@inproceedings{raso-etal-2012-c,
title = "The {C}-{ORAL}-{BRASIL} {I}: Reference Corpus for Spoken {B}razilian {P}ortuguese",
author = "Raso, Tommaso and
Mello, Heliana and
Mittmann, Maryual{\^e} Malvessi",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/624_Paper.pdf",
pages = "106--113",
abstract = "C-ORAL-BRASIL I is a Brazilian Portuguese spontaneous speech corpus compiled following the same architecture adopted by the C-ORAL-ROM resource. The main goal is the documentation of the diaphasic and diastratic variations in Brazilian Portuguese. The diatopic variety represented is that of the metropolitan area of Belo Horizonte, capital city of Minas Gerais. Even though it was not a primary goal, a nice balance was achieved in terms of speakers' diastratic features (sex, age and school level). The corpus is entirely dedicated to informal spontaneous speech and comprises 139 informal speech texts, 208,130 words and 21:08:52 hours of recording, distributed into family/private (80{\%}) and public (20{\%}) contexts. The LR includes audio files, transcripts in text format and text-to-speech alignment (accessible with WinPitch Pro software). C-ORAL-BRASIL I also provides transcripts with Part-of-Speech annotation implemented through the parser system Palavras. Transcripts were validated regarding the proper application of transcription criteria and also for the annotation of prosodic boundaries. Some quantitative features of C-ORAL-BRASIL I in comparison with the informal C-ORAL-ROM are reported.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raso-etal-2012-c">
<titleInfo>
<title>The C-ORAL-BRASIL I: Reference Corpus for Spoken Brazilian Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Raso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heliana</namePart>
<namePart type="family">Mello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryualê</namePart>
<namePart type="given">Malvessi</namePart>
<namePart type="family">Mittmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>C-ORAL-BRASIL I is a Brazilian Portuguese spontaneous speech corpus compiled following the same architecture adopted by the C-ORAL-ROM resource. The main goal is the documentation of the diaphasic and diastratic variations in Brazilian Portuguese. The diatopic variety represented is that of the metropolitan area of Belo Horizonte, capital city of Minas Gerais. Even though it was not a primary goal, a nice balance was achieved in terms of speakers’ diastratic features (sex, age and school level). The corpus is entirely dedicated to informal spontaneous speech and comprises 139 informal speech texts, 208,130 words and 21:08:52 hours of recording, distributed into family/private (80%) and public (20%) contexts. The LR includes audio files, transcripts in text format and text-to-speech alignment (accessible with WinPitch Pro software). C-ORAL-BRASIL I also provides transcripts with Part-of-Speech annotation implemented through the parser system Palavras. Transcripts were validated regarding the proper application of transcription criteria and also for the annotation of prosodic boundaries. Some quantitative features of C-ORAL-BRASIL I in comparison with the informal C-ORAL-ROM are reported.</abstract>
<identifier type="citekey">raso-etal-2012-c</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/624_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>106</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The C-ORAL-BRASIL I: Reference Corpus for Spoken Brazilian Portuguese
%A Raso, Tommaso
%A Mello, Heliana
%A Mittmann, Maryualê Malvessi
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F raso-etal-2012-c
%X C-ORAL-BRASIL I is a Brazilian Portuguese spontaneous speech corpus compiled following the same architecture adopted by the C-ORAL-ROM resource. The main goal is the documentation of the diaphasic and diastratic variations in Brazilian Portuguese. The diatopic variety represented is that of the metropolitan area of Belo Horizonte, capital city of Minas Gerais. Even though it was not a primary goal, a nice balance was achieved in terms of speakers’ diastratic features (sex, age and school level). The corpus is entirely dedicated to informal spontaneous speech and comprises 139 informal speech texts, 208,130 words and 21:08:52 hours of recording, distributed into family/private (80%) and public (20%) contexts. The LR includes audio files, transcripts in text format and text-to-speech alignment (accessible with WinPitch Pro software). C-ORAL-BRASIL I also provides transcripts with Part-of-Speech annotation implemented through the parser system Palavras. Transcripts were validated regarding the proper application of transcription criteria and also for the annotation of prosodic boundaries. Some quantitative features of C-ORAL-BRASIL I in comparison with the informal C-ORAL-ROM are reported.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/624_Paper.pdf
%P 106-113
Markdown (Informal)
[The C-ORAL-BRASIL I: Reference Corpus for Spoken Brazilian Portuguese](http://www.lrec-conf.org/proceedings/lrec2012/pdf/624_Paper.pdf) (Raso et al., LREC 2012)
ACL