Cross-Teager Energy Cepstral Coefficients For Replay Spoof Detection On Voice Assistants

Voice assistants (VAs) are highly vulnerable to replay attacks, where the imposter plays pre-recorded voice samples to gain an unauthorized access to personalised devices. To that effect, we present an appropriate microphone-channel selections scheme for Cross-Teager Energy Operator (CTEO) for spoofed speech detection (SSD) task. Here, a channel refers to the speech signal obtained from single microphone among the microphone array. The key idea of this work is channel selection based on maximum cross energies from a multichannel input, which is suitable for SSD task. This newly proposed feature set is named, Cross-Teager Energy Cepstal Coefficients (CTECCmax). The reason behind maximizing the cross-energies is to identify the distortions in replay speech signal which is added due to intermediate devices. This key idea is also cross-validated by selecting the least estimated cross-energies as feature set CTECCmin. The noticeable improvement in the performance is observed for CTECCmax over CTECCmin for two classifiers, namely, Gaussian Mixture Model (GMM) and Light Convolutional Neural Network (LCNN).