Speech recognition adaptation systems based on adaptation data

Patent metadata

Field	Value
Publication number	US-9620128-B2
Application number	US-201213564647-A
Country	US
Kind code	B2
Filing date	Aug 1, 2012
Priority date	May 31, 2012
Publication date	Apr 11, 2017
Grant date	Apr 11, 2017

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.

First claim

What is claimed is:

1. A computationally-implemented method, comprising:
managing adaptation data that is stored at a reference location, wherein the adaptation data is at least partly based on at least one speech interaction of a particular party;
determining an availability of the adaptation data by comparing a property of the adaptation data located at the referenced location with an expected value of the property of the adaptation data;
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
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, 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 said status includes an indicator of a success in determining speech of the speech-facilitated transaction.

2. 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.

3. 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 includes one or more of:
a training set of audio data and corresponding transcript data;
a regional dialect speech modification algorithm;
a foreign language accent modifier algorithm;
a speech impediment modification algorithm tailored to a particular user;
a frequently mispronounced word recognition adjustment algorithm;
a speech processing algorithm tailored to a user based at least one accent and/or tone;
a list of favorite words of a particular user;
an ambient noise level adjustment algorithm;
a value of a parameter in a speech interpretation algorithm;
a list of one or more words in a pronunciation dictionary whose pronunciations deviate a predetermined amount from their general pronunciations;
a training set of audio data and corresponding transcript data;
a phrase completion algorithm used to assist in interpreting spoken words based on context;
a pronunciation dictionary; and
a training set of one or more words related to a target device and one or more pronunciations of the one or more words.

4. 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.

5. 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 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.

6. 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 that a speech recognition component of the target device is processing speech of the particular party below a particular success rate.

7. 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 that a speech recognition component of the target device has a confidence rate below a particular threshold.

8. 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.

9. The computationally-implemented method of claim 8 , 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.

10. 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.

Assignees

• Levien Royce A
• Lord Richard T
• Lord Robert W
• Malamud Mark A
• Elwha Llc

Inventors

• Levien Royce A
• Lord Richard T
• Lord Robert W
• Malamud Mark A

Classifications

• G10L15/07 Primary

  to the speaker · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L15/06

  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 title

• G10L19/00 Primary

  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) · CPC title