PulseAugur
EN
LIVE 19:22:20

New DiT-based method enhances audio deepfake detection across domains

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a novel method for cross-domain audio deepfake detection using a Diffusion Transformer (DiT) as a reconstruction probe. This approach leverages multi-ratio residual maps generated by the DiT, which are sensitive to domain variations. By fusing these residuals with a projected auditory representation from WavLM, the system aims to improve detection accuracy across different generators, corpora, and recording conditions. Initial results show promising performance on benchmark datasets like ASVspoof 5 Eval and ITW Full, outperforming a reference WavLM-ResNet18 model under certain settings. AI

IMPACT This research could lead to more robust audio deepfake detection systems capable of handling diverse and unseen data variations.

RANK_REASON The cluster contains a research paper detailing a new method for audio deepfake detection.

Read on Hugging Face Daily Papers →

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

New DiT-based method enhances audio deepfake detection across domains

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Haotian Mo, Jie Liu, Siqi Shen, Songzhu Mei, Xinhai Chen, Xiangyang Wang, Yigui Feng, Shuai Li, Gencheng Liu, Keqi Yang, Qinglin Wang ·

    Audio-Anchored Fusion of Multi-Ratio DiT Reconstruction Residuals for Cross-Domain Audio Deepfake Detection

    arXiv:2607.26472v1 Announce Type: cross Abstract: Audio deepfake detectors often degrade when generators, corpora, or recording conditions change. We use a Diffusion Transformer (DiT), trained only on bona fide speech, as a frozen reconstruction probe. Reconstructions at masking …

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Audio-Anchored Fusion of Multi-Ratio DiT Reconstruction Residuals for Cross-Domain Audio Deepfake Detection

    Audio deepfake detectors often degrade when generators, corpora, or recording conditions change. We use a Diffusion Transformer (DiT), trained only on bona fide speech, as a frozen reconstruction probe. Reconstructions at masking ratios 0.5, 0.75, and 0.9 yield explicit multi-rat…

RELATED ENTITIES

RELATED TOPICS