Abstract: In one embodiment, a method includes receiving a first portion of a speech input from a first user from a first client system associated with the first user during a first turn of a dialog session, wherein the first user is in a multi-channel audio communication with one or more second users, determining an intent of the first user to speak to an assistant system privately based on contextual information associated with the first portion of the speech input during the first turn of the dialog session, and sending, to the first client system responsive to determining the intent of the first user to speak to the assistant system privately and during the dialog session, instructions for muting audio transmission of subsequent second portions of the speech input from the first user during the dialog session to one or more of the second users in the multi-channel audio communication.

Abstract: In one embodiment, an AR/VR system includes a social-networking application installed on the AR/VR system, which allows a user to access on online social network, including communicating with the user's social connections and interacting with content objects on the online social network. The AR/VR system also includes an AR/VR application, which allows the user to interact with an AR/VR platform by providing user input to the AR/VR application via various modalities. Based on the user input, the AR/VR platform generates responses and sends the generated responses to the AR/VR application, which then presents the responses to the user at the AR/VR system via various modalities.