@inproceedings{hamed-etal-2020-arzen,
title = "{A}rz{E}n: A Speech Corpus for Code-switched {E}gyptian {A}rabic-{E}nglish",
author = "Hamed, Injy and
Vu, Ngoc Thang and
Abdennadher, Slim",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.523",
pages = "4237--4246",
abstract = "In this paper, we present our ArzEn corpus, an Egyptian Arabic-English code-switching (CS) spontaneous speech corpus. The corpus is collected through informal interviews with 38 Egyptian bilingual university students and employees held in a soundproof room. A total of 12 hours are recorded, transcribed, validated and sentence segmented. The corpus is mainly designed to be used in Automatic Speech Recognition (ASR) systems, however, it also provides a useful resource for analyzing the CS phenomenon from linguistic, sociological, and psychological perspectives. In this paper, we first discuss the CS phenomenon in Egypt and the factors that gave rise to the current language. We then provide a detailed description on how the corpus was collected, giving an overview on the participants involved. We also present statistics on the CS involved in the corpus, as well as a summary to the effort exerted in the corpus development, in terms of number of hours required for transcription, validation, segmentation and speaker annotation. Finally, we discuss some factors contributing to the complexity of the corpus, as well as Arabic-English CS behaviour that could pose potential challenges to ASR systems.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamed-etal-2020-arzen">
<titleInfo>
<title>ArzEn: A Speech Corpus for Code-switched Egyptian Arabic-English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc</namePart>
<namePart type="given">Thang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slim</namePart>
<namePart type="family">Abdennadher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this paper, we present our ArzEn corpus, an Egyptian Arabic-English code-switching (CS) spontaneous speech corpus. The corpus is collected through informal interviews with 38 Egyptian bilingual university students and employees held in a soundproof room. A total of 12 hours are recorded, transcribed, validated and sentence segmented. The corpus is mainly designed to be used in Automatic Speech Recognition (ASR) systems, however, it also provides a useful resource for analyzing the CS phenomenon from linguistic, sociological, and psychological perspectives. In this paper, we first discuss the CS phenomenon in Egypt and the factors that gave rise to the current language. We then provide a detailed description on how the corpus was collected, giving an overview on the participants involved. We also present statistics on the CS involved in the corpus, as well as a summary to the effort exerted in the corpus development, in terms of number of hours required for transcription, validation, segmentation and speaker annotation. Finally, we discuss some factors contributing to the complexity of the corpus, as well as Arabic-English CS behaviour that could pose potential challenges to ASR systems.</abstract>
<identifier type="citekey">hamed-etal-2020-arzen</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.523</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4237</start>
<end>4246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArzEn: A Speech Corpus for Code-switched Egyptian Arabic-English
%A Hamed, Injy
%A Vu, Ngoc Thang
%A Abdennadher, Slim
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F hamed-etal-2020-arzen
%X In this paper, we present our ArzEn corpus, an Egyptian Arabic-English code-switching (CS) spontaneous speech corpus. The corpus is collected through informal interviews with 38 Egyptian bilingual university students and employees held in a soundproof room. A total of 12 hours are recorded, transcribed, validated and sentence segmented. The corpus is mainly designed to be used in Automatic Speech Recognition (ASR) systems, however, it also provides a useful resource for analyzing the CS phenomenon from linguistic, sociological, and psychological perspectives. In this paper, we first discuss the CS phenomenon in Egypt and the factors that gave rise to the current language. We then provide a detailed description on how the corpus was collected, giving an overview on the participants involved. We also present statistics on the CS involved in the corpus, as well as a summary to the effort exerted in the corpus development, in terms of number of hours required for transcription, validation, segmentation and speaker annotation. Finally, we discuss some factors contributing to the complexity of the corpus, as well as Arabic-English CS behaviour that could pose potential challenges to ASR systems.
%U https://aclanthology.org/2020.lrec-1.523
%P 4237-4246
Markdown (Informal)
[ArzEn: A Speech Corpus for Code-switched Egyptian Arabic-English](https://aclanthology.org/2020.lrec-1.523) (Hamed et al., LREC 2020)
ACL