<?xml version="1.0" standalone="yes"?>
<Paper uid="H93-1041">
  <Title>RECENT ADVANCES IN JANUS: A SPEECH TRANSLATION SYSTEM</Title>
  <Section position="8" start_page="215" end_page="215" type="concl">
    <SectionTitle>
5. CONCLUSION
</SectionTitle>
    <Paragraph position="0"> In this paper, we have discussed recent extensions to the JANUS system a speaker independent multi-lingual speech-to-speech translation system under development at Carnegie Mellon and Karlsruhe University. The components include an speech recognition using an N-best sentence search, to derive alternate hypotheses for later processing during the translation. The MT component attempts to produce a high-accuracy translation using precise syntactic and semantic analysis. Should this analysis fail due to ill-formed input or misrecognitions, a connectionist parser, PARSEC, and a semantic parser produce alternative minimalist analyses, to at least establish the basic meaning of an input utterance. Human-to-human dialogs appear to generate a larger and more varied breadth of expression than human-machine dialogs. Further research is in progress to quantify this observation and to increase robustness and coverage of the system in this environment. null</Paragraph>
  </Section>
class="xml-element"></Paper>