<?xml version="1.0" standalone="yes"?>
<Paper uid="H91-1049">
  <Title>A DYNAMICAL SYSTEM APPROACH TO CONTINUOUS SPEECH RECOGNITION</Title>
  <Section position="9" start_page="254" end_page="254" type="concl">
    <SectionTitle>
CONCLUSION
</SectionTitle>
    <Paragraph position="0"> In this paper, we have shown that segment model based on a stochastic linear system model which incorporates a modeling/observation noise term is effective for speech recognition. We have shown that classification performance using this model is significantly better than is obtained using either an independent-frame or a Gauss-Markov assumption on the observed frames. Finally, we have presented a novel approach to the system parameter estimation problem based on the EM algorithm.</Paragraph>
  </Section>
class="xml-element"></Paper>