@inproceedings{hernandez-mena-camacho-2014-ciempiess,
title = "{CIEMPIESS}: A New Open-Sourced {M}exican {S}panish Radio Corpus",
author = "Hernandez Mena, Carlos Daniel and
Camacho, Abel Herrera",
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 = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/182_Paper.pdf",
pages = "371--375",
abstract = "Corpus de Investigaci{\'o}n en Espa{\~n}ol de M{\'e}xico del Posgrado de Ingenier{\'\i}a El{\'e}ctrica y Servicio Social{''} (CIEMPIESS) is a new open-sourced corpus extracted from Spanish spoken FM podcasts in the dialect of the center of Mexico. The CIEMPIESS corpus was designed to be used in the field of automatic speech recongnition (ASR) and it is provided with two different kind of pronouncing dictionaries, one of them containing the phonemes of Mexican Spanish and the other containing this same phonemes plus allophones. Corpus annotation took into account the tonic vowel of every word and the four different sounds that letter {``}x{''} presents in the Spanish language. CIEMPIESS corpus is also provided with two different language models extracted from electronic newsletters, one of them takes into account the tonic vowels but not the other one. Both the dictionaries and the language models allow users to experiment different scenarios for the recognition task in order to adequate the corpus to their needs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hernandez-mena-camacho-2014-ciempiess">
<titleInfo>
<title>CIEMPIESS: A New Open-Sourced Mexican Spanish Radio Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="given">Daniel</namePart>
<namePart type="family">Hernandez Mena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abel</namePart>
<namePart type="given">Herrera</namePart>
<namePart type="family">Camacho</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>Corpus de Investigación en Español de México del Posgrado de Ingeniería Eléctrica y Servicio Social” (CIEMPIESS) is a new open-sourced corpus extracted from Spanish spoken FM podcasts in the dialect of the center of Mexico. The CIEMPIESS corpus was designed to be used in the field of automatic speech recongnition (ASR) and it is provided with two different kind of pronouncing dictionaries, one of them containing the phonemes of Mexican Spanish and the other containing this same phonemes plus allophones. Corpus annotation took into account the tonic vowel of every word and the four different sounds that letter “x” presents in the Spanish language. CIEMPIESS corpus is also provided with two different language models extracted from electronic newsletters, one of them takes into account the tonic vowels but not the other one. Both the dictionaries and the language models allow users to experiment different scenarios for the recognition task in order to adequate the corpus to their needs.</abstract>
<identifier type="citekey">hernandez-mena-camacho-2014-ciempiess</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/182_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>371</start>
<end>375</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CIEMPIESS: A New Open-Sourced Mexican Spanish Radio Corpus
%A Hernandez Mena, Carlos Daniel
%A Camacho, Abel Herrera
%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 hernandez-mena-camacho-2014-ciempiess
%X Corpus de Investigación en Español de México del Posgrado de Ingeniería Eléctrica y Servicio Social” (CIEMPIESS) is a new open-sourced corpus extracted from Spanish spoken FM podcasts in the dialect of the center of Mexico. The CIEMPIESS corpus was designed to be used in the field of automatic speech recongnition (ASR) and it is provided with two different kind of pronouncing dictionaries, one of them containing the phonemes of Mexican Spanish and the other containing this same phonemes plus allophones. Corpus annotation took into account the tonic vowel of every word and the four different sounds that letter “x” presents in the Spanish language. CIEMPIESS corpus is also provided with two different language models extracted from electronic newsletters, one of them takes into account the tonic vowels but not the other one. Both the dictionaries and the language models allow users to experiment different scenarios for the recognition task in order to adequate the corpus to their needs.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/182_Paper.pdf
%P 371-375
Markdown (Informal)
[CIEMPIESS: A New Open-Sourced Mexican Spanish Radio Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/182_Paper.pdf) (Hernandez Mena & Camacho, LREC 2014)
ACL
- Carlos Daniel Hernandez Mena and Abel Herrera Camacho. 2014. CIEMPIESS: A New Open-Sourced Mexican Spanish Radio Corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 371–375, Reykjavik, Iceland. European Language Resources Association (ELRA).