<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1017">
  <Title>WIT: A Toolkit for Building Robust and Real-Time Spoken Dialogue Systems</Title>
  <Section position="3" start_page="150" end_page="150" type="intro">
    <SectionTitle>
2 Overview
</SectionTitle>
    <Paragraph position="0"> A WIT-based spoken dialogue system has four main modules: the speech recognition module, the language understanding module, the language generation module, and the speech output module. These modules exploit domain-dependent knowledge sources, which are automatically generated from the domain-dependent system specifications. The relationship among the modules, knowledge sources, and specifications are depicted in Figure 1.</Paragraph>
    <Paragraph position="1"> WIT can also display and move a human-facelike animated agent, which is controlled by the speech output module, although this paper does not go into details because it focuses only on spoken dialogue. We also omit the GUI facilities provided by WIT.</Paragraph>
  </Section>
class="xml-element"></Paper>