Mechanism and apparatus for seamless voice wake and speaker verification

Patent metadata

Field	Value
Publication number	US-9852731-B2
Application number	US-201615223967-A
Country	US
Kind code	B2
Filing date	Jul 29, 2016
Priority date	Jul 11, 2013
Publication date	Dec 26, 2017
Grant date	Dec 26, 2017

Abstract

Technologies are described herein that allow a user to wake up a computing device operating in a low-power state and for the user to be verified by speaking a single wake phrase. Wake phrase recognition is performed by a low-power engine. In some embodiments, the low-power engine may also perform speaker verification. In other embodiments, the mobile device wakes up after a wake phrase is recognized and a component other than the low-power engine performs speaker verification on a portion of the audio input comprising the wake phrase. More than one wake phrases may be associated with a particular user, and separate users may be associated with different wake phrases. Different wake phrases may cause the device transition from a low-power state to various active states.

First claim

We claim:

1. A computing device, comprising:
a microphone;
a low-power engine to:
recognize a wake phrase in audio input provided by a user to the microphone while the computing device is in a low-power state; and
cause the computing device to transition from the low-power state to an active state after recognition of the wake phrase in the audio input provided by the user to the microphone while the computing device is in the low-power state;

a speaker verification module to:
attempt to verify the user based at least in part on a first portion of the audio input comprising the wake phrase while the computing device is in the low-power state or the active state; and

a command interpretation module to:
interpret a second portion of the audio input not comprising the wake phrase as a command to launch an application on the computing device and to launch the application when the command is a user agnostic command or not launch the application when the command is not a user agnostic command, wherein a user agnostic command comprises a command that does not require identifying information or personal data of the user.

2. The computing device of claim 1 , wherein a user agnostic command comprises a command that does not require user identifying information.

3. The computing device of claim 1 , wherein the attempt to verify the user is in the low-power state and the low-power engine is to cause the computing device to transition from the low-power state to the active state after the attempt to verify the user has failed.

4. The computing device of claim 1 , wherein the low-power engine is to cause the computing device to transition from a second low-power state to a second active state after recognition of the wake phrase in a second audio input provided by a second user to the microphone while the computing device is in the second low-power state and after verification of the second user based at least in part on a portion of the second audio input comprising the wake phrase while the computing device is in the second low-power state.

5. The computing device of claim 4 , wherein the command interpretation module is to interpret the first portion of the second audio input comprising the wake phrase as a second command to be performed by the computing device.

6. The computing device of claim 1 , wherein the low-power engine is included in an audio capture pipeline of the computing device when the computing device is in the low-power state and the low-power engine is removed from the audio capture pipeline when the computing device is in the active state.

7. The computing device of claim 1 , wherein the command interpretation module is to access a cloud-based service to determine information corresponding to the user agnostic command.

8. A method of waking a computing device, comprising:
while the computing device is in a low-power state:
receiving audio input from a user at the computing device; and
determining that the audio input comprises a wake phrase;

transitioning the computing device from the low-power state to an active state if the audio input comprises the wake phrase;
while the computing device is in the low-power state or the active state:
attempting to verify the user based at least in part on a first portion of the audio input comprising the wake phrase; and

while the computing device is in the active state:
interpreting a second portion of the audio input not comprising the wake phrase as a command to launch an application on the computing device; and
launching the application at the computing device when the command is a user agnostic command or not launching the application when the command is not a user agnostic command, wherein a user agnostic command comprises a command that does not require identifying information or personal data of the user.

9. The method of claim 8 , wherein a user agnostic command comprises a command that does not require user identifying information.

10. The method of claim 8 , wherein said attempting to verify the user is performed when the computing device in the low-power state and said transitioning the computing device from the low-power state to the active state is after said attempting to verify the user has failed.

11. The method of claim 8 , wherein the wake phrase is one of a plurality of wake phrases that may be used to verify the user.

12. The method of claim 8 , wherein the wake phrase is one of a plurality of wake phrases that may be used to verify a plurality of users, the plurality of wake phrases comprising a first wake phrase that may be used to verify a first user and a second wake phrase that may be used to verify a second user, the first wake phrase being different from the second wake phrase.

13. The method of claim 8 , further comprising:
interpreting a second audio input comprising the wake phrase as a second command to be executed by the computing device; and
performing the second command at the computing device.

14. The method of claim 8 , further comprising:
accessing a cloud-based service to determine information corresponding to the user agnostic command.

15. One or more non-transitory computer-readable storage media storing computer-executable instructions for causing a computing device to:
while the computing device is in a low-power state:
receive audio input from a user at the computing device; and
determine that the audio input comprises a wake phrase;

transition the computing device from the low-power state to an active state if the audio input comprises the wake phrase;
while the computing device is in the low-power state or the active state:
attempt to verify the user based at least in part on a first portion of the audio input comprising the wake phrase; and

while the computing device is in the active state:
interpret a second portion of the audio input not comprising the wake phrase as a command to launch an application on the computing device; and
launch the application at the computing device when the command is a user agnostic command or not launch the application when the command is not a user agnostic command, wherein a user agnostic command comprises a command that does not require identifying information or personal data of the user.

16. The one or more computer-readable storage media of claim 15 , wherein a user agnostic command comprises a command that does not require user identifying information.

17. The one or more computer-readable storage media of claim 15 , wherein said attempting to verify the user is performed when the computing device in the low-power state and said transitioning the computing device from the low-power state to the active state is after said attempting to verify the user has failed.

18. The one or more computer-readable storage media of claim 15 , wherein the wake phrase is one of a plurality of wake phrases that may be used to verify a plurality of users, the plurality of wake phrases comprising a first wake phrase that may be used to verify a first user and a second wake phrase that may be used to verify a second user, the first wake phrase being different from the second wake phrase.

19. The one or more computer-readable storage media of claim 15 , further comprising computer-executable instructions for causing the computing device to:
interpret a second audio input comprising the wake phrase as a second command to be executed by the computing device; and
perform the second command at the computing device.

20. The one or more computer-readable storage media of

Assignees

• Intel Corp

Inventors

• Dadu Saurabh
• Krishnamurthy Lakshman
• Tharappel Francis M
• Datta Prabhakar R
• Peebler Bryan R
• Deisher Michael E
• Joshi Mandar S
• Shah Saurin
• Vogel Brian K

Classifications

• G10L15/285

  Memory allocation or algorithm optimisation to reduce hardware requirements · CPC title

• G06F3/167

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

• Y02B60/1282

  Cross-Sectional Technologies · mapped topic

• G06F1/3293

  by switching to a less power-consuming processor, e.g. sub-CPU · CPC title

• G06F21/32

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title