Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracing

• URL: http://arxiv.org/abs/2606.10223v1
• Date: Mon, 08 Jun 2026 22:22:48 GMT
• Title: Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracing
• Abstract summary: We propose a dual-branch gated fusion framework that pairs XLSR-53 with CORES, a 66-dimensional descriptor.<n>On the MLAAD benchmark, our system achieves 97.6% ID accuracy, 4.9% EERc, and an 83.5% relative FPR95 reduction over the Interspeech 2025 baseline.
• Score: 2.657233098224094
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Attributing a synthetic utterance to its originating system remains an open challenge: closed-set models fail to reject unseen synthesizers and produce overconfident predictions. To address this, we propose a dual-branch gated fusion framework that pairs XLSR-53 with CORES, a 66-dimensional descriptor that, unlike prior Linear Filter Bank (LFB)-only work, spans cepstral, oscillatory, rhythmic, energy, and spectral dimensions to capture complementary synthesis artifacts. Our analysis shows XLSR-53 remains discriminative in-domain (ID) while CORES generalizes stably under distribution shift (OOD), yet their naive concatenation fails due to SSL representational imbalance. To resolve this, an input-conditioned gate adaptively weights each branch under joint training with cross-entropy, an energy margin loss for ID/OOD separation, and a gate diversity term. On the MLAAD benchmark, our system achieves 97.6\% ID accuracy, 4.9\% EERc, and an 83.5\% relative FPR95 reduction over the Interspeech 2025 baseline.

