Audio-replay attack detection countermeasures
This work addresses security vulnerabilities in speaker verification systems for applications like biometric authentication, but it is incremental as it builds on existing methods for a specific challenge dataset.
The paper tackled the problem of detecting audio-replay attacks in automatic speaker verification systems by comparing GMM-based methods, high-level feature extraction with SVM, and deep learning frameworks, finding that deep learning approaches maintained stable efficiency across varying acoustic conditions while SVM with high-level features contributed significantly to system performance through fusion.
This paper presents the Speech Technology Center (STC) replay attack detection systems proposed for Automatic Speaker Verification Spoofing and Countermeasures Challenge 2017. In this study we focused on comparison of different spoofing detection approaches. These were GMM based methods, high level features extraction with simple classifier and deep learning frameworks. Experiments performed on the development and evaluation parts of the challenge dataset demonstrated stable efficiency of deep learning approaches in case of changing acoustic conditions. At the same time SVM classifier with high level features provided a substantial input in the efficiency of the resulting STC systems according to the fusion systems results.