Spoofing and Anti-Spoofing (SAS) corpus v1.0

This dataset is associated with the paper ''SAS: A speaker verification spoofing database containing diverse attacks': presents the first version of a speaker verification spoofing and anti-spoofing database, named SAS corpus. The corpus includes nine spoofing techniques, two of which are speech synthesis, and seven are voice conversion. We design two protocols, one for standard speaker verification evaluation, and the other for producing spoofing materials. Hence, they allow the speech synthesis community to produce spoofing materials incrementally without knowledge of speaker verification spoofing and anti-spoofing. To provide a set of preliminary results, we conducted speaker verification experiments using two state-of-the-art systems. Without any anti-spoofing techniques, the two systems are extremely vulnerable to the spoofing attacks implemented in our SAS corpus'. N.B. the files in the following fileset should also be taken as part of the same dataset as those provided here: Wu et al. (2017). Key files for Spoofing and Anti-Spoofing (SAS) corpus v1.0, [dataset]. University of Edinburgh. The Centre for Speech Technology Research (CSTR). http://hdl.handle.net/10283/2741

本数据集关联论文《SAS：包含多样化攻击的说话人验证欺骗数据库》，该论文发布了名为SAS语料库的说话人验证欺骗与反欺骗数据库的首个版本。该语料库涵盖9种欺骗攻击技术，其中2种为语音合成（speech synthesis）技术，其余7种为语音转换（voice conversion）技术。我们设计了两套实验协议：一套用于标准说话人验证（speaker verification）评估，另一套用于生成欺骗样本。借此，语音合成领域的研究者无需掌握说话人验证欺骗与反欺骗相关专业知识，即可逐步生成欺骗样本。为提供一组基准实验结果，我们采用两套最先进的系统开展了说话人验证实验。在未应用任何反欺骗（anti-spoofing）技术的情况下，这两套系统对本SAS语料库中实现的欺骗攻击具有极高的脆弱性。注意：以下文件集中的文件同样属于本数据集，与本次提供的文件同属一个数据集：Wu等人（2017）. 欺骗与反欺骗（SAS）语料库v1.0关键文件[数据集]. 爱丁堡大学语音技术研究中心（Centre for Speech Technology Research, CSTR）. http://hdl.handle.net/10283/2741