SLIM：用于泛化音频深度伪造检测的风格-语言学失配模型
SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection
AI总结：
提出SLIM模型，通过利用真实样本自监督预训练学习风格-语言学依赖，并结合标准声学特征，提升了音频深度伪造检测的跨域泛化能力，同时提供模型决策的可解释性。
摘要：
音频深度伪造检测（ADD）对于打击滥用生成式AI模型合成的语音至关重要。现有的ADD模型存在泛化问题，在域内和域外数据之间存在巨大的性能差异。此外，现有模型的黑盒性质限制了它们在需要对模型决策提供解释的真实场景中的应用。为了缓解这些问题，我们引入了一种新的ADD模型，该模型显式利用假语音中的风格-语言学失配（SLIM）将其与真实语音分离。SLIM首先仅在真实样本上采用自监督预训练，以学习真实类别中的风格-语言学依赖关系。学习到的特征随后与标准预训练声学特征（如Wav2vec）互补使用，以在真实和虚假类别上学习分类器。当特征编码器被冻结时，SLIM在域外数据集上优于基准方法，同时在域内数据上取得有竞争力的结果。SLIM学习到的特征使我们能够量化样本中风格与语言内容之间的（失）配，从而促进对模型决策的解释。
英文摘要：
Audio deepfake detection (ADD) is crucial to combat the misuse of speech synthesized from generative AI models. Existing ADD models suffer from generalization issues, with a large performance discrepancy between in-domain and out-of-domain data. Moreover, the black-box nature of existing models limits their use in real-world scenarios, where explanations are required for model decisions. To alleviate these issues, we introduce a new ADD model that explicitly uses the StyleLInguistics Mismatch (SLIM) in fake speech to separate them from real speech. SLIM first employs self-supervised pretraining on only real samples to learn the style-linguistics dependency in the real class. The learned features are then used in complement with standard pretrained acoustic features (e.g., Wav2vec) to learn a classifier on the real and fake classes. When the feature encoders are frozen, SLIM outperforms benchmark methods on out-of-domain datasets while achieving competitive results on in-domain data. The features learned by SLIM allow us to quantify the (mis)match between style and linguistic content in a sample, hence facilitating an explanation of the model decision.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
