Methods and systems for managing adaptation data

• US 9,899,040 B2
• Filed: 10/26/2012
• Issued: 02/20/2018
• 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.
• Primary Examiner(s): Neway, Samuel G
• Application Number:
  US13/662,125
• Publication Number:
  US 20130325454A1
• Time in Patent Office: 1,943 Days
• Field of Search: 704200-504
• 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 method implemented using at least one computer processor, the method comprising:

retrieving 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 involved in a speech-facilitated transaction with the particular party; and

updating the adaptation data during the speech-facilitated transaction including at least;

receiving from the target device during the speech-facilitated transaction an indication that interpretation of speech data using the adaptation data has taken more than a specified amount of time,

obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time, and

facilitating transmission of the one or more updates to the target device prior to completion of the speech-facilitated transaction.

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

retrieving adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party and is derived from at least one previous speech-facilitated transaction involving the particular party.

3. The method of claim 1, wherein said retrieving adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party comprises:

retrieving adaptation data, wherein the adaptation data includes data linking pronunciation of one or more phonemes of the particular party to one or more concepts.

4. The method of claim 1, further comprising:

obtaining a reference to a location of the adaptation data.

5. The method of claim 1, wherein said retrieving adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party comprises:

retrieving adaptation data, wherein the adaptation data includes a pronunciation dictionary of the particular party.

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

retrieving adaptation data, wherein the adaptation data includes a word frequency table that reflects word usage of the particular party.

7. The method of claim 1, wherein said facilitating transmission of the adaptation data to a target device involved in a speech-facilitated transaction with 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 with the target device.

8. The method of claim 7, 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 with the target device 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 with the target device.

9. The method of claim 1, wherein said facilitating transmission of the adaptation data to a target device involved in a speech-facilitated transaction with 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.

10. The method of claim 1, wherein said facilitating transmission of the adaptation data to a target device involved in a speech-facilitated transaction with the particular party comprises:

facilitating transmission of the adaptation data to a target device in response to an indication received from a device associated with the particular party of a speech-facilitated transaction of the particular party with the target device.

11. The method of claim 1, wherein said retrieving adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party comprises:

retrieving adaptation data, wherein the adaptation data is correlated to an accent of the particular party.

12. The method of claim 1, wherein the facilitating transmission of the one or more updates to the target device prior to completion of the speech-facilitated transaction comprises:

facilitating transmission of the one or more updates to the target device prior to completion of the speech-facilitated transaction, in response to a request from the target device.

13. The method of claim 1, wherein said updating the adaptation data during the speech-facilitated transaction comprises:

updating the adaptation data during the speech-facilitated transaction after at least one word is spoken.

14. The method of claim 1, further comprising:

determining whether to update the adaptation data after an end of the speech-facilitated transaction at least partly based on a result of at least a portion of the speech-facilitated transaction.

15. The method of claim 1, wherein the receiving from the target device during the speech-facilitated transaction an indication that interpretation of speech data using the adaptation data has taken more than a specified amount of time comprises:

receiving from the target device during the speech-facilitated transaction an indication that interpretation of speech data using the adaptation data has taken more than a specified amount of time and an indication that at least a portion of the speech-facilitated transaction was unsuccessful.

16. The method of claim 15, wherein said receiving from the target device during the speech-facilitated transaction an indication that interpretation of speech data using the adaptation data has taken more than a specified amount of time and an indication that at least a portion of the speech-facilitated transaction was unsuccessful comprises:

receiving from the target device during the speech-facilitated transaction an indication that interpretation of speech data using the adaptation data has taken more than a specified amount of time and an indication that at least a portion of the speech data was unsuccessfully interpreted.

17. The method of claim 1, further comprising:

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

18. The method of claim 17, wherein said receiving an indication that at least a portion of the speech-facilitated transaction was unsuccessful comprises:

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

19. The method of claim 1, further comprising:

receiving a pronunciation of one or more words spoken by the particular party during the speech-facilitated transaction.

20. The method of claim 1, further comprising:

receiving a table of one or more words interpreted during the speech-facilitated transaction and a pronunciation of the one or more words by the particular party.

21. The method of claim 1, further comprising:

receiving the one or more updates from a further device; and

updating the adaptation data based on the received update data.

22. The method of claim 1, further comprising:

receiving an indication that the speech-facilitated transaction is moving too quickly for speech to be fully processed; and

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

23. The method of claim 1, further comprising:

receiving a result of a first portion of the speech-facilitated transaction during the speech-facilitated transaction.

24. The method of claim 1, wherein said obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time comprises:

changing an algorithm of the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time.

25. The method of claim 1, wherein said obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time comprises:

modifying at least one parameter of at least one algorithm of the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time.

26. The method of claim 1, wherein the obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time comprises:

modifying a pronunciation dictionary of the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time.

27. The method of claim 1, wherein the obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time comprises:

adding one or more words to a pronunciation dictionary of the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time.

28. The method of claim 1, wherein the obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time comprises:

substituting a pronunciation dictionary of the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time.

29. The method of claim 1, wherein the obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time comprises:

modifying a path of a path selection algorithm of the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time.

32. The method of claim 1, wherein the retrieving adaptation data, wherein the adaptation data is correlated to at least one aspect of speech of a particular party comprises:

retrieving adaptation data, wherein the adaptation data includes one or more pronunciation algorithms correlated to at least one aspect of speech of a particular party.

33. The method of claim 1, wherein the obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time comprises:

changing a pronunciation algorithm of the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time and an error rate that is above a threshold amount.

34. The method of claim 1, wherein the facilitating transmission of the adaptation data to a target device involved in a speech-facilitated transaction with the particular party comprises:

facilitating transmission of the adaptation data from a personal device associated with the particular party to a target device involved in a speech-facilitated transaction with the particular party.

35. The method of claim 1, wherein the obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time comprises:

obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time and an indication that one or more words have been repeated a specified number of times.

36. The method of claim 1, wherein the obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time comprises:

obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time and in response to a negative result of at least a portion of the speech-facilitated transaction.

37. The method of claim 1, wherein the obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time comprises:

obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time and in response to a negative result of recognition of one specific word.

30. A system comprising:

means for retrieving 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 involved in a speech-facilitated transaction with the particular party; and

means for updating the adaptation data during the speech-facilitated transaction including at least;

receiving from the target device during the speech-facilitated transaction an indication that interpretation of speech data using the adaptation data has taken more than a specified amount of time,

obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time, and

facilitating transmission of the one or more updates to the target device prior to completion of the speech-facilitated transaction.

31. A system comprising:

at least one computing device; and

one or more instructions stored in media that program the at least one computing device to execute operations including at least;

retrieving 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 involved in a speech-facilitated transaction with the particular party; and

updating the adaptation data during the speech-facilitated transaction including at least;

receiving from the target device during the speech-facilitated transaction an indication that interpretation of speech data using the adaptation data has taken more than a specified amount of time,

obtaining one or more updates to the adaptation data at least partly in response to the indication that interpretation of the speech data using the adaptation data has taken more than the specified amount of time, and

facilitating transmission of the one or more updates to the target device prior to completion of the speech-facilitated transaction.