A Training-Efficient Transformer-Based Anti-Spoofing Network for Logical Access in ASVspoof 5

• URL: http://arxiv.org/abs/2606.02980v1
• Date: Tue, 02 Jun 2026 00:38:12 GMT
• Title: A Training-Efficient Transformer-Based Anti-Spoofing Network for Logical Access in ASVspoof 5
• Abstract summary: This paper focuses on the ASVspoof 5 Track 1 closed condition, where standard cross-entropy training may not give enough attention to hard trials.<n>We propose TFPARN, a Transformer-based focal-pairwise attentive ranking network.<n>Compared with re-implemented AASIST and RawNet2 baselines under the same protocol, TFPARN achieves the best results, with a minDCF of 0.2430 and an EER of 12.52%.
• Score: 3.3748832979930037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Synthetic and manipulated speech can reduce the reliability of automatic speaker verification systems, so anti-spoofing methods need to be both accurate and efficient in training and inference. This paper focuses on the ASVspoof 5 Track 1 closed condition, where standard cross-entropy training may not give enough attention to hard trials and is not directly aligned with ranking- and threshold-based evaluation metrics. We propose TFPARN, a Transformer-based focal-pairwise attentive ranking network. The system extracts log-Mel features from speech, uses a Transformer encoder to model frame-level information, applies attention pooling to obtain utterance-level representations, and is trained with a combination of focal classification loss and pairwise ranking loss. RawBoost augmentation is used during training, and test-time augmentation is applied during evaluation to improve robustness. Compared with re-implemented AASIST and RawNet2 baselines under the same protocol, TFPARN achieves the best results, with a minDCF of 0.2430 and an EER of 12.52%. Ablation experiments further show that the pairwise loss, focal loss, and attention pooling all improve performance. TFPARN also uses the lowest inference memory among the compared systems, at 1.4 GB, runs at about 0.79 ms per utterance, and reaches its best checkpoint in less training time than AASIST. These results show that TFPARN provides a good balance between detection accuracy and computational cost for logical access anti-spoofing.

Related papers

• Evidential Deep Learning for Multi-Modal Anti-UAV Detection [0.0]
  This study evaluates whether evidential deep learning heads, Dempster-Shafer evidence fusion, and uncertainty-driven temporal sensor gating improve anti-UAV detection.
  arXiv  Detail & Related papers  (2026-09-01T18:09:46Z)
• SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute [62.3458279176813]
  Self-Verifying Refinement is an oracle-free multi-turn reinforcement learning framework.<n>It learns to use self-verification as a compute-control policy.<n>It achieves a macro-average accuracy of 0.563 with only 2.99 inference turns on average.
  arXiv  Detail & Related papers  (2026-07-30T16:20:58Z)
• RAT: Reference-Augmented Training for ASV Anti-Spoofing [0.18665975431697432]
  We introduce a spoofing countermeasure architecture conditioned on speaker-reference recordings.<n>We observe that it converges to a solution that effectively ignores the reference during inference.<n>We propose a Reference-Augmented Training (RAT) strategy, which yields improved detection performance.
  arXiv  Detail & Related papers  (2026-06-09T14:20:05Z)
• Rep Smarter, Not Harder: AI Hypertrophy Coaching with Wearable Sensors and Edge Neural Networks [0.9939775124582318]
  This paper introduces a novel system for real-time feedback on near-failure states during resistance exercise using only a single wrist-mounted Inertial Measurement Unit (IMU)<n>A ResNet-based model segments repetitions from the 6-axis IMU data in real-time and a classification model identifies exercise windows corresponding to near-failure states.<n> Deployment on a Raspberry Pi 5 yielded an average inference latency of 112 ms, and on an iPhone 16 yielded 23.5 ms, confirming the feasibility for edge computation.
  arXiv  Detail & Related papers  (2025-12-05T01:49:47Z)
• Boosted Training of Lightweight Early Exits for Optimizing CNN Image Classification Inference [47.027290803102666]
  We introduce a sequential training approach that aligns branch training with inference-time data distributions.<n>Experiments on the CINIC-10 dataset with a ResNet18 backbone demonstrate that BTS-EE consistently outperforms non-boosted training.<n>These results offer practical efficiency gains for applications such as industrial inspection, embedded vision, and UAV-based monitoring.
  arXiv  Detail & Related papers  (2025-09-10T06:47:49Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Distributed Adversarial Training to Robustify Deep Neural Networks at Scale [100.19539096465101]
  Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective approach, known as adversarial training (AT), has been shown to mitigate robust training. We propose a large-batch adversarial training framework implemented over multiple machines.
  arXiv  Detail & Related papers  (2022-06-13T15:39:43Z)
• Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teacher [54.50747989860957]
  We propose a semi-supervised learning algorithm named Progressive Teacher (PT) to utilize reliable FER datasets as well as large-scale unlabeled expression images for effective training. Experiments on widely-used databases RAF-DB and FERPlus validate the effectiveness of our method, which achieves state-of-the-art performance with accuracy of 89.57% on RAF-DB.
  arXiv  Detail & Related papers  (2022-05-28T07:47:53Z)
• Consistency Regularization Can Improve Robustness to Label Noise [4.340338299803562]
  This paper empirically studies the relevance of consistency regularization for training-time robustness to noisy labels. We show that a simple loss function that encourages consistency improves the robustness of the models to label noise.
  arXiv  Detail & Related papers  (2021-10-04T08:15:08Z)
• Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training [5.874575666947381]
  This study delves into semi-supervised object detection to improve detector performance with additional unlabeled data. We propose a novel two-stage filtering algorithm to generate accurate pseudo-labels. Our method achieves satisfactory improvements on MS-COCO and VOC benchmarks.
  arXiv  Detail & Related papers  (2021-07-11T12:14:42Z)
• Semi-supervised Contrastive Learning with Similarity Co-calibration [72.38187308270135]
  We propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL) SsCL combines the well-known contrastive loss in self-supervised learning with the cross entropy loss in semi-supervised learning. We show that SsCL produces more discriminative representation and is beneficial to few shot learning.
  arXiv  Detail & Related papers  (2021-05-16T09:13:56Z)
• Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training [55.824641135682725]
  Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD show that up to 80% of the performance of a system trained on ground-truth data can be recovered.
  arXiv  Detail & Related papers  (2020-11-26T18:51:26Z)
• Dynamically Mitigating Data Discrepancy with Balanced Focal Loss for Replay Attack Detection [10.851348154870852]
  We argue that for anti-spoofing, it needs more attention for indistinguishable samples over easily-classified ones in the modeling process. We propose to leverage a balanced focal loss function as the training objective to dynamically scale the loss based on the traits of the sample itself. With complementary features, our fusion system with only three kinds of features outperforms other systems by 22.5% for min-tDCF and 7% for EER.
  arXiv  Detail & Related papers  (2020-06-25T17:06:47Z)

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.