Situationally suspending wakeup word to enable voice command input

Patent metadata

Field	Value
Publication number	US-9542941-B1
Application number	US-201514872587-A
Country	US
Kind code	B1
Filing date	Oct 1, 2015
Priority date	Oct 1, 2015
Publication date	Jan 10, 2017
Grant date	Jan 10, 2017

Abstract

In one aspect, devices and methods are disclosed for receiving at least one signal from at least one sensor and, based on analyzing the at least one signal, situationally suspending a necessity of receiving a wakeup word to enable voice command input to a computer.

First claim

What is claimed is:

1. A device, comprising:
a processor; and
storage accessible to the processor and bearing instructions executable by the processor to:
receive a signal from a sensor;
determine whether the signal indicates a presence of multiple people;
responsive to a determination that the signal indicates a presence of multiple people, enable wakeup word enablement of voice command input; and
responsive to a determination that the signal does not indicate a presence of multiple people, disable wakeup word enablement of voice command input.

2. The device of claim 1 , wherein wakeup word enablement of voice command input is identifiable by the processor based on audible input to then enable voice command input using the processor.

3. The device of claim 1 , comprising at least one camera, wherein the signal comprises an image from the at least one camera, and wherein the instructions are executable by the processor to:
execute face recognition using the at least one image to determine whether multiple people are present in the at least one image.

4. The device of claim 1 , comprising at least one microphone, wherein the signal is from the at least one microphone, and wherein the instructions are executable to:
execute voice recognition using the signal to determine whether multiple people are present.

5. The device of claim 1 , comprising at least one Bluetooth receiver, wherein the signal is from the at least one Bluetooth receiver, and wherein the instructions are executable to:
determine, based at least in part on at least one Bluetooth parameter identified from the signal, whether multiple people are present.

6. The device of claim 1 , comprising at least one motion sensor, wherein the signal is from the at least one motion sensor, and wherein the instructions are executable to:
determine, based at least in part on the signal, whether multiple people are present.

7. The device of claim 1 , wherein the signal is from at least one vehicle occupant sensor, and wherein the instructions are executable to:
determine, based at least in part on the signal, whether multiple people are present.

8. The device of claim 7 , comprising the vehicle occupant sensor.

9. The device of claim 1 , comprising at least one thermal imager, wherein the signal is from the at least one thermal imager, and wherein the instructions are executable to:
determine, based at least in part on the signal, whether multiple people are present.

10. A computer readable storage medium that is not a transitory signal and that is not a signal per se, the computer readable storage medium comprising instructions executable by a processor to:
receive a signal from at least one sensor;
determine whether the signal indicates a presence of multiple people;
responsive to a determination that the signal indicates a presence of multiple people, enable wakeup word enablement of voice command input; and
responsive to a determination that the signal does not indicate a presence of multiple people, disable wakeup word enablement of voice command input.

11. The computer readable storage medium of claim 10 , wherein wakeup word enablement of voice command input is identifiable by the processor based on audible input to then enable voice command input using the processor.

12. The computer readable storage medium of claim 10 , wherein the signal comprises an image from at least one camera, and wherein the instructions are executable to:
execute face recognition using the at least one image to determine whether multiple people are present in the at least one image.

13. The computer readable storage medium of claim 10 , wherein the signal is from at least one microphone, and wherein the instructions are executable to:
execute voice recognition using the signal to determine whether multiple people are present.

14. The computer readable storage medium of claim 10 , wherein the signal is from at least one Bluetooth receiver, and wherein the instructions are executable to:
determine, based at least in part on at least one Bluetooth parameter identified from the signal, whether multiple people are present.

15. The computer readable storage medium of claim 10 , wherein the signal is from at least one motion sensor, and wherein the instructions are executable to:
determine, based at least in part on the signal, whether multiple people are present.

16. The computer readable storage medium of claim 10 , wherein the signal is from at least one vehicle occupant sensor, and wherein the instructions are executable to:
determine, based at least in part on the signal, whether multiple people are present.

17. A method, comprising:
receiving at least one signal from at least one sensor;
determining, from the at least one signal, that a user is alone;
responsive to determining that the user is alone, suspending a need to receive a wakeup word to enable voice command input to a computer and enabling voice command input to the computer without receiving the wakeup word.

18. The method of claim 17 , comprising:
determining, from at least one signal from the at least one sensor, that the user is not alone; and
responsive to determining that the user is not alone, enabling voice command input only responsive to receiving the wakeup word.

19. The method of claim 17 , wherein the method comprises:
determining whether the signal indicates a presence of multiple people;
responsive to determining that the signal indicates a presence of multiple people, enabling wakeup word enablement of voice command input; and
responsive to determining that the signal does not indicate a presence of multiple people, disabling wakeup word enablement of voice command input.

20. The method of claim 17 , comprising:
receiving the at least one signal from at least one of: a microphone, a digital camera, and a thermal imager.

Assignees

• Lenovo Singapore Pte Ltd

Inventors

• Weksler Arnold S
• Mese John Carl
• Peterson Nathan J
• Vanblon Russell Speight

Classifications

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/22 Primary

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

• G10L2015/088

  Word spotting · CPC title

• G06F3/167 Primary

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