<?xml version="1.0" standalone="yes"?>
<Paper uid="H93-1017">
  <Title>Vassilios Digalakis</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Many advanced speech recognition techniques cannot be developed or used in practical speech recognition systems because of their extreme computational requirements. Simpler speech recognition techniques can be used to recognize speech in reasonable time, but they compromise word recognition accuracy. In this paper we aim to improve the speed/accuracy trade-off in speeeh recognition systems using progressive search techniques.</Paragraph>
    <Paragraph position="1"> We define progressive search techniques as those which can be used to efficiently implement other, computationally burdensome techniques. They use results of a simple and fast speech recognition technique to constrain the search space of a following more accurate but slower running technique. This may be done iteratively---each progressive search pass uses a previous pass' constraints to run more ettieiently, and provides more constraints for subsequent passes.</Paragraph>
    <Paragraph position="2"> We will refer to the faster speech recognition techniques as &amp;quot;earlier-pass techniques&amp;quot;, and the slower more accurate techniques as &amp;quot;advanced techniques.&amp;quot; Constraining the costly advanced techniques in this way can make them run significantly faster without significant loss in accuracy.</Paragraph>
    <Paragraph position="3"> The key notions in progressive search techniques are:  1. An early-pass speech recognition phase builds a lattice, which contains all the likely recognition unit strings (e.g. word sequences) given the techniques used in that recognition pass.</Paragraph>
    <Paragraph position="4"> 2. A subsequent pass uses this lattice as a grammar that  constrains the search space of an advanced technique (e.g., only the word sequences contained in a word lattice of pass p would be considered in pass p+l).</Paragraph>
    <Paragraph position="5"> Allowing a sufficient breadth of lattice entries should allow later passes to recover the correct word sequence, while ruling out very unlikely sequences, thus achieving high accuracy and high speed speech recognition.</Paragraph>
  </Section>
class="xml-element"></Paper>