{
  "annotation_id": "035d112a-d544-416d-a233-9a8702e6873f",
  "date_created": "2026-02-17T05:53:07.764000Z",
  "date_modified": "2026-02-17T05:53:07.764000Z",
  "file_hash": "dd5b71c6015e459aa7beae08753c2bee4c6c365a09059b62ff37e05053b446d0",
  "private": false,
  "record": {
    "abstract": "Audio deepfake detection has become increasingly challenging due to rapid advances in speech synthesis and voice conversion technologies, particularly under channel distortions, replay attacks, and real-world recording conditions. This paper proposes a resolution-aware audio deepfake detection framework that explicitly models and aligns multi-resolution spectral representations through cross-scale attention and consistency learning. Unlike conventional single-resolution or implicit feature-fusion approaches, the proposed method enforces agreement across complementary time--frequency scales. The proposed framework is evaluated on three representative benchmarks: ASVspoof 2019 (LA and PA), the Fake-or-Real (FoR) dataset, and the In-the-Wild Audio Deepfake dataset under a speaker-disjoint protocol. The method achieves near-perfect performance on ASVspoof LA (EER 0.16%), strong robustness on ASVspoof PA (EER 5.09%), FoR rerecorded audio (EER 4.54%), and in-the-wild deepfakes (AUC 0.98, EER 4.81%), significantly outperforming single-resolution and non-attention baselines under challenging conditions. The proposed model remains lightweight and efficient, requiring only 159k parameters and less than 1~GFLOP per inference, making it suitable for practical deployment. Comprehensive ablation studies confirm the critical contributions of cross-scale attention and consistency learning, while gradient-based interpretability analysis reveals that the model learns resolution-consistent and semantically meaningful spectral cues across diverse spoofing conditions. These results demonstrate that explicit cross-resolution modeling provides a principled, robust, and scalable foundation for next-generation audio deepfake detection systems.",
    "arxiv_id": "2601.06560",
    "authors": [
      "K. A. Shahriar"
    ],
    "categories": [
      "eess.AS",
      "cs.SD"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Lightweight Resolution-Aware Audio Deepfake Detection via Cross-Scale Attention and Consistency Learning",
    "url": "https://arxiv.org/abs/2601.06560",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "ae532b52-605e-4707-9320-d2c004c08f48",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}