Search papers, labs, and topics across Lattice.
This paper introduces an innovative E-Branchformer architecture for audio deepfake detection that utilizes self-supervised speech representations to enhance detection accuracy. By employing parallel branches to capture both global contextual dependencies and local temporal patterns, the model achieves state-of-the-art performance on multiple datasets, including ASVspoof 2021 LA, DF, and In-the-Wild. The integration of depthwise convolution and Squeeze-and-Excitation modules significantly boosts the model's discriminative capabilities, resulting in equal error rates of 0.88%, 1.85%, and 6.30%, respectively.
Achieving an unprecedented equal error rate of 0.88% in audio deepfake detection, this model sets a new benchmark for robustness against sophisticated voice synthesis attacks.
The rapid advancement of voice synthesis technologies such as text-to-speech and voice conversion poses significant threats to speech-based authentication systems, necessitating robust deepfake detection methods. In this work, we propose a novel E-Branchformer-based architecture that effectively leverages self-supervised speech representations for audio deepfake detection. Our model employs parallel branches to simultaneously capture global contextual dependencies through multi-head self-attention and local temporal patterns through convolutional processing. To enhance discriminative capability, we integrate depthwise convolution and Squeeze-and-Excitation modules that enrich the classification token with refined patch token information after feature merging. Extensive experiments on ASVspoof 2021 LA, DF, and In-the-Wild datasets demonstrate state-of-the-art performance with equal error rates of 0.88%, 1.85%, and 6.30% respectively, substantially outperforming existing methods. Comprehensive ablation studies validate that the dual-branch architecture provides complementary discriminative information, Squeeze-and-Excitation Aggregation significantly improves SSL feature integration, and the combination of DWConv and SE modules is critical for effective class token enhancement. The superior performance on real-world scenarios demonstrates strong generalization capability to diverse acoustic conditions and unseen spoofing attacks.
