@inproceedings{baur-etal-2014-using,
title = "Using a Serious Game to Collect a Child Learner Speech Corpus",
author = "Baur, Claudia and
Rayner, Manny and
Tsourakis, Nikos",
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/787_Paper.pdf",
pages = "2726--2732",
abstract = "We present an English-L2 child learner speech corpus, produced by 14 year old Swiss German-L1 students in their third year of learning English, which is currently in the process of being collected. The collection method uses a web-enabled multimodal language game implemented using the CALL-SLT platform, in which subjects hold prompted conversations with an animated agent. Prompts consist of a short animated Engligh-language video clip together with a German-language piece of text indicating the semantic content of the requested response. Grammar-based speech understanding is used to decide whether responses are accepted or rejected, and dialogue flow is controlled using a simple XML-based scripting language; the scripts are written to allow multiple dialogue paths, the choice being made randomly. The system is gamified using a score-and-badge framework with four levels of badges. We describe the application, the data collection and annotation procedures, and the initial tranche of data. The full corpus, when complete, should contain at least 5,000 annotated utterances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baur-etal-2014-using">
<titleInfo>
<title>Using a Serious Game to Collect a Child Learner Speech Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Baur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manny</namePart>
<namePart type="family">Rayner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikos</namePart>
<namePart type="family">Tsourakis</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>We present an English-L2 child learner speech corpus, produced by 14 year old Swiss German-L1 students in their third year of learning English, which is currently in the process of being collected. The collection method uses a web-enabled multimodal language game implemented using the CALL-SLT platform, in which subjects hold prompted conversations with an animated agent. Prompts consist of a short animated Engligh-language video clip together with a German-language piece of text indicating the semantic content of the requested response. Grammar-based speech understanding is used to decide whether responses are accepted or rejected, and dialogue flow is controlled using a simple XML-based scripting language; the scripts are written to allow multiple dialogue paths, the choice being made randomly. The system is gamified using a score-and-badge framework with four levels of badges. We describe the application, the data collection and annotation procedures, and the initial tranche of data. The full corpus, when complete, should contain at least 5,000 annotated utterances.</abstract>
<identifier type="citekey">baur-etal-2014-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/787_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2726</start>
<end>2732</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using a Serious Game to Collect a Child Learner Speech Corpus
%A Baur, Claudia
%A Rayner, Manny
%A Tsourakis, Nikos
%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 baur-etal-2014-using
%X We present an English-L2 child learner speech corpus, produced by 14 year old Swiss German-L1 students in their third year of learning English, which is currently in the process of being collected. The collection method uses a web-enabled multimodal language game implemented using the CALL-SLT platform, in which subjects hold prompted conversations with an animated agent. Prompts consist of a short animated Engligh-language video clip together with a German-language piece of text indicating the semantic content of the requested response. Grammar-based speech understanding is used to decide whether responses are accepted or rejected, and dialogue flow is controlled using a simple XML-based scripting language; the scripts are written to allow multiple dialogue paths, the choice being made randomly. The system is gamified using a score-and-badge framework with four levels of badges. We describe the application, the data collection and annotation procedures, and the initial tranche of data. The full corpus, when complete, should contain at least 5,000 annotated utterances.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/787_Paper.pdf
%P 2726-2732
Markdown (Informal)
[Using a Serious Game to Collect a Child Learner Speech Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/787_Paper.pdf) (Baur et al., LREC 2014)
ACL