{"ID":2828745,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.13744","arxiv_id":"2512.13744","title":"Toward Noise-Aware Audio Deepfake Detection: Survey, SNR-Benchmarks, and Practical Recipes","abstract":"Deepfake audio detection has progressed rapidly with strong pre-trained encoders (e.g., WavLM, Wav2Vec2, MMS). However, performance in realistic capture conditions - background noise (domestic/office/transport), room reverberation, and consumer channels - often lags clean-lab results. We survey and evaluate robustness for state-of-the-art audio deepfake detection models and present a reproducible framework that mixes MS-SNSD noises with ASVspoof 2021 DF utterances to evaluate under controlled signal-to-noise ratios (SNRs). SNR is a measured proxy for noise severity used widely in speech; it lets us sweep from near-clean (35 dB) to very noisy (-5 dB) to quantify graceful degradation. We study multi-condition training and fixed-SNR testing for pretrained encoders (WavLM, Wav2Vec2, MMS), reporting accuracy, ROC-AUC, and EER on binary and four-class (authenticity x corruption) tasks. In our experiments, finetuning reduces EER by 10-15 percentage points at 10-0 dB SNR across backbones.","short_abstract":"Deepfake audio detection has progressed rapidly with strong pre-trained encoders (e.g., WavLM, Wav2Vec2, MMS). However, performance in realistic capture conditions - background noise (domestic/office/transport), room reverberation, and consumer channels - often lags clean-lab results. We survey and evaluate robustness...","url_abs":"https://arxiv.org/abs/2512.13744","url_pdf":"https://arxiv.org/pdf/2512.13744v1","authors":"[\"Udayon Sen\",\"Alka Luqman\",\"Anupam Chattopadhyay\"]","published":"2025-12-15T02:22:37Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.AI\"]","methods":"[]","has_code":false}