Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms

TL;DR

This paper introduces S2pecNet, a novel deep learning approach that fuses multi-order spectral patterns and reconstructs spectrograms to improve robustness against audio spoofing attacks, achieving state-of-the-art results.

Contribution

The paper presents a spectral fusion-reconstruction strategy utilizing multi-order spectral patterns for enhanced audio anti-spoofing performance.

Findings

Achieved an EER of 0.77% on ASVspoof2019 LA dataset

Outperformed existing methods in anti-spoofing accuracy

Demonstrated effectiveness of multi-order spectral fusion

Abstract

Robust audio anti-spoofing has been increasingly challenging due to the recent advancements on deepfake techniques. While spectrograms have demonstrated their capability for anti-spoofing, complementary information presented in multi-order spectral patterns have not been well explored, which limits their effectiveness for varying spoofing attacks. Therefore, we propose a novel deep learning method with a spectral fusion-reconstruction strategy, namely S2pecNet, to utilise multi-order spectral patterns for robust audio anti-spoofing representations. Specifically, spectral patterns up to second-order are fused in a coarse-to-fine manner and two branches are designed for the fine-level fusion from the spectral and temporal contexts. A reconstruction from the fused representation to the input spectrograms further reduces the potential fused information loss. Our method achieved the state-of-the-art performance with an EER of 0.77% on a widely used dataset: ASVspoof2019 LA Challenge.