Replay spoof detection using energy separation based instantaneous frequency estimation from quadrature and in-phase components

Abstract

Replay attacks in speech are becoming easier to mount with the advent of high quality of recording and playback devices. This makes these replay attacks a major concern for the security of Automatic Speaker Verification (ASV) systems and voice assistants. In the past, auditory transform-based as well as Instantaneous Frequency (IF)-based features have been proposed for replay spoofed speech detection (SSD). In this context, IF has been estimated either by derivative of analytic phase via Hilbert transform, or by using high temporal resolution Teager Energy Operator (TEO)-based Energy Separation Algorithm (ESA). However, excellent temporal resolution of ESA comes with lacking in using relative phase information and vice-versa. To that effect, we propose novel Cochlear Filter Cepstral Coefficients-based Instantaneous Frequency using Quadrature Energy Separation Algorithm (CFCCIF-QESA) features, with excellent temporal resolution as well as relative phase information. CFCCIF-QESA is designed by exploiting relative phase shift to estimate IF, without estimating phase explicitly from the signal. To motivate and validate effectiveness of proposed QESA approach for IF estimation, we have employed information-theoretic measures, such as Mutual Information (MI), Kullback–Leibler (KL) divergence, and Jensen–Shannon (JS) divergence. The proposed CFCCIF-QESA feature set is extensively evaluated on standard statistically meaningful ASVSpoof 2017 version2.0 dataset. When evaluated on the ASVSpoof 2017 v2.0 dataset, CFCCIF-QESA achieves improved performance as compared to CFCCIF-ESA and CQCC feature sets on GMM, CNN, and LCNN classifiers. Furthermore, in the case of cross-database evaluation using ASVSpoof 2017 v2.0 and VSDC, CFCCIF-QESA also performs relatively better as compared to CFCCIF-ESA and CQCC on GMM classifier. However, for the case of self-classification on the ASVSpoof 2019 PA data, CFCCIF-QESA only outperforms CFCCIF-ESA. Whereas, on BTAS 2016 dataset, it performs relatively close to CFCCIF-ESA. Finally, results are presented for the case when the ASV system is not under attack.