SPEECH RECOGNITION ADAPTATION SYSTEMS BASED ON ADAPTATION DATA

• US 20130325448A1
• Filed: 08/01/2012
• 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 9,620,128 B2
• Time in Patent Office: Days
• US Class Current: 704/201
• 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 15/07 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 19/00 Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis in musical instruments G10H

Abstract

The instant application includes computationally-implemented systems and methods that include managing adaptation data, the adaptation data is at least partly based on at least one speech interaction of a particular party, facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, such that the adaptation data is to be applied to the target device to assist in execution of the speech-facilitated transaction, and facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and to be used in determining whether to modify the adaptation data. 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 at least partly based on at least one speech interaction of a particular party;

facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction;

facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

9. The computationally-implemented method of claim 1, wherein said managing adaptation data, wherein the adaptation data is at least partly based on at least one speech interaction of a particular party comprises:

storing a reference to a location of adaptation data; and

testing an availability of the adaptation data at the location specified by the stored reference.

11. The computationally-implemented method of claim 9, wherein said testing an availability of the adaptation data at the location specified by the stored reference comprises:

testing the availability of the adaptation data by comparing a size of the adaptation data located at the referenced location with an expected value of the size of the adaptation data.

13. The computationally-implemented method of claim 1, wherein said managing adaptation data, wherein the adaptation data is at least partly based on at least one speech interaction of a particular party comprises:

determining a location configured to store the adaptation data; and

facilitating transmission of the adaptation data to the determined location.

29. The computationally-implemented method of claim 1, wherein said managing adaptation data, wherein the adaptation data is at least partly based on at least one speech interaction of a particular party comprises:

managing adaptation data, wherein the adaptation data is at least partly based on at least one speech interaction of a particular party with a particular device.

39. The computationally-implemented method of claim 1, wherein said managing adaptation data, wherein the adaptation data is at least partly based on at least one speech interaction of a particular party comprises:

managing adaptation data comprising a training set of audio data and corresponding transcript data.

52. The computationally-implemented method of claim 1, wherein said facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction comprises:

transmitting adaptation data to a target device when there is indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction.

57. The computationally-implemented method of claim 1, wherein said facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction comprises:

broadcasting availability data indicating that adaptation data is available to be received, said adaptation data configured to be received by the target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction.

62. The computationally-implemented method of claim 1, wherein said facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction comprises:

facilitating transmission of the adaptation data to the target device upon receipt of an indication from the target device of a status of the speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction.

64. The computationally-implemented method of claim 62, wherein said facilitating transmission of the adaptation data to the target device upon receipt of an indication from the target device of a status of the speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction comprises:

facilitating transmission of the adaptation data to the target device upon receipt of an indication from the target device of a particular number of attempts to receive a particular type of response from the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction.

66. The computationally-implemented method of claim 62, wherein said facilitating transmission of the adaptation data to the target device upon receipt of an indication from the target device of a status of the speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction comprises:

facilitating transmission of the adaptation data to the target device upon receipt of an indication from the target device that a speech recognition component of the target device is processing speech of the particular party below a particular success rate.

70. The computationally-implemented method of claim 62, wherein said facilitating transmission of the adaptation data to the target device upon receipt of an indication from the target device of a status of the speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction comprises:

facilitating transmission of the adaptation data to the target device upon receipt of an indication from the target device that a speech recognition component of the target device has a confidence rate below a particular threshold.

88. The computationally-implemented method of claim 1, wherein said facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction comprises:

facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to improve performance in processing speech received during execution of the speech-facilitated transaction.

89. The computationally-implemented method of claim 88, wherein said facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to improve performance in processing speech received during execution of the speech-facilitated transaction comprises:

facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to improve speed in processing speech received during execution of the speech-facilitated transaction.

90. The computationally-implemented method of claim 1, wherein said facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction comprises:

facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to process speech received during execution of the speech-facilitated transaction.

92. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

generating adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

93. The computationally-implemented method of claim 92, wherein said generating adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

generating adaptation result data that is based on a result of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

94. The computationally-implemented method of claim 93, wherein said generating adaptation result data that is based on a result of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

observing the speech-facilitated transaction;

creating adaptation result data based on a result of the observed speech-facilitated transaction; and

determining whether to modify the adaptation data based on the created adaptation result data.

100. The computationally-implemented method of claim 94, wherein said creating adaptation result data based on a result of the observed speech-facilitated transaction comprises:

creating adaptation result data based on a measured statistic of the observed speech-facilitated transaction.

101. The computationally-implemented method of claim 100, wherein said creating adaptation result data based on a measured statistic of the observed speech-facilitated transaction comprises:

creating adaptation result data based on an error rate of the observed speech-facilitated transaction.

102. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

receiving adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

104. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

receiving data regarding the speech-facilitated transaction; and

processing the received data into adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

107. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

receiving adaptation result data from a further device, said adaptation result data based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

108. The computationally-implemented method of claim 107, wherein said receiving adaptation result data from a further device, said adaptation result data based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

receiving adaptation result data from a further device observing the speech-facilitated transaction, said adaptation result data based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

109. The computationally-implemented method of claim 107, wherein said receiving adaptation result data from a further device, said adaptation result data based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

receiving adaptation result data from a further device configured to communicate with the target device, said adaptation result data based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

110. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

facilitating acquisition of adaptation result data that is based on particular party feedback regarding the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

111. The computationally-implemented method of claim 110, wherein said facilitating acquisition of adaptation result data that is based on particular party feedback regarding the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

facilitating acquisition of adaptation result data that is based on particular party feedback given to the target device regarding the speech-facilitated transaction, and configured to be used in determining whether to modify the adaptation data.

