ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林计算机科学及其应用实验室）；National Institute of Informatics（国立信息学研究所）；Institute for Advancing Intelligence, TCG CREST（TCG CREST 智能推进研究所）；EURECOM（欧洲通信学院）；Cerence Inc.（赛轮思公司）；Avignon Université（阿维尼翁大学）；Nuance Communications（Nuance 通信公司）；University of Eastern Finland（东芬兰大学）
Xuechen Liu, Xin Wang, Md Sahidullah, Jose Patino, Héctor Delgado, Tomi Kinnunen, Massimiliano Todisco, Junichi Yamagishi, Nicholas Evans, Andreas Nautsch, Kong Aik Lee
备注：
IEEE/ACM Transactions on Audio, Speech, and Language Processing
Benchmarking initiatives support the meaningful comparison of competing solutions to prominent problems in speech and language processing. Successive benchmarking evaluations typically reflect a progressive evolution from ideal lab conditions towards to those encountered in the wild. ASVspoof, the spoofing and deepfake detection initiative and challenge series, has followed the same trend. This article provides a summary of the ASVspoof 2021 challenge and the results of 54 participating teams that submitted to the evaluation phase. For the logical access (LA) task, results indicate that countermeasures are robust to newly introduced encoding and transmission effects. Results for the physical access (PA) task indicate the potential to detect replay attacks in real, as opposed to simulated physical spaces, but a lack of robustness to variations between simulated and real acoustic environments. The Deepfake (DF) task, new to the 2021 edition, targets solutions to the detection of manipulated, compressed speech data posted online. While detection solutions offer some resilience to compression effects, they lack generalization across different source datasets. In addition to a summary of the top-performing systems for each task, new analyses of influential data factors and results for hidden data subsets, the article includes a review of post-challenge results, an outline of the principal challenge limitations and a road-map for the future of ASVspoof.
ASVspoof 2021 is the forth edition in the series of bi-annual challenges which aim to promote the study of spoofing and the design of countermeasures to protect automatic speaker verification systems from manipulation. In addition to a continued focus upon logical and physical access tasks in which there are a number of advances compared to previous editions, ASVspoof 2021 introduces a new task involving deepfake speech detection. This paper describes all three tasks, the new databases for each of them, the evaluation metrics, four challenge baselines, the evaluation platform and a summary of …
EURECOM（欧洲通信研究院）；National Institute of Informatics（国立信息学研究所）；University of Eastern Finland（东芬兰大学）；Inria（法国国家信息与自动化研究所）；University of Edinburgh（爱丁堡大学）；NEC Corp.（日本电气股份有限公司）
ASVspoof, now in its third edition, is a series of community-led challenges which promote the development of countermeasures to protect automatic speaker verification (ASV) from the threat of spoofing. Advances in the 2019 edition include: (i) a consideration of both logical access (LA) and physical access (PA) scenarios and the three major forms of spoofing attack, namely synthetic, converted and replayed speech; (ii) spoofing attacks generated with state-of-the-art neural acoustic and waveform models; (iii) an improved, controlled simulation of replay attacks; (iv) use of the tandem detectio…
Temporal Variability and Multi-Viewed Self-Supervised Representations to Tackle the ASVspoof5 Deepfake Challenge
Communication University of China（中国传媒大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Duke University（杜克大学）；Duke Kunshan University（昆山杜克大学）
The present paper proposes a waveform boundary detection system for audio spoofing attacks containing partially manipulated segments. Partially spoofed/fake audio, where part of the utterance is replaced, either with synthetic or natural audio clips, has recently been reported as one scenario of audio deepfakes. As deepfakes can be a threat to social security, the detection of such spoofing audio is essential. Accordingly, we propose to address the problem with a deep learning-based frame-level detection system that can detect partially spoofed audio and locate the manipulated pieces. Our prop…
Boundary and Intra-Segment Learning for Partial Audio Deepfake Localization
Sun Yat-sen University（中山大学）；China Mobile Internet Corporation（中国移动互联网公司）；The Hong Kong Polytechnic University（香港理工大学）；Nanyang Technological University（南洋理工大学）
Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment
