@inproceedings{kamiya-etal-2010-construction,
title = "Construction of Back-Channel Utterance Corpus for Responsive Spoken Dialogue System Development",
author = "Kamiya, Yuki and
Ohno, Tomohiro and
Matsubara, Shigeki and
Kashioka, Hideki",
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/260_Paper.pdf",
abstract = "In spoken dialogues, if a spoken dialogue system does not respond at all during users utterances, the user might feel uneasy because the user does not know whether or not the system has recognized the utterances. In particular, back-channel utterances, which the system outputs as voices such as yeah and uh huh in English have important roles for a driver in in-car speech dialogues because the driver does not look owards a listener while driving. This paper describes construction of a back-channel utterance corpus and its analysis to develop the system which can output back-channel utterances at the proper timing in the responsive in-car speech dialogue. First, we constructed the back-channel utterance corpus by integrating the back-channel utterances that four subjects provided for the drivers utterances in 60 dialogues in the CIAIR in-car speech dialogue corpus. Next, we analyzed the corpus and revealed the relation between back-channel utterance timings and information on bunsetsu, clause, pause and rate of speech. Based on the analysis, we examined the possibility of detecting back-channel utterance timings by machine learning technique. As the result of the experiment, we confirmed that our technique achieved as same detection capability as a human.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kamiya-etal-2010-construction">
<titleInfo>
<title>Construction of Back-Channel Utterance Corpus for Responsive Spoken Dialogue System Development</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Kamiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomohiro</namePart>
<namePart type="family">Ohno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shigeki</namePart>
<namePart type="family">Matsubara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Kashioka</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>In spoken dialogues, if a spoken dialogue system does not respond at all during users utterances, the user might feel uneasy because the user does not know whether or not the system has recognized the utterances. In particular, back-channel utterances, which the system outputs as voices such as yeah and uh huh in English have important roles for a driver in in-car speech dialogues because the driver does not look owards a listener while driving. This paper describes construction of a back-channel utterance corpus and its analysis to develop the system which can output back-channel utterances at the proper timing in the responsive in-car speech dialogue. First, we constructed the back-channel utterance corpus by integrating the back-channel utterances that four subjects provided for the drivers utterances in 60 dialogues in the CIAIR in-car speech dialogue corpus. Next, we analyzed the corpus and revealed the relation between back-channel utterance timings and information on bunsetsu, clause, pause and rate of speech. Based on the analysis, we examined the possibility of detecting back-channel utterance timings by machine learning technique. As the result of the experiment, we confirmed that our technique achieved as same detection capability as a human.</abstract>
<identifier type="citekey">kamiya-etal-2010-construction</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/260_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Construction of Back-Channel Utterance Corpus for Responsive Spoken Dialogue System Development
%A Kamiya, Yuki
%A Ohno, Tomohiro
%A Matsubara, Shigeki
%A Kashioka, Hideki
%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 kamiya-etal-2010-construction
%X In spoken dialogues, if a spoken dialogue system does not respond at all during users utterances, the user might feel uneasy because the user does not know whether or not the system has recognized the utterances. In particular, back-channel utterances, which the system outputs as voices such as yeah and uh huh in English have important roles for a driver in in-car speech dialogues because the driver does not look owards a listener while driving. This paper describes construction of a back-channel utterance corpus and its analysis to develop the system which can output back-channel utterances at the proper timing in the responsive in-car speech dialogue. First, we constructed the back-channel utterance corpus by integrating the back-channel utterances that four subjects provided for the drivers utterances in 60 dialogues in the CIAIR in-car speech dialogue corpus. Next, we analyzed the corpus and revealed the relation between back-channel utterance timings and information on bunsetsu, clause, pause and rate of speech. Based on the analysis, we examined the possibility of detecting back-channel utterance timings by machine learning technique. As the result of the experiment, we confirmed that our technique achieved as same detection capability as a human.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/260_Paper.pdf
Markdown (Informal)
[Construction of Back-Channel Utterance Corpus for Responsive Spoken Dialogue System Development](http://www.lrec-conf.org/proceedings/lrec2010/pdf/260_Paper.pdf) (Kamiya et al., LREC 2010)
ACL