Efficient encrypted speech retrieval based on hadoop cluster under SW CPU

Efficient encrypted speech retrieval based on hadoop cluster under SW CPU

연구 분야: Cryptography

학회: Multimedia Tools and Applications

Most encrypted speech retrieval algorithms are over-optimized for discriminability and robustness, which leads to poor security and efficiency. And it’s inefficient to compute large amounts of data in a single machine. Therefore, in this paper, based on the traditional model of ciphertext speech retrieval system, an efficient encrypted speech retrieval based on Hadoop cluster under SW CPU is proposed. The study uses the SW CPU as a cloud and introduces the Hadoop cluster technology. In the proposed algorithm, firstly, the peak frequency and spectral crest factor of the speech are extracted and fused. Secondly, the hyper chaotic measurement matrix is generated by the key so that it is iterated with the feature vectors and further binarized to generate the BioHashing sequence. A pseudo-random sequence is generated by the key, mapping encryption is performed on the speech segments to generate the encrypted speech, and linear-feedback shift register (LSFR) encryption is performed on the BioHashing sequence to generate the hash index. Finally, the hash index and encrypted speech are uploaded to the cloud via WinSCP. In the SW CPU, multi-processor simultaneous operation can speed up the processing of large amounts of data. The experimental results show that the proposed BioHashing algorithm has a good compromise relationship and the proposed system model has a good security. Moreover, the Hadoop cluster technology effectively improves the retrieval performance.