@inproceedings{maeda-etal-2006-low,
title = "Low-cost Customized Speech Corpus Creation for Speech Technology Applications",
author = "Maeda, Kazuaki and
Cieri, Christopher and
Walker, Kevin",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/776_pdf.pdf",
abstract = "Speech technology applications, such as speech recognition, speech synthesis, and speech dialog systems, often require corpora based on highly customized specifications. Existing corpora available to the community, such as TIMIT and other corpora distributed by LDC and ELDA, do not always meet the requirements of such applications. In such cases, the developers need to create their own corpora. The creation of a highly customized speech corpus, however, could be a very expensive and time-consuming task, especially for small organizations. It requires multidisciplinary expertise in linguistics, management and engineering as it involves subtasks such as the corpus design, human subject recruitment, recording, quality assurance, and in some cases, segmentation, transcription and annotation. This paper describes LDC's recent involvement in the creation of a low-cost yet highly-customized speech corpus for a commercial organization under a novel data creation and licensing model, which benefits both the particular data requester and the general linguistic data user community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maeda-etal-2006-low">
<titleInfo>
<title>Low-cost Customized Speech Corpus Creation for Speech Technology Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazuaki</namePart>
<namePart type="family">Maeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speech technology applications, such as speech recognition, speech synthesis, and speech dialog systems, often require corpora based on highly customized specifications. Existing corpora available to the community, such as TIMIT and other corpora distributed by LDC and ELDA, do not always meet the requirements of such applications. In such cases, the developers need to create their own corpora. The creation of a highly customized speech corpus, however, could be a very expensive and time-consuming task, especially for small organizations. It requires multidisciplinary expertise in linguistics, management and engineering as it involves subtasks such as the corpus design, human subject recruitment, recording, quality assurance, and in some cases, segmentation, transcription and annotation. This paper describes LDC’s recent involvement in the creation of a low-cost yet highly-customized speech corpus for a commercial organization under a novel data creation and licensing model, which benefits both the particular data requester and the general linguistic data user community.</abstract>
<identifier type="citekey">maeda-etal-2006-low</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/776_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Low-cost Customized Speech Corpus Creation for Speech Technology Applications
%A Maeda, Kazuaki
%A Cieri, Christopher
%A Walker, Kevin
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F maeda-etal-2006-low
%X Speech technology applications, such as speech recognition, speech synthesis, and speech dialog systems, often require corpora based on highly customized specifications. Existing corpora available to the community, such as TIMIT and other corpora distributed by LDC and ELDA, do not always meet the requirements of such applications. In such cases, the developers need to create their own corpora. The creation of a highly customized speech corpus, however, could be a very expensive and time-consuming task, especially for small organizations. It requires multidisciplinary expertise in linguistics, management and engineering as it involves subtasks such as the corpus design, human subject recruitment, recording, quality assurance, and in some cases, segmentation, transcription and annotation. This paper describes LDC’s recent involvement in the creation of a low-cost yet highly-customized speech corpus for a commercial organization under a novel data creation and licensing model, which benefits both the particular data requester and the general linguistic data user community.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/776_pdf.pdf
Markdown (Informal)
[Low-cost Customized Speech Corpus Creation for Speech Technology Applications](http://www.lrec-conf.org/proceedings/lrec2006/pdf/776_pdf.pdf) (Maeda et al., LREC 2006)
ACL