unibuc-cs/XMAD-Bench
收藏Hugging Face2025-06-20 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/unibuc-cs/XMAD-Bench
下载链接
链接失效反馈官方服务：
资源简介：
XMAD-Bench是一个大规模的跨域多语种音频Deepfake基准数据集，包含了668.8小时的真实和Deepfake语音。该数据集旨在为音频Deepfake检测器提供一个具有挑战性的跨域评估环境，其中训练集和测试集中的说话者、生成方法和真实音频源各不相同。
XMAD-Bench is a large-scale cross-domain multilingual audio deepfake benchmark comprising 668.8 hours of real and deepfake speech. The dataset is designed to provide a challenging cross-domain evaluation environment for audio deepfake detectors, where the speakers, generative methods, and real audio sources are distinct across the training and test sets.
提供机构：
unibuc-cs
