Utilizing spoken cues to influence response rendering for virtual assistants

A system for integration of a virtual assistant into a real-time spoken conversation session among a plurality of live participants, the system comprising:

• an interpretation module arranged to:
• receive a first utterance information that expresses a first utterance spoken during the spoken conversation session by a first live participant included in the plurality of live participants of the spoken conversation session, the plurality of live participants including a second live participant, and
• process the received first utterance information using at least one machine-trained model to determine an intent or content for a first command or query included in the first utterance;
• a recipient subset(s) selection module configured to selectively identify a first recipient subset of one or more of the plurality of live participants based on at least the determined intent or content for the first utterance, the first recipient subset excluding at least the second live participant;
• a response generation module configured to automatically generate, using the virtual assistant, a first response for the first command or query;
• and
• a response routing module arranged to selectively provide, during the spoken conversation session, the first response automatically generated by the virtual assistant to the identified first recipient subset without providing the first response to the second live participant.