<?xml version="1.0" standalone="yes"?>
<Paper uid="E93-1039">
  <Title>apos;Structure and Usage of Current Bell Labs Text</Title>
  <Section position="9" start_page="337" end_page="337" type="evalu">
    <SectionTitle>
6 Synthesis
</SectionTitle>
    <Paragraph position="0"> We showed in the previous section how constituents of the type shown in (21) can generate intonationally annotated strings. The resulting string for the current example is &amp;quot;wodgets@lhstar include@lhb sprockets@\[hstar, llb\].&amp;quot; The final aspect of generation involves translating such a string into a form usable by a suitable speech synthesiser. Currently, we use the Bell Laboratories ITS system (\[5\]) as a post-processor to synthesise the speech wave. Example (28) shows the translated output for the same example, as it is sent to this synthesiser.</Paragraph>
    <Paragraph position="1">  We stress that we use TTS as an unmodified output device, without any fine tuning other than in the lexicon. While TTS is particularly easy to use with Pierrehumbert's notation, we are confident that our system can easily be adapted to other synthesisers.</Paragraph>
  </Section>
class="xml-element"></Paper>