School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou, China（信息与电子工程学院，浙江工商大学，杭州，中国）；Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, USA（电气与计算机工程系，新泽西理工学院，纽卡斯尔，美国）
This paper describes our submitted systems to the 2022 ADD challenge withing the tracks 1 and 2. Our approach is based on the combination of a pre-trained wav2vec2 feature extractor and a downstream classifier to detect spoofed audio. This method exploits the contextualized speech representations at the different transformer layers to fully capture discriminative information. Furthermore, the classification model is adapted to the application scenario using different data augmentation techniques. We evaluate our system for audio synthesis detection in both the ASVspoof 2021 and the 2022 ADD ch…
Despite several years of research in deepfake and spoofing detection for automatic speaker verification, little is known about the artefacts that classifiers use to distinguish between bona fide and spoofed utterances. An understanding of these is crucial to the design of trustworthy, explainable solutions. In this paper we report an extension of our previous work to better understand classifier behaviour to the use of SHapley Additive exPlanations (SHAP) to attack analysis. Our goal is to identify the artefacts that characterise utterances generated by different attacks algorithms. Using a pa…
Fraunhofer Institute for Applied and Integrated Security AISEC（弗劳恩霍夫应用与集成安全研究所AISEC）；Technical University of Munich（慕尼黑工业大学）；The University of Edinburgh（爱丁堡大学）
We present our analysis of a significant data artifact in the official 2019/2021 ASVspoof Challenge Dataset. We identify an uneven distribution of silence duration in the training and test splits, which tends to correlate with the target prediction label. Bonafide instances tend to have significantly longer leading and trailing silences than spoofed instances. In this paper, we explore this phenomenon and its impact in depth. We compare several types of models trained on a) only the duration of the leading silence and b) only on the duration of leading and trailing silence. Results show that m…
Wav2DF-TSL: Two-stage Learning with Efficient Pre-training and Hierarchical Experts Fusion for Robust Audio Deepfake Detection
School of Computer Science and Technology, Xinjiang University, Urumqi, China（新疆大学计算机科学与技术学院）；Hefei iFly Digital Technology Co. Ltd., Hefei, China（合肥iFly数字技术有限公司）；University of Science and Technology of China, Hefei, China（中国科学技术大学）；Department of Electronic Engineering, Tsinghua University, Beijing, China（清华大学电子工程系）
BreathNet: Generalizable Audio Deepfake Detection via Breath-Cue-Guided Feature Refinement
Guangdong Key Laboratory of Information Security, School of Computer Science and Engineering, Sun Yat-sen University（广东信息安全重点实验室，计算机科学与工程学院，中山大学）；State Key Laboratory of Multi-modal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；China Mobile Internet Corporation, China Mobile Communications Corporation（中国移动互联网有限公司，中国移动通信集团）；Guangdong Laboratory of Machine Perception and Intelligent Computing, Faculty of Engineering, Shenzhen MSU-BIT University（广东机器感知与智能计算实验室，工程学院，深圳MSU-BIT大学）
What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection
School of Computing, Wichita State University（威奇托州立大学计算学院）；Institut national de la recherche scientifique (INRS–EMT)（国家科学研究院（INRS–EMT））；INRS-UQO Mixed Research Unit on Cybersecurity（INRS-UQO网络安全混合研究单位）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；Beijing Jiaotong University（北京交通大学）；Hebei University of Technology（河北工业大学）
Fraunhofer AISEC（弗劳恩霍夫人工智能安全研究所）；Wrocław University of Science and Technology（沃斯克拉大学科学与技术学院）；Resemble AI（Resemble AI公司）；Technical University of Cluj-Napoca（克鲁克斯-纳波卡技术大学）；Neodyme AG（Neodyme公司）；TU Munich（慕尼黑技术大学）
Artefacts that serve to distinguish bona fide speech from spoofed or deepfake speech are known to reside in specific subbands and temporal segments. Various approaches can be used to capture and model such artefacts, however, none works well across a spectrum of diverse spoofing attacks. Reliable detection then often depends upon the fusion of multiple detection systems, each tuned to detect different forms of attack. In this paper we show that better performance can be achieved when the fusion is performed within the model itself and when the representation is learned automatically from raw w…
RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection
School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Tsinghua University（清华大学）
