<?xml version="1.0" standalone="yes"?>
<Paper uid="H89-1005">
  <Title>SPEAKER INDEPENDENT PHONETIC TRANSCRIPTION OF FLUENT SPEECH FOR LARGE VOCABULARY SPEECH RECOGNITION</Title>
  <Section position="3" start_page="0" end_page="75" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Though rarely explicitly stated, a fundamental assumption on which many speech recognition systems are implicitly based is that speech is literate. That is, it is a code for communication having a small number of discrete phonetic symbols in its alphabet. These symbols are, however, merely mental constructs and, as such, are not directly accessible but are, instead, observable only in their highly variable acoustic manifestation. It is also well-known but equally seldom expressed that a hidden Markov model comprises a finite set of discrete inaccessible states observable only via a set of random processes, one associated with each hidden state. When these two simple ideas are juxtaposed, it seems to us inescapable that the most natural representation of speech by a hidden Markov model is one in which the hypothetical phonetic symbols are identified with the hidden states of the Markov chain and the variability of the measurable acoustic signal is captured by the observable, state-dependent random processes.</Paragraph>
    <Paragraph position="1">  The mathematical details of just such a model are given in \[6\]. Its application to a smallvocabulary continuous speech recognition system and a large-vocabulary isolated word recognition system are described in \[7\] and \[8\], respectively. Here we present a brief overview of the use of this approach in large vocabulary continuous speech recognition and some preliminary results of two experiments performed with it on the TIMIT \[4\] and DARPA \[9\] databases.</Paragraph>
  </Section>
class="xml-element"></Paper>