<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1025">
  <Title>Dependencies between Student State and Speech Recognition Problems in Spoken Tutoring Dialogues</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> Speech recognition problems are a reality in current spoken dialogue systems. In order to better understand these phenomena, we study dependencies between speech recognition problems and several higher level dialogue factors that define our notion of student state: frustration/anger, certainty and correctness. We apply Chi Square (kh2) analysis to a corpus of speech-based computer tutoring dialogues to discover these dependencies both within and across turns. Significant dependencies are combined to produce interesting insights regarding speech recognition problems and to propose new strategies for handling these problems.</Paragraph>
    <Paragraph position="1"> We also find that tutoring, as a new domain for speech applications, exhibits interesting tradeoffs and new factors to consider for spoken dialogue design.</Paragraph>
  </Section>
class="xml-element"></Paper>