<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0310">
  <Title>Using Dialogue Representations for Concept-to-Speech Generation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Conversational systems that use speech as the input and output modality are often realized by architectures that decouple speech processing components from language processing components. In this paper, we show how speech generation can be more closely coupled with the dialogue manager of a working mixed-initiative spoken dialogue system. In particular, we use representations from the semantic interpretation, task model and dialogue strategy modules to better communicate the meaning of system replies through prosodically appropriate synthetic speech.</Paragraph>
    <Paragraph position="1"> While dialogue prosody has been a topic of much study, our implemented concept-to-speech (CTS) system offers original proposals for specific couplings of dialogue computation with prosodic computation.</Paragraph>
    <Paragraph position="2"> Further, it embodies and extends theoretical work on intonational meaning in a more general, robust and rigorous way than earlier CTS systems, in an architecture that reflects compositional aspects of dialogue and intonation interpretation.</Paragraph>
  </Section>
class="xml-element"></Paper>