Speaker identification system using empirical mode decomposition and an artificial neural network

Research highlights? Develop a speaker identification system based on neural network. ? Presents a speaker identification system using empirical mode decomposition feature extraction. ? Signal feature extraction using empirical mode decomposition. This paper presents a speaker identification system using empirical mode decomposition (EMD) feature extraction method and artificial neural network in speaker identification. The EMD is an adaptive multi-resolution decomposition technique that appears to be suitable for non-linear, non-stationary data analysis. The EMD sifts the complex signal of time series without losing its original properties and then obtains some useful intrinsic mode function (IMF) components. Calculating the energy of each component can reduce the computation dimensions and enhance the performance of classification. The features were used as inputs to neural network classifiers for speaker identification. In the speaker identification, the back-propagation neural network (BPNN) and generalized regression neural network (GRNN) were applied to verify the performances and the training time in the proposed system. The experimental results indicated the GRNN can achieve better recognition rate performance with feature extraction using the EMD method than BPNN.

[1]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[2]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[3]  Engin Avci,et al.  Speech recognition using a wavelet packet adaptive network based fuzzy inference system , 2006, Expert Syst. Appl..

[4]  Cun-Jian Chen,et al.  Local variance projection log energy entropy features for illumination robust face recognition , 2008, 2008 International Symposium on Biometrics and Security Technologies.

[5]  Emine Ayaz,et al.  Feature extraction related to bearing damage in electric motors by wavelet analysis , 2003, J. Frankl. Inst..

[6]  Shung-Yung Lung.  Wavelet feature selection based neural networks with application to the text independent speaker identification , 2006, Pattern Recognit..

[7]  S. Liu,et al.  A practical guide to biometric security technology , 2001 .

[8]  Hikmet Kerem Cigizoglu,et al.  Generalized regression neural network in modelling river sediment yield , 2006, Adv. Eng. Softw..

[9]  Jien-Chen Chen,et al.  Continuous wavelet transform technique for fault signal diagnosis of internal combustion engines , 2006 .

[10]  Sharath Pankanti,et al.  Biometrics: The Future of Identification - Guest Editors' Introduction , 2000, Computer.

[11]  M. Portnoff.  Time-frequency representation of digital signals and systems based on short-time Fourier analysis , 1980 .

[12]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[13]  Jian-Da Wu,et al.  Driver identification based on voice signal using continuous wavelet transform and artificial neural network techniques , 2009, Expert Syst. Appl..

[14]  Toby Berger,et al.  Efficient text-independent speaker verification with structural Gaussian mixture models and neural network , 2003, IEEE Trans. Speech Audio Process..

[15]  K. Coughlin,et al.  11-Year solar cycle in the stratosphere extracted by the empirical mode decomposition method , 2004 .

[16]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[17]  Michael J. Corinthios.  A Fast Fourier Transform for High-Speed Signal Processing , 1971, IEEE Transactions on Computers.

[18]  Zhu Ruigeng,et al.  An engineering geology evaluation method based on an artificial neural network and its application , 1997 .