@inproceedings{honda-akiba-2010-language,
title = "Language Modeling Approach for Retrieving Passages in Lecture Audio Data",
author = "Honda, Koichiro and
Akiba, Tomoyosi",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/462_Paper.pdf",
abstract = "Spoken Document Retrieval (SDR) is a promising technology for enhancing the utility of spoken materials. After the spoken documents have been transcribed by using a Large Vocabulary Continuous Speech Recognition (LVCSR) decoder, a text-based ad hoc retrieval method can be applied directly to the transcribed documents. However, recognition errors will significantly degrade the retrieval performance. To address this problem, we have previously proposed a method that aimed to fill the gap between automatically transcribed text and correctly transcribed text by using a statistical translation technique. In this paper, we extend the method by (1) using neighboring context to index the target passage, and (2) applying a language modeling approach for document retrieval. Our experimental evaluation shows that context information can improve retrieval performance, and that the language modeling approach is effective in incorporating context information into the proposed SDR method, which uses a translation model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="honda-akiba-2010-language">
<titleInfo>
<title>Language Modeling Approach for Retrieving Passages in Lecture Audio Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Koichiro</namePart>
<namePart type="family">Honda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyosi</namePart>
<namePart type="family">Akiba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Spoken Document Retrieval (SDR) is a promising technology for enhancing the utility of spoken materials. After the spoken documents have been transcribed by using a Large Vocabulary Continuous Speech Recognition (LVCSR) decoder, a text-based ad hoc retrieval method can be applied directly to the transcribed documents. However, recognition errors will significantly degrade the retrieval performance. To address this problem, we have previously proposed a method that aimed to fill the gap between automatically transcribed text and correctly transcribed text by using a statistical translation technique. In this paper, we extend the method by (1) using neighboring context to index the target passage, and (2) applying a language modeling approach for document retrieval. Our experimental evaluation shows that context information can improve retrieval performance, and that the language modeling approach is effective in incorporating context information into the proposed SDR method, which uses a translation model.</abstract>
<identifier type="citekey">honda-akiba-2010-language</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/462_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Modeling Approach for Retrieving Passages in Lecture Audio Data
%A Honda, Koichiro
%A Akiba, Tomoyosi
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F honda-akiba-2010-language
%X Spoken Document Retrieval (SDR) is a promising technology for enhancing the utility of spoken materials. After the spoken documents have been transcribed by using a Large Vocabulary Continuous Speech Recognition (LVCSR) decoder, a text-based ad hoc retrieval method can be applied directly to the transcribed documents. However, recognition errors will significantly degrade the retrieval performance. To address this problem, we have previously proposed a method that aimed to fill the gap between automatically transcribed text and correctly transcribed text by using a statistical translation technique. In this paper, we extend the method by (1) using neighboring context to index the target passage, and (2) applying a language modeling approach for document retrieval. Our experimental evaluation shows that context information can improve retrieval performance, and that the language modeling approach is effective in incorporating context information into the proposed SDR method, which uses a translation model.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/462_Paper.pdf
Markdown (Informal)
[Language Modeling Approach for Retrieving Passages in Lecture Audio Data](http://www.lrec-conf.org/proceedings/lrec2010/pdf/462_Paper.pdf) (Honda & Akiba, LREC 2010)
ACL