<?xml version="1.0" standalone="yes"?>
<Paper uid="H01-1017">
  <Title>Dialogue Interaction with the DARPA Communicator Infrastructure: The Development of Useful Software</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Over the last five years, three technological advances have cooperated to push speech-enabled dialogue systems back into the limelight: the availability of robust real-time speech recognition tools, the explosion of Internet-accessible information sources, and the proliferation of mobile information access devices such as cell phones. However, the systems being fielded, and the standards arising from these efforts, represent only a limited set of capabilities for robust voice-enabled interaction with knowledge sources. The most prominent indication of these limitations is the fact that these systems are overwhelmingly system-directed; the system asks a question, and the user responds. While this type of interactions sidesteps a number of problems in speech recognition and dialogue tracking, it is overwhelmingly likely that these restrictions are not manageable in the long term.</Paragraph>
    <Paragraph position="1"> The DARPA Communicator program [1] is exploring how to engage human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities in dialogue systems. To support this exploration, the Communicator program has funded the development of a distributed message-passing infrastructure for dialogue systems which all Communicator participants are using. In this presentation, we describe the features of and requirements for a genuinely useful software infrastructure for this purpose.</Paragraph>
  </Section>
class="xml-element"></Paper>