<?xml version="1.0" standalone="yes"?>
<Paper uid="H91-1010">
  <Title>New Results with the Lincoln Tied-Mixture HMM CSR System 1</Title>
  <Section position="7" start_page="66" end_page="66" type="evalu">
    <SectionTitle>
EVALUATION TESTS
</SectionTitle>
    <Paragraph position="0"> The SD and SI-109 RM evaluation tests were run with WPG and no grammar (NG). The systems are identical to the systems tested in the last set of evaluation tests\[ll\] except the enhanced duration models were used. The SD system used two observation streams and the SI-109 system used three observation streams. The average word error rates with the WPG are 1.77% and 4.39% respectively (Table 7).</Paragraph>
    <Paragraph position="1"> Due to the limited time between the distribution of the ATIS development data and the deadline for the evaluation tests, it was not possible to test all desired systems nor was it possible to adequately set the recognition parameters such as the grammar weight and word insertion penalty. As noted earlier, the open vocabulary, disfluencies, partial words, thinking noises, and extraneous noises were not modeled. The tested system is an SI TM-2 XW triphone system with the improved duration model. The test set perplexity of the class A test data was 24 with .8% out-of-vocabulary words using the informal baseline language model and the recognition word error rate was 26.5% (Table 8). The non-Class A test sets were also tested. Their results and perplexities are shown in Table 8. The recognition output sentences (top-l) were sent to Unisys to be input to their natural language system\[9\].</Paragraph>
  </Section>
class="xml-element"></Paper>