SceneFake: An initial dataset and benchmarks for scene fake audio detection

doi:10.1016/j.patcog.2024.110468

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	SceneFake: An initial dataset and benchmarks for scene fake audio detection
	Yi, Jiangyan1 ; Wang, Chenglong 1,2; Tao, Jianhua3,4 ; Zhang, Chu Yuan 1; Fan, Cunhang5 ; Tian, Zhengkun1 ; Ma, Haoxin1 ; Fu, Ruibo1
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
	2024-08-01
卷号	152 页码:12
通讯作者	Yi, Jiangyan(jiangyan.yi@nlpr.ia.ac.cn)
摘要	Many datasets have been designed to further the development of fake audio detection. However, fake utterances in previous datasets are mostly generated by altering timbre, prosody, linguistic content or channel noise of original audio. These datasets leave out a scenario, in which the acoustic scene of an original audio is manipulated with a forged one. It will pose a major threat to our society if some people misuse the manipulated audio with malicious purpose. Therefore, this motivates us to fill in the gap. This paper proposes such a dataset for scene fake audio detection named SceneFake, where a manipulated audio is generated by only tampering with the acoustic scene of an real utterance by using speech enhancement technologies. Some scene fake audio detection benchmark results on the SceneFake dataset are reported in this paper. In addition, an analysis of fake attacks with different speech enhancement technologies and signal-to-noise ratios are presented in this paper. The results indicate that scene fake utterances cannot be reliably detected by baseline models trained on the ASVspoof 2019 dataset. Although these models perform well on the SceneFake training set and seen testing set, their performance is poor on the unseen test set. The dataset2 and benchmark source codes3 are publicly available.
关键词	Scene manipulation Fake audio detection Speech enhancement SceneFake dateset
DOI	10.1016/j.patcog.2024.110468
关键词[WOS]	SPEAKER VERIFICATION ; SPEECH ENHANCEMENT ; IDENTIFICATION
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation China (NSFC)[62322120] ; National Natural Science Foundation China (NSFC)[62306316] ; National Natural Science Foundation China (NSFC)[U21B2010] ; National Natural Science Foundation China (NSFC)[62101553] ; National Natural Science Foundation China (NSFC)[62206278]
项目资助者	National Natural Science Foundation China (NSFC)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001226983800001
出版者	ELSEVIER SCI LTD
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58468
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	Yi, Jiangyan
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China 2.Univ Sci & Technol China, Hefei, Peoples R China 3.Tsinghua Univ, Dept Automat, Beijing, Peoples R China 4.Tsinghua Univ, Beijing Natl Res Ctr Informat Sci & Technol, Beijing, Peoples R China 5.Anhui Univ, Hefei, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Yi, Jiangyan,Wang, Chenglong,Tao, Jianhua,et al. SceneFake: An initial dataset and benchmarks for scene fake audio detection[J]. PATTERN RECOGNITION,2024,152:12.
APA	Yi, Jiangyan.,Wang, Chenglong.,Tao, Jianhua.,Zhang, Chu Yuan.,Fan, Cunhang.,...&Fu, Ruibo.(2024).SceneFake: An initial dataset and benchmarks for scene fake audio detection.PATTERN RECOGNITION,152,12.
MLA	Yi, Jiangyan,et al."SceneFake: An initial dataset and benchmarks for scene fake audio detection".PATTERN RECOGNITION 152(2024):12.