@inproceedings{demuynck-etal-2004-automatic,
title = "Automatic Phonemic Labeling and Segmentation of Spoken {D}utch",
author = "Demuynck, Kris and
Laureys, Tom and
Wambacq, Patrick and
Van Compernolle, Dirk",
editor = "Lino, Maria Teresa and
Xavier, Maria Francisca and
Ferreira, F{\'a}tima and
Costa, Rute and
Silva, Raquel",
booktitle = "Proceedings of the Fourth International Conference on Language Resources and Evaluation ({LREC}{'}04)",
month = may,
year = "2004",
address = "Lisbon, Portugal",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2004/pdf/447.pdf",
abstract = "The CGN corpus (Corpus Gesproken Nederlands/Corpus Spoken Dutch) is a large speech corpus of contemporary Dutch as spoken in Belgium (3.3 million words) and in the Netherlands (5.6 million words). Due to its size, manual phonemic annotation was limited to 10{\%} of the data and automatic systems were used to complement this data. This paper describes the automatic generation of the phonemic annotations and the corresponding segmentations. First, we detail the processes used to generate possible pronunciations for each sentence and to select to most likely one. Next, we identify the remaining difficulties when handling the CGN data and explain how we solved them. We conclude with an evaluation of the quality of the resulting transcriptions and segmentations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="demuynck-etal-2004-automatic">
<titleInfo>
<title>Automatic Phonemic Labeling and Segmentation of Spoken Dutch</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kris</namePart>
<namePart type="family">Demuynck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Laureys</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Wambacq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Van Compernolle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2004-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Teresa</namePart>
<namePart type="family">Lino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Francisca</namePart>
<namePart type="family">Xavier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fátima</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rute</namePart>
<namePart type="family">Costa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Lisbon, Portugal</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The CGN corpus (Corpus Gesproken Nederlands/Corpus Spoken Dutch) is a large speech corpus of contemporary Dutch as spoken in Belgium (3.3 million words) and in the Netherlands (5.6 million words). Due to its size, manual phonemic annotation was limited to 10% of the data and automatic systems were used to complement this data. This paper describes the automatic generation of the phonemic annotations and the corresponding segmentations. First, we detail the processes used to generate possible pronunciations for each sentence and to select to most likely one. Next, we identify the remaining difficulties when handling the CGN data and explain how we solved them. We conclude with an evaluation of the quality of the resulting transcriptions and segmentations.</abstract>
<identifier type="citekey">demuynck-etal-2004-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2004/pdf/447.pdf</url>
</location>
<part>
<date>2004-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Phonemic Labeling and Segmentation of Spoken Dutch
%A Demuynck, Kris
%A Laureys, Tom
%A Wambacq, Patrick
%A Van Compernolle, Dirk
%Y Lino, Maria Teresa
%Y Xavier, Maria Francisca
%Y Ferreira, Fátima
%Y Costa, Rute
%Y Silva, Raquel
%S Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)
%D 2004
%8 May
%I European Language Resources Association (ELRA)
%C Lisbon, Portugal
%F demuynck-etal-2004-automatic
%X The CGN corpus (Corpus Gesproken Nederlands/Corpus Spoken Dutch) is a large speech corpus of contemporary Dutch as spoken in Belgium (3.3 million words) and in the Netherlands (5.6 million words). Due to its size, manual phonemic annotation was limited to 10% of the data and automatic systems were used to complement this data. This paper describes the automatic generation of the phonemic annotations and the corresponding segmentations. First, we detail the processes used to generate possible pronunciations for each sentence and to select to most likely one. Next, we identify the remaining difficulties when handling the CGN data and explain how we solved them. We conclude with an evaluation of the quality of the resulting transcriptions and segmentations.
%U http://www.lrec-conf.org/proceedings/lrec2004/pdf/447.pdf
Markdown (Informal)
[Automatic Phonemic Labeling and Segmentation of Spoken Dutch](http://www.lrec-conf.org/proceedings/lrec2004/pdf/447.pdf) (Demuynck et al., LREC 2004)
ACL
- Kris Demuynck, Tom Laureys, Patrick Wambacq, and Dirk Van Compernolle. 2004. Automatic Phonemic Labeling and Segmentation of Spoken Dutch. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04), Lisbon, Portugal. European Language Resources Association (ELRA).