EVDA
收藏arXiv2024-05-15 更新2024-08-06 收录
下载链接：
http://arxiv.org/abs/2405.08596v2
下载链接
链接失效反馈官方服务：
资源简介：
EVDA是一个用于评估深伪音频检测中持续学习方法的基准，包含了来自Anti-Spoofing Voice系列和中国假音频检测系列的经典数据集，以及由GPT-4和GPT-4o等模型生成的新深伪音频数据。
EVDA is a benchmark for evaluating continual learning methods in deepfake audio detection. It comprises classic datasets from the Anti-Spoofing Voice series and the Chinese Fake Audio Detection series, as well as newly generated deepfake audio data created by models such as GPT-4 and GPT-4o.
创建时间：
2024-05-14
