@inproceedings{hamed-etal-2024-zaebuc,
title = "{ZAEBUC}-Spoken: A Multilingual Multidialectal {A}rabic-{E}nglish Speech Corpus",
author = "Hamed, Injy and
Eryani, Fadhl and
Palfreyman, David and
Habash, Nizar",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1546",
pages = "17770--17782",
abstract = "We present ZAEBUC-Spoken, a multilingual multidialectal Arabic-English speech corpus. The corpus comprises twelve hours of Zoom meetings involving multiple speakers role-playing a work situation where Students brainstorm ideas for a certain topic and then discuss it with an Interlocutor. The meetings cover different topics and are divided into phases with different language setups. The corpus presents a challenging set for automatic speech recognition (ASR), including two languages (Arabic and English) with Arabic spoken in multiple variants (Modern Standard Arabic, Gulf Arabic, and Egyptian Arabic) and English used with various accents. Adding to the complexity of the corpus, there is also code-switching between these languages and dialects. As part of our work, we take inspiration from established sets of transcription guidelines to present a set of guidelines handling issues of conversational speech, code-switching and orthography of both languages. We further enrich the corpus with two layers of annotations; (1) dialectness level annotation for the portion of the corpus where mixing occurs between different variants of Arabic, and (2) automatic morphological annotations, including tokenization, lemmatization, and part-of-speech tagging.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamed-etal-2024-zaebuc">
<titleInfo>
<title>ZAEBUC-Spoken: A Multilingual Multidialectal Arabic-English Speech Corpus</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">Fadhl</namePart>
<namePart type="family">Eryani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Palfreyman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present ZAEBUC-Spoken, a multilingual multidialectal Arabic-English speech corpus. The corpus comprises twelve hours of Zoom meetings involving multiple speakers role-playing a work situation where Students brainstorm ideas for a certain topic and then discuss it with an Interlocutor. The meetings cover different topics and are divided into phases with different language setups. The corpus presents a challenging set for automatic speech recognition (ASR), including two languages (Arabic and English) with Arabic spoken in multiple variants (Modern Standard Arabic, Gulf Arabic, and Egyptian Arabic) and English used with various accents. Adding to the complexity of the corpus, there is also code-switching between these languages and dialects. As part of our work, we take inspiration from established sets of transcription guidelines to present a set of guidelines handling issues of conversational speech, code-switching and orthography of both languages. We further enrich the corpus with two layers of annotations; (1) dialectness level annotation for the portion of the corpus where mixing occurs between different variants of Arabic, and (2) automatic morphological annotations, including tokenization, lemmatization, and part-of-speech tagging.</abstract>
<identifier type="citekey">hamed-etal-2024-zaebuc</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1546</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17770</start>
<end>17782</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ZAEBUC-Spoken: A Multilingual Multidialectal Arabic-English Speech Corpus
%A Hamed, Injy
%A Eryani, Fadhl
%A Palfreyman, David
%A Habash, Nizar
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F hamed-etal-2024-zaebuc
%X We present ZAEBUC-Spoken, a multilingual multidialectal Arabic-English speech corpus. The corpus comprises twelve hours of Zoom meetings involving multiple speakers role-playing a work situation where Students brainstorm ideas for a certain topic and then discuss it with an Interlocutor. The meetings cover different topics and are divided into phases with different language setups. The corpus presents a challenging set for automatic speech recognition (ASR), including two languages (Arabic and English) with Arabic spoken in multiple variants (Modern Standard Arabic, Gulf Arabic, and Egyptian Arabic) and English used with various accents. Adding to the complexity of the corpus, there is also code-switching between these languages and dialects. As part of our work, we take inspiration from established sets of transcription guidelines to present a set of guidelines handling issues of conversational speech, code-switching and orthography of both languages. We further enrich the corpus with two layers of annotations; (1) dialectness level annotation for the portion of the corpus where mixing occurs between different variants of Arabic, and (2) automatic morphological annotations, including tokenization, lemmatization, and part-of-speech tagging.
%U https://aclanthology.org/2024.lrec-main.1546
%P 17770-17782
Markdown (Informal)
[ZAEBUC-Spoken: A Multilingual Multidialectal Arabic-English Speech Corpus](https://aclanthology.org/2024.lrec-main.1546) (Hamed et al., LREC-COLING 2024)
ACL