English

Are audio DeepFake detection models polyglots?

Sound 2025-08-07 v2 Audio and Speech Processing

Abstract

Since the majority of audio DeepFake (DF) detection methods are trained on English-centric datasets, their applicability to non-English languages remains largely unexplored. In this work, we present a benchmark for the multilingual audio DF detection challenge by evaluating various adaptation strategies. Our experiments focus on analyzing models trained on English benchmark datasets, as well as intra-linguistic (same-language) and cross-linguistic adaptation approaches. Our results indicate considerable variations in detection efficacy, highlighting the difficulties of multilingual settings. We show that limiting the dataset to English negatively impacts the efficacy, while stressing the importance of the data in the target language.

Keywords

Cite

@article{arxiv.2412.17924,
  title  = {Are audio DeepFake detection models polyglots?},
  author = {Bartłomiej Marek and Piotr Kawa and Piotr Syga},
  journal= {arXiv preprint arXiv:2412.17924},
  year   = {2025}
}

Comments

Keywords: Audio DeepFakes, DeepFake detection, multilingual audio DeepFakes

R2 v1 2026-06-28T20:47:21.777Z