Enhancing Anti-spoofing Countermeasures Robustness through Joint Optimization and Transfer Learning

TL;DR

This paper introduces a transfer learning-based speech enhancement method that significantly improves the robustness of anti-spoofing countermeasures against noise and reverberation, outperforming traditional data augmentation techniques.

Contribution

The study proposes a novel joint optimization and transfer learning approach for speech enhancement to bolster anti-spoofing systems in challenging acoustic environments.

Findings

Improves recognition accuracy by up to 15.8% in noisy conditions.

Achieves better robustness compared to conventional data augmentation.

Effectively enhances anti-spoofing performance in reverberant environments.

Abstract

Current research in synthesized speech detection primarily focuses on the generalization of detection systems to unknown spoofing methods of noise-free speech. However, the performance of anti-spoofing countermeasures (CM) system is often don't work as well in more challenging scenarios, such as those involving noise and reverberation. To address the problem of enhancing the robustness of CM systems, we propose a transfer learning-based speech enhancement front-end joint optimization (TL-SEJ) method, investigating its effectiveness in improving robustness against noise and reverberation. We evaluated the proposed method's performance through a series of comparative and ablation experiments. The experimental results show that, across different signal-to-noise ratio test conditions, the proposed TL-SEJ method improves recognition accuracy by 2.7% to 15.8% compared to the baseline. Compared to conventional data augmentation methods, our system achieves an accuracy improvement ranging from 0.7% to 5.8% in various noisy conditions and from 1.7% to 2.8% under different RT60 reverberation scenarios. These experiments demonstrate that the proposed method effectively enhances system robustness in noisy and reverberant conditions.