测试音频伪造检测在多语言与媒体变换下的鲁棒性。
RADAR Challenge 2026: Robust Audio Deepfake Recognition under Media Transformations
- 构建多语言媒体变换数据集，模拟真实传播环境。
- 超10万条语音样本，使用等错误率评估检测性能。
- 33支团队参与，暴露现有方法在复杂场景的不足。
RADAR Challenge 2026 是一项针对媒体变换下鲁棒音频伪造识别的 APSIPA 大挑战，旨在模拟真实音频分发管道中的压缩、重采样、噪声和混响等现实条件。挑战包含两个阶段：英语开发阶段（提供标注数据用于分析与论文撰写），以及包含超过10万个语句的多语言评估阶段，涵盖英语、新加坡英语、普通话、台湾国语、日语和越南语。系统通过二分类的真实/伪造等错误率（EER）进行评估。本文介绍了挑战任务、数据集构建、评估协议及整体结果。挑战期间，共有33支队伍提交开发阶段成果，22支队伍参与最终评估。结果显示，在多语言与媒体变换条件下，音频伪造检测仍面临显著挑战。
原文摘要 · Abstract (English)
RADAR Challenge 2026 is an APSIPA Grand Challenge on Robust Audio Deepfake Recognition under Media Transformations, designed to simulate realistic media conditions in real-world audio distribution pipelines, including compression, resampling, noise, and reverberation. It consists of two phases: an English development phase with labeled data for analysis and paper writing, and a multilingual evaluation phase containing more than 100,000 utterances in English, Singapore English, Mandarin Chinese, Taiwanese Mandarin, Japanese, and Vietnamese. Systems are evaluated using equal error rate (EER) for binary real/fake classification. This paper describes the challenge task, the construction of the data set, the evaluation protocol, and the overall results. During the challenge, 33 teams submitted to the development phase and 22 teams submitted to the final evaluation phase. The reported results highlight the remaining challenges of robust audio deepfake detection under multilingual and media-transformed conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。