<?xml version="1.0" standalone="yes"?>
<Paper uid="H05-1119">
  <Title>Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), pages 947-954, Vancouver, October 2005. c(c)2005 Association for Computational Linguistics SEARCHING THE AUDIO NOTEBOOK: KEYWORD SEARCH IN RECORDED CONVERSATIONS</Title>
  <Section position="10" start_page="952" end_page="953" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we have presented a system for searching recordings of conversational speech, particularly meet- null phrase-posterior computation (shown for ICSI meeting set only).</Paragraph>
    <Paragraph position="1"> FOM word phoneme exact computation 72.1 82.3 node posterior ignored 72.0 79.2 relative change [%] -0.1 -3.8  is unindexed &amp;quot;linear search,&amp;quot; index lookup only (segments selected via the index without subsequent linear search), and the combination of both.</Paragraph>
    <Paragraph position="2"> test set linear index twosearch lookup stage  ings and telephone conversations. We identified user requirements as accurate ranking of phrase matches, domain independence, and reasonable response time. We have addressed these by hybrid word/phoneme lattice search and a supporting indexing scheme. Unlike many other spoken-document retrieval systems, we search recognition alternates instead of only speech recognition transcripts. This yields a significant improvement of key-word spotting accuracy. We have combined word-level search with phonetic search, which not only enables the system to handle the open-vocabulary problem, but also substantially improves in-vocabulary accuracy. We have proposed a posterior-lattice representation that allows for unified word and phoneme indexing and search. To speed up the search process, we proposed M-gram based lattice indexing, which extends our open vocabulary search ability for large collection of audio. Tested on five different recording sets including meetings, conversations, and interviews, a search accuracy (FOM) of 84% has been achieved - dramatically better than searching speech recognition transcripts (under 40%).</Paragraph>
    <Paragraph position="3">  search-enabled audio notebook.</Paragraph>
  </Section>
class="xml-element"></Paper>