User profiling for voice input processing

Patent metadata

Field	Value
Publication number	US-9633660-B2
Application number	US-201514941249-A
Country	US
Kind code	B2
Filing date	Nov 13, 2015
Priority date	Feb 25, 2010
Publication date	Apr 25, 2017
Grant date	Apr 25, 2017

Abstract

The present disclosure generally relates to systems and methods for processing received voice inputs for user identification. In an example process, voice input can be processed using a subset of words from a library used to identify the words or phrases of the voice input. The subset can be selected such that voice inputs provided by the user are more likely to include words from the subset. The subset of the library can be selected using any suitable approach, including for example based on the user's interests and words that relate to those interests. For example, the subset can include one or more words related to media items stored by the user on the electronic device, names of the user's contacts, applications or processes used by the user, or any other words relating to the user's interactions with the device.

First claim

What is claimed is:

1. A method for processing a voice input, comprising:
receiving a voice input;
identifying a user providing the voice input;
identifying a subset of library words associated with the identified user; and
processing the received voice input using the identified subset.

2. The method of claim 1 , further comprising:
identifying an electronic device operation corresponding to the processed voice input.

3. The method of claim 2 , further comprising:
retrieving at least one instruction from the processed voice input; and
identifying at least one electronic device operation corresponding to the retrieved at least one input.

4. The method of claim 3 , wherein:
the at least one instruction comprises an operation and an argument qualifying the operation.

5. The method of claim 4 , wherein:
the operation comprises a media playback operation; and;
the argument comprises a particular media item.

6. The method of claim 1 , further comprising:
identifying the user's interests; and
selecting a subset of library words that relate to the user's interests.

7. The method of claim 1 , wherein processing further comprises:
detecting a plurality of words in the received voice input;
comparing the identified plurality of words with the identified subset of library words; and
identifying a plurality of words from the identified subset that correspond to the detected plurality of words.

8. The method of claim 7 , further comprising:
extracting an instruction for the identified plurality of words; and
identifying an operation corresponding to the extracted instruction.

9. The method of claim 1 , wherein identifying the user further comprises:
extracting a voice print from the received voice input;
comparing the extracted voice print with a library of known voice prints; and
identifying the user having a voice print in the library of known voice prints that corresponds to the received voice print.

10. An electronic device controllable by voice inputs, comprising a processor, an input interface, and an output interface, the processor operative to:
direct the input interface to receive a voice input from a user;
identify the user providing the received voice input;
provide the identity of the user to a library of words used to process voice inputs;
receive a subset of the library of words, wherein the subset includes words likely to be used by the identified user;
process the voice input using the received subset; and
direct the output interface to provide an output based on the processed voice input.

11. The electronic device of claim 10 , wherein the processor is further operative to:
direct the output interface to play back a media item.

12. The electronic device of claim 11 , wherein the processor is further operative to:
identify a media playback operation from the voice input; and
identify a media item qualifying the media playback operation from the voice input.

13. The electronic device of claim 10 , wherein the processor is further operative to identify the user from at least one of:
the content of the voice input;
the time at which the voice input was provided; and
the voice signature of the voice print.

14. The electronic device of claim 10 , wherein:
the subset of media item words includes words corresponding to metadata values of content selected by the user for storage on the electronic device.

15. The electronic device of claim 14 , wherein the content selected by the user for storage on the electronic device comprises at least one of:
media items;
contact information;
applications;
calendar information; and
settings.

16. A method for defining a subset of a library used for processing voice inputs, comprising:
providing a library of words from which to process voice inputs;
identifying a user's interests;
extracting, from the user's interests, words that the user is likely to use to provide a voice input; and
defining a subset of the library, wherein the subset comprises at least the words of the library matching the extracted words.

17. The method of claim 16 , further comprising:
identifying particular media items of interest to the user; and
including metadata values for the identified particular media items in the defined subset.

18. The method of claim 17 , wherein the metadata values comprise at least one of:
artist;
title;
album;
genre;
year;
play count;
rating; and
playlist.

19. The method of claim 16 , further comparing the extracted words to the words of the library;
identifying words of the library that share at least a common root with at least one extracted word; and
including the identified words of the library in the defined subset.

20. A non-transitory computer readable media for processing a voice input, the computer readable media comprising computer program logic recorded thereon for:
receiving a voice input;
identifying a user providing the voice input;
identifying a subset of library words associated with the identified user; and
processing the received voice input using the identified subset.

21. The computer readable media of claim 20 , further comprising additional computer program logic recorded thereon for:
detecting a plurality of words in the received voice input;
comparing the identified plurality of words with the identified subset of library words; and
identifying a plurality of words from the identified subset that correspond to the detected plurality of words.

22. The computer readable media of claim 21 , further comprising additional computer program logic recorded thereon for:
extracting an instruction for the identified plurality of words; and
identifying an operation corresponding to the extracted instruction.

Assignees

• Apple Inc

Inventors

• Haughay Allen P

Classifications

• G10L15/22

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

• G10L17/00

  Speaker identification or verification techniques · CPC title

• G10L2015/227

  of the speaker; Human-factor methodology · CPC title

• G10L17/08 Primary

  Use of distortion metrics or a particular distance between probe pattern and reference templates · CPC title

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title