Existing speech retrieval systems are frequently confronted with expanding volumes of speech data.The dynamic updating strategy applied to construct the index can timely process to add or remove unnecessary speech dat...Existing speech retrieval systems are frequently confronted with expanding volumes of speech data.The dynamic updating strategy applied to construct the index can timely process to add or remove unnecessary speech data to meet users’real-time retrieval requirements.This study proposes an efficient method for retrieving encryption speech,using unsupervised deep hashing and B+ tree dynamic index,which avoid privacy leak-age of speech data and enhance the accuracy and efficiency of retrieval.The cloud’s encryption speech library is constructed by using the multi-threaded Dijk-Gentry-Halevi-Vaikuntanathan(DGHV)Fully Homomorphic Encryption(FHE)technique,which encrypts the original speech.In addition,this research employs Residual Neural Network18-Gated Recurrent Unit(ResNet18-GRU),which is used to learn the compact binary hash codes,store binary hash codes in the designed B+tree index table,and create a mapping relation of one to one between the binary hash codes and the corresponding encrypted speech.External B+tree index technology is applied to achieve dynamic index updating of the B+tree index table,thereby satisfying users’needs for real-time retrieval.The experimental results on THCHS-30 and TIMIT showed that the retrieval accuracy of the proposed method is more than 95.84%compared to the existing unsupervised hashing methods.The retrieval efficiency is greatly improved.Compared to the method of using hash index tables,and the speech data’s security is effectively guaranteed.展开更多
Searching for rare astronomical objects based on spectral data is similar to finding needles in a haystack owing to their rarity and the immense data volume gathered from large astronomical spectroscopic surveys.In th...Searching for rare astronomical objects based on spectral data is similar to finding needles in a haystack owing to their rarity and the immense data volume gathered from large astronomical spectroscopic surveys.In this paper,we propose a novel automated approximate nearest neighbor search method based on unsupervised hashing learning for rare spectra retrieval.The proposed method employs a multilayer neural network using autoencoders as the local compact feature extractors.Autoencoders are trained with a non-gradient learning algorithm with graph Laplace regularization.This algorithm also simplifies the tuning of network architecture hyperparameters and the learning control hyperparameters.Meanwhile,the graph Laplace regularization can enhance the robustness by reducing the sensibility to noise.The proposed model is data-driven;thus,it can be viewed as a general-purpose retrieval model.The proposed model is evaluated in experiments and real-world applications where rare Otype stars and their subclass are retrieved from the dataset obtained from the Large Sky Area Multi-Object Fiber Spectroscopic Telescope(Guo Shoujing Telescope).The experimental and application results show that the proposed model outperformed the baseline methods,demonstrating the effectiveness of the proposed method in rare spectra retrieval tasks.展开更多
基金supported by the NationalNatural Science Foundation of China(No.61862041).
文摘Existing speech retrieval systems are frequently confronted with expanding volumes of speech data.The dynamic updating strategy applied to construct the index can timely process to add or remove unnecessary speech data to meet users’real-time retrieval requirements.This study proposes an efficient method for retrieving encryption speech,using unsupervised deep hashing and B+ tree dynamic index,which avoid privacy leak-age of speech data and enhance the accuracy and efficiency of retrieval.The cloud’s encryption speech library is constructed by using the multi-threaded Dijk-Gentry-Halevi-Vaikuntanathan(DGHV)Fully Homomorphic Encryption(FHE)technique,which encrypts the original speech.In addition,this research employs Residual Neural Network18-Gated Recurrent Unit(ResNet18-GRU),which is used to learn the compact binary hash codes,store binary hash codes in the designed B+tree index table,and create a mapping relation of one to one between the binary hash codes and the corresponding encrypted speech.External B+tree index technology is applied to achieve dynamic index updating of the B+tree index table,thereby satisfying users’needs for real-time retrieval.The experimental results on THCHS-30 and TIMIT showed that the retrieval accuracy of the proposed method is more than 95.84%compared to the existing unsupervised hashing methods.The retrieval efficiency is greatly improved.Compared to the method of using hash index tables,and the speech data’s security is effectively guaranteed.
基金supported by the Postdoctoral Science Foundation of China(Grant No.2020M682348)the Key Research Foundation of Henan Higher Education Institutions(Grant No.21A520002)+1 种基金the National Key Research and Development Program of China(Grant No.2018AAA0100203)the Joint Research Fund in Astronomy(Grant No.U1531242)under a cooperative agreement between the National Natural Science Foundation of China and the Chinese Academy of Sciences(CAS)。
文摘Searching for rare astronomical objects based on spectral data is similar to finding needles in a haystack owing to their rarity and the immense data volume gathered from large astronomical spectroscopic surveys.In this paper,we propose a novel automated approximate nearest neighbor search method based on unsupervised hashing learning for rare spectra retrieval.The proposed method employs a multilayer neural network using autoencoders as the local compact feature extractors.Autoencoders are trained with a non-gradient learning algorithm with graph Laplace regularization.This algorithm also simplifies the tuning of network architecture hyperparameters and the learning control hyperparameters.Meanwhile,the graph Laplace regularization can enhance the robustness by reducing the sensibility to noise.The proposed model is data-driven;thus,it can be viewed as a general-purpose retrieval model.The proposed model is evaluated in experiments and real-world applications where rare Otype stars and their subclass are retrieved from the dataset obtained from the Large Sky Area Multi-Object Fiber Spectroscopic Telescope(Guo Shoujing Telescope).The experimental and application results show that the proposed model outperformed the baseline methods,demonstrating the effectiveness of the proposed method in rare spectra retrieval tasks.