<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-2120">
  <Title>CONSTRUCTION OF CORPUS-BASED SYNTACTIC RULES FOR ACCURATE SPEECH RECOGNITION JUNKO HOSAKA TOSHIYUKI TAKEZAWA ATR Interpreting Telephony Research Laboratories</Title>
  <Section position="6" start_page="40" end_page="40" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have described phrase-based syntactic rules which are used as constraints in the Japanese speech recognition module of our experimental speech-to-speech translation system. For constructing rules we took into account the error tendency in speech recognition.</Paragraph>
    <Paragraph position="1"> We treated precisely those syntactic categories which tend to be recognized erroneously. To increase the efficacy of each rule, the rule construction is strongly motivated by our dialogue corpus. By applying the refined phrase-based syntactic rules, the speech recognition rate for the top candidates improved from 37.2 % to 70.1% and for the top 5 candidates from 73.7 % to 83.9 %.</Paragraph>
    <Paragraph position="2"> The implementation of syntactic rules bascd on our dialogue corpus is continuing in order to increase coverage. Currently we are studying postposition deletion in nominal phrases, which is one of the features of spoken Japanese. When adding rules and enlarging vocabulary, we cammt avoid decreasing speech recognition accuracy, but our further experiments showed that careful rule construction filtered out unacceptable sentence candidates much more effectively.</Paragraph>
    <Paragraph position="3"> Though we believe that our dialogue corpus for the, current domain provides enough expressions of spoken Japanese, we are going to apply the same method to other domains to establish the generality of the rules.</Paragraph>
  </Section>
class="xml-element"></Paper>