<?xml version="1.0" standalone="yes"?>
<Paper uid="N04-4034">
  <Title>Multi-Speaker Language Modeling</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> In conventional language modeling, the words from only one speaker at a time are represented, even for conversational tasks such as meetings and telephone calls. In a conversational or meeting setting, however, speakers can have signi cant in uence on each other.</Paragraph>
    <Paragraph position="1"> To recover such un-modeled inter-speaker information, we introduce an approach for conversational language modeling that considers words from other speakers when predicting words from the current one. By augmenting a normal trigram context, our new multi-speaker language model (MSLM) improves on both Switchboard and ICSI Meeting Recorder corpora. Using an MSLM and a conditional mutual information based word clustering algorithm, we achieve a 8.9% perplexity reduction on Switchboard and a 12.2% reduction on the</Paragraph>
  </Section>
class="xml-element"></Paper>