@inproceedings{fauth-etal-2014-designing,
title = "Designing a Bilingual Speech Corpus for {F}rench and {G}erman Language Learners: a Two-Step Process",
author = {Fauth, Camille and
Bonneau, Anne and
Zimmerer, Frank and
Trouvain, Juergen and
Andreeva, Bistra and
Colotte, Vincent and
Fohr, Dominique and
Jouvet, Denis and
J{\"u}gler, Jeanin and
Laprie, Yves and
Mella, Odile and
M{\"o}bius, Bernd},
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/484_Paper.pdf",
pages = "1477--1482",
abstract = "We present the design of a corpus of native and non-native speech for the language pair French-German, with a special emphasis on phonetic and prosodic aspects. To our knowledge there is no suitable corpus, in terms of size and coverage, currently available for the target language pair. To select the target L1-L2 interference phenomena we prepare a small preliminary corpus (corpus1), which is analyzed for coverage and cross-checked jointly by French and German experts. Based on this analysis, target phenomena on the phonetic and phonological level are selected on the basis of the expected degree of deviation from the native performance and the frequency of occurrence. 14 speakers performed both L2 (either French or German) and L1 material (either German or French). This allowed us to test, recordings duration, recordings material, the performance of our automatic aligner software. Then, we built corpus2 taking into account what we learned about corpus1. The aims are the same but we adapted speech material to avoid too long recording sessions. 100 speakers will be recorded. The corpus (corpus1 and corpus2) will be prepared as a searchable database, available for the scientific community after completion of the project.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fauth-etal-2014-designing">
<titleInfo>
<title>Designing a Bilingual Speech Corpus for French and German Language Learners: a Two-Step Process</title>
</titleInfo>
<name type="personal">
<namePart type="given">Camille</namePart>
<namePart type="family">Fauth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Bonneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Zimmerer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juergen</namePart>
<namePart type="family">Trouvain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bistra</namePart>
<namePart type="family">Andreeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Colotte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominique</namePart>
<namePart type="family">Fohr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Jouvet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeanin</namePart>
<namePart type="family">Jügler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Laprie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Odile</namePart>
<namePart type="family">Mella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernd</namePart>
<namePart type="family">Möbius</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 the design of a corpus of native and non-native speech for the language pair French-German, with a special emphasis on phonetic and prosodic aspects. To our knowledge there is no suitable corpus, in terms of size and coverage, currently available for the target language pair. To select the target L1-L2 interference phenomena we prepare a small preliminary corpus (corpus1), which is analyzed for coverage and cross-checked jointly by French and German experts. Based on this analysis, target phenomena on the phonetic and phonological level are selected on the basis of the expected degree of deviation from the native performance and the frequency of occurrence. 14 speakers performed both L2 (either French or German) and L1 material (either German or French). This allowed us to test, recordings duration, recordings material, the performance of our automatic aligner software. Then, we built corpus2 taking into account what we learned about corpus1. The aims are the same but we adapted speech material to avoid too long recording sessions. 100 speakers will be recorded. The corpus (corpus1 and corpus2) will be prepared as a searchable database, available for the scientific community after completion of the project.</abstract>
<identifier type="citekey">fauth-etal-2014-designing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/484_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1477</start>
<end>1482</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Designing a Bilingual Speech Corpus for French and German Language Learners: a Two-Step Process
%A Fauth, Camille
%A Bonneau, Anne
%A Zimmerer, Frank
%A Trouvain, Juergen
%A Andreeva, Bistra
%A Colotte, Vincent
%A Fohr, Dominique
%A Jouvet, Denis
%A Jügler, Jeanin
%A Laprie, Yves
%A Mella, Odile
%A Möbius, Bernd
%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 fauth-etal-2014-designing
%X We present the design of a corpus of native and non-native speech for the language pair French-German, with a special emphasis on phonetic and prosodic aspects. To our knowledge there is no suitable corpus, in terms of size and coverage, currently available for the target language pair. To select the target L1-L2 interference phenomena we prepare a small preliminary corpus (corpus1), which is analyzed for coverage and cross-checked jointly by French and German experts. Based on this analysis, target phenomena on the phonetic and phonological level are selected on the basis of the expected degree of deviation from the native performance and the frequency of occurrence. 14 speakers performed both L2 (either French or German) and L1 material (either German or French). This allowed us to test, recordings duration, recordings material, the performance of our automatic aligner software. Then, we built corpus2 taking into account what we learned about corpus1. The aims are the same but we adapted speech material to avoid too long recording sessions. 100 speakers will be recorded. The corpus (corpus1 and corpus2) will be prepared as a searchable database, available for the scientific community after completion of the project.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/484_Paper.pdf
%P 1477-1482
Markdown (Informal)
[Designing a Bilingual Speech Corpus for French and German Language Learners: a Two-Step Process](http://www.lrec-conf.org/proceedings/lrec2014/pdf/484_Paper.pdf) (Fauth et al., LREC 2014)
ACL
- Camille Fauth, Anne Bonneau, Frank Zimmerer, Juergen Trouvain, Bistra Andreeva, Vincent Colotte, Dominique Fohr, Denis Jouvet, Jeanin Jügler, Yves Laprie, Odile Mella, and Bernd Möbius. 2014. Designing a Bilingual Speech Corpus for French and German Language Learners: a Two-Step Process. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1477–1482, Reykjavik, Iceland. European Language Resources Association (ELRA).