@inproceedings{sakr-elzahaby-2026-saar,
title = "{S}a{A}r-{DF} at {A}r{A}-{DF} 2026: When More Data Hurts {---} Diversity-Driven Ensembling for {A}rabic Speech Deepfake Detection",
author = "Sakr, Abdelrahman and
Elzahaby, 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.193/",
pages = "1501--1506",
ISBN = "979-8-89176-497-2",
abstract = "We describe our system for Track 1 (dialectgeneralization) of the ArA-DF-2026 Arabic speech deepfake detection shared task. Starting from the organizers' XLS-R+AASIST baseline (14.65{\%} EER on the development test set), we show that (i) raw-waveform augmentation (RawBoost) roughly halves the error rate, (ii) replacing the AASIST back-end with a simple mean-pooling head over a posttrained self-supervised frontend removes a hard performance ceiling that persists even after full convergence, and (iii) a large, architecturally diverse ensemble is the only lever that keeps improving once single-model performance saturates. Our final system, a 13-member weighted ensemble spanning three frontend sizes, two back-ends, and four training-data recipes, reaches 2.34{\%} EER on the development-test leaderboard and 2.42{\%} EER on the official held-out blind evaluation set (144,210 utterances, 9{\texttimes} larger than the development test). We also report two negative results of practical value: injecting a large (54k-clip) multi-system Arabic text-to-speech corpus and a vocoder-copy-synthesis pseudospoof corpus both degrade accuracy, indicating that indiscriminately adding synthetic speech is harmful when its generation artifacts do not match the target domain. Our code is publicly available at https://github.com/Body123/aradf-2026-saar-df."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakr-elzahaby-2026-saar">
<titleInfo>
<title>SaAr-DF at ArA-DF 2026: When More Data Hurts — Diversity-Driven Ensembling for Arabic Speech Deepfake Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="family">Sakr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Elzahaby</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 our system for Track 1 (dialectgeneralization) of the ArA-DF-2026 Arabic speech deepfake detection shared task. Starting from the organizers’ XLS-R+AASIST baseline (14.65% EER on the development test set), we show that (i) raw-waveform augmentation (RawBoost) roughly halves the error rate, (ii) replacing the AASIST back-end with a simple mean-pooling head over a posttrained self-supervised frontend removes a hard performance ceiling that persists even after full convergence, and (iii) a large, architecturally diverse ensemble is the only lever that keeps improving once single-model performance saturates. Our final system, a 13-member weighted ensemble spanning three frontend sizes, two back-ends, and four training-data recipes, reaches 2.34% EER on the development-test leaderboard and 2.42% EER on the official held-out blind evaluation set (144,210 utterances, 9× larger than the development test). We also report two negative results of practical value: injecting a large (54k-clip) multi-system Arabic text-to-speech corpus and a vocoder-copy-synthesis pseudospoof corpus both degrade accuracy, indicating that indiscriminately adding synthetic speech is harmful when its generation artifacts do not match the target domain. Our code is publicly available at https://github.com/Body123/aradf-2026-saar-df.</abstract>
<identifier type="citekey">sakr-elzahaby-2026-saar</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.193/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1501</start>
<end>1506</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SaAr-DF at ArA-DF 2026: When More Data Hurts — Diversity-Driven Ensembling for Arabic Speech Deepfake Detection
%A Sakr, Abdelrahman
%A Elzahaby, 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 sakr-elzahaby-2026-saar
%X We describe our system for Track 1 (dialectgeneralization) of the ArA-DF-2026 Arabic speech deepfake detection shared task. Starting from the organizers’ XLS-R+AASIST baseline (14.65% EER on the development test set), we show that (i) raw-waveform augmentation (RawBoost) roughly halves the error rate, (ii) replacing the AASIST back-end with a simple mean-pooling head over a posttrained self-supervised frontend removes a hard performance ceiling that persists even after full convergence, and (iii) a large, architecturally diverse ensemble is the only lever that keeps improving once single-model performance saturates. Our final system, a 13-member weighted ensemble spanning three frontend sizes, two back-ends, and four training-data recipes, reaches 2.34% EER on the development-test leaderboard and 2.42% EER on the official held-out blind evaluation set (144,210 utterances, 9× larger than the development test). We also report two negative results of practical value: injecting a large (54k-clip) multi-system Arabic text-to-speech corpus and a vocoder-copy-synthesis pseudospoof corpus both degrade accuracy, indicating that indiscriminately adding synthetic speech is harmful when its generation artifacts do not match the target domain. Our code is publicly available at https://github.com/Body123/aradf-2026-saar-df.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.193/
%P 1501-1506
Markdown (Informal)
[SaAr-DF at ArA-DF 2026: When More Data Hurts — Diversity-Driven Ensembling for Arabic Speech Deepfake Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.193/) (Sakr & Elzahaby, ArabicNLP 2026)
ACL