Speech recognition adaptation systems based on adaptation data

• US 9,899,026 B2
• Filed: 08/01/2012
• 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:
  US13/564,651
• Publication Number:
  US 20140039882A1
• Time in Patent Office: 2,029 Days
• 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 15/07 to the speaker
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

The instant application includes computationally-implemented systems and methods that 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, wherein the adaptation data is configured to be applied to the target device to assist in execution of a speech-facilitated transaction, facilitating reception of adaptation result data that is based on at least one aspect of the speech-facilitated transaction between the particular party and the target device, determining whether to modify the adaptation data at least partly based on the adaptation result data, and facilitating transmission of at least a portion of modified adaptation data to a receiving device. In addition to the foregoing, other aspects are described in the claims, drawings, and text.

Claims

1. A system comprising:

circuitry configured to receive at least one property of a target device from the target device, the at least one property including at least a type of the target device;

circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type;

circuitry configured to transmit the subset of the adaptation data to the target device;

circuitry configured to receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data; and

circuitry configured to determine whether to modify the subset of the adaptation data that includes pronunciation data for the one or more words that have been linked to the type of the target device, at least partly based on the result data.

2. The system of claim 1, further comprising:

circuitry configured to manage the adaptation data associated with speech of the particular party.

3. The system of claim 1, further comprising:

circuitry configured to selectively provide authorization to view the adaptation data.

4. The system of claim 1, wherein said circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type comprises:

circuitry configured to select a subset of adaptation data associated with a spoken language of a particular party based at least partly on the type of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type.

5. The system of claim 1, wherein said circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type comprises:

circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device being a home device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type.

6. The system of claim 1, wherein said circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type comprises:

circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device and a processing capacity of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type.

7. The system of claim 1, wherein said circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type comprises:

circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device and a speech processing capability of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type.

8. The system of claim 1, further comprising:

circuitry configured to present the subset of the adaptation data for selection; and

circuitry configured to receive a selection of the subset of the adaptation data from the particular party.

9. The system of claim 1, wherein said circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type comprises:

circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device and one or more user preferences, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type.

10. The system of claim 1, further comprising:

circuitry configured to select the target device.

11. The system of claim 1, wherein said circuitry configured to receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data comprises:

circuitry configured to receive result data from the target device that is based at least partly on a measure of success of interpretation of speech of the particular party by the target device using the subset of the adaptation data.

12. The system of claim 1, wherein said circuitry configured to receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data comprises:

circuitry configured to receive result data from the target device including at least one word improperly interpreted by the target device using the subset of the adaptation data.

13. The system of claim 1, wherein said circuitry configured to receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data comprises:

circuitry configured to receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data, upon conclusion of a speech-facilitated transaction involving the target device.

14. The system of claim 1, wherein said circuitry configured to receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data comprises:

circuitry configured to receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data, prior to completion of a speech-facilitated transaction involving the target device.

15. The system of claim 1, further comprising:

circuitry configured to monitor a speech-facilitated transaction involving the target device and the particular party.

16. The system of claim 1, further comprising:

circuitry configured to modify the adaptation data.

17. The system of claim 1, wherein said circuitry configured to receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data comprises:

circuitry configured to receive result data from the target device including a voice sample.

18. The system of claim 1, further comprising:

circuitry configured to transmit modified adaptation data to the target device.

19. The system of claim 1, further comprising:

circuitry configured to transmit at least a portion of modified adaptation data to a receiving device.

20. The system of claim 1, further comprising:

circuitry configured to transmit at least a portion of modified adaptation data to a receiving device that is of a same type as the type of the target device.

21. The system of claim 1, further comprising:

circuitry configured to increment a counter at least partly based on the result data.

22. The system of claim 1, wherein the circuitry configured to transmit the subset of the adaptation data to the target device comprises:

circuitry configured to transmit the subset of the adaptation data to the target device to enable application of the pronunciation data to interpret at least some of a speech-facilitated transaction between the particular party and the target device.

23. The system of claim 1, wherein the circuitry configured to transmit the subset of the adaptation data to the target device comprises:

circuitry configured to transmit the subset of the adaptation data to the target device to reduce processing power load of the target device during speech recognition.

24. The system of claim 1, wherein the circuitry configured to receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data comprises:

circuitry configured to receive word frequency data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data.

25. The system of claim 1, wherein the circuitry configured to receive at least one property of a target device from the target device, the at least one property including at least a type of the target device comprises:

circuitry configured to receive at least one property of a target device from the target device, the at least one property including at least a type of the target device and a mode of the target device.

26. The system of claim 25, wherein the circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type comprises:

circuitry configured to select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device and the mode of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device and the mode of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type.

27. The system of claim 1, wherein the circuitry configured to determine whether to modify the subset of the adaptation data that includes pronunciation data for the one or more words that have been linked to the type of the target device, at least partly based on the result data comprises:

circuitry configured to determine whether to modify a selection of the one or more words that have been linked to the type of the target device, at least partly based on the result data.

28. A process implemented using at least one computer processor, the process comprising:

receive at least one property of a target device from the target device, the at least one property including at least a type of the target device;

select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type;

transmit the subset of the adaptation data to the target device;

receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data; and

determine whether to modify the subset of the adaptation data that includes pronunciation data for the one or more words that have been linked to the type of the target device, at least partly based on the result data.

29. A system comprising:

one or more computer readable media bearing one or more computer executable instructions;

at least one processor component configured by the one or more computer executable instructions to execute operations including at least;

receive at least one property of a target device from the target device, the at least one property including at least a type of the target device;

select a subset of adaptation data associated with speech of a particular party based at least partly on the type of the target device, wherein the subset of the adaptation data includes pronunciation data for one or more words that have been linked to the type of the target device based at least partly on frequency of use of the one or more words during one or more prior speech-facilitated transactions of the particular party with one or more other target devices of the type;

transmit the subset of the adaptation data to the target device;

receive result data from the target device that is based at least partly on interpretation of speech of the particular party by the target device using the subset of the adaptation data; and

determine whether to modify the subset of the adaptation data that includes pronunciation data for the one or more words that have been linked to the type of the target device, at least partly based on the result data.