The train and dev sets of ADD 2022

Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021. However, the recent shared tasks have not covered many real-life and challenging scenarios. The first Audio Deep synthesis Detection challenge (ADD) was motivated to fill in the gap. The ADD 2022 (http://addchallenge.cn/add2022) includes three tracks: low-quality fake audio detection (LF), partially fake audio detection (PF) and audio fake game (FG). The LF track focuses on dealing with bona fide and fully fake utterances with various real-world noises etc. The PF track aims to distinguish the partially fake audio from the real. The FG track is a rivalry game, which includes two tasks: an audio generation task and an audio fake detection task. In this paper, we describe the datasets, evaluation metrics, and protocols. We also report major findings that reflect the recent advances in audio deepfake detection tasks.

The ADD 2022 dataset is publicly available.

This data set is licensed with a CC BY-NC-ND 4.0 license.

If you use this dataset, please cite the following paper:

Jiangyan Yi, Ruibo Fu, Jianhua Tao, Shuai Nie, Haoxin Ma, Chenglong Wang, Tao Wang, Zhengkun Tian, Ye Bai, Cunhang Fan, Shan Liang, Shiming Wang, Shuai Zhang, Xinrui Yan, Le Xu, Zhengqi Wen, Haizhou Li:ADD 2022: the first Audio Deep Synthesis Detection Challenge. ICASSP 2022: 9216-9220

音频深度伪造检测（Audio deepfake detection）是一个新兴研究方向，已被纳入ASVspoof 2021竞赛范畴。但现有相关共享任务尚未覆盖诸多真实场景与高挑战性情境。首届音频深度合成检测挑战赛（ADD，Audio Deep synthesis Detection challenge）正是为填补这一空白而设立。ADD 2022（http://addchallenge.cn/add2022）包含三个赛道：低质量伪造音频检测（low-quality fake audio detection，简称LF）、部分伪造音频检测（partially fake audio detection，简称PF）以及音频伪造博弈赛（audio fake game，简称FG）。其中LF赛道聚焦处理带有各类真实世界噪声等干扰的真实语音与全伪造语音；PF赛道旨在区分部分伪造音频与真实音频；FG赛道为对抗博弈类赛事，包含两项任务：音频生成任务与音频伪造检测任务。本文对本次挑战赛的数据集、评估指标与评测协议进行了详细介绍，并汇报了反映当前音频深度伪造检测领域最新进展的主要研究成果。

ADD 2022数据集已公开可获取。

本数据集采用CC BY-NC-ND 4.0许可协议进行授权。

若您使用本数据集，请引用以下论文：
易江岩, 傅瑞波, 陶建华, 聂帅, 马浩鑫, 王成龙, 王涛, 田正坤, 白烨, 范存航, 梁珊, 王仕明, 张帅, 闫新蕊, 徐乐, 温正琪, 李海洲: ADD 2022：首届音频深度合成检测挑战赛. ICASSP 2022: 9216-9220