Scholarlink

With the rapid advancement of AI-driven speech synthesis and voice conversion technologies, deepfake audio has emerged as a serious threat to communication integrity and cybersecurity. In this paper, we propose a lightweight hybrid attention architecture named MBAAF for audio spoofing detection, which integrates feature-specific attention modules across a multi-branch input pipeline. Specifically, Mel-Frequency Cepstral Coefficients (MFCC) and Short-Time Fourier Transform (STFT) branches are refined using Temporal Gating Blocks (TGB), while Constant-Q Cepstral Coefficients (CQCC) are enhanced with a Convolutional Block Attention Module (CBAM). These refined features are fused and processed by a compact ResNeSt backbone for final classification. Experiments show that MBAAF attains 0.15% EER and 0.011 t-DCF on ASVSpoof2019 LA and sets a new state-of-the-art of 0.092% EER on the In-the-Wild dataset, using only 135K parameters. These results highlight the effectiveness of heterogeneous attention placement and confirm that a compact, modular design can achieve both high accuracy and efficiency for real-time, low-resource deployment.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

MBAAF: Multi-branch Lightweight Architecture for Audio Spoofing Detection with Temporal Gating and CBAM-Based Attention Fusion

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Khanh-Duy Cao-Phan,
  • Thi Phuc Dang

摘要

With the rapid advancement of AI-driven speech synthesis and voice conversion technologies, deepfake audio has emerged as a serious threat to communication integrity and cybersecurity. In this paper, we propose a lightweight hybrid attention architecture named MBAAF for audio spoofing detection, which integrates feature-specific attention modules across a multi-branch input pipeline. Specifically, Mel-Frequency Cepstral Coefficients (MFCC) and Short-Time Fourier Transform (STFT) branches are refined using Temporal Gating Blocks (TGB), while Constant-Q Cepstral Coefficients (CQCC) are enhanced with a Convolutional Block Attention Module (CBAM). These refined features are fused and processed by a compact ResNeSt backbone for final classification. Experiments show that MBAAF attains 0.15% EER and 0.011 t-DCF on ASVSpoof2019 LA and sets a new state-of-the-art of 0.092% EER on the In-the-Wild dataset, using only 135K parameters. These results highlight the effectiveness of heterogeneous attention placement and confirm that a compact, modular design can achieve both high accuracy and efficiency for real-time, low-resource deployment.