User-specific customization of video conferences using multimodal biometric characterization

1. A method comprising, by a device:

detecting that a person is visible to a camera of the device;

determining a first biometric characteristic of the person discernable by the device;

associating the first biometric characteristic with a user identifier unique to the person;

determining, while the person is identifiable based on the first biometric characteristic, a second biometric characteristic of the person discernable by the device;

associating the second biometric characteristic with the user identifier;

determining that a detected person has a detected biometric characteristic;

determining, with a given degree of confidence, that the detected person is associated with the user identifier by matching the detected biometric characteristic to the first biometric characteristic or the second biometric characteristic, wherein the given degree of confidence is higher when both the first and second biometric characteristics of the detected person are discernable by the device than when only one of the first and second biometric characteristics of the detected person is discernable by the device; and

applying, while the detected person is identifiable based on the detected biometric characteristic, a user-specific customization associated with the user identifier.

2. The method of claim 1 , wherein:

the first biometric characteristic represents a facial recognition result identifying the detected person; and

the method further comprises associating the user identifier with the detected person in response to the identifying.

3. The method of claim 1 , wherein at least one of the first biometric characteristic or the second biometric characteristic represents a persistent attribute of the detected person discernable in video or audio data captured by the camera or in data received from a biometric sensor of the device other than the camera.

4. The method of claim 1 , wherein:

at least one of the first biometric characteristic or the second biometric characteristic represents a transient attribute of the detected person discernable in video or audio data captured by the camera or in data received from a biometric sensor of the device other than the camera; and

the user-specific customization is dependent on the transient attribute.

5. The method of claim 1 , wherein:

at least one of the first biometric characteristic or the second biometric characteristic represents a current contextual attribute of the detected person discernable in video or audio data captured by the camera or in data received from a biometric sensor of the device other than the camera; and

the user-specific customization is dependent on the current contextual attribute.

6. The method of claim 1 , further comprising:

determining, while the detected person is identifiable based on at least one of the first biometric characteristic or the second biometric characteristic, a third biometric characteristic of the person discernable by the device;

associating the third biometric characteristic with the user identifier; and

subsequent to associating the third biometric characteristic with the user identifier, identifying, with a given degree of confidence and while the detected person is identifiable based on the third biometric characteristic, the detected person, wherein the given degree of confidence is higher when at least one of the first biometric characteristic of the detected person or the second biometric characteristic of the detected person is also discernable by the device than when only the third biometric characteristic is discernable by the device.

7. The method of claim 1 , wherein applying the user-specific customization comprises modifying the appearance of the detected person or an attribute of the voice of the detected person in a video stream output by the device.

8. The method of claim 1 , wherein applying the user-specific customization comprises modifying a visual or audible attribute of a scene in which the detected person appears in a video stream output by the device.

9. The method of claim 1 , further comprising:

storing a plurality of biometric characteristics of the detected person in association with the user identifier in a data structure, the data structure storing information representing one or more persons visible to the camera including the detected person, and the plurality of biometric characteristics including the first and second biometric characteristics;

obtaining biometric data from the camera or from a biometric sensor of the device other than the camera; and

updating the plurality of biometric characteristics of the detected person stored in association with the user identifier in the data structure dependent on the obtained biometric data.

10. The method of claim 9 , wherein obtaining the biometric data comprises:

determining that a trigger condition for updating the plurality of biometric characteristics of the detected person stored in association with the user identifier in the data structure has been met; and

requesting, in response to determining that the trigger condition has been met, current biometric data from the camera or from the biometric sensor of the device other than the camera.

11. A system, comprising:

one or more processors; and

one or more computer-readable non-transitory storage media coupled to one or more of the processors and comprising program instructions operable when executed by one or more of the processors to cause the system to:

detect that a person is visible to a camera of a device;

determine a first biometric characteristic of the person discernable by the device;

associate the first biometric characteristic with a user identifier unique to the person;

determine, while the person is identifiable based on the first biometric characteristic, a second biometric characteristic of the person discernable by the device;

associate the second biometric characteristic with the user identifier;

determine that a detected person has a detected biometric characteristic;

determine, with a given degree of confidence, that the detected person is associated with the user identifier by matching the detected biometric characteristic to the first biometric characteristic or the second biometric characteristic, wherein the given degree of confidence is higher when both the first and second biometric characteristics of the detected person are discernable by the device than when only one of the first and second biometric characteristics of the detected person is discernable by the device; and

apply, while the detected person is identifiable based on the detected biometric characteristic, a user-specific customization associated with the user identifier.

12. The system of claim 11 , wherein:

at least one of the first biometric characteristic or the second biometric characteristic represents a transient attribute or a current contextual attribute of the detected person discernable in video or audio data captured by the camera or in data received from a biometric sensor of the device other than the camera; and

the user-specific customization is dependent on the transient attribute or the current contextual attribute.

13. The system of claim 11 , wherein to apply the user-specific customization, the program instructions are further operable to cause the system to:

modify the appearance of the detected person or an attribute of the voice of the detected person in a video stream output by the device; or

modify a visual or audible attribute of a scene in which the detected person appears in a video stream output by the device.

14. The system of claim 11 , wherein when executed by the one or more of the processors, the program instructions are further operable to cause the system to:

store a plurality of biometric characteristics of the detected person in association with the user identifier in a data structure, the data structure storing information representing one or more persons visible to the camera including the detected person, and the plurality of biometric characteristics including the first and second biometric characteristics;

obtain biometric data from the camera or from a biometric sensor of the device other than the camera; and

update the plurality of biometric characteristics of the detected person stored in association with the user identifier in the data structure dependent on the obtained biometric data.

15. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

detect that a person is visible to a camera of a device;

determine a first biometric characteristic of the person discernable by the device;

associate the first biometric characteristic with a user identifier unique to the person;

determine, while the person is identifiable based on the first biometric characteristic, a second biometric characteristic of the person discernable by the device;

associate the second biometric characteristic with the user identifier;

determine that a detected person has a detected biometric characteristic;

determine, with a given degree of confidence, that the detected person is associated with the user identifier by matching the detected biometric characteristic to the first biometric characteristic or the second biometric characteristic, wherein the given degree of confidence is higher when both the first and second biometric characteristics of the detected person are discernable by the device than when only one of the first and second biometric characteristics of the detected person is discernable by the device; and

apply, while the detected person is identifiable based on the detected biometric characteristic, a user-specific customization associated with the user identifier.

16. The media of claim 15 , wherein:

at least one of the first biometric characteristic or the second biometric characteristic represents a transient attribute or a current contextual attribute of the detected person discernable in video or audio data captured by the camera or in data received from a biometric sensor of the device other than the camera; and

the user-specific customization is dependent on the transient attribute or the current contextual attribute.

17. The media of claim 15 , wherein to apply the user-specific customization, the software is further operable to:

modify the appearance of the detected person or an attribute of the voice of the detected person in a video stream output by the device; or

modify a visual or audible attribute of a scene in which the detected person appears in a video stream output by the device.

18. The media of claim 15 , wherein, when executed, the software is further operable to:

store a plurality of biometric characteristics of the detected person in association with the user identifier in a data structure, the data structure storing information representing one or more persons visible to the camera including the detected person, and the plurality of biometric characteristics including the first and second biometric characteristics;

obtain biometric data from the camera or from a biometric sensor of the device other than the camera; and

update the plurality of biometric characteristics of the detected person stored in association with the user identifier in the data structure dependent on the obtained biometric data.