Disentangled Global-Local Feature Learning with E-Branchformer for Audio Deepfake Detection

2026-09-08

AI Summary

为应对语音合成技术对认证系统的威胁，提出基于E-Branchformer的新架构，通过并行分支捕捉全局和局部特征，并结合深度卷积和挤压激励模块增强鉴别能力，以实现音频深伪检测。

Abstract

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.

Problem

• audio deepfake detection
• voice synthesis technologies
• speech-based authentication systems

Innovation

• E-Branchformer
• self-supervised speech representations
• multi-head self-attention
• depthwise convolution
• Squeeze-and-Excitation