Multi-format speech BioHashing based on spectrogram
- PDF / 2,171,442 Bytes
- 21 Pages / 439.642 x 666.49 pts Page_size
- 104 Downloads / 183 Views
Multi-format speech BioHashing based on spectrogram Yi-bo Huang1
· Yong Wang1 · Qiu-yu Zhang2 · Wei-zhao Zhang1 · Man-hong Fan1
Received: 7 October 2019 / Revised: 30 April 2020 / Accepted: 11 June 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In order to solve the security problem of speech perception hash authentication, the application scope of speech authentication algorithm, and improve the robustness, discrimination and real-time authentication in the process of authentication, a multi-format speech BioHashing algorithm based on spectrogram is proposed. Firstly, the speech signal to be processed is converted into spectrogram and feature extraction is carried out by two-dimensional discrete cosine transform. Then, the dimensionality of the eigenvector is reduced by non-negative matrix factorization, and generation of BioHashing sequences by inner product of reduced dimension eigenvectors and orthogonal normalized random matrices. Finally, the BioHashing is encrypted by equal-length scrambling using Henon chaotic map. The algorithm also validates the unidirectionality of BioHashing with trapdoor by comparative difference method. The experimental results show that the proposed algorithm has the characteristics of good security, strong robustness, high real-time performance and wide application range. Keywords Speech content authentication · BioHashing · Spectrogram · Henon map · Comparative difference method
1 Introduction In recent years, with the rapid development and increasing popularity of mobile communication technologies, data storage technologies and multimedia home collection devices, multimedia information has become the main medium for transmitting information. Authentication, retrieval, and recognition are extremely important applications in multimedia information processing. How to realize it quickly and accurately has attracted social attention and research. Speech signal is an important information carrier, how to achieve its fast authentication and ensure the security of data transmission has become a hot issue [23, 26, 43]. In recent years, with the introduction of BioHashing, 1) The key is difficult to forge Yi-bo Huang
huang [email protected] 1
College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou 730070, China
2
School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China
Multimedia Tools and Applications
or distribute. 2) Guessing the key is very difficult. 3) The key will not be lost or forgotten, and it is also difficult to copy or share [2], which makes the BioHashing technology significantly improved in the robustness and discrimination of the traditional hash, and the security is also significantly improved. this makes BioHashing widely applied to the field of identity authentication [6, 9, 12, 13, 15]. At present, the main speech feature extraction methods based on hash include doubletree complex wavelet Transform (DT-CWT) [24, 28], frequency band variance [39], linear pred
Data Loading...
