<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0716">
  <Title>Generating Synthetic Speech Prosody with Lazy Learning in Tree Structures</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Natural prosody production remains a problem in speech synthesis systems. Several automatic prediction methods have already been tried for this, including decision trees (Ross, 1995), neural networks (Traber, 1992), and HMMs (Jensen et al., 1994). The original aspect of our prediction approach is a tree structure representation of sentences, and the use of tree similarity measurements to achieve the prosody prediction. We think that reasoning on a whole structure rather than on local features of a sentence should better reflect the many relations influencing the prosody. This approach is an attempt to achieve such a goal.</Paragraph>
    <Paragraph position="1"> The data used in this work is a part of the Boston University Radio (WBUR) News Corpus (Ostendorfet al., 1995). The prosodic information consists of ToBI labeling of accents and breaks (Silverman et al., 1992). The syntactic and part-of-speech informations were obtained from the part of the corpus processed in the Penn Treebank project (Marcus et al., 1993).</Paragraph>
    <Paragraph position="2"> We firstly describe the tree structures defined for this work, then present the tree metrics that we are using, and finally discuss how they are manipulated to achieve the prosody prediction.</Paragraph>
  </Section>
class="xml-element"></Paper>