@inproceedings{djanibekov-etal-2025-dialectal,
title = "Dialectal Coverage And Generalization in {A}rabic Speech Recognition",
author = "Djanibekov, Amirbek and
Toyin, Hawau Olamide and
Alshalan, Raghad and
Alatir, Abdullah and
Aldarmaki, Hanan",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1427/",
doi = "10.18653/v1/2025.acl-long.1427",
pages = "29490--29502",
ISBN = "979-8-89176-251-0",
abstract = "Developing robust automatic speech recognition (ASR) systems for Arabic requires effective strategies to manage its diversity. Existing ASR systems mainly cover the modern standard Arabic (MSA) variety and few high-resource dialects, but fall short in coverage and generalization across the multitude of spoken variants. Code-switching with English and French is also common in different regions of the Arab world, which challenges the performance of monolingual Arabic models. In this work, we introduce a suite of ASR models optimized to effectively recognize multiple variants of spoken Arabic, including MSA, various dialects, and code-switching. We provide open-source pre-trained models that cover data from 17 Arabic-speaking countries, and fine-tuned MSA and dialectal ASR models that include at least 11 variants, as well as multi-lingual ASR models covering embedded languages in code-switched utterances. We evaluate ASR performance across these spoken varieties and demonstrate both coverage and performance gains compared to prior models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="djanibekov-etal-2025-dialectal">
<titleInfo>
<title>Dialectal Coverage And Generalization in Arabic Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amirbek</namePart>
<namePart type="family">Djanibekov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hawau</namePart>
<namePart type="given">Olamide</namePart>
<namePart type="family">Toyin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghad</namePart>
<namePart type="family">Alshalan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Alatir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanan</namePart>
<namePart type="family">Aldarmaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Developing robust automatic speech recognition (ASR) systems for Arabic requires effective strategies to manage its diversity. Existing ASR systems mainly cover the modern standard Arabic (MSA) variety and few high-resource dialects, but fall short in coverage and generalization across the multitude of spoken variants. Code-switching with English and French is also common in different regions of the Arab world, which challenges the performance of monolingual Arabic models. In this work, we introduce a suite of ASR models optimized to effectively recognize multiple variants of spoken Arabic, including MSA, various dialects, and code-switching. We provide open-source pre-trained models that cover data from 17 Arabic-speaking countries, and fine-tuned MSA and dialectal ASR models that include at least 11 variants, as well as multi-lingual ASR models covering embedded languages in code-switched utterances. We evaluate ASR performance across these spoken varieties and demonstrate both coverage and performance gains compared to prior models.</abstract>
<identifier type="citekey">djanibekov-etal-2025-dialectal</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1427</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1427/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>29490</start>
<end>29502</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialectal Coverage And Generalization in Arabic Speech Recognition
%A Djanibekov, Amirbek
%A Toyin, Hawau Olamide
%A Alshalan, Raghad
%A Alatir, Abdullah
%A Aldarmaki, Hanan
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F djanibekov-etal-2025-dialectal
%X Developing robust automatic speech recognition (ASR) systems for Arabic requires effective strategies to manage its diversity. Existing ASR systems mainly cover the modern standard Arabic (MSA) variety and few high-resource dialects, but fall short in coverage and generalization across the multitude of spoken variants. Code-switching with English and French is also common in different regions of the Arab world, which challenges the performance of monolingual Arabic models. In this work, we introduce a suite of ASR models optimized to effectively recognize multiple variants of spoken Arabic, including MSA, various dialects, and code-switching. We provide open-source pre-trained models that cover data from 17 Arabic-speaking countries, and fine-tuned MSA and dialectal ASR models that include at least 11 variants, as well as multi-lingual ASR models covering embedded languages in code-switched utterances. We evaluate ASR performance across these spoken varieties and demonstrate both coverage and performance gains compared to prior models.
%R 10.18653/v1/2025.acl-long.1427
%U https://aclanthology.org/2025.acl-long.1427/
%U https://doi.org/10.18653/v1/2025.acl-long.1427
%P 29490-29502
Markdown (Informal)
[Dialectal Coverage And Generalization in Arabic Speech Recognition](https://aclanthology.org/2025.acl-long.1427/) (Djanibekov et al., ACL 2025)
ACL
- Amirbek Djanibekov, Hawau Olamide Toyin, Raghad Alshalan, Abdullah Alatir, and Hanan Aldarmaki. 2025. Dialectal Coverage And Generalization in Arabic Speech Recognition. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 29490–29502, Vienna, Austria. Association for Computational Linguistics.