@inproceedings{bougares-etal-2026-whitehouse,
title = "{W}hite{H}ouse: Translation of the {C}asablanca Corpus for Multi-dialectal {A}rabic Speech Translation",
author = "Bougares, Fethi and
Mdhaffar, Salima and
Est{\`e}ve, Yannick",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.463/",
doi = "10.63317/4zqn965acien",
pages = "5849--5855",
abstract = "Remarkable progress has been made recently in the speech processing of Arabic dialects. This is primarily due to the availability of large multilingual pre-trained models as well as the development of multiple well-annotated datasets that support training, fine-tuning, and evaluation of various speech models. However, most existing research on Arabic speech processing did not consider Automatic Speech Translation (AST) and focused mainly on Dialect Identification (DI) and Automatic Speech Recognition (ASR) tasks. To address this gap, we introduce WhiteHouse, the first multi-dialectal Arabic-English Speech Translation Corpus. WhiteHouse supplements the recently created Casablanca dataset with English translation for each utterance in the transcripts. This results in a three-way parallel speech-transcription-translation multi-dialectal Arabic dataset. WhiteHouse dataset is used to evaluate various SoTA speech translation models. Our experiments show that SoTA speech translation models performs poorly when evaluated on Arabic dialectal conditions. All the data used during training and testing are released for public use and further improvements"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bougares-etal-2026-whitehouse">
<titleInfo>
<title>WhiteHouse: Translation of the Casablanca Corpus for Multi-dialectal Arabic Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salima</namePart>
<namePart type="family">Mdhaffar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannick</namePart>
<namePart type="family">Estève</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Remarkable progress has been made recently in the speech processing of Arabic dialects. This is primarily due to the availability of large multilingual pre-trained models as well as the development of multiple well-annotated datasets that support training, fine-tuning, and evaluation of various speech models. However, most existing research on Arabic speech processing did not consider Automatic Speech Translation (AST) and focused mainly on Dialect Identification (DI) and Automatic Speech Recognition (ASR) tasks. To address this gap, we introduce WhiteHouse, the first multi-dialectal Arabic-English Speech Translation Corpus. WhiteHouse supplements the recently created Casablanca dataset with English translation for each utterance in the transcripts. This results in a three-way parallel speech-transcription-translation multi-dialectal Arabic dataset. WhiteHouse dataset is used to evaluate various SoTA speech translation models. Our experiments show that SoTA speech translation models performs poorly when evaluated on Arabic dialectal conditions. All the data used during training and testing are released for public use and further improvements</abstract>
<identifier type="citekey">bougares-etal-2026-whitehouse</identifier>
<identifier type="doi">10.63317/4zqn965acien</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.463/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5849</start>
<end>5855</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WhiteHouse: Translation of the Casablanca Corpus for Multi-dialectal Arabic Speech Translation
%A Bougares, Fethi
%A Mdhaffar, Salima
%A Estève, Yannick
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F bougares-etal-2026-whitehouse
%X Remarkable progress has been made recently in the speech processing of Arabic dialects. This is primarily due to the availability of large multilingual pre-trained models as well as the development of multiple well-annotated datasets that support training, fine-tuning, and evaluation of various speech models. However, most existing research on Arabic speech processing did not consider Automatic Speech Translation (AST) and focused mainly on Dialect Identification (DI) and Automatic Speech Recognition (ASR) tasks. To address this gap, we introduce WhiteHouse, the first multi-dialectal Arabic-English Speech Translation Corpus. WhiteHouse supplements the recently created Casablanca dataset with English translation for each utterance in the transcripts. This results in a three-way parallel speech-transcription-translation multi-dialectal Arabic dataset. WhiteHouse dataset is used to evaluate various SoTA speech translation models. Our experiments show that SoTA speech translation models performs poorly when evaluated on Arabic dialectal conditions. All the data used during training and testing are released for public use and further improvements
%R 10.63317/4zqn965acien
%U https://aclanthology.org/2026.lrec-1.463/
%U https://doi.org/10.63317/4zqn965acien
%P 5849-5855
Markdown (Informal)
[WhiteHouse: Translation of the Casablanca Corpus for Multi-dialectal Arabic Speech Translation](https://aclanthology.org/2026.lrec-1.463/) (Bougares et al., LREC 2026)
ACL