@inproceedings{duchateau-etal-2004-use,
title = "Use and Evaluation of Prosodic Annotations in {D}utch",
author = "Duchateau, Jacques and
Ceyssens, Tim and
Van hamme, Hugo",
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/304.pdf",
abstract = "In the development of annotations for a spoken database, an important issue is whether the annotations can be generated automatically with sufficient precision, or whether expensive manual annotations are needed. In this paper, the case of prosodic annotations is discussed, which was investigated on the CGN database (Spoken Dutch Corpus). The main conclusions of this work are as follows. First, it was found that the available amount of manual prosodic annotations is sufficient for the development of our (baseline, decision tree based) prosodic models. In other words, more manual annotations do not improve the models. Second, the developed prosodic models for prominence are insufficiently accurate to produce automatic prominence annotations that are as good as the manual ones. But on the other hand the consistency between manual and automatic break annotations is as high as the inter-transcriber consistency for breaks. So given the current amount of manual break annotations, annotations for the remainder of the CGN database can be generated automatically with the same quality as the manual annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duchateau-etal-2004-use">
<titleInfo>
<title>Use and Evaluation of Prosodic Annotations in Dutch</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacques</namePart>
<namePart type="family">Duchateau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Ceyssens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Van hamme</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>In the development of annotations for a spoken database, an important issue is whether the annotations can be generated automatically with sufficient precision, or whether expensive manual annotations are needed. In this paper, the case of prosodic annotations is discussed, which was investigated on the CGN database (Spoken Dutch Corpus). The main conclusions of this work are as follows. First, it was found that the available amount of manual prosodic annotations is sufficient for the development of our (baseline, decision tree based) prosodic models. In other words, more manual annotations do not improve the models. Second, the developed prosodic models for prominence are insufficiently accurate to produce automatic prominence annotations that are as good as the manual ones. But on the other hand the consistency between manual and automatic break annotations is as high as the inter-transcriber consistency for breaks. So given the current amount of manual break annotations, annotations for the remainder of the CGN database can be generated automatically with the same quality as the manual annotations.</abstract>
<identifier type="citekey">duchateau-etal-2004-use</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2004/pdf/304.pdf</url>
</location>
<part>
<date>2004-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Use and Evaluation of Prosodic Annotations in Dutch
%A Duchateau, Jacques
%A Ceyssens, Tim
%A Van hamme, Hugo
%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 duchateau-etal-2004-use
%X In the development of annotations for a spoken database, an important issue is whether the annotations can be generated automatically with sufficient precision, or whether expensive manual annotations are needed. In this paper, the case of prosodic annotations is discussed, which was investigated on the CGN database (Spoken Dutch Corpus). The main conclusions of this work are as follows. First, it was found that the available amount of manual prosodic annotations is sufficient for the development of our (baseline, decision tree based) prosodic models. In other words, more manual annotations do not improve the models. Second, the developed prosodic models for prominence are insufficiently accurate to produce automatic prominence annotations that are as good as the manual ones. But on the other hand the consistency between manual and automatic break annotations is as high as the inter-transcriber consistency for breaks. So given the current amount of manual break annotations, annotations for the remainder of the CGN database can be generated automatically with the same quality as the manual annotations.
%U http://www.lrec-conf.org/proceedings/lrec2004/pdf/304.pdf
Markdown (Informal)
[Use and Evaluation of Prosodic Annotations in Dutch](http://www.lrec-conf.org/proceedings/lrec2004/pdf/304.pdf) (Duchateau et al., LREC 2004)
ACL
- Jacques Duchateau, Tim Ceyssens, and Hugo Van hamme. 2004. Use and Evaluation of Prosodic Annotations in Dutch. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04), Lisbon, Portugal. European Language Resources Association (ELRA).