@inproceedings{albani-sonbol-2026-r,
title = "{R}{\_}{A} at {A}r{A}-{DF} 2026: Fine-Tuned Self-Supervised Encoders with Acoustic Degradation For Robust {A}rabic Deepfake Detection",
author = "Albani, Mhd Adnan and
Sonbol, Riad",
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.192/",
pages = "1496--1500",
ISBN = "979-8-89176-497-2",
abstract = "We describe our submission to ArA-DF 2026, the ArabicNLP shared task on Arabic speech deepfake detection, in which systems classify audio as real or deepfake. We participated in both tracks: Track{~}1 (Dialect Generalization) and Track{~}2 (Acoustic Robustness). Our systems investigated finetuning three large self-supervised speech encoders {---} WavLM, wav2vec2-XLS-R, and HuBERT {---} with a learnable attentive-pooling head. We evaluated each encoder separately and further combined encoders through a logistic-regression meta-classifier. In addition to improve robustness we apply an acoustic degradation pipeline (additive noise, lossy codec re-encoding, band-limiting, and gain) to 50{\%} of the training data. For track one the best achieved result is, a fully fine-tuned WavLM with attentive pooling and augmentation, which scored 2.19{\%} EER test set, and a deepfake-pretrained XLS-R achieves 7.80{\%} EER on Track2 which out performed the official baseline. Our ablation study shows that augmentation and backbone choice are the primary factors, while adding correlated ensemble members yields no gain."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="albani-sonbol-2026-r">
<titleInfo>
<title>R_A at ArA-DF 2026: Fine-Tuned Self-Supervised Encoders with Acoustic Degradation For Robust Arabic Deepfake Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mhd</namePart>
<namePart type="given">Adnan</namePart>
<namePart type="family">Albani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riad</namePart>
<namePart type="family">Sonbol</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 submission to ArA-DF 2026, the ArabicNLP shared task on Arabic speech deepfake detection, in which systems classify audio as real or deepfake. We participated in both tracks: Track 1 (Dialect Generalization) and Track 2 (Acoustic Robustness). Our systems investigated finetuning three large self-supervised speech encoders — WavLM, wav2vec2-XLS-R, and HuBERT — with a learnable attentive-pooling head. We evaluated each encoder separately and further combined encoders through a logistic-regression meta-classifier. In addition to improve robustness we apply an acoustic degradation pipeline (additive noise, lossy codec re-encoding, band-limiting, and gain) to 50% of the training data. For track one the best achieved result is, a fully fine-tuned WavLM with attentive pooling and augmentation, which scored 2.19% EER test set, and a deepfake-pretrained XLS-R achieves 7.80% EER on Track2 which out performed the official baseline. Our ablation study shows that augmentation and backbone choice are the primary factors, while adding correlated ensemble members yields no gain.</abstract>
<identifier type="citekey">albani-sonbol-2026-r</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.192/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1496</start>
<end>1500</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T R_A at ArA-DF 2026: Fine-Tuned Self-Supervised Encoders with Acoustic Degradation For Robust Arabic Deepfake Detection
%A Albani, Mhd Adnan
%A Sonbol, Riad
%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 albani-sonbol-2026-r
%X We describe our submission to ArA-DF 2026, the ArabicNLP shared task on Arabic speech deepfake detection, in which systems classify audio as real or deepfake. We participated in both tracks: Track 1 (Dialect Generalization) and Track 2 (Acoustic Robustness). Our systems investigated finetuning three large self-supervised speech encoders — WavLM, wav2vec2-XLS-R, and HuBERT — with a learnable attentive-pooling head. We evaluated each encoder separately and further combined encoders through a logistic-regression meta-classifier. In addition to improve robustness we apply an acoustic degradation pipeline (additive noise, lossy codec re-encoding, band-limiting, and gain) to 50% of the training data. For track one the best achieved result is, a fully fine-tuned WavLM with attentive pooling and augmentation, which scored 2.19% EER test set, and a deepfake-pretrained XLS-R achieves 7.80% EER on Track2 which out performed the official baseline. Our ablation study shows that augmentation and backbone choice are the primary factors, while adding correlated ensemble members yields no gain.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.192/
%P 1496-1500
Markdown (Informal)
[R_A at ArA-DF 2026: Fine-Tuned Self-Supervised Encoders with Acoustic Degradation For Robust Arabic Deepfake Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.192/) (Albani & Sonbol, ArabicNLP 2026)
ACL