An Encrypted Speech Retrieval Method Based on Deep Perceptual Hashing and CNN-BiLSTM

Abstract

ABSTRACRT Since convolutional neural network (CNN) can only extract local features, and long shortterm memory (LSTM) neural network model has a large number of learning calculations, a long processing time and an obvious degree of information loss as the length of speech increases. Utilizing the characteristics of autonomous feature extraction in deep learning, CNN and bidirectional long short-term memory (BiLSTM) network are combined to present an encrypted speech retrieval method based on deep perceptual hashing and CNN-BiLSTM. Firstly, the proposed method extracts the Log-Mel Spectrogram/MFCC features of the original speech and enters the CNN and BiLSTM networks in turn for model training. Secondly, we use the trained fusion network model to learn the deep perceptual feature and generate deep perceptual hashing sequences. Finally, the normalized Hamming distance algorithm is used for matching retrieval. In order to protect the speech security in the cloud, a speech encryption algorithm based on a 4D hyperchaotic system is proposed. The experimental results show that the proposed method has good discrimination, robustness, recall and precision compared with the existing methods, and it has good retrieval efficiency and retrieval accuracy for longer speech. Meanwhile, the proposed speech encryption algorithm has a high key space to resist exhaustive attacks. INDEX TERMS Encrypted speech retrieval, CNN-BiLSTM, Deep perceptual hashing, Speech feature extraction, 4D hyperchaotic system.

Research on Emotion Analysis and Psychoanalysis Application With Convolutional Neural Network and Bidirectional Long Short-Term Memory

“…(2) Bi-LSTM (Zou et al, 2021): Only the Bi-LSTM neural network is used for text feature learning. (3) CNN-BiLSTM (Zhang et al, 2020): The CNN and Bi-LSTM are input, respectively, for encoding; relevant features are extracted, and finally classified them by fusion in the full connection layer. (4) BiLSTM-CNN (Zhu et al, 2019): The vector is input into Bi-LSTM and then the result is input into the CNN for final classification.…”

“…CNN-BiLSTM ( Zhang et al, 2020 ): The CNN and Bi-LSTM are input, respectively, for encoding; relevant features are extracted, and finally classified them by fusion in the full connection layer.…”

Network Intrusion Detection Method Based on CNN-BiLSTM-Attention Model

“…model performance. Literature [45] proposes the DDoS attack detection method based on CNN-AttBiLSTM. Firstly, before the CNN-AttBiLSTM model, a combination of the Random Forest and Pearson correlation analysis algorithms is used to select important features to reduce redundant data.…”

DS2B: Dynamic and Secure Substitution Box for Efficient Speech Encryption Engine

“…Security of speech information is essential for many applications including smart devices, e-learning, and video conferencing [10], [11]. Speech includes a lot of confidential data, it is important to encrypt the speech data before uploading it to the cloud [12]. A number of schemes have been proposed in the literature for encrypting speech files [13]- [16].…”