Towards Conversationally Intelligent Dialog Systems

Abstract

Spoken dialog systems, lacking the means to address the complex phenomena of spontaneous speech and conversational dynamics, force users into a constrained mode of dialog that resembles text-based interaction more closely than spoken conversation. Turn-taking is simplified and discourse-related information is lost, as discourse markers are largely ignored and prosodic information is not captured or utilized. We hypothesize that incorporating a few of these key conversational phenomena at specific points in a dialog will reduce cognitive load in spoken human-computer interaction and expand the potential application areas of dialog systems to tasks requiring more complex interactions. In this paper, we describe our approach to adding conversational intelligence to dialog systems and our work to date validating the hypothesis that adding conversational intelligence to existing dialog systems will significantly reduce users' cognitive load.