English(EN) Similarity Choice and Negative Scaling in Supervised Contrastive Learning for Deepfake Audio Detection

研究人员探索用于深度伪造音频检测的监督对比学习

作者 PulseAugur 编辑部 · [1 个来源] · 2026-04-30 04:00

研究人员探索了监督对比学习技术以改进深度伪造音频检测。他们的研究侧重于使用跨批次队列改变相似度度量（如余弦相似度和角度相似度）以及不同的负样本缩放方法。研究结果表明，在特定评估数据集上，使用延迟队列的余弦相似度取得了最佳性能，而角度相似度在减少对大型负样本集依赖方面显示出潜力。 AI

影响提供了改进的合成音频检测方法，可能增强音频系统的安全性与可信度。

排序理由学术论文，详细介绍了关于深度伪造音频检测的监督对比学习的对照研究。

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 学术论文，详细介绍了关于深度伪造音频检测的监督对比学习的对照研究。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 161 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Jaskirat Sudan, Hashim Ali, Surya Subramani, Hafiz Malik · 2026-04-30 04:00

深度伪造音频检测的监督对比学习中的相似度选择与负面缩放

arXiv:2604.26057v1 Announce Type: cross Abstract: Supervised contrastive learning (SupCon) is widely used to shape representations, but has seen limited targeted study for audio deepfake detection. Existing work typically combines contrastive terms with broader pipelines; however…