<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1042">
  <Title>INTEGRATED TECHNIQUES FOR PHRASE EXTRACTION FROM SPEECH</Title>
  <Section position="7" start_page="232" end_page="232" type="concl">
    <SectionTitle>
FUTURE WORK
</SectionTitle>
    <Paragraph position="0"> We have shown the the approach described here both improves overall word accuracy in recognition and provides a means for extracting targeted information even recognition performance is quite poor. Our next goal is to apply the technique to new domains. As part of this effort we are developing a set of tools for building and evaluating grammars.</Paragraph>
    <Paragraph position="1"> We are also also applying these techniques in new applications. In particular, we have recently performed experiments in Event Spotting, which is an extension of wordspotting where the goal is to determine the location of phrases, rather than single keywords. We used the parser/extraction portion of the system to find examples of phrase types in the corpus and to evaluate the results, as well as in the language model of the recognizer. In an experiment detecting time and date phrases in the Switchboard corpus (which is conversational telephone quality data), we saw an increase in detection rate over strictly bi-gram or phoneme loop language models (Jeanrenaud, et al. 1994).</Paragraph>
    <Paragraph position="2"> Acknowledgement This work was funded by ARPA and the Air Force Rome Laboratory under contract F30602-89C-0170. null</Paragraph>
  </Section>
class="xml-element"></Paper>