@inproceedings{alabau-martinez-2006-bilingual,
title = "Bilingual speech corpus in two phonetically similar languages",
author = "Alabau, Vicente and
Mart{\'\i}nez, Carlos D.",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/256_pdf.pdf",
abstract = "As Speech Recognition Systems improve, they become suitable for facingnew problems. Multilingual speech recognition is one such problems. In the present work, the case of the Comunitat Valenciana multilingual environment is studied. The official languages in the Comunitat Valenciana (Spanish and Valencian) share most of their acoustic units, and their vocabularies and syntax are quite similar. They have influenced each other for many years.A small corpus on an Information System task was developed for experimentationpurposes.This choice will make it possible to develop a working prototype in the future,and it is simple enough to build semi-automatic language models. The design of the acoustic corpus is discussed, showing that all combinations of accents have been studied (native, non-native speakers, male, female, etc.).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alabau-martinez-2006-bilingual">
<titleInfo>
<title>Bilingual speech corpus in two phonetically similar languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vicente</namePart>
<namePart type="family">Alabau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As Speech Recognition Systems improve, they become suitable for facingnew problems. Multilingual speech recognition is one such problems. In the present work, the case of the Comunitat Valenciana multilingual environment is studied. The official languages in the Comunitat Valenciana (Spanish and Valencian) share most of their acoustic units, and their vocabularies and syntax are quite similar. They have influenced each other for many years.A small corpus on an Information System task was developed for experimentationpurposes.This choice will make it possible to develop a working prototype in the future,and it is simple enough to build semi-automatic language models. The design of the acoustic corpus is discussed, showing that all combinations of accents have been studied (native, non-native speakers, male, female, etc.).</abstract>
<identifier type="citekey">alabau-martinez-2006-bilingual</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/256_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual speech corpus in two phonetically similar languages
%A Alabau, Vicente
%A Martínez, Carlos D.
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F alabau-martinez-2006-bilingual
%X As Speech Recognition Systems improve, they become suitable for facingnew problems. Multilingual speech recognition is one such problems. In the present work, the case of the Comunitat Valenciana multilingual environment is studied. The official languages in the Comunitat Valenciana (Spanish and Valencian) share most of their acoustic units, and their vocabularies and syntax are quite similar. They have influenced each other for many years.A small corpus on an Information System task was developed for experimentationpurposes.This choice will make it possible to develop a working prototype in the future,and it is simple enough to build semi-automatic language models. The design of the acoustic corpus is discussed, showing that all combinations of accents have been studied (native, non-native speakers, male, female, etc.).
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/256_pdf.pdf
Markdown (Informal)
[Bilingual speech corpus in two phonetically similar languages](http://www.lrec-conf.org/proceedings/lrec2006/pdf/256_pdf.pdf) (Alabau & Martínez, LREC 2006)
ACL