ADD 2022: the First Audio Deep Synthesis Detection Challenge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Jiangyan, Fu, Ruibo, Tao, Jianhua, Nie, Shuai, Ma, Haoxin, Wang, Chenglong, Wang, Tao, Tian, Zhengkun, Zhang, Xiaohui, Bai, Ye, Fan, Cunhang, Liang, Shan, Wang, Shiming, Zhang, Shuai, Yan, Xinrui, Xu, Le, Wen, Zhengqi, Li, Haizhou, Lian, Zheng, Liu, Bin
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929405086924800
author Yi, Jiangyan
Fu, Ruibo
Tao, Jianhua
Nie, Shuai
Ma, Haoxin
Wang, Chenglong
Wang, Tao
Tian, Zhengkun
Zhang, Xiaohui
Bai, Ye
Fan, Cunhang
Liang, Shan
Wang, Shiming
Zhang, Shuai
Yan, Xinrui
Xu, Le
Wen, Zhengqi
Li, Haizhou
Lian, Zheng
Liu, Bin
author_facet Yi, Jiangyan
Fu, Ruibo
Tao, Jianhua
Nie, Shuai
Ma, Haoxin
Wang, Chenglong
Wang, Tao
Tian, Zhengkun
Zhang, Xiaohui
Bai, Ye
Fan, Cunhang
Liang, Shan
Wang, Shiming
Zhang, Shuai
Yan, Xinrui
Xu, Le
Wen, Zhengqi
Li, Haizhou
Lian, Zheng
Liu, Bin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2202_08433
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle ADD 2022: the First Audio Deep Synthesis Detection Challenge
Yi, Jiangyan
Fu, Ruibo
Tao, Jianhua
Nie, Shuai
Ma, Haoxin
Wang, Chenglong
Wang, Tao
Tian, Zhengkun
Zhang, Xiaohui
Bai, Ye
Fan, Cunhang
Liang, Shan
Wang, Shiming
Zhang, Shuai
Yan, Xinrui
Xu, Le
Wen, Zhengqi
Li, Haizhou
Lian, Zheng
Liu, Bin
Sound
Machine Learning
Audio and Speech Processing
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.
title ADD 2022: the First Audio Deep Synthesis Detection Challenge
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2202.08433