Speaker identification based on hybrid feature extraction techniques

Abualadas, Feras E. and M.Khedher, Akram M. Zeki and Al-Ani, Muzhir Shaban and Messikh, Az-Eddine (2019) Speaker identification based on hybrid feature extraction techniques. International Journal of Advanced Computer Science and Applications, 10 (3). pp. 322-327. ISSN 2158-107X E-ISSN 2156-5570

	PDF - Published Version Restricted to Repository staff only Download (456kB) | Request a copy
	PDF (SCOPUS) - Published Version Restricted to Repository staff only Download (165kB) | Request a copy
Preview	PDF (WOS) Download (108kB) | Preview

Abstract

One of the most exciting areas of signal processing is speech processing; speech contains many features or characteristics that can discriminate the identity of the person. The human voice is considered one of the important biometric characteristics that can be used for person identification. This work is concerned with studying the effect of appropriate extracted features from various levels of discrete wavelet transformation (DWT) and the concatenation of two techniques (discrete wavelet and curvelet transform) and study the effect of reducing the number of features by using principal component analysis (PCA) on speaker identification. Backpropagation (BP) neural network was also introduced as a classifier.

Item Type:	Article (Journal)
Additional Information:	6153/72390
Uncontrolled Keywords:	Speaker identification; biometrics; speaker verification; speaker recognition; text-independent; text-dependent
Subjects:	T Technology > T Technology (General)
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Information and Communication Technology Kulliyyah of Information and Communication Technology
Depositing User:	Akram M Zeki
Date Deposited:	29 May 2019 12:30
Last Modified:	01 Aug 2019 11:21
URI:	http://irep.iium.edu.my/id/eprint/72390

Actions (login required)

View Item