Transferring Audio Deepfake Detection Capability across Languages
Zhongjie Ba, Qing Wen, Peng Cheng, Yuwei Wang, Feng Lin, Li Lu, Zhenguang Liu
Abstract
The proliferation of deepfake content has motivated a surge of detection studies. However, existing detection methods in the audio area exclusively work in English, and there is a lack of data resources in other languages. Cross-lingual deepfake detection, a critical but rarely explored area, urges more study. This paper conducts the first comprehensive study on the cross-lingual perspective of deepfake detection. We observe that English data enriched in deepfake algorithms can teach a detector the knowledge of various spoofing artifacts, contributing to performing detection across language domains. Based on the observation, we first construct a first-of-its-kind cross-lingual evaluation dataset including heterogeneous spoofed speech uttered in the two most widely spoken languages, then explored domain adaptation (DA) techniques to transfer the artifacts detection capability and propose effective and practical DA strategies fitting the cross-lingual scenario. Our adversarial-based DA paradigm teaches the model to learn real/fake knowledge while losing language dependency. Extensive experiments over 137-hour audio clips validate the adapted models can detect fake audio generated by unseen algorithms in the new domain.
Ask Lune
Know where this paper stands in minutes, not an afternoon.
Lune can read the top-tier papers that cite it and the ones closest to it, and tells you what it claims, what came after and where it falls short, each point cited to the paper it comes from. No skimming, no AI slop.
9 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
its abstract · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers9
- Exposing the Deception: Uncovering More Forgery Clues for Deepfake DetectionZhongjie Ba, Qingyu Liu, Zhenguang Liu, Shuang Wu et al.AAAI 2024 · 101 citations
- DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery CluesKun Pan, Yifang Yin, Yao Wei, Feng Lin et al.ACM MM 2023 · 35 citations
- "Better Be Computer or I'm Dumb": A Large-Scale Evaluation of Humans as Audio Deepfake DetectorsKevin Warren, Tyler Tucker, Anna Crowder, Daniel Olszewski et al.CCS 2024 · 9 citations
- IndicSynth: A Large-Scale Multilingual Synthetic Speech Dataset for Low-Resource Indian LanguagesDivya V. Sharma, Vijval Ekbote, Anubha GuptaACL 2025 · 6 citations
- Multi-level SSL Feature Gating for Audio Deepfake DetectionHoan My Tran, Damien Lolive, Aghilas Sini, Arnaud Delhay et al.ACM MM 2025 · 3 citations
Related papers
- SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation MethodsWen Huang, Yanmei Gu, Zhiming Wang, Huijia Zhu et al.ACL 2025
- Joint Audio-Visual Deepfake DetectionYipin Zhou, Ser-Nam LimICCV 2021 · 232 citations
- WhiADD: Semantic-Acoustic Fusion for Robust Audio Deepfake DetectionJianqiao Cui, Bingyao Yu, Qihao Wang, Fei Meng et al.ACM MM 2025 · 1 citation
- ILLUSION: Unveiling Truth with a Comprehensive Multi-Modal, Multi-Lingual Deepfake DatasetKartik Thakral, Rishabh Ranjan, Akanksha Singh, Akshat Jain et al.ICLR 2025
- Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake DetectionLiang Chen, Yong Zhang, Yibing Song, Lingqiao Liu et al.CVPR 2022 · 251 citations
