@inproceedings{adda-decker-etal-2008-developments,
title = {Developments of {``}L{\"e}tzebuergesch{''} Resources for Automatic Speech Processing and Linguistic Studies},
author = "Adda-Decker, Martine and
Pellegrini, Thomas and
Bilinski, Eric and
Adda, Gilles",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/855_paper.pdf",
abstract = {In the present contribution we start with an overview of the linguistic situation of Luxembourg. We then describe specificities of spoken and written L{\"e}tzebuergesch, with respect to automatic speech processing. Multilingual code-switching and code-mixing, poor writing standardization as compared to languages such as English or French, a large diversity of spoken varieties, together with a limited written production of L{\"e}tzebuergesch language contribute to pose many interesting challenges to automatic speech processing both for speech technologies and linguistic studies. Multilingual filtering has been investigated to sort out Luxembourgish from German and French. Word list coverage and language model perplexity results, using sibling resources collected from the Web, are presented. A phonemic inventory has been adopted for pronunciation dictionary development, a grapheme-phoneme tool has been developed and pronunciation research issues related to the multilingual context are highlighted. Results achieved in resource development allow to envision the realisation of an ASR system.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adda-decker-etal-2008-developments">
<titleInfo>
<title>Developments of “Lëtzebuergesch” Resources for Automatic Speech Processing and Linguistic Studies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martine</namePart>
<namePart type="family">Adda-Decker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Pellegrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Bilinski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Adda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the present contribution we start with an overview of the linguistic situation of Luxembourg. We then describe specificities of spoken and written Lëtzebuergesch, with respect to automatic speech processing. Multilingual code-switching and code-mixing, poor writing standardization as compared to languages such as English or French, a large diversity of spoken varieties, together with a limited written production of Lëtzebuergesch language contribute to pose many interesting challenges to automatic speech processing both for speech technologies and linguistic studies. Multilingual filtering has been investigated to sort out Luxembourgish from German and French. Word list coverage and language model perplexity results, using sibling resources collected from the Web, are presented. A phonemic inventory has been adopted for pronunciation dictionary development, a grapheme-phoneme tool has been developed and pronunciation research issues related to the multilingual context are highlighted. Results achieved in resource development allow to envision the realisation of an ASR system.</abstract>
<identifier type="citekey">adda-decker-etal-2008-developments</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/855_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developments of “Lëtzebuergesch” Resources for Automatic Speech Processing and Linguistic Studies
%A Adda-Decker, Martine
%A Pellegrini, Thomas
%A Bilinski, Eric
%A Adda, Gilles
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F adda-decker-etal-2008-developments
%X In the present contribution we start with an overview of the linguistic situation of Luxembourg. We then describe specificities of spoken and written Lëtzebuergesch, with respect to automatic speech processing. Multilingual code-switching and code-mixing, poor writing standardization as compared to languages such as English or French, a large diversity of spoken varieties, together with a limited written production of Lëtzebuergesch language contribute to pose many interesting challenges to automatic speech processing both for speech technologies and linguistic studies. Multilingual filtering has been investigated to sort out Luxembourgish from German and French. Word list coverage and language model perplexity results, using sibling resources collected from the Web, are presented. A phonemic inventory has been adopted for pronunciation dictionary development, a grapheme-phoneme tool has been developed and pronunciation research issues related to the multilingual context are highlighted. Results achieved in resource development allow to envision the realisation of an ASR system.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/855_paper.pdf
Markdown (Informal)
[Developments of “Lëtzebuergesch” Resources for Automatic Speech Processing and Linguistic Studies](http://www.lrec-conf.org/proceedings/lrec2008/pdf/855_paper.pdf) (Adda-Decker et al., LREC 2008)
ACL