ADD 2023: the Second Audio Deepfake Detection Challenge

Jiangyan Yi; Jianhua Tao; Ruibo Fu; Xinrui Yan; Chenglong Wang; Tao Wang; Chu Yuan Zhang; Xiaohui Zhang; Yan Zhao; Yong Ren; Le Xu; Junzuo Zhou; Hao Gu; Zhengqi Wen; Shan Liang; Zheng Lian; Shuai Nie; Haizhou Li

ADD 2023: the Second Audio Deepfake Detection Challenge

Jiangyan Yi^*, Jianhua Tao^*, Ruibo Fu, Xinrui Yan, Chenglong Wang, Tao Wang, Chu Yuan Zhang, Xiaohui Zhang, Yan Zhao, Yong Ren, Le Xu, Junzuo Zhou, Hao Gu, Zhengqi Wen, Shan Liang, Zheng Lian, Shuai Nie, Haizhou Li

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

7 Citations (Scopus)

Abstract

Audio deepfake detection is an emerging topic in the artificial intelligence community. The second Audio Deepfake Detection Challenge (ADD 2023) aims to spur researchers around the world to build new innovative technologies that can further accelerate and foster research on detecting and analyzing deepfake speech utterances. Different from previous challenges (e.g. ADD 2022), ADD 2023 focuses on surpassing the constraints of binary real/fake classification, and actually localizing the manipulated intervals in a partially fake speech as well as pinpointing the source responsible for generating any fake audio. Furthermore, ADD 2023 includes more rounds of evaluation for the fake audio game sub-challenge. The ADD 2023 challenge includes three subchallenges: audio fake game (FG), manipulation region location (RL) and deepfake algorithm recognition (AR). This paper describes the datasets, evaluation metrics, and protocols. Some findings are also reported in audio deepfake detection tasks.

Original language	English
Pages (from-to)	125-130
Number of pages	6
Journal	CEUR Workshop Proceedings
Volume	3597
Publication status	Published - 2023
Externally published	Yes
Event	2023 Workshop on Deepfake Audio Detection and Analysis, DADA 2023 - Macao, China Duration: 19 Aug 2023 → …

Keywords

Audio deepfake
audio fake game
deepfake algorithm recognition
fake detection
manipulation region location

Cite this

@article{9123b6b9056f4f0291698dc291d0fc85,

title = "ADD 2023: the Second Audio Deepfake Detection Challenge",

abstract = "Audio deepfake detection is an emerging topic in the artificial intelligence community. The second Audio Deepfake Detection Challenge (ADD 2023) aims to spur researchers around the world to build new innovative technologies that can further accelerate and foster research on detecting and analyzing deepfake speech utterances. Different from previous challenges (e.g. ADD 2022), ADD 2023 focuses on surpassing the constraints of binary real/fake classification, and actually localizing the manipulated intervals in a partially fake speech as well as pinpointing the source responsible for generating any fake audio. Furthermore, ADD 2023 includes more rounds of evaluation for the fake audio game sub-challenge. The ADD 2023 challenge includes three subchallenges: audio fake game (FG), manipulation region location (RL) and deepfake algorithm recognition (AR). This paper describes the datasets, evaluation metrics, and protocols. Some findings are also reported in audio deepfake detection tasks.",

keywords = "Audio deepfake, audio fake game, deepfake algorithm recognition, fake detection, manipulation region location",

author = "Jiangyan Yi and Jianhua Tao and Ruibo Fu and Xinrui Yan and Chenglong Wang and Tao Wang and Zhang, {Chu Yuan} and Xiaohui Zhang and Yan Zhao and Yong Ren and Le Xu and Junzuo Zhou and Hao Gu and Zhengqi Wen and Shan Liang and Zheng Lian and Shuai Nie and Haizhou Li",

year = "2023",

language = "English",

volume = "3597",

pages = "125--130",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

}

TY - JOUR

T1 - ADD 2023

T2 - 2023 Workshop on Deepfake Audio Detection and Analysis, DADA 2023

AU - Yi, Jiangyan

AU - Tao, Jianhua

AU - Fu, Ruibo

AU - Yan, Xinrui

AU - Wang, Chenglong

AU - Wang, Tao

AU - Zhang, Chu Yuan

AU - Zhang, Xiaohui

AU - Zhao, Yan

AU - Ren, Yong

AU - Xu, Le

AU - Zhou, Junzuo

AU - Gu, Hao

AU - Wen, Zhengqi

AU - Liang, Shan

AU - Lian, Zheng

AU - Nie, Shuai

AU - Li, Haizhou

PY - 2023

Y1 - 2023

N2 - Audio deepfake detection is an emerging topic in the artificial intelligence community. The second Audio Deepfake Detection Challenge (ADD 2023) aims to spur researchers around the world to build new innovative technologies that can further accelerate and foster research on detecting and analyzing deepfake speech utterances. Different from previous challenges (e.g. ADD 2022), ADD 2023 focuses on surpassing the constraints of binary real/fake classification, and actually localizing the manipulated intervals in a partially fake speech as well as pinpointing the source responsible for generating any fake audio. Furthermore, ADD 2023 includes more rounds of evaluation for the fake audio game sub-challenge. The ADD 2023 challenge includes three subchallenges: audio fake game (FG), manipulation region location (RL) and deepfake algorithm recognition (AR). This paper describes the datasets, evaluation metrics, and protocols. Some findings are also reported in audio deepfake detection tasks.

AB - Audio deepfake detection is an emerging topic in the artificial intelligence community. The second Audio Deepfake Detection Challenge (ADD 2023) aims to spur researchers around the world to build new innovative technologies that can further accelerate and foster research on detecting and analyzing deepfake speech utterances. Different from previous challenges (e.g. ADD 2022), ADD 2023 focuses on surpassing the constraints of binary real/fake classification, and actually localizing the manipulated intervals in a partially fake speech as well as pinpointing the source responsible for generating any fake audio. Furthermore, ADD 2023 includes more rounds of evaluation for the fake audio game sub-challenge. The ADD 2023 challenge includes three subchallenges: audio fake game (FG), manipulation region location (RL) and deepfake algorithm recognition (AR). This paper describes the datasets, evaluation metrics, and protocols. Some findings are also reported in audio deepfake detection tasks.

KW - Audio deepfake

KW - audio fake game

KW - deepfake algorithm recognition

KW - fake detection

KW - manipulation region location

UR - http://www.scopus.com/inward/record.url?scp=85181112468&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85181112468

SN - 1613-0073

VL - 3597

SP - 125

EP - 130

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 19 August 2023

ER -

ADD 2023: the Second Audio Deepfake Detection Challenge

Abstract

Keywords

Other files and links

Cite this