Methods, apparatus and computer-readable media (transitory and non-transitory) are disclosed for receiving audio information based on sensing of one or more audible sounds; identifying one or more voice profiles, wherein each of the voice profiles is associated with an individual and indicates one or more voice characteristics of the associated individual; determining at least a given voice profile of the one or more voice profiles matches the audio information; determining co-presence of the user with at least the individual associated with the given voice profile based on determining the given voice profile matches the audio information; identifying an action that includes a trigger based on co-presence of the user and the individual associated with the given voice profile; and invoking the action based on the determined co-presence of the user with at least the individual associated with the given voice profile.