Using Formant Characteristics of Russian Vowels and Consonants for User Authentication

Author:

Belova Ye. P.1ORCID

Affiliation:

1. Ufa University of Science and Technology (UUST)

Abstract

The article proposes a method for user authentication based on formant characteristics. A biometric image has been developed consisting of the formant characteristics of 46 sounds of the Russian language (6 vowels, 4 diphthongs and 36 consonants). An authentication system architecture based on formant characteristics and frequency of the leading formant of vowels and consonants is proposed. A Module for extracting the formant characteristics of vowels and consonants has been developed. A block diagram of the Module for extracting the formant characteristics of vowels and consonants and block diagrams of its submodules are presented. The Random Forest algorithm, k-nearest neighbors, logistic regression, multilayer perceptron and Support Vector Machine are combined into a cluster of algorithms. A block diagram of training and testing models based on a cluster of algorithms is given. Models were trained on the basis of algorithms clusters. The results of the experiment were obtained and their analysis was carried out.

Publisher

Siberian State University of Telecommunications and Informatics

Reference12 articles.

1. Oganesyan A. G. Effektivnyi algoritm vydeleniya formant iz spektra rechevogo signala [Efficient algorithm for extracting formants from the spectrum of a speech signal]. Vychislitel'naya tekhnika i informatika, Moscow, 2006, vol. LIX, no.1, pp. 177-183.

2. Sysoev O. V., Glauzdovskii V. V., Kurpatov V. L. Issledovanie vozmozhnosti primeneniya formantnykh kharakteristik v zadachakh biometricheskoi autentifikatsii [Study of the possibility of using formant characteristics in biometric authentication tasks] Sibirskii informatsionno-kommunikatsionnyi zhurnal, 2017, no. 1 (63), pp. 93-97.

3. Shokhin A. A., Sedel'nikov S. Yu. Metodika formantnogo analiza dlya biometricheskoi autentifikatsii pol'zovatelei [Methods of formant analysis for biometric user authentication] Informatika i vychislitel'naya tekhnika, 2018, no. 4, pp. 36-41.

4. Peterson G. E., Barney H. L. Control methods used in a study of the vowels. The Journal of the Acoustical Society of America, 1952, no. 24(2), pp.175-184.

5. Babosov E. G., Avdeev A. V., Zueva E. V. Issledovanie vozmozhnosti ispol'zovaniya for-mantnykh kharakteristik zvukov rechi dlya autentifikatsii pol'zovatelei [Study of the possibility of using the formant characteristics of speech sounds for user authentication] Mediko-biologicheskie i tekhnicheskie sistemy, 2015, no. 3 (79), pp. 172-178.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3