@inproceedings{issa-cheng-2026-human,
title = "Human Perception of {A}rabic Fake Audio",
author = "Issa, Elsayed and
Cheng, Yi-Fang",
editor = {Chen, Nancy F. and
Chen, Yiming and
Gao, Xiaoxue and
Li, Haizhou and
Schuller, Bj{\"o}rn and
Sisman, Berrak and
Yue, Xianghu},
booktitle = "Proceedings of the Workshop on Secure, Safe, and Privacy-Preserving Speech and Audio {AI} ({T}rust{A}udio 2026)",
month = nov,
year = "2026",
address = "Hengqin, Zhuhai, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.trustaudio-1.5/",
pages = "35--49",
ISBN = "979-8-89176-452-1",
abstract = "Audio deepfake research has focused on a few high resource languages, leaving human perception of synthesized Arabic speech unexplored. We present the current study of how human listeners perceive Arabic audio deepfakes. Thirty eight native speakers judged Modern Standard Arabic stimuli in two formats generated with proprietary and open-source models. The two formats are a binary task pairing genuine clips with text-to-speech counterparts and a unary task requiring single-clip authenticity judgments of voice-cloned political speech. The results showed that listeners performed only moderately above chance in both formats (binary: 62.9{\%}; unary balanced accuracy: 64.6{\%}). In the unary task, listeners showed a systematic bias toward judging audio as authentic ($d'=0.77$, $c=0.27$), accepting 45{\%} of synthetic clips as real. Confidence was positively related to accuracy in the binary condition but inversely related in the unary condition. Because the two conditions also differ in synthesis method, speakers, and stimuli, we treat this as a descriptive contrast between conditions rather than an effect of task format. An exploratory coded analysis of participants' rationales suggested that reasoning from subjective certainty was associated with lower accuracy and concrete perceptual cues with higher accuracy, while no cue category reliably predicted confidence. These findings suggest that individual listeners are an unreliable safeguard against Arabic fake audio detection, and motivate future direct comparisons with automatic detectors."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="issa-cheng-2026-human">
<titleInfo>
<title>Human Perception of Arabic Fake Audio</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elsayed</namePart>
<namePart type="family">Issa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-Fang</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Secure, Safe, and Privacy-Preserving Speech and Audio AI (TrustAudio 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoxue</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haizhou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Björn</namePart>
<namePart type="family">Schuller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrak</namePart>
<namePart type="family">Sisman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianghu</namePart>
<namePart type="family">Yue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, Zhuhai, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-452-1</identifier>
</relatedItem>
<abstract>Audio deepfake research has focused on a few high resource languages, leaving human perception of synthesized Arabic speech unexplored. We present the current study of how human listeners perceive Arabic audio deepfakes. Thirty eight native speakers judged Modern Standard Arabic stimuli in two formats generated with proprietary and open-source models. The two formats are a binary task pairing genuine clips with text-to-speech counterparts and a unary task requiring single-clip authenticity judgments of voice-cloned political speech. The results showed that listeners performed only moderately above chance in both formats (binary: 62.9%; unary balanced accuracy: 64.6%). In the unary task, listeners showed a systematic bias toward judging audio as authentic (d’=0.77, c=0.27), accepting 45% of synthetic clips as real. Confidence was positively related to accuracy in the binary condition but inversely related in the unary condition. Because the two conditions also differ in synthesis method, speakers, and stimuli, we treat this as a descriptive contrast between conditions rather than an effect of task format. An exploratory coded analysis of participants’ rationales suggested that reasoning from subjective certainty was associated with lower accuracy and concrete perceptual cues with higher accuracy, while no cue category reliably predicted confidence. These findings suggest that individual listeners are an unreliable safeguard against Arabic fake audio detection, and motivate future direct comparisons with automatic detectors.</abstract>
<identifier type="citekey">issa-cheng-2026-human</identifier>
<location>
<url>https://aclanthology.org/2026.trustaudio-1.5/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>35</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Human Perception of Arabic Fake Audio
%A Issa, Elsayed
%A Cheng, Yi-Fang
%Y Chen, Nancy F.
%Y Chen, Yiming
%Y Gao, Xiaoxue
%Y Li, Haizhou
%Y Schuller, Björn
%Y Sisman, Berrak
%Y Yue, Xianghu
%S Proceedings of the Workshop on Secure, Safe, and Privacy-Preserving Speech and Audio AI (TrustAudio 2026)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, Zhuhai, China
%@ 979-8-89176-452-1
%F issa-cheng-2026-human
%X Audio deepfake research has focused on a few high resource languages, leaving human perception of synthesized Arabic speech unexplored. We present the current study of how human listeners perceive Arabic audio deepfakes. Thirty eight native speakers judged Modern Standard Arabic stimuli in two formats generated with proprietary and open-source models. The two formats are a binary task pairing genuine clips with text-to-speech counterparts and a unary task requiring single-clip authenticity judgments of voice-cloned political speech. The results showed that listeners performed only moderately above chance in both formats (binary: 62.9%; unary balanced accuracy: 64.6%). In the unary task, listeners showed a systematic bias toward judging audio as authentic (d’=0.77, c=0.27), accepting 45% of synthetic clips as real. Confidence was positively related to accuracy in the binary condition but inversely related in the unary condition. Because the two conditions also differ in synthesis method, speakers, and stimuli, we treat this as a descriptive contrast between conditions rather than an effect of task format. An exploratory coded analysis of participants’ rationales suggested that reasoning from subjective certainty was associated with lower accuracy and concrete perceptual cues with higher accuracy, while no cue category reliably predicted confidence. These findings suggest that individual listeners are an unreliable safeguard against Arabic fake audio detection, and motivate future direct comparisons with automatic detectors.
%U https://aclanthology.org/2026.trustaudio-1.5/
%P 35-49
Markdown (Informal)
[Human Perception of Arabic Fake Audio](https://aclanthology.org/2026.trustaudio-1.5/) (Issa & Cheng, TrustAudio 2026)
ACL
- Elsayed Issa and Yi-Fang Cheng. 2026. Human Perception of Arabic Fake Audio. In Proceedings of the Workshop on Secure, Safe, and Privacy-Preserving Speech and Audio AI (TrustAudio 2026), pages 35–49, Hengqin, Zhuhai, China. Association for Computational Linguistics.