Efficient and Privacy-Preserving Voice-Based Search over mHealth Data

In-home IoT devices play a major role in healthcare systems as smart personal assistants. They usually come with a voice-enabled feature to add an extra level of usability and convenience to elderly, disabled people, and patients. In this paper, we propose an efficient and privacy-preserving voice-based search scheme to enhance the efficiency and the privacy of in-home healthcare applications. We consider an application scenario where patients use the devices to record and upload their voice to servers and the caregivers search the interested voices of their patient's based on the voice content, mood, tone and background sound. Our scheme preserves the richness and privacy of voice data and enables accurate and efficient voice-based search, while in current systems that use speech recognition the richness and privacy of voice data are compromised. Specifically, our scheme achieves the privacy by employing a homomorphic encryption, only encrypted voice data is uploaded to the server who is unable to access the original voice data. In addition, our scheme enables the server to selectively and accurately respond to caregiver's queries on the voice data based on voice's feature similarity. We evaluate our scheme through real experiments and show that our scheme even with privacy preservation can successfully match similar voice data at an average accuracy of 80.8%.

[1]  Xiaohui Liang,et al.  Fully Anonymous Profile Matching in Mobile Social Networks , 2013, IEEE Journal on Selected Areas in Communications.

[2]  Donald F. Towsley,et al.  Covert single-hop communication in a wireless network with distributed artificial noise generation , 2014, 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[3]  Donald F. Towsley,et al.  Covert communications on Poisson packet channels , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[4]  Ian McGraw,et al.  Personalized speech recognition on mobile devices , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Geeta Nijhawan,et al.  ISOLATED SPEECH RECOGNITIONUSING MFCC AND DTW , 2013 .

[6]  Lida Xu,et al.  The internet of things: a survey , 2014, Information Systems Frontiers.

[7]  Carl A. Gunter,et al.  Dynamic Searchable Encryption via Blind Storage , 2014, 2014 IEEE Symposium on Security and Privacy.

[8]  Rafail Ostrovsky,et al.  Public Key Encryption with Keyword Search , 2004, EUROCRYPT.

[9]  Donald F. Towsley,et al.  Covert communications on renewal packet channels , 2016, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[10]  Wen Hu,et al.  Talos: Encrypted Query Processing for the Internet of Things , 2015, SenSys.

[11]  Cong Wang,et al.  Secure Ranked Keyword Search over Encrypted Cloud Data , 2010, 2010 IEEE 30th International Conference on Distributed Computing Systems.

[12]  Bo Zhang,et al.  An efficient public key encryption with conjunctive-subset keywords search , 2011, J. Netw. Comput. Appl..

[13]  Gerhard Nussbaum.  People with Disabilities: Assistive Homes and Environments , 2006, ICCHP.

[14]  Günter Fahrnberger,et al.  SIMS: A Comprehensive Approach for a Secure Instant Messaging Sifter , 2014, 2014 IEEE 13th International Conference on Trust, Security and Privacy in Computing and Communications.

[15]  Thomas R. Ioerger,et al.  Precision and Disclosure in Text and Voice Interviews on Smartphones , 2015, PloS one.

[16]  Saikat Guha,et al.  Covert Wireless Communication With Artificial Noise Generation , 2017, IEEE Transactions on Wireless Communications.

[17]  Yi Yang,et al.  Enabling Fine-Grained Multi-Keyword Search Supporting Classified Sub-Dictionaries over Encrypted Cloud Data , 2016, IEEE Transactions on Dependable and Secure Computing.

[18]  Markus Forsberg.  Why is Speech Recognition Difficult? , 2003 .

[19]  D. Ceer.  Pervasive medical devices: less invasive, more productive , 2006, IEEE Pervasive Computing.

[20]  I. Elamvazuthi,et al.  Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques , 2010, ArXiv.

[21]  Xiaohui Liang,et al.  EPPA: An Efficient and Privacy-Preserving Aggregation Scheme for Secure Smart Grid Communications , 2012, IEEE Transactions on Parallel and Distributed Systems.

[22]  Oliver Chiu-sing Choy,et al.  An efficient MFCC extraction method in speech recognition , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[23]  Héctor M. Pérez Meana,et al.  Speaker recognition using Mel frequency Cepstral Coefficients (MFCC) and Vector quantization (VQ) techniques , 2012, CONIELECOMP 2012, 22nd International Conference on Electrical Communications and Computers.

[24]  Song Ci,et al.  A remote markerless human gait tracking for e-healthcare based on content-aware wireless multimedia communications , 2010, IEEE Wireless Communications.

[25]  Clarence Goh,et al.  Robust Computer Voice Recognition Using Improved MFCC Algorithm , 2009, 2009 International Conference on New Trends in Information and Service Science.

[26]  Yilin Mo,et al.  Privacy Preserving Maximum Consensus , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[27]  A. Holopainen,et al.  Use of Smart Phone Technologies to Offer Easy-to-Use and Cost-Effective Telemedicine Services , 2007, First International Conference on the Digital Society (ICDS'07).

[28]  Nidhika Birla,et al.  VOICE COMMAND RECOGNITION SYSTEM BASED ON MFCC AND DTW , 2010 .

[29]  Ling He,et al.  Using information theoretic vector quantization for inverted MFCC based speaker verification , 2009, 2009 2nd International Conference on Computer, Control and Communication.