Identification and authentication of user voice using DNN features and i-vector

Kydyrbekova Aizat,Akhmediyarova Ainur,Bagashar Zhumazhanov,Othman Mohamed,Mamyrbayev Orken,Duc Pham

doi:10.1080/23311916.2020.1751557

Abstract

Currently, computerized systems, such as language learning, telephone advertising, criminal cases, computerized health care and education systems are rapidly spreading and creating an urgent need for improved productivity. Speech recordings are a rich source of personal, confidential data that can be used to support a wide variety of applications, from health profiling to biometric recognition. Therefore, it is important that the speech recordings are properly protected, so that they cannot be misused. The leakage of encrypted biometric information is irreversible and biometric links are renewable. The article proposes a block diagram of the identification of the users of the systems by individual voice characteristics, based on the joint use of the Deep Neural Network (DNN) method and i -vector in the model of the elementary speech units, distinguished by increased security from various types of attacks on the biometric identification system, which allowed identifying the users with probability of first and second errors genus 0.025 and 0.005. The analysis of the vulnerability of the modules of the biometric voice identification system was performed and a structural scheme of the voice identification system of the user identification by voice with enhanced the protection against attacks was proposed. The use of elementary speech units in the developed identification systems makes it possible to improve computational indicators, reduce subjective decisions in biometric systems, and increase the security against attacks on the voice biometric identification systems.

Highlights

Automatic speech recognition is one of the active research topics that is trying to teach an independent machine ability to recognize and process the human speech
Developing a reliable speech identification and authentication system requires a set of reliable methods that play a pivotal role for the successful speech recognition, for example, effective feature extraction methods for capturing the speech variability and the speaker, acoustic modeling techniques, pronunciation modeling methods and various benchmark tests
Speech recognition was previously studied in the literature, as in (Juang & Rabiner, 2005; Mangu et al, 2000; Varga & Steeneken, 1993; Wu et al, 1998), and recently the main research efforts have been focused on improving the speech recognition systems using new methods and ideas, as in (Chan et al, 2016; Gahremani et al, 2014; Gemmeke et al, 2011; Kundu et al, 2016; Yao et al, 2012)

Summary

Introduction

Automatic speech recognition is one of the active research topics that is trying to teach an independent machine ability to recognize and process the human speech. Call management, security identification, client request processing and computer dictation. There are many factors that affect the reliability of any speech identification and authentication system, for example, speech spectral density, speech segments, context-sensitive, stress and pronunciation. Developing a reliable speech identification and authentication system requires a set of reliable methods that play a pivotal role for the successful speech recognition, for example, effective feature extraction methods for capturing the speech variability and the speaker, acoustic modeling techniques, pronunciation modeling methods and various benchmark tests. Speech recognition was previously studied in the literature, as in (Juang & Rabiner, 2005; Mangu et al, 2000; Varga & Steeneken, 1993; Wu et al, 1998), and recently the main research efforts have been focused on improving the speech recognition systems using new methods and ideas, as in (Chan et al, 2016; Gahremani et al, 2014; Gemmeke et al, 2011; Kundu et al, 2016; Yao et al, 2012)

Objectives

Results

Conclusion