@inproceedings{p-iyengar-2026-pi,
title = "pi-labs.ai at {A}r{A}-{DF} 2026: Score-Level Fusion of Self-Supervised Speech Encoders with an {AASIST} Back-End for {A}rabic Audio Deepfake Detection",
author = "P, Vardhini and
Iyengar, Raghu Sesha",
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.197/",
pages = "1525--1530",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents our submission to the ArADF 2026 Shared Task on Arabic Audio Deepfake Detection, focusing on Track 1, which evaluates robustness to previously unseen Arabic dialects. Our proposed system combines two complementary self-supervised speech encoders, XLS-R-300M and WavLM-Large, each integrated with an AASIST graph-attention back-end for spoofing detection. The final prediction is obtained through score-level fusion of the two independently trained models, enabling the system to leverage the complementary representations learned by each encoder. To improve robustness to domain shift, we introduce two complementary adaptation strategies: telephony channel augmentation to reduce the mismatch between the training and evaluation domains, and an iterative pseudolabel self-training framework that exploits highconfidence predictions on unlabeled evaluation data for progressive model refinement. On the official ArA-DF 2026 Track 1 evaluation set, our system achieved an Equal Error Rate (EER) of 0.9265{\%}, ranking 4th on the official leaderboard. These results demonstrate that combining complementary self-supervised speech representations with domain-aware adaptation techniques provides an effective and robust solution for cross-dialect Arabic audio deepfake detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="p-iyengar-2026-pi">
<titleInfo>
<title>pi-labs.ai at ArA-DF 2026: Score-Level Fusion of Self-Supervised Speech Encoders with an AASIST Back-End for Arabic Audio Deepfake Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vardhini</namePart>
<namePart type="family">P</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghu</namePart>
<namePart type="given">Sesha</namePart>
<namePart type="family">Iyengar</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 presents our submission to the ArADF 2026 Shared Task on Arabic Audio Deepfake Detection, focusing on Track 1, which evaluates robustness to previously unseen Arabic dialects. Our proposed system combines two complementary self-supervised speech encoders, XLS-R-300M and WavLM-Large, each integrated with an AASIST graph-attention back-end for spoofing detection. The final prediction is obtained through score-level fusion of the two independently trained models, enabling the system to leverage the complementary representations learned by each encoder. To improve robustness to domain shift, we introduce two complementary adaptation strategies: telephony channel augmentation to reduce the mismatch between the training and evaluation domains, and an iterative pseudolabel self-training framework that exploits highconfidence predictions on unlabeled evaluation data for progressive model refinement. On the official ArA-DF 2026 Track 1 evaluation set, our system achieved an Equal Error Rate (EER) of 0.9265%, ranking 4th on the official leaderboard. These results demonstrate that combining complementary self-supervised speech representations with domain-aware adaptation techniques provides an effective and robust solution for cross-dialect Arabic audio deepfake detection.</abstract>
<identifier type="citekey">p-iyengar-2026-pi</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.197/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1525</start>
<end>1530</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T pi-labs.ai at ArA-DF 2026: Score-Level Fusion of Self-Supervised Speech Encoders with an AASIST Back-End for Arabic Audio Deepfake Detection
%A P, Vardhini
%A Iyengar, Raghu Sesha
%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 p-iyengar-2026-pi
%X This paper presents our submission to the ArADF 2026 Shared Task on Arabic Audio Deepfake Detection, focusing on Track 1, which evaluates robustness to previously unseen Arabic dialects. Our proposed system combines two complementary self-supervised speech encoders, XLS-R-300M and WavLM-Large, each integrated with an AASIST graph-attention back-end for spoofing detection. The final prediction is obtained through score-level fusion of the two independently trained models, enabling the system to leverage the complementary representations learned by each encoder. To improve robustness to domain shift, we introduce two complementary adaptation strategies: telephony channel augmentation to reduce the mismatch between the training and evaluation domains, and an iterative pseudolabel self-training framework that exploits highconfidence predictions on unlabeled evaluation data for progressive model refinement. On the official ArA-DF 2026 Track 1 evaluation set, our system achieved an Equal Error Rate (EER) of 0.9265%, ranking 4th on the official leaderboard. These results demonstrate that combining complementary self-supervised speech representations with domain-aware adaptation techniques provides an effective and robust solution for cross-dialect Arabic audio deepfake detection.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.197/
%P 1525-1530
Markdown (Informal)
[pi-labs.ai at ArA-DF 2026: Score-Level Fusion of Self-Supervised Speech Encoders with an AASIST Back-End for Arabic Audio Deepfake Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.197/) (P & Iyengar, ArabicNLP 2026)
ACL