Arabic word dependent speaker identification system using artificial neural network

被引:0
|
作者
Al-Qaisi, Aws [1 ]
机构
[1] Communication Engineering Department, Faculty of Engineering Technology, Al-Balqa Applied University, Jordan
关键词
Loudspeakers - Speech recognition - Radial basis function networks - Signal to noise ratio;
D O I
10.46300/9106.2020.14.41
中图分类号
学科分类号
摘要
The security of systems is a vital issue for any society. Hence, the need for authentication mechanisms that protect the confidentiality of users is important. This paper proposes a speech based security system that is able to identify Arabic speakers by using an Arabic word)اركش) which means Thank you. The pre-processing steps are performed on the speech signals to enhance the signal to noise ratio. Features of speakers are obtained as Mel-Frequency Cepstral Coefficients (MFCC). Moreover, feature selection (FS) and radial basis function neural network (RBFNN) are implemented to classify and identify speakers. The proposed security system gives a 97.5% accuracy rate in its user identification process. © 2020, North Atlantic University Union. All rights reserved.
引用
收藏
页码:290 / 295
相关论文
共 50 条
  • [1] A Word-Dependent Automatic Arabic Speaker Identification System
    Al-Dahri, Suliman S.
    Al-Jassar, Youssaf H.
    Alotaibi, Yousef A.
    Alsulaiman, Mansour M.
    Abdullah-Al-Mamun, Khondaker
    [J]. ISSPIT: 8TH IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, 2008, : 198 - 202
  • [2] Text Dependent Speaker Identification and Speech Recognition Using Artificial Neural Network
    Swamy, Suma
    Shalini, T.
    Nagabhushan, Sindhu P.
    Nawaz, Sumaiah
    Ramakrishnan, K. V.
    [J]. GLOBAL TRENDS IN COMPUTING AND COMMUNICATION SYSTEMS, PT 1, 2012, 269 : 160 - +
  • [3] Speaker identification system using empirical mode decomposition and an artificial neural network
    Wu, Jian-Da
    Tsai, Yi-Jang
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (05) : 6112 - 6117
  • [4] A real time speaker identification using artificial neural network
    Hossain, Md. Murad
    Ahmed, Boshir
    Asrafi, Mahrnuda
    [J]. PROCEEDINGS OF 10TH INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION TECHNOLOGY (ICCIT 2007), 2007, : 325 - 329
  • [5] Speaker Identification System based on PLP Coefficients and Artificial Neural Network
    Chelali, Fatma Zohra
    Djeradi, Amar
    Djeradi, Rachida
    [J]. WORLD CONGRESS ON ENGINEERING, WCE 2011, VOL II, 2011, : 1641 - 1646
  • [6] System Identification Using Artificial Neural Network
    Wilfred, K. J. Nidhil
    Sreeraj, S.
    Vijay, B.
    Bagyaveereswaran, V.
    [J]. 2015 INTERNATIONAL CONFERENCED ON CIRCUITS, POWER AND COMPUTING TECHNOLOGIES (ICCPCT-2015), 2015,
  • [7] Speaker Identification and Spoken word Recognition In Noisy Background using Artificial Neural Networks
    Shafee, Shaik
    Anuradha, Dr. B.
    [J]. 2016 INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONICS, AND OPTIMIZATION TECHNIQUES (ICEEOT), 2016, : 912 - 917
  • [8] Speaker Identification System Using Wavelet Transform and Neural Network
    Daqrouq, K.
    Abu Hilal, T.
    Sherif, M.
    El-Hajar, S.
    Al-Qawasmi, A.
    [J]. 2009 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTATIONAL TOOLS FOR ENGINEERING APPLICATIONS, 2009, : 560 - +
  • [9] A speaker identification system using a model of artificial neural networks for an elevator application
    Adami, AG
    Barone, DAC
    [J]. INFORMATION SCIENCES, 2001, 138 (1-4) : 1 - 5
  • [10] Speaker Recognition and Verification Using Artificial Neural Network
    Chauhan, Neha
    Chandra, Mahesh
    [J]. 2017 2ND IEEE INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, SIGNAL PROCESSING AND NETWORKING (WISPNET), 2017, : 1147 - 1149