SMART LISTENING MODES SUPPORTING QUASI ALWAYS-ON LISTENING

• US 20170311261A1
• Filed: 03/20/2017
• Published: 10/26/2017
• Est. Priority Date: 04/25/2016
• Status: Active Grant

• Current Assignee: Sensory Incorporated
• Original Assignee: Sensory Incorporated
• Inventors: Mozer, Todd F., Pellom, Bryan
• Granted Patent: US 10,880,833 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04W 52/0229 where the received signal is a wanted signal
• CPC Class Codes: H04W 8/24 Transfer of terminal data
• CPC Class Codes: Y02D 30/70 in wireless communication networks

Abstract

Smart listening modes for supporting quasi always-on listening on an electronic device are provided. In one embodiment, the electronic device can determine that a user is likely to utter a voice trigger in order to access the always-on listening functionality of the electronic device. In response to this determination, the electronic device can automatically enable the always-on listening functionality. Similarly, the electronic device can determine that a user is no longer likely to utter the voice trigger in order to access the always-on listening functionality of the electronic device. In response to this second determination, the electronic device can automatically disable the always-on listening functionality.

Claims

1. A method comprising:

determining, by an electronic device, that a user is likely to utter a voice trigger in order to access always-on listening functionality of the electronic device; and

in response to the determining, enabling, by the electronic device, the always-on listening functionality.

2. The method of claim 1 further comprising, subsequently to the enabling:

determining that the user is no longer likely to utter the voice trigger in order to access the always-on listening functionality of the electronic device; and

in response to determining that the user is no longer likely to utter the voice trigger, disabling the always-on listening functionality.

3. The method of claim 1 wherein the determining is performed using a machine learning-based analysis that uses a machine learning model of the user'"'"'s past interactions with the electronic device in order to determine a probability of whether the user is likely to utter the voice trigger.

4. The method of claim 3 wherein the machine learning-based analysis takes into account a plurality of factors include time of day, geographic location of the electronic device, environmental conditions, device physical state, and device software state.

5. The method of claim 1 wherein the determining is performed by detecting an occurrence of a pre-defined trigger event.

6. The method of claim 5 wherein if the pre-defined trigger event is detected, the always-on listening functionality is enabled for a pre-configured period of time.

7. The method of claim 1 wherein the determining is performed by determining that the user is physically close to the electronic device.

8. The method of claim 7 wherein determining that the user is physically close to the electronic device comprises detecting presence of a second factor device associated with the user.

9. A non-transitory computer readable storage medium having stored thereon program code executable by an electronic device, the program code causing the electronic device to:

determine that a user is likely to utter a voice trigger in order to access always-on listening functionality of the electronic device; and

in response to the determining, enable the always-on listening functionality.

10. The non-transitory computer readable storage medium of claim 9 wherein the program code further causes the electronic device to, subsequently to the enabling:

determine that the user is no longer likely to utter the voice trigger in order to access the always-on listening functionality of the electronic device; and

in response to determining that the user is no longer likely to utter the voice trigger, disable the always-on listening functionality.

11. The non-transitory computer readable storage medium of claim 9 wherein the determining is performed using a machine learning-based analysis that uses a machine learning model of the user'"'"'s past interactions with the electronic device in order to determine a probability of whether the user is likely to utter the voice trigger.

12. The non-transitory computer readable storage medium of claim 11 wherein the machine learning-based analysis takes into account a plurality of factors include time of day, geographic location of the electronic device, environmental conditions, device physical state, and device software state.

13. The non-transitory computer readable storage medium of claim 9 wherein the determining is performed by detecting an occurrence of a pre-defined trigger event.

14. The non-transitory computer readable storage medium of claim 13 wherein if the pre-defined trigger event is detected, the always-on listening functionality is enabled for a pre-configured period of time.

15. The non-transitory computer readable storage medium of claim 9 wherein the determining is performed by determining that the user is physically close to the electronic device.

16. The non-transitory computer readable storage medium of claim 15 wherein determining that the user is physically close to the electronic device comprises detecting presence of a second factor device associated with the user.

17. An electronic device comprising:

a processor; and

a non-transitory computer readable medium having stored thereon program code that, when executed by the processor, causes the processor to;

determine that a user is likely to utter a voice trigger in order to access always-on listening functionality of the electronic device; and

in response to the determining, enable the always-on listening functionality.

18. The electronic device of claim 17 wherein the program code further causes the processor to, subsequently to the enabling:

determine that the user is no longer likely to utter the voice trigger in order to access the always-on listening functionality of the electronic device; and

in response to determining that the user is no longer likely to utter the voice trigger, disable the always-on listening functionality.

19. The electronic device of claim 17 wherein the determining is performed using a machine learning-based analysis that uses a machine learning model of the user'"'"'s past interactions with the electronic device in order to determine a probability of whether the user is likely to utter the voice trigger.

20. The electronic device of claim 19 wherein the machine learning-based analysis takes into account a plurality of factors include time of day, geographic location of the electronic device, environmental conditions, device physical state, and device software state.

21. The electronic device of claim 17 wherein the determining is performed by detecting an occurrence of a pre-defined trigger event.

22. The electronic device of claim 21 wherein if the pre-defined trigger event is detected, the always-on listening functionality is enabled for a pre-configured period of time.

23. The electronic device of claim 17 wherein the determining is performed by determining that the user is physically close to the electronic device.

24. The electronic device of claim 23 wherein determining that the user is physically close to the electronic device comprises detecting presence of a second factor device associated with the user.