A novel privacy-preserving speech recognition framework using bidirectional LSTM

被引:0
作者
Qingren Wang
Chuankai Feng
Yan Xu
Hong Zhong
Victor S. Sheng
机构
[1] Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education,
[2] School of Computer Science and Technology,undefined
[3] Anhui University,undefined
[4] Department of Computer Science,undefined
[5] Texas Tech University,undefined
来源
Journal of Cloud Computing | / 9卷
关键词
Bidirectional LSTM; Privacy-preserving; Speech recognition; Edge-cloud computing; Internet of things;
D O I
暂无
中图分类号
学科分类号
摘要
Utilizing speech as the transmission medium in Internet of things (IoTs) is an effective way to reduce latency while improving the efficiency of human-machine interaction. In the field of speech recognition, Recurrent Neural Network (RNN) has significant advantages to achieve accuracy improvement on speech recognition. However, some of RNN-based intelligence speech recognition applications are insufficient in the privacy-preserving of speech data, and others with privacy-preserving are time-consuming, especially about model training and speech recognition. Therefore, in this paper we propose a novel Privacy-preserving Speech Recognition framework using Bidirectional Long short-term memory neural network, namely PSRBL. On the one hand, PSRBL designs new functions to construct security activation functions by combing with an additive secret sharing protocol, namely a secure piecewise-linear Sigmoid and a secure piecewise-linear Tanh respectively, to achieve privacy-preserving of speech data during speech recognition process running on edge servers. On the other hand, in order to reduce the time spent on both the training and the recognition of the speech model while keeping high accuracy during speech recognition process, PSRBL first utilizes secure activation functions to refit original activation functions in the bidirectional Long Short-Term Memory neural network (LSTM), and then makes full use of the left and the right context information of speech data by employing bidirectional LSTM. Experiments conducted on the speech dataset TIMIT show that our framework PSRBL performs well. Specifically compared with the state-of-the-art ones, PSRBL significantly reduces the time consumption on both the training and the recognition of the speech model under the premise that PSRBL and the comparisons are consistent in the privacy-preserving of speech data.
引用
收藏
相关论文
共 50 条
[41]   A Privacy-Preserving Data-Sharing Framework for Smart Grid [J].
Alharbi, Khalid Nawaf ;
Lin, Xiaodong ;
Shao, Jun .
IEEE INTERNET OF THINGS JOURNAL, 2017, 4 (02) :555-562
[42]   A bio-inspired privacy-preserving framework for healthcare systems [J].
Dhasarathan, Chandramohan ;
Kumar, Manish ;
Srivastava, Atul Kumar ;
Al-Turjman, Fadi ;
Shankar, Achyut ;
Kumar, Manoj .
JOURNAL OF SUPERCOMPUTING, 2021, 77 (10) :11099-11134
[43]   A Secure and Privacy-Preserving E-Government Framework Using Blockchain and Artificial Immunity [J].
Elisa, Noe ;
Yang, Longzhi ;
Chao, Fei ;
Naik, Nitin ;
Boongoen, Tossapon .
IEEE ACCESS, 2023, 11 :8773-8789
[44]   Healthcare Applications Using Blockchain With a Cloud-Assisted Decentralized Privacy-Preserving Framework [J].
Deebak, Bakkiam David ;
Hwang, Seong Oun .
IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (05) :5897-5916
[45]   A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks [J].
Nikfam, Farzad ;
Casaburi, Raffaele ;
Marchisio, Alberto ;
Martina, Maurizio ;
Shafique, Muhammad .
INFORMATION, 2023, 14 (10)
[46]   A Hierarchical Asynchronous Federated Learning Privacy-Preserving Framework for IoVs [J].
Zhou, Rui ;
Niu, Xianhua ;
Xiong, Ling ;
Wang, Yangpeng ;
Zhao, Yue ;
Yu, Kai .
FRONTIERS IN CYBER SECURITY, FCS 2023, 2024, 1992 :99-113
[47]   A Secure and Privacy-Preserving Data Transmission Scheme in the Healthcare Framework [J].
Yang, Huijie ;
Zhou, Tianqi ;
Wang, Chen ;
He, Debiao .
INFORMATION SECURITY PRACTICE AND EXPERIENCE, ISPEC 2021, 2021, 13107 :374-391
[48]   APIVADS: A Novel Privacy-Preserving Pivot Attack Detection Scheme Based on Statistical Pattern Recognition [J].
Marques, Rafael Salema ;
Al-Khateeb, Haider ;
Epiphaniou, Gregory ;
Maple, Carsten .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2022, 17 :700-715
[49]   Efficient and Privacy-Preserving Speaker Recognition for Cybertwin-Driven 6G [J].
Li, Qi ;
Lin, Xiaodong .
IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (22) :16195-16206
[50]   Privacy-Preserving Face Recognition With Multi-Edge Assistance for Intelligent Security Systems [J].
Gao, Wenjing ;
Yu, Jia ;
Hao, Rong ;
Kong, Fanyu ;
Liu, Xiaodong .
IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (12) :10948-10958