深度合成语音鉴别在ACM MM 2022上的首届国际研讨会，论文提交截止时间2022年6月20日，欢迎大家投稿！

官网（文末阅读原文，可直接访问）http://addchallenge.cn/ddam2022


01 Overview

Audio information processing plays an important role in multimedia fields. Audio is not only a media in video, but also can be transcribed into text media. In the Internet era, multimedia information is in geometric progression, and the mixture of real and fake information has brought a certain impact on the society. Audio deepfake detection is an emerging topic in multimedia fields, which was included in the ASVspoof 2021. However, the recent shared tasks have not covered many real-life and challenging multimedia scenarios. In order to fill in the gap，the first Audio Deep synthesis Detection challenge (ADD 2022, http://addchallenge.cn) was successfully held by Prof. Jianhua Tao from Institute of Automation, Chinese Academy of Sciences and Prof. Haizhou Li from National University of Singapore. The datasets of the ADD 2022 [1] were requested by more than 120 teams from 15 countries.

In this workshop, we aim to bring together researchers from the fields of audio deepfake detection, audio deep synthesis, audio fake game and adversarial attacks to further discuss recent research and future directions for detecting deepfake and manipulated audios in multimedia. As far as we know, we are the first workshop to focus on deepfake detection of audio multimedia, which is of great significance.

[1] Jiangyan Yi, Ruibo Fu, Jianhua Tao et al., "ADD 2022: the First Audio Deep Synthesis Detection Challenge", International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022.



02 Dates

03 Call for Papers

Audio deepfake detection is an emerging topic in multimedia fields. However, the current researches have not covered many real-life and challenging multimedia scenarios. We invite submissions on any aspect of audio deep synthesis and detection in audio deep learning systems. Topics include but not limited to:

  • Low-quality fake audio detection

  • Partially fake audio detection

  • Audio fake game

  • Explainable multimedia synthesis detection

  • Robust speech synthesis and detection

  • Adversarial examples for speech synthesis

  • Evaluation metrics for deepfake generation and detection system

04 Paper Submission

Format: Submitted papers (.pdf format) must use the ACM Article Template https://www.acm.org/publications/proceedings-template. Please remember to add Concepts and Keywords. Please use the template in traditional double-column format to prepare your submissions. For example, word users may use Word Interim Template, and latex users may use sample-sigconf template

Length: Submitted papers may consist of up to 8 pages. Up to two additional pages may be added for references. The reference pages must only contain references. Overlength papers will be rejected without review.