Abstract
In this paper, we present an efficient retrieval algorithm for encrypted speech based on an inverse fast Fourier transform and measurement matrix. Our approach improves query performance, as well as retrieval efficiency and accuracy, compared to existing content-based encrypted speech retrieval methods. Our proposed algorithm constructs a perceptual hash scheme using perceptual hash sequences from original speech files. By classifying the sequences and applying run-length compression, we decrease the cloud storage required for the hash index. We secure the speech database by encrypting it with Henon chaos scrambling, which offers excellent resistance to attacks. Experimental results show that the robustness, discrimination, and feature extraction efficiency of our proposed method are better than the existing alternatives, with good recall and precision ratios and with high retrieval efficiency and accuracy.
Highlights
With the rapid development of Internet technology, speech is widely used in the fields of radio and television, court evidence, telephone service, conference recording, etc
The proposed retrieval algorithm of encrypted speech Having provided both some theoretical fundamentals and an overview of our system, we present the implementation of the three main parts in more detail
These results indicate that the bit error ratio (BER) values of the same perceived content were all less than 0.1801 for our algorithm, which is much smaller than the minimum of discrimination
Summary
With the rapid development of Internet technology, speech is widely used in the fields of radio and television, court evidence, telephone service, conference recording, etc. A good content-based retrieval algorithm for encrypted speech realizes the retrieval process of speech content information by researching the physical features of speech, such as frequency spectrum and amplitude, and auditory features such as pitch and timbre [2], protecting the privacy of the speech data and retrieving data efficiently and accurately. Zhao et al proposed an encrypted perceptual hashing retrieval method using the multifractal characteristic It has good robustness and high retrieval accuracy but poor discrimination and low retrieval efficiency [23]. He et al proposed a retrieval method for encrypted speech using syllable-level perceptual hashing. It has good robustness and high security, but poor speech feature discrimination and mediocre retrieval efficiency [24].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
