arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.08433cs.SDcs.LGeess.AS
收藏

ADD 2022:首届音频深度合成检测挑战赛

ADD 2022: the First Audio Deep Synthesis Detection Challenge

National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学);National University of Singapore(新加坡国立大学)
Jiangyan Yi, Ruibo Fu, Jianhua Tao, Shuai Nie, Haoxin Ma, Chenglong Wang, Tao Wang, Zhengkun Tian, Xiaohui Zhang, Ye Bai, Cunhang Fan, Shan Liang, Shiming Wang,… 展开作者

Jiangyan Yi, Ruibo Fu, Jianhua Tao, Shuai Nie, Haoxin Ma, Chenglong Wang, Tao Wang, Zhengkun Tian, Xiaohui Zhang, Ye Bai, Cunhang Fan, Shan Liang, Shiming Wang, Shuai Zhang, Xinrui Yan, Le Xu, Zhengqi Wen, Haizhou Li, Zheng Lian, Bin Liu

AI总结:

本文介绍首届 ADD 2022 挑战赛,设置低质量伪造、部分伪造检测及音频伪造博弈三赛道,并给出数据集、指标、协议与最新进展发现。

摘要:

音频深度伪造检测是一个新兴课题,已被纳入 ASVspoof 2021。然而,近期的联合评测任务尚未覆盖许多真实且具有挑战性的场景。首届 Audio Deep synthesis Detection challenge(音频深度合成检测挑战赛,ADD)正是为填补这一空白而发起。ADD 2022 包含三个赛道:低质量伪造音频检测(LF)、部分伪造音频检测(PF)和音频伪造博弈(FG)。LF 赛道聚焦于处理含各类真实噪声等的真实语音与完全伪造语音;PF 赛道旨在区分部分伪造音频与真实音频;FG 赛道是一种对抗博弈,包含音频生成任务和音频伪造检测任务两项任务。本文介绍了数据集、评价指标和协议,并报告了反映音频深度伪造检测任务最新进展的主要发现。

英文摘要:

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 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