receiving data regarding the capability of the one or more other devices configured to process detected speech data from a further device that is not one of the one or more other devices.

106. The computationally-implemented method of claim 105, wherein said receiving data regarding the capability of the one or more other devices configured to process detected speech data from a further device that is not one of the one or more other devices comprises:

receiving data regarding the capability of the one or more other devices configured to process detected speech data from a further device that is configured to communicate on a same network as the one or more other devices.

107. The computationally-implemented method of claim 105, wherein said receiving data regarding the capability of the one or more other devices configured to process detected speech data from a further device that is not one of the one or more other devices comprises:

receiving data regarding the capability of the one or more other devices configured to process detected speech data from a further device that is at least partially controlled by a same entity that controls at least one of the one or more other devices.

108. The computationally-implemented method of claim 105, wherein said receiving data regarding the capability of the one or more other devices configured to process detected speech data from a further device that is not one of the one or more other devices comprises:

receiving data regarding the capability of the one or more other devices configured to process detected speech data from a further device that is configured to provide one or more services to at least one of the one or more other devices.

109. The computationally-implemented method of claim 1, wherein said obtaining a destination of one or more of the adaptation data and the speech data comprises:

acquiring other device data regarding a capability of one or more other devices configured to process detected speech data; and

determining a destination of the one or more of the adaptation data and the speech data at least partly based on the acquired other device data.

112. The computationally-implemented method of claim 109, wherein said acquiring other device data regarding a capability of one or more other devices configured to process detected speech data comprises:

acquiring other device data regarding a speech data processing capability of one or more detected other devices.

117. The computationally-implemented method of claim 1, wherein said transmitting one or more of the speech data and the adaptation data to the acquired destination comprises:

transmitting one or more of the speech data and the adaptation data to a target device acquired as the destination.

119. The computationally-implemented method of claim 117, wherein said transmitting one or more of the speech data and the adaptation data to a target device acquired as the destination comprises:

transmitting the detected speech data to the target device acquired as the destination.

120. The computationally-implemented method of claim 119, wherein said transmitting the detected speech data to the target device acquired as the destination comprises:

converting detected speech data into data that is recognizable by the target device; and

transmitting the converted detected speech data to the target device acquired as the destination.

121. The computationally-implemented method of claim 120, wherein said converting detected speech data into data that is recognizable by the target device comprises:

converting detected speech data into data that is recognizable by the target device, wherein said detected speech data is unrecognizable to the target device prior to conversion.

122. The computationally-implemented method of claim 120, wherein said converting detected speech data into data that is recognizable by the target device comprises:

converting detected speech data into data that is recognizable by a target device, wherein the target device is configured to process the converted data more quickly than the target device is configured to process speech data.

124. The computationally-implemented method of claim 122, wherein said converting detected speech data into data that is recognizable by a target device, wherein the target device is configured to process the converted data more quickly than the target device is configured to process speech data comprises:

converting detected speech data into data that is recognizable by a target device, based on feedback received from the target device indicating that the target device is configured to process the converted data more quickly than the target device is configured to process speech data.

128. The computationally-implemented method of claim 1, wherein said transmitting one or more of the speech data and the adaptation data to the acquired destination comprises:

transmitting one or more of the speech data and the adaptation data to a particular component of a target device.

132. The computationally-implemented method of claim 1, wherein said transmitting one or more of the speech data and the adaptation data to the acquired destination comprises:

transmitting one or more of the speech data and the adaptation data to a further device, said one or more of the speech data and the adaptation data configured to be processed by a target device.

2. (canceled)

3. (canceled)

4. (canceled)

5. (canceled)

6. (canceled)

7. (canceled)

8. (canceled)

10. (canceled)

12. (canceled)

13. (canceled)

14. (canceled)

15. (canceled)

16. (canceled)

17. (canceled)

19. (canceled)

20. (canceled)

21. (canceled)

22. (canceled)

24. (canceled)

25. (canceled)

26. (canceled)

27. (canceled)

28. (canceled)

29. (canceled)

31. (canceled)

32. (canceled)

33. (canceled)

34. (canceled)

37. (canceled)

38. (canceled)

41. (canceled)

42. (canceled)

44. (canceled)

45. (canceled)

46. (canceled)

47. (canceled)

48. (canceled)

51. (canceled)

52. (canceled)

53. (canceled)

54. (canceled)

57. (canceled)

58. (canceled)

59. (canceled)

60. (canceled)

63. (canceled)

64. (canceled)

65. (canceled)

66. (canceled)

70. (canceled)

72. (canceled)

73. (canceled)

74. (canceled)

75. (canceled)

76. (canceled)

78. (canceled)

82. (canceled)

85. (canceled)

87. (canceled)

90. (canceled)

93. (canceled)

94. (canceled)

100. (canceled)

101. (canceled)

102. (canceled)

110. (canceled)

111. (canceled)

113. (canceled)

114. (canceled)

115. (canceled)

116. (canceled)

118. (canceled)

123. (canceled)

125. (canceled)

126. (canceled)

127. (canceled)

129. (canceled)

130. (canceled)

131. (canceled)

133-266. -266. (canceled)

267. A computationally-implemented system, comprising

circuitry for detecting speech data related to a speech-facilitated transaction;

circuitry for acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party;

circuitry for obtaining a destination of one or more of the adaptation data and the speech data; and

circuitry for transmitting one or more of the speech data and the adaptation data to the acquired destination.

268. (canceled)

269. A device defined by a computational language comprising:

one or more interchained physical machines ordered for detecting speech data related to a speech-facilitated transaction;

one or more interchained physical machines ordered for acquiring adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the detected speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party;

one or more interchained physical machines ordered for obtaining a destination of one or more of the adaptation data and the speech data; and

one or more interchained physical machines ordered for transmitting one or more of the speech data and the adaptation data to the acquired destination.