@inproceedings{wasfy-anber-2026-kand,
title = "{KAND} {CA} at {NADI} 2026 Shared Task: Multi-Stage Fine-Tuning for Spoken {A}rabic Dialects",
author = "Wasfy, Ahmed and
Anber, Nourhan",
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.12/",
pages = "110--117",
ISBN = "979-8-89176-497-2",
abstract = "We describe the KAND CA systems for all five subtasks of the NADI 2026 shared task on multidialectal Arabic speech processing. For the three ASR subtasks, a single family of staged, fully fine-tuned Whisper large-v3 models {---} broad dialectal adaptation, then only task-matched gold data {---} is combined with task-specific levers: an mT5 spellingcorrection post-editor trained on the task references (Subtask 1.1, final country-average WER 0.5111), chained continue-fine-tuning through the Subtask 1.1 data before the Mixed- ASR dev split (Subtask 1.2, WER 0.48), and a fresh two-epoch schedule over a 46K-clip external gold Tunisian{--}French corpus with an accent-only French post-pass (Subtask 1.3, WER 15.21{\%}). For spoken dialect identification (Task 2), where in-domain accuracy anti-predicted blind-test accuracy, our system fuses an architecturally distinct FastConformerencoder classifier, a decorrelated enhancedaudio view, and an ASR-transcript text route, reaching 0.5114 accuracy. For dialectal TTS (Subtask 3) we submitted 4,001 voice-cloned clips across ten dialects (UTMOS 2.72). We also report extensive negative results and release our models, correctors, and code publicly."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wasfy-anber-2026-kand">
<titleInfo>
<title>KAND CA at NADI 2026 Shared Task: Multi-Stage Fine-Tuning for Spoken Arabic Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Wasfy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nourhan</namePart>
<namePart type="family">Anber</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>We describe the KAND CA systems for all five subtasks of the NADI 2026 shared task on multidialectal Arabic speech processing. For the three ASR subtasks, a single family of staged, fully fine-tuned Whisper large-v3 models — broad dialectal adaptation, then only task-matched gold data — is combined with task-specific levers: an mT5 spellingcorrection post-editor trained on the task references (Subtask 1.1, final country-average WER 0.5111), chained continue-fine-tuning through the Subtask 1.1 data before the Mixed- ASR dev split (Subtask 1.2, WER 0.48), and a fresh two-epoch schedule over a 46K-clip external gold Tunisian–French corpus with an accent-only French post-pass (Subtask 1.3, WER 15.21%). For spoken dialect identification (Task 2), where in-domain accuracy anti-predicted blind-test accuracy, our system fuses an architecturally distinct FastConformerencoder classifier, a decorrelated enhancedaudio view, and an ASR-transcript text route, reaching 0.5114 accuracy. For dialectal TTS (Subtask 3) we submitted 4,001 voice-cloned clips across ten dialects (UTMOS 2.72). We also report extensive negative results and release our models, correctors, and code publicly.</abstract>
<identifier type="citekey">wasfy-anber-2026-kand</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.12/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>110</start>
<end>117</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KAND CA at NADI 2026 Shared Task: Multi-Stage Fine-Tuning for Spoken Arabic Dialects
%A Wasfy, Ahmed
%A Anber, Nourhan
%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 wasfy-anber-2026-kand
%X We describe the KAND CA systems for all five subtasks of the NADI 2026 shared task on multidialectal Arabic speech processing. For the three ASR subtasks, a single family of staged, fully fine-tuned Whisper large-v3 models — broad dialectal adaptation, then only task-matched gold data — is combined with task-specific levers: an mT5 spellingcorrection post-editor trained on the task references (Subtask 1.1, final country-average WER 0.5111), chained continue-fine-tuning through the Subtask 1.1 data before the Mixed- ASR dev split (Subtask 1.2, WER 0.48), and a fresh two-epoch schedule over a 46K-clip external gold Tunisian–French corpus with an accent-only French post-pass (Subtask 1.3, WER 15.21%). For spoken dialect identification (Task 2), where in-domain accuracy anti-predicted blind-test accuracy, our system fuses an architecturally distinct FastConformerencoder classifier, a decorrelated enhancedaudio view, and an ASR-transcript text route, reaching 0.5114 accuracy. For dialectal TTS (Subtask 3) we submitted 4,001 voice-cloned clips across ten dialects (UTMOS 2.72). We also report extensive negative results and release our models, correctors, and code publicly.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.12/
%P 110-117
Markdown (Informal)
[KAND CA at NADI 2026 Shared Task: Multi-Stage Fine-Tuning for Spoken Arabic Dialects](https://aclanthology.org/2026.arabicnlp-sharedtasks.12/) (Wasfy & Anber, ArabicNLP 2026)
ACL