Related papers

• Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata [57.27430779838529]
  We present an exact and tractable algorithm for sampling from the constrained mean-field posterior under any constraint expressible as a finite automaton.<n>The approach guarantees constraint satisfaction by construction, supports both greedy and sampling-based decoding, and is compatible with parallel and block-wise decoding.<n> Empirical evaluations on Dream-7B and LLaDA-8 show substantial accuracy gains across various tasks.
  arXiv  Detail & Related papers  (2026-07-08T05:48:57Z)
• Spectrally Regularized Latent Flow Matching for Turbulence Generation [0.0]
  We introduce a latent flow matching framework with a spectrally regularized compression stage.<n>On a 2562 DNS dataset at Re_f approx 2250, replacing an MSE-trained VAE with a zone-weighted log-spectral objective raises deep-dissipation retained spectral power.<n>The improved latent representation also yields a substantially better sampling cost-fidelity tradeoff.
  arXiv  Detail & Related papers  (2026-06-10T06:09:51Z)
• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path [10.000577340093434]
  The Topologically Regularized Side-Path (TRSP) is a non-invasive architectural intervention that achieves spectral balance.<n>TRSP employs a parameter-free Triangular Box mechanism, scaled by a lightweight, length-aware gate, to regularize the token interaction topology.<n>Experiments show significant improvements across general capabilities and long-context benchmarks.
  arXiv  Detail & Related papers  (2026-06-02T09:11:50Z)
• Reusing Fusion-Time Spectral Reliability for Adaptive Fusion and Expert Routing in RGB-Infrared Object Detection [0.0]
  We propose to extract a parameter-free, 7-dimensional spectral reliability descriptor.<n>Describes band energy, amplitude ratio, phase consistency, and cross-modal correlation.<n>We show that preserving fusion-time reliability as an explicit signal benefits both adaptive fusion and post-fusion conditional computation.
  arXiv  Detail & Related papers  (2026-05-31T11:28:41Z)
• A Penalty-Free Pipeline for Direct Quantum-Annealer Portfolio Optimization [0.0]
  Direct quantum-annealer portfolio optimization is commonly formulated as a penalty-encoded QUBO submitted to D-Wave hardware.<n>We show that this standard formulation fails on current devices and identify the structural reason.<n>We propose dropping the penalty entirely: build an objective-only QUBO from the expected returns and sample it on hardware.
  arXiv  Detail & Related papers  (2026-05-17T19:50:04Z)
• Aletheia: Physics-Conditioned Localized Artifact Attention (PhyLAA-X) for End-to-End Generalizable and Robust Deepfake Video Detection [0.0]
  We introduce PhyLAAA-X, a novel physics-conditioned extension of Localized Artifact Attention (LAA-X)<n>PhyLAA-X injects optical-flow curl, specular-reflectance and spatially-updance into the LAA-X attention via cross-attention gating a consistency loss.<n>This forces the network to learn boundaries where semantic inconsistencies and physical violations co-occur.
  arXiv  Detail & Related papers  (2026-04-13T08:14:50Z)
• Relational Preference Encoding in Looped Transformer Internal States [0.0]
  We investigate how looped transformers encode human preference in their internal iteration states.<n>Using Ouro-2.6B-Thinking, a 2.6B- parameter looped transformer with iterative refinement, we extract hidden states from each loop iteration.<n>We train lightweight evaluator heads to predict human preference on the Anthropic HH-RLHF dataset.<n>Our pairwise evaluator achieves 95.2% test accuracy on 8,552 unseen examples, surpassing a full-batch L-BFGS probe (84.5%) while the base model remains completely frozen.
  arXiv  Detail & Related papers  (2026-04-10T20:00:49Z)
• WS-Net: Weak-Signal Representation Learning and Gated Abundance Reconstruction for Hyperspectral Unmixing via State-Space and Weak Signal Attention Fusion [6.0621081081000385]
  Weak spectral responses in hyperspectral images are often obscured by dominant endmembers and sensor noise.<n>This paper introduces WS-Net, a deep unmixing framework designed to address weak-signal collapse.<n>The framework maintains stable accuracy under low-SNR conditions, particularly for weak endmembers.
  arXiv  Detail & Related papers  (2026-03-10T00:12:33Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• SKANet: A Cognitive Dual-Stream Framework with Adaptive Modality Fusion for Robust Compound GNSS Interference Classification [47.20483076887704]
  Global Navigation Satellite Systems (GNSS) face growing threats from sophisticated jamming interference.<n>We propose a cognitive deep learning framework built upon a dual-stream architecture that integrates Time-Frequency Images (TFIs) and Power Spectral Density (PSD)<n>We show that SKANet achieves an overall accuracy of 96.99%, exhibiting superior robustness for compound jamming classification.
  arXiv  Detail & Related papers  (2026-01-19T07:42:45Z)
• Rectified Diffusion Guidance for Conditional Generation [94.83538269086613]
  We revisit the theory behind CFG and rigorously confirm that the improper combination coefficients (textiti.e.) brings about expectation shift the generative distribution.<n>We show that our approach enjoys a textbftextitform solution given the strength.<n> Empirical evidence on real-world data demonstrate the compatibility of our design with existing state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2024-10-24T13:41:32Z)
• Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems [61.90743116707422]
  This paper investigates multi-pass rescoring and cross adaptation based system combination approaches for hybrid TDNN and Conformer E2E ASR systems. The best combined system obtained using multi-pass rescoring produced statistically significant word error rate (WER) reductions of 2.5% to 3.9% absolute (22.5% to 28.9% relative) over the stand alone Conformer system on the NIST Hub5'00, Rt03 and Rt02 evaluation data.
  arXiv  Detail & Related papers  (2022-06-23T10:17:13Z)
• Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription [73.66530509749305]
  In this paper, we argue that, even in difficult cases, some end-to-end approaches show performance close to the hybrid baseline. We experimentally compare and analyze CTC-Attention versus RNN-Transducer approaches along with RNN versus Transformer architectures. Our best end-to-end model based on RNN-Transducer, together with improved beam search, reaches quality by only 3.8% WER abs. worse than the LF-MMI TDNN-F CHiME-6 Challenge baseline.
  arXiv  Detail & Related papers  (2020-04-22T19:08:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.