PulseAugur
EN
LIVE 08:08:16

New RAT training method improves deepfake audio detection

Researchers have developed a new training strategy called Reference-Augmented Training (RAT) to improve the detection of audio deepfakes. While initially designed to use speaker reference recordings, the method surprisingly enhances deepfake detection even when the reference is absent or mismatched during inference. This approach achieved state-of-the-art results on the ASVspoof 5 benchmark, outperforming larger ensemble systems. AI

IMPACT This new training method could lead to more robust defenses against sophisticated audio deepfakes.

RANK_REASON The cluster contains an academic paper detailing a new research methodology and benchmark results.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Vojt\v{e}ch Stan\v{e}k, Anton Firc, Jakub Re\v{s}, Kamil Malinka ·

    RAT: Reference-Augmented Training for ASV Anti-Spoofing

    arXiv:2606.10908v1 Announce Type: cross Abstract: We introduce a spoofing countermeasure architecture conditioned on speaker-reference recordings, but observe that it converges to a solution that effectively ignores the reference during inference. Surprisingly, training with a re…

  2. arXiv cs.AI TIER_1 English(EN) · Kamil Malinka ·

    RAT: Reference-Augmented Training for ASV Anti-Spoofing

    We introduce a spoofing countermeasure architecture conditioned on speaker-reference recordings, but observe that it converges to a solution that effectively ignores the reference during inference. Surprisingly, training with a reference channel induces invariance that improves d…