Customizing a voice-based interface using surrounding factors

Patent metadata

Field	Value
Publication number	US-11114089-B2
Application number	US-201816194613-A
Country	US
Kind code	B2
Filing date	Nov 19, 2018
Priority date	Nov 19, 2018
Publication date	Sep 7, 2021
Grant date	Sep 7, 2021

Abstract

A method, system, and computer program product for applying a profile to an assistive device based on a multitude of cues includes: gathering audio inputs surrounding an assistive device; analyzing, by the assistive device, the audio inputs; determining, based on the analyzing, scenario cues; classifying a current environment surrounding the assistive device from the scenario cues; comparing the current environment to device profiles of the assistive device; determining, based on the comparing, a matching profile; and, in response to determining the matching profile, executing the matching profile on the assistive device.

First claim

What is claimed is:

1. A computer-implemented method comprising:
gathering audio inputs surrounding an assistive device;
analyzing, by the assistive device, the audio inputs;
determining, based on the analyzing, scenario cues, wherein determining the scenario cues comprises:
determining whether the audio inputs include known voices and unknown voices;

assigning weights to each scenario cue to indicate their importance;
classifying a current environment surrounding the assistive device from the scenario cues and the assigned weights;
comparing the current environment to device profiles of the assistive device;
determining, based on the comparing, a matching profile, the matching profile including privacy settings, wherein the matching profile is determined based on whether the audio inputs include the known voices or the unknown voices and based on the assigned weights of each scenario cue; and
in response to determining the matching profile, executing the matching profile on the assistive device.

2. The method of claim 1 , wherein determining the matching profile includes selecting a device profile from the device profiles that is most similar to the current environment.

3. The method of claim 2 , wherein the matching profile is a current profile.

4. The method of claim 2 , wherein the matching profile is a device profile different from a current profile.

5. The method of claim 1 , wherein scenario cues include at least known or unknown voices.

6. The method of claim 5 , wherein classifying the current environment includes determining that there are scenario cues of unknown voices.

7. The method of claim 6 , wherein the matching profile is a profile that withholds personal information.

8. The method of claim 1 , wherein the device profiles are set up by a user of the assistive device.

9. The method of claim 1 , further comprising:
in response to executing the matching profile, receiving a request from a user to change a factor of the matching profile; and
executing a different device profile that includes the changed factor.

10. The method of claim 1 , further comprising:
in response to executing the matching profile, receiving a request from a user to change a factor of the matching profile; and
creating a new device profile using the matching profile and the changed factor.

11. The method of claim 1 , wherein scenario cues include at least one of utensil sounds and appliance noises.

12. A system having one or more computer processors, the system configured to:
gather audio inputs surrounding an assistive device;
analyze, by the assistive device, the audio inputs;
determine, based on the analyzing, scenario cues, wherein determining the scenario cues comprises:
determining whether the audio inputs include known voices and unknown voices;

assign weights to each scenario cue to indicate their importance;
classify a current environment surrounding the assistive device from the scenario cues and the assigned weights;
compare the current environment to device profiles of the assistive device;
determine, based on the comparing, a matching profile, the matching profile including privacy settings, wherein the matching profile is determined based on whether the audio inputs include the known voices or the unknown voices and based on the assigned weights of each scenario cue; and
in response to determining the matching profile, execute the matching profile on the assistive device.

13. The system of claim 12 , wherein determining the matching profile includes selecting a device profile from the device profiles that is most similar to the current environment.

14. The system of claim 13 , wherein the matching profile is a current profile.

15. The system of claim 13 , wherein the matching profile is a device profile different from a current profile.

16. The system of claim 12 , further comprising:
in response to executing the matching profile, receive a request from a user to change a factor of the matching profile; and
execute a different device profile that includes the changed factor.

17. The system of claim 12 , further comprising:
in response to executing the matching profile, receive a request from a user to change a factor of the matching profile; and
create a new device profile using the matching profile and the changed factor.

18. A computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a server to cause the server to perform a method, the method comprising:
gathering audio inputs surrounding an assistive device;
analyzing, by the assistive device, the audio inputs;
determining, based on the analyzing, scenario cues, wherein determining the scenario cues comprises:
determining whether the audio inputs include known voices and unknown voices;

assigning weights to each scenario cue to indicate their importance;
classifying a current environment surrounding the assistive device from the scenario cues and the assigned weights;
comparing the current environment to device profiles of the assistive device;
determining, based on the comparing, a matching profile, the matching profile including privacy settings, wherein the matching profile is determined based on whether the audio inputs include the known voices or the unknown voices and based on the assigned weights of each scenario cue; and
in response to determining the matching profile, executing the matching profile on the assistive device.

19. The computer program product of claim 18 , wherein determining the matching profile includes selecting a device profile from the device profiles that is most similar to the current environment.

20. The computer program product of claim 18 , further comprising:
in response to executing the matching profile, receiving a request from a user to change a factor of the matching profile; and
executing a different device profile that includes the changed factor.

Assignees

• IBM

Inventors

• Chapman Matthew
• Xing Chengxuan
• Daniel Andrew J
• Harrison Ashley

Classifications

• G10L15/07 Primary

  to the speaker · CPC title

• G10L15/22

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

• G06F21/6245

  Protecting personal data, e.g. for financial or medical purposes · CPC title

• G10L2015/228

  of application context · CPC title

• G10L15/20

  Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence) · CPC title