System and method for personalization in speech recogniton

Patent metadata

Field	Value
Publication number	US-2016035346-A1
Application number	US-201414446441-A
Country	US
Kind code	A1
Filing date	Jul 30, 2014
Priority date	Jul 30, 2014
Publication date	Feb 4, 2016
Grant date	—

Abstract

Systems, methods, and computer-readable storage devices are for identifying a user profile for speech recognition. The user profile is selected from one of several user profiles which are all associated with a speaker, and can be selected based on the identity of the speaker, the location of the speaker, the device the speaker is using, or other relevant parameters. Such parameters can be hierarchical, having multiple layers, and can also be dependent or independent from one another. Using the parameters identified, the user profile is selected and used to recognize speech.

First claim

We claim:

1 . A method comprising:
identifying a speaker providing speech; identifying a current location of the speaker; identifying a microphone receiving the speech; selecting a user profile from a plurality of user profiles based on the current location and the microphone, wherein each user profile in the plurality of user profiles is associated with the speaker; and performing speech recognition on the speech received from the speaker using the user profile.

2 . The method of claim 1 , wherein the user profile is specific to acoustics of the current location.

3 . The method of claim 1 , wherein the selecting of the user profile is further based on a recipient profile associated with a recipient of the speech.

4 . The method of claim 3 , further comprising modifying an aspect of the speech recognition based on a speech adaptation of the speaker which occurs when communicating with the speaker.

5 . The method of claim 4 , wherein the speech adaptation of the speaker is an accent change.

6 . The method of claim 1 , further comprising presenting a query to a user, wherein the query presented to the user comprises a request regarding acoustics in the current location.

7 . The method of claim 1 , wherein the sound profile is based on a number of microphones within a threshold distance from the speaker.

8 . The method of claim 1 , wherein the speech recognition comprises a multi-pass recognition.

9 . A system comprising:
a processor; and a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
identifying a speaker providing speech;
identifying a current location of the speaker;
identifying a microphone receiving the speech;
selecting a user profile from a plurality of user profiles based on the current location and the microphone, wherein each user profile in the plurality of user profiles is associated with the speaker; and
performing speech recognition on the speech received from the speaker using the user profile.

10 . The system of claim 9 , wherein the user profile is specific to acoustics of the current location.

11 . The system of claim 9 , wherein the selecting of the user profile is further based on a recipient profile associated with a recipient of the speech.

12 . The system of claim 11 , the computer-readable storage medium having additional instructions stored which result in operations comprising modifying an aspect of the speech recognition based on a speech adaptation of the speaker which occurs when communicating with the speaker.

13 . The system of claim 12 , wherein the speech adaptation of the speaker is an accent change.

14 . The system of claim 9 , the computer-readable storage medium having additional instructions stored which result in operations comprising presenting a query to a user, wherein the query presented to the user comprises a request regarding acoustics in the current location.

15 . The system of claim 9 , wherein the sound profile is based on a number of microphones within a threshold distance from the speaker.

16 . The system of claim 9 , wherein the speech recognition comprises a multi-pass recognition.

17 . A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
identifying a speaker providing speech; identifying a current location of the speaker; identifying a microphone receiving the speech; selecting a user profile from a plurality of user profiles based on the current location and the microphone, wherein each user profile in the plurality of user profiles is associated with the speaker; and performing speech recognition on the speech received from the speaker using the user profile.

18 . The computer-readable storage device of claim 17 , wherein the user profile is specific to acoustics of the current location.

19 . The computer-readable storage device of claim 17 , wherein the selecting of the user profile is further based on a recipient profile associated with a recipient of the speech.

20 . The computer-readable storage device of claim 19 , having additional instructions stored which result in operations comprising modifying an aspect of the speech recognition based on a speech adaptation of the speaker which occurs when communicating with the speaker.

Assignees

• At & T Ip I Lp

Inventors

• Chengalvarayan Rathinavelu

Classifications

• G10L15/07 Primary

  to the speaker · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L17/005

  Physics · mapped topic

• G10L2015/226

  using non-speech characteristics · CPC title

• G10L15/005

  Language recognition · CPC title