Voice Quality Features for Replay Attack Detection

Replay attacks are attempts to get fraudulent access to an automatic speaker verification system. In this paper, we investigate the usefulness of voice quality features to detect replay attacks. The voice quality features are used together with the state-of-the-art constant Q cepstral coefficients (CQCC) features. The two feature sets are fused at the score level. Thus, the log-likelihood scores estimated from the two feature sets are linearly weighted to obtain a single fused score. The fused score is used to classify whether a given speech sample is genuine or spoofed. Our experiments with the ASVspoof 2017 dataset demonstrate that the fusion of log-likelihood scores extracted from the CQCC and voice quality features improve the Equal Error Rate (EER) compared to the baseline system which is based only on CQCC features.