Technique of voice recognition based on neural networks
Abstract
The problem of voice recognition for use in access control systems was considered. The technique of quick print announcer voice without loss of data characterizing the vote was offered. It proposed to use a Kohonen self-organizing map to identify the speaker, characterized by neuronal release of maximum activity, which reduced the recognition time by 30-80 % compared with existing solutions.
About the Authors
P. A. Menshakou
Gomel State Technical University named after P.O. Sukhoi
Belarus
Belarus
I. A. Murashko
Gomel State Technical University named after P.O. Sukhoi
Belarus
Belarus
References
1. Adeyemo Z.K, Oyeyemi O.J., Akanbi I.A. Development of Hybrid Radio Frequency Identification and Biometric Security Attendance System // Int. J. of Applied Science and Technology. 2014. Vol. 4, № 5. P. 190-197.
2. Biometrics, Computer Security Systems and Artificial Intelligence Applications / Ed. K. Saeed, J. Pejas, R. Mosdorf. Springer, 2006. 345 p.
3. You Y. Audio Coding: Theory and Applications. New York: Springer, 2010. 349 p.
4. Herbig T., Gerl F., Minker W. Self-Learning Speaker Identification: A System for Enhanced Speech Recognition. Berlin: Springer, 2011. 172 p.
5. Al-Shayea Q., Al-Ani M. Speaker Identification: A Novel Fusion Samples Approach // Int. J. of Computer Science and Information Security (IJCSIS). 2016. Vol. 14, № 7. P. 423-427.
6. Kohonen T. Self-Organizing Maps. Berlin: Springer, 1997. 425 p.
7. Bosi M., Goldberg R.E. Introduction to digital audio coding and standards. Springer, 2010. 434 p.
8. Menshakou P.A., Murashko I.A. Voice User Identification in Access Control Systems // Proc. Int. Conf. Open Semantic Technologies for Intelligent Systems (OSTIS-2017). Minsk: BSUIR, 2017. P. 175-178.
9. Petrovsky A., Azarov E. Instantaneous harmonic analysis: techniques and applications to speech signal processing // Speech and computer, Lecture notes in computer science. 2014. Vol. 8773. P. 24-33.
10. Alejandro C. Analysis of Kohonen’s Neural Network with application to speech recognition // Mexican International Conference on Artificial Intelligence. Mexico: Guanajuato, 2009. P. 8.
11. Data Mining Algorithms In R/Clustering/Self-Organizing Maps (SOM) [Electronic resource]. - Access mode: https://en.wikibooks.org/wiki/Data_Mining_Algorithms_In_R/Clustering/Self-Organizing_Maps (SOM). - Date of access: 15.02.2017.
12. Koikkalainen P., Oja E. Self-Organizing hierarchical feature maps // Proc. Int. Joint Conference on Neural Networks. Vol. II. San Diego, 1990. P. 279-284.
Review
For citations:
Menshakou P.A., Murashko I.A. Technique of voice recognition based on neural networks. Doklady BGUIR. 2017;(4):12-18. (In Russ.)
Views: 451
Email this article 