<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1016">
  <Title>On Using Written Language Training Data for Spoken Language Modeling</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Speech recognition accuracy is affected as much by the language model as by the acoustic model. In general, the word error rate is roughly proportional to the square root of the perplexity of the language model. In addition, in a natural unlimited vocabulary task, a substantial portion of the word errors come from words that are not even in the recognition vocabulary. These out-of-vocabulary (OOV) words have no chance of being recognized correctly. Thus, our goal is to estimate a good language model from the available training text, and to determine a vocabulary that is likely to cover the test vocabulary.</Paragraph>
    <Paragraph position="1"> The straightforward solution to improving the language model might be to increase the complexity of the model (e.g., use a higher order Markov chain) and/or obtain more language model training text. But this by itself will not necessarily provide a better model, especially if the text is not an ideal model of what people will actltally say. The simple solution to increase the coverage of the vocabulary is to increase the vocabulary size. But this also increases the word error rate and the computation and size of the recognition process.</Paragraph>
    <Paragraph position="2"> In this paper we consider several simple techniques for improving the power of the language model. First, in Section 3, we explore the effect of increasing the vocabulary size on recognition accuracy in an unlimited vocabulary task. Second, in Section 4, we consider ways to model the differences between the language model Iraining text and the way people actually speak. And third, in Section 5, we show that simply increasing the amount of language model training helps significantly.</Paragraph>
  </Section>
class="xml-element"></Paper>