Developing multimodal conversational agents: From the use of VoiceXML to android-based applications

Abstract

The current industrial development of commercial conversational agents and dialog systems deploys robust interfaces in strictly defined application domains. However, commercial systems have not yet adopted new perspectives proposed in the academic settings, which would allow straightforward adaptation of these interfaces. In this paper, we propose two approaches to bridge the gap between the academic and industrial perspectives in order to develop conversational agents using an academic paradigm for dialog management while employing the industrial standards, like the VoiceXML language or the Android OS. Our proposal has been evaluated with the successful development of different spoken and multimodal systems. © 2014 Springer International Publishing Switzerland.