@inproceedings{garcia-mateo-etal-2014-corilga,
title = "{CORILGA}: a {G}alician Multilevel Annotated Speech Corpus for Linguistic Analysis",
author = "Garc{\'i}a-Mateo, Carmen and
Cardenal, Antonio and
Regueira, Xos{\'e} Luis and
Rei, Elisa Fern{\'a}ndez and
Martinez, Marta and
Seara, Roberto and
Varela, Roc{\'i}o and
Basanta, Noem{\'i}",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}`14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L14-1579/",
pages = "2653--2657",
abstract = "This paper describes the CORILGA (Corpus Oral Informatizado da Lingua Galega). CORILGA is a large high-quality corpus of spoken Galician from the 1960s up to present-day, including both formal and informal spoken language from both standard and non-standard varieties, and across different generations and social levels. The corpus will be available to the research community upon completion. Galician is one of the EU languages that needs further research before highly effective language technology solutions can be implemented. A software repository for speech resources in Galician is also described. The repository includes a structured database, a graphical interface and processing tools. The use of a database enables to perform search in a simple and fast way based in a number of different criteria. The web-based user interface facilitates users the access to the different materials. Last but not least a set of transcription-based modules for automatic speech recognition has been developed, thus facilitating the orthographic labelling of the recordings."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-mateo-etal-2014-corilga">
<titleInfo>
<title>CORILGA: a Galician Multilevel Annotated Speech Corpus for Linguistic Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carmen</namePart>
<namePart type="family">García-Mateo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Cardenal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xosé</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Regueira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="given">Fernández</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Martinez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Seara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rocío</namePart>
<namePart type="family">Varela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noemí</namePart>
<namePart type="family">Basanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC‘14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the CORILGA (Corpus Oral Informatizado da Lingua Galega). CORILGA is a large high-quality corpus of spoken Galician from the 1960s up to present-day, including both formal and informal spoken language from both standard and non-standard varieties, and across different generations and social levels. The corpus will be available to the research community upon completion. Galician is one of the EU languages that needs further research before highly effective language technology solutions can be implemented. A software repository for speech resources in Galician is also described. The repository includes a structured database, a graphical interface and processing tools. The use of a database enables to perform search in a simple and fast way based in a number of different criteria. The web-based user interface facilitates users the access to the different materials. Last but not least a set of transcription-based modules for automatic speech recognition has been developed, thus facilitating the orthographic labelling of the recordings.</abstract>
<identifier type="citekey">garcia-mateo-etal-2014-corilga</identifier>
<location>
<url>https://aclanthology.org/L14-1579/</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2653</start>
<end>2657</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CORILGA: a Galician Multilevel Annotated Speech Corpus for Linguistic Analysis
%A García-Mateo, Carmen
%A Cardenal, Antonio
%A Regueira, Xosé Luis
%A Rei, Elisa Fernández
%A Martinez, Marta
%A Seara, Roberto
%A Varela, Rocío
%A Basanta, Noemí
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC‘14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F garcia-mateo-etal-2014-corilga
%X This paper describes the CORILGA (Corpus Oral Informatizado da Lingua Galega). CORILGA is a large high-quality corpus of spoken Galician from the 1960s up to present-day, including both formal and informal spoken language from both standard and non-standard varieties, and across different generations and social levels. The corpus will be available to the research community upon completion. Galician is one of the EU languages that needs further research before highly effective language technology solutions can be implemented. A software repository for speech resources in Galician is also described. The repository includes a structured database, a graphical interface and processing tools. The use of a database enables to perform search in a simple and fast way based in a number of different criteria. The web-based user interface facilitates users the access to the different materials. Last but not least a set of transcription-based modules for automatic speech recognition has been developed, thus facilitating the orthographic labelling of the recordings.
%U https://aclanthology.org/L14-1579/
%P 2653-2657
Markdown (Informal)
[CORILGA: a Galician Multilevel Annotated Speech Corpus for Linguistic Analysis](https://aclanthology.org/L14-1579/) (García-Mateo et al., LREC 2014)
ACL
- Carmen García-Mateo, Antonio Cardenal, Xosé Luis Regueira, Elisa Fernández Rei, Marta Martinez, Roberto Seara, Rocío Varela, and Noemí Basanta. 2014. CORILGA: a Galician Multilevel Annotated Speech Corpus for Linguistic Analysis. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2653–2657, Reykjavik, Iceland. European Language Resources Association (ELRA).