<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1087">
  <Title>Language Identification via Large Vocabulary Speaker Independent Continuous Speech Recognition</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> In this paper we describe preliminary work being conducted at Dragon Systems exploring the use of large vocabulary continuous speech recognition as an engine for automatically classifying spoken utterances by language.</Paragraph>
    <Paragraph position="1"> Several approaches to the problem of language identification have already appeared in the literature, but they generally address the problem as quite separate from the problem of speech recognition. For example, LIMSI \[1\] has reported results in French-English discrimination via phone recognition and a number of sites, such as OGI \[2\], have performed language classification by using broad phonetic labels and analyzing sets of phonological &amp;quot;features&amp;quot;. null Our approach to the problem of language identification grows naturally out of our model for the underlying stochastic process giving rise to speech. In earlier papers (\[3\], \[4\]) we have described our unified approach to the problems of topic and speaker identification via large vocabulary continuous speech recognition and demonstrated the success of this strategy even in classifying speech data in domains where the recognition task is far too difficult to obtain accurate transcriptions. We believe that the contextual information - both acoustic and language model - available in full-scale large vocabulary continuous speech recognition is invaluable in extracting reliable data from difficult speech channels. We now examine how this same framework supports work on the problem of language identification.</Paragraph>
    <Paragraph position="2"> In the next section we describe the theoretical foundations upon which our message classification systems are based and discuss some simplifying approximations introduced in their implementation. We then describe our initial testing of English-Spanish discrimination, primarily work with microphone data using our Wall Street Journal speech recognition system, but also work we are now beginning in language identification on telephone speech. Finally, we discuss some lessons learned from these early explorations and suggest plans for future work.</Paragraph>
  </Section>
class="xml-element"></Paper>