@inproceedings{cresti-etal-2004-c,
title = "The {C}-{ORAL}-{ROM} {CORPUS}. A Multilingual Resource of Spontaneous Speech for {R}omance Languages",
author = "Cresti, Emanuela and
do Nascimento, Fernanda Bacelar and
Sandoval, Antonio Moreno and
Veronis, Jean and
Martin, Philippe and
Choukri, Khalid",
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/357.pdf",
abstract = "The C-ORAL-ROM project has delivered a multilingual corpus of spontaneous speech for the main romance languages (Italian, French, Portuguese and Spanish). The collection aims to represent the variety of speech acts performed in everyday language and to enable the description of prosodic and syntactic structures in the four romance languages. Sampling criteria are defined in a corpus design scheme. C-ORAL-ROM adopts two different sampling strategies, one for the formal and one for the informal part: While a set of typical domains of application is selected to document the formal use of language, the informal part documents speech variation using parameters referring to the event{'}s structure (dialogue vs. monologue) and the sociological domain of use (family-private vs public). The four romance corpora are tagged with respect to terminal and non terminal prosodic breaks. Terminal breaks are assumed to be the more relevant cues for the identification of relevant linguistic domains in spontaneous speech (utterances). Relations with other concurrent criteria are discussed. The multimedia storage of the C-ORAL-ROM corpus is based on this principle; each textual string ending with a terminal break is aligned, through the Win Pitch speech software, to its acoustic counterpart, generating the data base of all utterances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cresti-etal-2004-c">
<titleInfo>
<title>The C-ORAL-ROM CORPUS. A Multilingual Resource of Spontaneous Speech for Romance Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emanuela</namePart>
<namePart type="family">Cresti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernanda</namePart>
<namePart type="given">Bacelar</namePart>
<namePart type="family">do Nascimento</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Moreno</namePart>
<namePart type="family">Sandoval</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean</namePart>
<namePart type="family">Veronis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</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 C-ORAL-ROM project has delivered a multilingual corpus of spontaneous speech for the main romance languages (Italian, French, Portuguese and Spanish). The collection aims to represent the variety of speech acts performed in everyday language and to enable the description of prosodic and syntactic structures in the four romance languages. Sampling criteria are defined in a corpus design scheme. C-ORAL-ROM adopts two different sampling strategies, one for the formal and one for the informal part: While a set of typical domains of application is selected to document the formal use of language, the informal part documents speech variation using parameters referring to the event’s structure (dialogue vs. monologue) and the sociological domain of use (family-private vs public). The four romance corpora are tagged with respect to terminal and non terminal prosodic breaks. Terminal breaks are assumed to be the more relevant cues for the identification of relevant linguistic domains in spontaneous speech (utterances). Relations with other concurrent criteria are discussed. The multimedia storage of the C-ORAL-ROM corpus is based on this principle; each textual string ending with a terminal break is aligned, through the Win Pitch speech software, to its acoustic counterpart, generating the data base of all utterances.</abstract>
<identifier type="citekey">cresti-etal-2004-c</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2004/pdf/357.pdf</url>
</location>
<part>
<date>2004-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The C-ORAL-ROM CORPUS. A Multilingual Resource of Spontaneous Speech for Romance Languages
%A Cresti, Emanuela
%A do Nascimento, Fernanda Bacelar
%A Sandoval, Antonio Moreno
%A Veronis, Jean
%A Martin, Philippe
%A Choukri, Khalid
%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 cresti-etal-2004-c
%X The C-ORAL-ROM project has delivered a multilingual corpus of spontaneous speech for the main romance languages (Italian, French, Portuguese and Spanish). The collection aims to represent the variety of speech acts performed in everyday language and to enable the description of prosodic and syntactic structures in the four romance languages. Sampling criteria are defined in a corpus design scheme. C-ORAL-ROM adopts two different sampling strategies, one for the formal and one for the informal part: While a set of typical domains of application is selected to document the formal use of language, the informal part documents speech variation using parameters referring to the event’s structure (dialogue vs. monologue) and the sociological domain of use (family-private vs public). The four romance corpora are tagged with respect to terminal and non terminal prosodic breaks. Terminal breaks are assumed to be the more relevant cues for the identification of relevant linguistic domains in spontaneous speech (utterances). Relations with other concurrent criteria are discussed. The multimedia storage of the C-ORAL-ROM corpus is based on this principle; each textual string ending with a terminal break is aligned, through the Win Pitch speech software, to its acoustic counterpart, generating the data base of all utterances.
%U http://www.lrec-conf.org/proceedings/lrec2004/pdf/357.pdf
Markdown (Informal)
[The C-ORAL-ROM CORPUS. A Multilingual Resource of Spontaneous Speech for Romance Languages](http://www.lrec-conf.org/proceedings/lrec2004/pdf/357.pdf) (Cresti et al., LREC 2004)
ACL