An efficient retrieval algorithm of encrypted speech based on inverse fast Fourier transform and measurement matrix

Abstract

In this paper, we present an efficient retrieval algorithm for encrypted speech based on an inverse fast Fouriertransform and measurement matrix. Our approach improves query performance, as well as retrieval efficiency andaccuracy, compared to existing content-based encrypted speech retrieval methods. Our proposed algorithm constructsa perceptual hash scheme using perceptual hash sequences from original speech files. By classifying the sequences andapplying run-length compression, we decrease the cloud storage required for the hash index. We secure the speechdatabase by encrypting it with Henon chaos scrambling, which offers excellent resistance to attacks. Experimentalresults show that the robustness, discrimination, and feature extraction efficiency of our proposed method are betterthan the existing alternatives, with good recall and precision ratios and with high retrieval efficiency and accuracy.