Computational modeling of turn-taking dynamics in spoken conversations

The study of human interaction dynamics has been at the center of multiple research disciplines including computer and social sciences, conversational analysis, and psychology, for decades. Recent interest has been shown with the aim of designing computational models to improve human-machine interaction systems as well as support humans in their decision-making processes. Turn-taking is one of the key aspects of conversational dynamics in dyadic conversations and is an integral part of human-human and human-machine interaction systems. It is used for discourse organization of a conversation by means of explicit phrasing, intonation, and pausing, and it involves intricate timing. In verbal (e.g., telephone) conversations, the turn transitions are facilitated by inter- and intra-speaker silences and overlaps. In early research of turn-taking in the speech community, the studies include durational aspects of turns, cues for turn-yielding intention, and designing turn-transition modeling for spoken dialog agents. Compared to the studies of turn transitions, very few works have been done for classifying overlap discourse, especially the competitive act of overlaps and the function of silences.