User authentication of voice controlled devices

Patent metadata

Field	Value
Publication number	US-9384751-B2
Application number	US-201313888029-A
Country	US
Kind code	B2
Filing date	May 6, 2013
Priority date	May 6, 2013
Publication date	Jul 5, 2016
Grant date	Jul 5, 2016

Abstract

Methods, systems, and devices are described herein. One method can include receiving a voice command from a user at a voice controlled device, determining a presence of the user to the device using a sensor, converting the voice command to a device specific command, and performing the device specific command using the device in response to the determined presence.

First claim

What is claimed:

1. A method for user authentication of a voice controlled device, the method comprising:
receiving a voice command from a user at the voice controlled device;
determining a presence of the user to the voice controlled device using a sensor, wherein the presence of the user is within a threshold presence in proximity to the voice controlled device;
determining a confidence measure based on the determined threshold presence, wherein the confidence measure indicates the user's intention to address the voice controlled device;
converting the voice command to a device specific command when the presence of the user is within the threshold presence;
performing the device specific command using the device in response to the determined threshold presence and confidence measure; and
denying the device specific command in response to identifying that the user is not within the threshold presence based on the determined confidence measure.

2. The method of claim 1 , wherein determining the presence of the user includes performing multi-modality user authentication.

3. The method of claim 1 , wherein determining the presence of the user includes performing microphone based proximity analysis.

4. The method of claim 1 , wherein determining the presence of the user includes:
processing data from a number of sensors, including the sensor; and
determining the presence of the user by fusing the processed data from the number of sensors.

5. The method of claim 1 , including determining to perform the device specific command including determining the presence of the user using facial recognition techniques.

6. The method of claim 1 , wherein determining the user is within the threshold presence includes:
analyzing a signal strength of the voice command from a number of sensors to determine the user is within a threshold distance from the voice control device and an angle of the user when issuing the voice command.

7. The method of claim 6 , including verifying an authorization of the user using the sensor, wherein verifying the authorization of the user includes comparing a measurement from the sensor to a database.

8. The method of claim 1 , wherein determining the presence of the user to the voice controlled device includes:
determining the presence of the user using a number of sensors, wherein the number of sensors includes the sensor and wherein each of the number of sensors include a component of an external device in an environment; and
communicating the determined presence of the user to a connected device in the environment.

9. A voice controlled device, comprising:
a microphone component to receive a voice command from a user;
a sensor component to take a presence measurement associated with the user; and
a computing component operable to:
determine a presence of the user to the voice controlled device based on the presence measurement;
determine a confidence measure for the voice command based on the presence measurement, wherein the confidence measure is based on a threshold presence of the user in proximity to the voice controlled device, and wherein the confidence measure indicates the user's intention to address the voice controlled device;
convert the received voice command to text when the confidence measure is within the threshold presence;
convert the text to a device specific command;
perform the device specific command based on the determined presence and confidence measure; and
deny the device specific command in response to identifying that the user is not within the threshold presence based on the determined confidence measure.

10. The device of claim 9 , wherein the computing component operable to determine the presence is operable to determine the presence of the user based on at least one of a motion measurement of the sensor, a temperature change measured by the sensor, a distance of the user measured by the sensor, and video verification measured by the sensor.

11. The device of claim 9 , where the computing component operable to determine the confidence measure is operable to determine the confidence measure based on a sensor fusion associated with an intended confidence.

12. The device of claim 9 , wherein the computing component is operable to determine that the user is addressing the voice controlled device in addition to the determined presence of the user.

13. The device of claim 9 , wherein the computing component is operable to determine the user is within a threshold proximity to the voice controlled device to determine the presence of the user to the voice controlled device.

14. The device of claim 9 , wherein the computing component is operable to perform a multi-layered authentication including communicating the determined presence to a connected device.

15. A system for user authentication of a voice controlled device, comprising:
a sensor device to take a presence measurement associated with a user; and
a voice controlled device, including:
a microphone component to receive a voice command from a user; and
a computing component operable to:
determine a presence of the user to the voice controlled device using the presence measurement;
identify the user is within a threshold presence to the device based on the determined presence;
determine a confidence measure for the voice command based on the presence measurement, wherein the confidence measure indicates the user's intention to address the voice controlled device;
convert the received voice command to text;
convert the text to a device specific command;
perform the device specific command in response to identifying the user is within the threshold presence to the voice controlled device and based on the determined confidence measure;
communicate the determined presence of the user to a connected device; and
deny the device specific command in response to identifying that the user is not within the threshold presence based on the determined confidence measure.

16. The system of claim 15 , wherein the computing component is operable to authorize the user using an authorization measurement from the sensor device.

17. The system of claim 15 , wherein the computing component is further operable to:
receive a determined presence of a different user from the connected device; and
instruct a different connected device to use the communicated determined presence to authenticate the different user within a threshold period of time.

18. The system of claim 15 , wherein the computing component is operable to communicate the device specific command to the connected device and the connected device is operable to perform the device specific command.

19. The system of claim 15 , wherein the sensor device includes a plurality of sensor devices in an environment to take a plurality of presence measurements.

Assignees

• Honeywell Int Inc

Inventors

• Venkatesha Sharath
• Pham Hai D
• Padmanabhan Aravind
• Mcaward James G

Classifications

• G06F21/32

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

• H04L63/0861

  using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231) · CPC title

• G10L21/00 Primary

  Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility (G10L19/00 takes precedence) · CPC title

• H04L12/2803

  Home automation networks · CPC title

• G10L15/26 Primary

  Speech to text systems (G10L15/08 takes precedence) · CPC title