<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0716">
  <Title>Generating Synthetic Speech Prosody with Lazy Learning in Tree Structures</Title>
  <Section position="7" start_page="89" end_page="89" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented a new prosody prediction method. Its original aspect is to consider sentences as tree structures. Tree similarity metrics and analogy-based learning in a corpus of such structures are used to predict the prosody of a new sentence. Further experiments are needed to validate this approach.</Paragraph>
    <Paragraph position="1"> An additional development of our method would be the introduction of focus labels. In a dialogue context, some extra information can refine the intonation. With the tree structures that we are using, it is easy to introduce special markers upon the nodes of the structure.</Paragraph>
    <Paragraph position="2"> According to their nature and location, they can indicate some focus either on a word, on a phrase or on a whole sentence. With the adaptation of the tree metrics, the prediction process is kept unchanged.</Paragraph>
  </Section>
class="xml-element"></Paper>