结合自监督WavLM与多融合注意力分类器的音频深度伪造检测
Audio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion Attentive Classifier
AI总结：
本文提出结合自监督WavLM模型与新型多融合注意力（MFA）分类器进行音频深度伪造检测，首次利用WavLM提取利于欺骗检测的特征，并在ASVspoof数据集上取得领先或具竞争力的结果。
摘要：
随着语音合成和语音转换技术的快速发展，音频深度伪造已成为自动说话人验证（ASV）系统的严重威胁。目前已提出许多对策来检测此类攻击。在本文中，我们报告了将自监督WavLM模型与多融合注意力分类器相结合用于音频深度伪造检测的工作。我们的方法首次利用WavLM模型提取更有利于欺骗检测的特征。然后，我们提出了一种基于注意力统计池化（ASP）层的新型多融合注意力（MFA）分类器。MFA在时间和层级上捕获音频特征的互补信息。实验表明，我们的方法在ASVspoof 2021 DF数据集上取得了最先进的结果，并在ASVspoof 2019和2021 LA数据集上提供了有竞争力的结果。
英文摘要：
With the rapid development of speech synthesis and voice conversion technologies, Audio Deepfake has become a serious threat to the Automatic Speaker Verification (ASV) system. Numerous countermeasures are proposed to detect this type of attack. In this paper, we report our efforts to combine the self-supervised WavLM model and Multi-Fusion Attentive classifier for audio deepfake detection. Our method exploits the WavLM model to extract features that are more conducive to spoofing detection for the first time. Then, we propose a novel Multi-Fusion Attentive (MFA) classifier based on the Attentive Statistics Pooling (ASP) layer. The MFA captures the complementary information of audio features at both time and layer levels. Experiments demonstrate that our methods achieve state-of-the-art results on the ASVspoof 2021 DF set and provide competitive results on the ASVspoof 2019 and 2021 LA set.
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。
