本研究分析了部分伪造语音信号中信号拼接引入的伪影，发现仅通过分析这些伪影即可在 PartialSpoof 和 HAD 数据集上分别实现 6.16% 和 7.36% 的检测等错误率（EER），无需训练检测器，揭示了现有数据集的潜在偏差并指明未来改进方向。
摘要：
语音深度伪造检测近期在多媒体取证社区中获得了显著关注。相关问题也已被探讨，例如部分伪造信号的识别，即包含真实和伪造语音片段的音轨。然而，生成高质量拼接音频并非看起来那么简单。拼接信号通常通过基础信号连接创建。此过程可能引入明显的伪影，使生成的数据更易被检测。我们分析了信号连接产生的拼接音轨，研究了其伪影，并评估这些伪影是否在现有数据集中引入偏差。研究发现，通过分析拼接伪影，我们分别在 PartialSpoof 和 HAD 数据集上实现了 6.16% 和 7.36% 的检测 EER，而无需训练任何检测器。这些结果凸显了生成可靠拼接音频数据的复杂性，并引发了有助于改进未来研究的讨论。
英文摘要：
Speech deepfake detection has recently gained significant attention within the multimedia forensics community. Related issues have also been explored, such as the identification of partially fake signals, i.e., tracks that include both real and fake speech segments. However, generating high-quality spliced audio is not as straightforward as it may appear. Spliced signals are typically created through basic signal concatenation. This process could introduce noticeable artifacts that can make the generated data easier to detect. We analyze spliced audio tracks resulting from signal concatenation, investigate their artifacts and assess whether such artifacts introduce any bias in existing datasets. Our findings reveal that by analyzing splicing artifacts, we can achieve a detection EER of 6.16% and 7.36% on PartialSpoof and HAD datasets, respectively, without needing to train any detector. These results underscore the complexities of generating reliable spliced audio data and lead to discussions that can help improve future research in this area.
Deep Spectro-temporal Artifacts for Detecting Synthesized Speech
Tianjin University（天津大学）；National Institute of Informatics（国立情报学研究所）；Taiyuan University of Technology（太原理工大学）；Japan Advanced Institute of Science and Technology（北陆先端科学技术大学院大学）
FakeChain: Exposing Shallow Cues in Multi-Step Deepfake Detection
Sungkyunkwan University Department of Artificial Intelligence Suwon Gyeonggi-do South Korea；Sungkyunkwan University Computer Science \& Engineering Department Suwon Gyeonggi-do South Korea；Sungkyunkwan University
Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detection
School of Cyber Science and Engineering, Southeast University（东南大学网络空间安全学院）；Purple Mountain Laboratories（紫金山实验室）；Engineering Research Center of Blockchain Application, Supervision And Management (Southeast University), Ministry of Education（教育部区块链应用监管工程研究中心（东南大学））；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education（教育部新一代人工智能技术及其跨学科应用重点实验室（东南大学））
DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices
Nanyang Technological University（南洋理工大学）；Alibaba Group（阿里巴巴集团）；East China Normal University（华东师范大学）；Kyushu University（九州大学）；Institute of Computing Innovation, Zhejiang University（浙江大学计算创新研究院）
Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所台湾国际研究生计划社交网络与人本计算项目）；Department of Computer Science, National Chengchi University（国立政治大学资讯科学系）；Institute of Information Systems and Applications, National Tsing Hua University（国立清华大学资讯系统与应用研究所）；National Institute of Informatics（国立情报学研究所）；Department of Electrical Engineering and the Institute of Communications Engineering, National Tsing Hua University（国立清华大学电机工程学系与通讯工程研究所）；Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）
A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment
University of Eastern Finland（东芬兰大学）；National Institute of Informatics（国立信息学研究所）；University of Edinburgh（爱丁堡大学）；Nagoya University（名古屋大学）；University of Tokyo（东京大学）；ObEN（ObEN公司）；University of Science and Technology of China（中国科学技术大学）
AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Deepfake Detection of Frontal Face Videos
Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Academia Sinica（学术.sinica.edu.tw 社会网络与人本计算计划，台湾国际研究生计划，台湾.sinica.edu.tw）；Department of Computer Science, National Chengchi University（计算机科学系，国立政治大学）；Institute of Information Systems and Applications, National Tsing Hua University（信息系统与应用研究所，国立清华大学）；Research Center for Information Technology Innovation, Academia Sinica（资讯技术创新研究中心，学术.sinica.edu.tw）；Institute of Information Science, Academia Sinica（资讯研究所，学术.sinica.edu.tw）
Robust AI-Synthesized Speech Detection Using Feature Decomposition Learning and Synthesizer Feature Augmentation
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）计算机科学与技术学院）；College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；Alibaba Group（阿里巴巴集团）；College of Computer Science, Chongqing University（重庆大学计算机学院）
