<?xml version="1.0" standalone="yes"?>
<Paper uid="P96-1038">
  <Title>A Prosodic Analysis of Discourse Segments in Direction- Giving Monologues</Title>
  <Section position="7" start_page="290" end_page="290" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> Although this paper reports results from only a single speaker, the findings are promising. We have demonstrated that a theory-based method for discourse analysis can provide reliable segmentations of spontaneous as well as read speech. In addition, the availability of speech in the text-and-speech labeling method led to significantly higher reliability scores.</Paragraph>
    <Paragraph position="1"> The stronger correlations found for intonational features of the text-and-speech labelings suggest not only that discourse labelers make use of prosody in their analyses, but also that obtaining such data can lead to more robust modeling of the relationship between intonation and discourse structure.</Paragraph>
    <Paragraph position="2"> The following preliminary results can be considered for incorporation in such a model. First, segment-initial utterances differ from medial and fi8We present results only for text-and-speech labelings; results for text-alone were quite similar. Note that 'increase' means that there is a significantly greater increase in f0, rms, or rate from prior to current phrase for category 1 than for category 2 of the comparison, and 'decrease' means that there is a significantly greater decrease. T-tests again were one-tailed unless marked by t, and significance levels were .002 or better except those marked by *, which were at .01 or better.</Paragraph>
    <Paragraph position="3"> nal utterances in both prominence and rhythmic properties. Segment-medial and segment-final utterances are distinguished more clearly by rhythmic features, primarily pause. Finally, all correlations found for global parameters can also be computed based on relative change in acoustic-prosodic parameters in a window of two phrases.</Paragraph>
    <Paragraph position="4"> Ongoing research is addressing the development of automatic classification algorithms for discourse boundary type; the role of prosody in conveying hierarchical relationships among discourse segments; individual speaker differences; and discourse segmentation methods that can be used by naive subjects.</Paragraph>
  </Section>
class="xml-element"></Paper>