Abstract: Disclosed herein includes a system, a method, and a non-transitory computer readable medium for rendering a three-dimensional (3D) model of an avatar according to an audio stream including a vocal output of a person and image data capturing a face of the person. In one aspect, phonemes of the vocal output are predicted according to the audio stream, and the predicted phonemes of the vocal output are translated into visemes. In one aspect, a plurality of blendshapes and corresponding weights are determined, according to the corresponding image data of the face, to form the 3D model of the avatar of the person. The visemes may be combined with the 3D model of the avatar to form a 3D representation of the avatar, by synchronizing the visemes with the 3D model of the avatar in time.

Abstract: Private real-time communications are provided between meeting attendees during a meeting using one or more augmented reality headsets. An augmented reality headset worn by a sending meeting attendee continuously monitors a current direction of the sending meeting attendee's gaze during the meeting, and detects that the sending meeting attendee has selected a receiving meeting attendee when the current direction of the sending attendee's gaze intersects with a location of the receiving meeting attendee. The augmented reality headset worn by the sending meeting attendee also receives a messaging command issued by the sending meeting attendee, also based on monitoring the sending meeting attendee's gaze during the meeting. In response to the messaging command, the augmented reality headset worn by the sending meeting attendee automatically transmits the private message to a device associated with the receiving meeting attendee, such as an augmented reality headset worn by the receiving meeting attendee.

Abstract: Private real-time communications are provided between meeting attendees during a meeting using one or more augmented reality headsets. An augmented reality headset worn by a sending meeting attendee continuously monitors a current direction of the sending meeting attendee's gaze during the meeting, and detects that the sending meeting attendee has selected a receiving meeting attendee when the current direction of the sending attendee's gaze intersects with a location of the receiving meeting attendee. The augmented reality headset worn by the sending meeting attendee also receives a messaging command issued by the sending meeting attendee, also based on monitoring the sending meeting attendee's gaze during the meeting. In response to the messaging command, the augmented reality headset worn by the sending meeting attendee automatically transmits the private message to a device associated with the receiving meeting attendee, such as an augmented reality headset worn by the receiving meeting attendee.

Abstract: A technique involves electronically providing live video of a first participant of the online meeting to a set of other participants of the online meeting. The live video displays live physical movement of the first participant. The technique further involves receiving a live video replacement command from the first participant after electronically providing the live video of the first participant of the online meeting to the set of other participants of the online meeting. The technique further involves electronically providing recorded video of the first participant of the online meeting to the set of other participants of the online meeting in place of the live video in response to the live video replacement command. The recorded video displays recorded physical movement of the first participant. Such operation affords the first participant with a period of privacy during the online meeting without calling attention to the video's change in state.