<?xml version="1.0" standalone="yes"?>
<Paper uid="H93-1020">
  <Title>ON THE USE OF TIED-MIXTURE DISTRIBUTIONS</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Tied-mixture (or semi-continuous) distributions have rapidly become an important tool for acoustic modeling in speech recognition since their introduction by Huang and Jack \[1\] and nellegarda and iahamoo \[2\], finding widespread use in a number of high-performance recognition systems. Tied mixtures have a number of advantageous properties that have contributed to their success. Like discrete, &amp;quot;non-parametric&amp;quot; distributions, tied mixtures can model a wide range of distributions including those with an &amp;quot;irregular shape,&amp;quot; while retaining the smoothed form characteristic of simpler parametric models. Additionally, because the component distributions of the mixtures are shared, the number of free parameters is reduced, and tied-mixtures have been found to produce robust estimates with relatively small amounts of training data. Under the general heading of tied mixtures, there are a number of possible choices of parameterization that lead to systems with different characteristics. This paper outlines these choices and provides a set of controlled experiments assessing tradeotis in speaker-independent recognition on the Resource Management corpus in the context of the stochastic segment model (SSM). In addition, we introduce new variations on training algorithms that reduce computational requirements and generalize the tied mixture formalism to include segment-level mixtures.</Paragraph>
  </Section>
class="xml-element"></Paper>