@inproceedings{sabaa-sabaa-2026-sabaa,
title = "Sabaa at {NADI} 2026 Subtask 1.1: Matching Annotation Conventions for Dialectal {A}rabic {ASR}",
author = "Sabaa, Mohamed and
Sabaa, Amr",
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.2/",
pages = "31--36",
ISBN = "979-8-89176-497-2",
abstract = "This paper describes our submission to NADI 2026 Subtask 1.1, speech recognition for eight Arabic dialects under noisy conditions. Our system adapts whisper-large-v3-turbo with one low-rank adapter per dialect, decodes with tuned beam search, and applies a normalization step that matches the spelling conventions of the reference transcriptions rather than applying generic orthographic rules. We train only on the shared-task data, which places our results well below those of systems built with large external corpora, and we report our numbers with that constraint in mind. Country-average WER falls from 0.804 for the zero-shot backbone to 0.6053 on the test set. We also report three observations that shaped the system: per-dialect adapters outperform a jointly trained adapter on all eight dialects even when the joint model is trained for twice as long; replacing beam search with temperature sampling in order to produce diverse hypotheses for rescoring costs more accuracy than the rescoring recovers; and because the official scorer normalizes hypothesis and reference identically, generic character-level normalization cannot help, whereas learning each dialect{'}s annotation convention from the training transcriptions does."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sabaa-sabaa-2026-sabaa">
<titleInfo>
<title>Sabaa at NADI 2026 Subtask 1.1: Matching Annotation Conventions for Dialectal Arabic ASR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Sabaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Sabaa</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>This paper describes our submission to NADI 2026 Subtask 1.1, speech recognition for eight Arabic dialects under noisy conditions. Our system adapts whisper-large-v3-turbo with one low-rank adapter per dialect, decodes with tuned beam search, and applies a normalization step that matches the spelling conventions of the reference transcriptions rather than applying generic orthographic rules. We train only on the shared-task data, which places our results well below those of systems built with large external corpora, and we report our numbers with that constraint in mind. Country-average WER falls from 0.804 for the zero-shot backbone to 0.6053 on the test set. We also report three observations that shaped the system: per-dialect adapters outperform a jointly trained adapter on all eight dialects even when the joint model is trained for twice as long; replacing beam search with temperature sampling in order to produce diverse hypotheses for rescoring costs more accuracy than the rescoring recovers; and because the official scorer normalizes hypothesis and reference identically, generic character-level normalization cannot help, whereas learning each dialect’s annotation convention from the training transcriptions does.</abstract>
<identifier type="citekey">sabaa-sabaa-2026-sabaa</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.2/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>31</start>
<end>36</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sabaa at NADI 2026 Subtask 1.1: Matching Annotation Conventions for Dialectal Arabic ASR
%A Sabaa, Mohamed
%A Sabaa, Amr
%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 sabaa-sabaa-2026-sabaa
%X This paper describes our submission to NADI 2026 Subtask 1.1, speech recognition for eight Arabic dialects under noisy conditions. Our system adapts whisper-large-v3-turbo with one low-rank adapter per dialect, decodes with tuned beam search, and applies a normalization step that matches the spelling conventions of the reference transcriptions rather than applying generic orthographic rules. We train only on the shared-task data, which places our results well below those of systems built with large external corpora, and we report our numbers with that constraint in mind. Country-average WER falls from 0.804 for the zero-shot backbone to 0.6053 on the test set. We also report three observations that shaped the system: per-dialect adapters outperform a jointly trained adapter on all eight dialects even when the joint model is trained for twice as long; replacing beam search with temperature sampling in order to produce diverse hypotheses for rescoring costs more accuracy than the rescoring recovers; and because the official scorer normalizes hypothesis and reference identically, generic character-level normalization cannot help, whereas learning each dialect’s annotation convention from the training transcriptions does.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.2/
%P 31-36
Markdown (Informal)
[Sabaa at NADI 2026 Subtask 1.1: Matching Annotation Conventions for Dialectal Arabic ASR](https://aclanthology.org/2026.arabicnlp-sharedtasks.2/) (Sabaa & Sabaa, ArabicNLP 2026)
ACL