<?xml version="1.0" standalone="yes"?>
<Paper uid="H89-2047">
  <Title>Improvements in the Stochastic Segment Model for Phoneme Recognition</Title>
  <Section position="8" start_page="336" end_page="337" type="concl">
    <SectionTitle>
CONCLUSIONS
</SectionTitle>
    <Paragraph position="0"> In summary, we have shown that with sufficient training data, it is possible to model detailed time correlation in a segment-based model which can outperform HMMs in context-independent phoneme classification tasks. It remains to be shown that this result also holds for phoneme recognition, when phoneme segmentation boundaries are not known. In addition, the result should be extended to  new tasks, where automatic training will be required.</Paragraph>
    <Paragraph position="1"> There are several directions to further develop the SSM. Since context-dependent models have been shown to give dramatic improvements in HMM word recognition, it is important to demonstrate similar results for segment models. This will require research in robust paraameter estimation techniques. In addition, research on the variable-to-fixed length transformation is also important. Although a constrained transformatiou is probably an advantage of the segment model, it is not clear that linear time warping is the best transformation for all phonemes, and it may be useful to develop a mechanism for estimating transformations.</Paragraph>
  </Section>
class="xml-element"></Paper>