112. The computationally-implemented method of claim 110, wherein said facilitating acquisition of adaptation result data that is based on particular party feedback regarding the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

requesting particular party feedback regarding the speech-facilitated transaction;

receiving particular party feedback regarding the speech-facilitated transaction as adaptation result data; and

determining whether to modify the adaptation data based at least in part on the received adaptation result data.

113. The computationally-implemented method of claim 112, wherein said requesting particular party feedback regarding the speech-facilitated transaction comprises:

requesting that the target device collect feedback from the particular party.

117. The computationally-implemented method of claim 112, wherein said receiving particular party feedback regarding the speech-facilitated transaction as adaptation result data comprises:

receiving survey result data from the particular party regarding the speech-facilitated transaction as adaptation result data.

119. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

presenting a request for the particular party to complete a survey regarding the speech-facilitated transaction.

120. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

collecting a result of a survey regarding the speech-facilitated transaction as adaptation result data configured to be used in determining whether to modify the adaptation data.

122. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

facilitating acquisition of adaptation result data that is based on analysis of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

123. The computationally-implemented method of claim 122, wherein said facilitating acquisition of adaptation result data that is based on analysis of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

facilitating acquisition of analysis performed by the target device of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

124. The computationally-implemented method of claim 122, wherein said facilitating acquisition of adaptation result data that is based on analysis of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

facilitating acquisition of adaptation result data that is based on analysis of a recognition rate of one or more words used in the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

129. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

facilitating acquisition of adaptation result data that comprises pronunciation information based on one or more words spoken during the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

130. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

facilitating acquisition of adaptation result data that comprises frequency information for one or more words used in the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

131. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

facilitating acquisition of adaptation result data that comprises a phonemic transcription of one or more words used in the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

132. The computationally-implemented method of claim 131, wherein said facilitating acquisition of adaptation result data that comprises a phonemic transcription of one or more words used in the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

facilitating acquisition of adaptation result data that comprises a user-specific phonemic transcription of one or more words used in the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

135. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

acquiring adaptation result data based on at least one aspect of a completed portion of the speech-facilitated transaction, prior to completion of the speech-facilitated transaction;

determining a performance of a processing of the completed portion of the speech-facilitated transaction at least partly based on the adaptation result data; and

modifying the adaptation data based on the determined performance.

137. The computationally-implemented method of claim 1, wherein said facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data comprises:

receiving adaptation result data based on at least one aspect of the speech-facilitated transaction;

determining whether to modify the adaptation data based on the received adaptation result data; and

modifying the adaptation data based on the adaptation result data.

139. The computationally-implemented method of claim 137, wherein said determining whether to modify the adaptation data based on the received adaptation result data comprises:

determining, for at least one portion of the speech-facilitated transaction, whether the adaptation data improved performance of a speech recognition component processing the speech of the speech-facilitated transaction.

2. (canceled)

3. (canceled)

4. (canceled)

5. (canceled)

6. (canceled)

7. (canceled)

8. (canceled)

10. (canceled)

12. (canceled)

14. (canceled)

15. (canceled)

16. (canceled)

17. (canceled)

18. (canceled)

19. (canceled)

20. (canceled)

21. (canceled)

22. (canceled)

23. (canceled)

24. (canceled)

25. (canceled)

26. (canceled)

27. (canceled)

28. (canceled)

30. (canceled)

31. (canceled)

32. (canceled)

33. (canceled)

34. (canceled)

35. (canceled)

36. (canceled)

37. (canceled)

38. (canceled)

40. (canceled)

41. (canceled)

42. (canceled)

43. (canceled)

44. (canceled)

45. (canceled)

46. (canceled)

47. (canceled)

48. (canceled)

49. (canceled)

50. (canceled)

51. (canceled)

53. (canceled)

54. (canceled)

55. (canceled)

56. (canceled)

58. (canceled)

59. (canceled)

60. (canceled)

61. (canceled)

63. (canceled)

65. (canceled)

67. (canceled)

68. (canceled)

69. (canceled)

71. (canceled)

72. (canceled)

73. (canceled)

74. (canceled)

75. (canceled)

76. (canceled)

77. (canceled)

78. (canceled)

79. (canceled)

80. (canceled)

81. (canceled)

82. (canceled)

83. (canceled)

84. (canceled)

85. (canceled)

86. (canceled)

87. (canceled)

91. (canceled)

95. (canceled)

96. (canceled)

97. (canceled)

98. (canceled)

99. (canceled)

103. (canceled)

105. (canceled)

106. (canceled)

114. (canceled)

115. (canceled)

116. (canceled)

118. (canceled)

121. (canceled)

125. (canceled)

126. (canceled)

127. (canceled)

128. (canceled)

133. (canceled)

134. (canceled)

136. (canceled)

138. (canceled)

140. (canceled)

141. (canceled)

142. A computationally-implemented system, comprising:

means for managing adaptation data, wherein the adaptation data is at least partly based on at least one speech interaction of a particular party;

means for facilitating transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction; and

means for facilitating acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

143-284. -284. (canceled)

285. A device specified by computational language, comprising:

one or more interchained groups of ordered matter arranged to manage adaptation data, wherein the adaptation data is at least partly based on at least one speech interaction of a particular party;

one or more interchained groups of ordered matter arranged to facilitate transmission of the adaptation data to a target device when there is an indication of a speech-facilitated transaction between the target device and the particular party, wherein the adaptation data is configured to be applied to the target device to assist in execution of the speech-facilitated transaction; and

one or more interchained groups of ordered matter arranged to facilitate acquisition of adaptation result data that is based on at least one aspect of the speech-facilitated transaction and configured to be used in determining whether to modify the adaptation data.

286. (canceled)