RT Journal Article
A1 Noor Almaadeed
AD Department of Computer Engineering, Brunel University, Kingston Lane, Uxbridge, Middlesex UB8 3PH, UK
AD Department of Computer Science and Engineering, College of Engineering, Qatar University, Doha, Qatar
A1 Amar Aggoun
AD Department of Computer Science and Technology, University of Bedfordshire, University Square, Luton, LU1, 3JU, UK
A1 Abbes Amira
AD Department of Computer Science and Engineering, College of Engineering, Qatar University, Doha, Qatar
AD Department of Engineering and Computer Science, University of the West of Scotland, Paisley, UK

PB iet
T1 Speaker identification using multimodal neural networks and wavelet analysis
JN IET Biometrics
VO 4
IS 1
SP 18
OP 28
AB The rapid momentum of the technology progress in the recent years has led to a tremendous rise in the use of biometric authentication systems. The objective of this research is to investigate the problem of identifying a speaker from its voice regardless of the content. In this study, the authors designed and implemented a novel text-independent multimodal speaker identification system based on wavelet analysis and neural networks. Wavelet analysis comprises discrete wavelet transform, wavelet packet transform, wavelet sub-band coding and Mel-frequency cepstral coefficients (MFCCs). The learning module comprises general regressive, probabilistic and radial basis function neural networks, forming decisions through a majority voting scheme. The system was found to be competitive and it improved the identification rate by 15% as compared with the classical MFCC. In addition, it reduced the identification time by 40% as compared with the back-propagation neural network, Gaussian mixture model and principal component analysis. Performance tests conducted using the GRID database corpora have shown that this approach has faster identification time and greater accuracy compared with traditional approaches, and it is applicable to real-time, text-independent speaker identification systems.
K1 multimodal neural networks
K1 Gaussian mixture model
K1 discrete wavelet transform
K1 probabilistic neural networks
K1 MFCC
K1 learning module
K1 back-propagation neural network
K1 text-independent multimodal speaker identification system
K1 GRID database corpora
K1 principal component analysis
K1 majority voting scheme
K1 wavelet subband coding
K1 general regressive neural networks
K1 wavelet analysis
K1 biometric authentication systems
K1 radial basis function neural networks
K1 Mel-frequency cepstral coefficients
K1 wavelet packet transform
DO https://doi.org/10.1049/iet-bmt.2014.0011
UL https://digital-library.theiet.org/;jsessionid=n380kfeslm7c.x-iet-live-01content/journals/10.1049/iet-bmt.2014.0011
LA English
SN 2047-4938
YR 2015
OL EN