@inproceedings{ishimoto-etal-2014-towards,
title = "Towards Automatic Transformation between Different Transcription Conventions: Prediction of Intonation Markers from Linguistic and Acoustic Features",
author = "Ishimoto, Yuichi and
Tsuchiya, Tomoyuki and
Koiso, Hanae and
Den, Yasuharu",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/716_Paper.pdf",
pages = "311--315",
abstract = "Because of the tremendous effort required for recording and transcription, large-scale spoken language corpora have been hardly developed in Japanese, with a notable exception of the Corpus of Spontaneous Japanese (CSJ). Various research groups have individually developed conversation corpora in Japanese, but these corpora are transcribed by different conventions and have few annotations in common, and some of them lack fundamental annotations, which are prerequisites for conversation research. To solve this situation by sharing existing conversation corpora that cover diverse styles and settings, we have tried to automatically transform a transcription made by one convention into that made by another convention. Using a conversation corpus transcribed in both the Conversation-Analysis-style (CA-style) and CSJ-style, we analyzed the correspondence between CA{'}s {`}intonation markers{'} and CSJ{'}s {`}tone labels,{'} and constructed a statistical model that converts tone labels into intonation markers with reference to linguistic and acoustic features of the speech. The result showed that there is considerable variance in intonation marking even between trained transcribers. The model predicted with 85{\%} accuracy the presence of the intonation markers, and classified the types of the markers with 72{\%} accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ishimoto-etal-2014-towards">
<titleInfo>
<title>Towards Automatic Transformation between Different Transcription Conventions: Prediction of Intonation Markers from Linguistic and Acoustic Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuichi</namePart>
<namePart type="family">Ishimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Tsuchiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanae</namePart>
<namePart type="family">Koiso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuharu</namePart>
<namePart type="family">Den</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Because of the tremendous effort required for recording and transcription, large-scale spoken language corpora have been hardly developed in Japanese, with a notable exception of the Corpus of Spontaneous Japanese (CSJ). Various research groups have individually developed conversation corpora in Japanese, but these corpora are transcribed by different conventions and have few annotations in common, and some of them lack fundamental annotations, which are prerequisites for conversation research. To solve this situation by sharing existing conversation corpora that cover diverse styles and settings, we have tried to automatically transform a transcription made by one convention into that made by another convention. Using a conversation corpus transcribed in both the Conversation-Analysis-style (CA-style) and CSJ-style, we analyzed the correspondence between CA’s ‘intonation markers’ and CSJ’s ‘tone labels,’ and constructed a statistical model that converts tone labels into intonation markers with reference to linguistic and acoustic features of the speech. The result showed that there is considerable variance in intonation marking even between trained transcribers. The model predicted with 85% accuracy the presence of the intonation markers, and classified the types of the markers with 72% accuracy.</abstract>
<identifier type="citekey">ishimoto-etal-2014-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/716_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>311</start>
<end>315</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Automatic Transformation between Different Transcription Conventions: Prediction of Intonation Markers from Linguistic and Acoustic Features
%A Ishimoto, Yuichi
%A Tsuchiya, Tomoyuki
%A Koiso, Hanae
%A Den, Yasuharu
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F ishimoto-etal-2014-towards
%X Because of the tremendous effort required for recording and transcription, large-scale spoken language corpora have been hardly developed in Japanese, with a notable exception of the Corpus of Spontaneous Japanese (CSJ). Various research groups have individually developed conversation corpora in Japanese, but these corpora are transcribed by different conventions and have few annotations in common, and some of them lack fundamental annotations, which are prerequisites for conversation research. To solve this situation by sharing existing conversation corpora that cover diverse styles and settings, we have tried to automatically transform a transcription made by one convention into that made by another convention. Using a conversation corpus transcribed in both the Conversation-Analysis-style (CA-style) and CSJ-style, we analyzed the correspondence between CA’s ‘intonation markers’ and CSJ’s ‘tone labels,’ and constructed a statistical model that converts tone labels into intonation markers with reference to linguistic and acoustic features of the speech. The result showed that there is considerable variance in intonation marking even between trained transcribers. The model predicted with 85% accuracy the presence of the intonation markers, and classified the types of the markers with 72% accuracy.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/716_Paper.pdf
%P 311-315
Markdown (Informal)
[Towards Automatic Transformation between Different Transcription Conventions: Prediction of Intonation Markers from Linguistic and Acoustic Features](http://www.lrec-conf.org/proceedings/lrec2014/pdf/716_Paper.pdf) (Ishimoto et al., LREC 2014)
ACL