9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Recovering Participant Identities in Meetings from a Probabilistic Description of Vocal Interaction

Kornel Laskowski (1), Tanja Schultz (2)

(1) Universität Karlsruhe (TH), Germany; (2) Carnegie Mellon University, USA

An important decision in the design of automatic conversation understanding systems is the level at which information streams representing specific participants are merged. In the current work, we explore participant-dependence of low-level interactive aspects of conversation, namely the observed contextual preferences for talkspurt deployment. We argue that strong participant-dependence at this level gives cause for merging participant streams as early as possible. We demonstrate that our probabilistic description of talkspurt deployment preferences is strongly participant-dependent, and frequently predictive of participant identity.

Full Paper

Bibliographic reference.  Laskowski, Kornel / Schultz, Tanja (2008): "Recovering participant identities in meetings from a probabilistic description of vocal interaction", In INTERSPEECH-2008, 82-85.