@inproceedings{youssef-etal-2026-using,
title = "Using {LALM}s for Pronunciation Error Detection in {A}rabic",
author = "Youssef, Osama E. and
Ali, Ahmed and
Magdy, Walid",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-main.12/",
pages = "164--169",
ISBN = "979-8-89176-473-6",
abstract = "This paper presents Qwen-MDD-AR, our system for the Iqra{'}Eval.2 Interspeech 2026 challenge on Modern Standard Arabic pronunciation assessment. Built on Qwen3-ASR-1.7B, it frames Arabic mispronunciation detection and diagnosis as autoregressive speech-to-phoneme generation. We add the 68-phoneme MSA inventory as special tokens, freeze the audio encoder, and adapt the decoder with LoRA. Using only provided challenge data, our submission ranked 6th of 19 teams on the hidden QuranMB.v2 test set, with 0.6702 F1 and 0.0445 PER. In a controlled comparison on our internal mixed held-out set, a Wav2Vec2-BERT CTC baseline trained on the same data achieved better PER, precision, and F1, while Qwen-MDD-AR obtained the same recall and a small Correct Diagnosis advantage (0.9496 vs. 0.9328). Results suggest LoRA-adapted LALMs are a practical alternative for Arabic MDD, while alignment accuracy and inference cost remain open."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="youssef-etal-2026-using">
<titleInfo>
<title>Using LALMs for Pronunciation Error Detection in Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Osama</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Youssef</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-473-6</identifier>
</relatedItem>
<abstract>This paper presents Qwen-MDD-AR, our system for the Iqra’Eval.2 Interspeech 2026 challenge on Modern Standard Arabic pronunciation assessment. Built on Qwen3-ASR-1.7B, it frames Arabic mispronunciation detection and diagnosis as autoregressive speech-to-phoneme generation. We add the 68-phoneme MSA inventory as special tokens, freeze the audio encoder, and adapt the decoder with LoRA. Using only provided challenge data, our submission ranked 6th of 19 teams on the hidden QuranMB.v2 test set, with 0.6702 F1 and 0.0445 PER. In a controlled comparison on our internal mixed held-out set, a Wav2Vec2-BERT CTC baseline trained on the same data achieved better PER, precision, and F1, while Qwen-MDD-AR obtained the same recall and a small Correct Diagnosis advantage (0.9496 vs. 0.9328). Results suggest LoRA-adapted LALMs are a practical alternative for Arabic MDD, while alignment accuracy and inference cost remain open.</abstract>
<identifier type="citekey">youssef-etal-2026-using</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.12/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>164</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using LALMs for Pronunciation Error Detection in Arabic
%A Youssef, Osama E.
%A Ali, Ahmed
%A Magdy, Walid
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-473-6
%F youssef-etal-2026-using
%X This paper presents Qwen-MDD-AR, our system for the Iqra’Eval.2 Interspeech 2026 challenge on Modern Standard Arabic pronunciation assessment. Built on Qwen3-ASR-1.7B, it frames Arabic mispronunciation detection and diagnosis as autoregressive speech-to-phoneme generation. We add the 68-phoneme MSA inventory as special tokens, freeze the audio encoder, and adapt the decoder with LoRA. Using only provided challenge data, our submission ranked 6th of 19 teams on the hidden QuranMB.v2 test set, with 0.6702 F1 and 0.0445 PER. In a controlled comparison on our internal mixed held-out set, a Wav2Vec2-BERT CTC baseline trained on the same data achieved better PER, precision, and F1, while Qwen-MDD-AR obtained the same recall and a small Correct Diagnosis advantage (0.9496 vs. 0.9328). Results suggest LoRA-adapted LALMs are a practical alternative for Arabic MDD, while alignment accuracy and inference cost remain open.
%U https://aclanthology.org/2026.arabicnlp-main.12/
%P 164-169
Markdown (Informal)
[Using LALMs for Pronunciation Error Detection in Arabic](https://aclanthology.org/2026.arabicnlp-main.12/) (Youssef et al., ArabicNLP 2026)
ACL