@inproceedings{alkurbi-2026-wifaq,
title = "Wifaq at {NADI} 2026 Shared Task: Data Expansion and System Combination for Robust {A}rabic {ASR}",
author = "Alkurbi, Sulaiman",
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: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.6/",
pages = "58--62",
ISBN = "979-8-89176-497-2",
abstract = "Wifaq is our entry to NADI 2026 Subtask 1.1, which evaluates country-level Arabic automatic speech recognition across eight dialects under noisy conditions. We fully fine-tune four 600M-parameter W2v-BERT 2.0 CTC models on nested mixtures of task and ex- ternal speech, decode them with a shared 5-gram KenLM, and combine their hypotheses by word voting; each run fits on one 16 GB NVIDIA RTX 4070 Ti SUPER. The submitted four-way ensemble ranked first among nine entries on the blind test with 43.23{\%} WER and 20.0{\%} CER. On a reused 800-utterance local holdout, it lowers WER from 46.12{\%} for the strongest single model to 44.0{\%}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alkurbi-2026-wifaq">
<titleInfo>
<title>Wifaq at NADI 2026 Shared Task: Data Expansion and System Combination for Robust Arabic ASR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sulaiman</namePart>
<namePart type="family">Alkurbi</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: Shared Tasks</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">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>Wifaq is our entry to NADI 2026 Subtask 1.1, which evaluates country-level Arabic automatic speech recognition across eight dialects under noisy conditions. We fully fine-tune four 600M-parameter W2v-BERT 2.0 CTC models on nested mixtures of task and ex- ternal speech, decode them with a shared 5-gram KenLM, and combine their hypotheses by word voting; each run fits on one 16 GB NVIDIA RTX 4070 Ti SUPER. The submitted four-way ensemble ranked first among nine entries on the blind test with 43.23% WER and 20.0% CER. On a reused 800-utterance local holdout, it lowers WER from 46.12% for the strongest single model to 44.0%</abstract>
<identifier type="citekey">alkurbi-2026-wifaq</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.6/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>58</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wifaq at NADI 2026 Shared Task: Data Expansion and System Combination for Robust Arabic ASR
%A Alkurbi, Sulaiman
%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: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F alkurbi-2026-wifaq
%X Wifaq is our entry to NADI 2026 Subtask 1.1, which evaluates country-level Arabic automatic speech recognition across eight dialects under noisy conditions. We fully fine-tune four 600M-parameter W2v-BERT 2.0 CTC models on nested mixtures of task and ex- ternal speech, decode them with a shared 5-gram KenLM, and combine their hypotheses by word voting; each run fits on one 16 GB NVIDIA RTX 4070 Ti SUPER. The submitted four-way ensemble ranked first among nine entries on the blind test with 43.23% WER and 20.0% CER. On a reused 800-utterance local holdout, it lowers WER from 46.12% for the strongest single model to 44.0%
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.6/
%P 58-62
Markdown (Informal)
[Wifaq at NADI 2026 Shared Task: Data Expansion and System Combination for Robust Arabic ASR](https://aclanthology.org/2026.arabicnlp-sharedtasks.6/) (Alkurbi, ArabicNLP 2026)
ACL