Application BP Neural Network in the Speaker Recognition Based on Chaos Particle Swarm Optimization Algorithm

Abstract:

According to the question that BP Neural Network has slow velocity of convergence and is apt to fall into the minimum value, chaos thought is adopted in the particle swarm optimization (PSO). For this, chaos particle swarm optimization algorithm, which improve the ability of getting rid of fractional extreme point in the PSO, is presented and applied to the BP network exercise so that the calculation accuracy and velocity of convergence of BP network are increased. The method of training the BP network for speaker recognition, the recognition rate and speed of training have been greatly improved, making the speaker recognition based on BP neural network to get better results.

• Periodical: Advanced Materials Research (Volumes 765-767)
• Pages: 2805-2808
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.765-767.2805
• Online since: September 2013
• Authors: Guo Wen Wang, Shi Xin Luo, Li He, Gang Yin
• Keywords: BP Neural Network (BPNN), Particle Swarm Optimization (PSO), Recognition Rate, Speech Features

References

[1] KSR Murty, B Yegnanarayana. Combining evidence from residual phase and MFCC features for speaker recognition. Signal Processing Letters, IEEE. Jan. 2006: 52-55.

DOI: 10.1109/lsp.2005.860538

[2] A Martin, D Charlet, L Mauuary. Robust speech/non-speech detection using LDA applied to MFCC. Acoustics, Speech, and Signal Processing, 2001: 237-240.

DOI: 10.1109/icassp.2001.940811

[3] J. Karhunen, J, Joutsensalo. Generalization of principal component analysis, optimization problems and neural networks [J] Neural networks. 1995. 549-562.

DOI: 10.1016/0893-6080(94)00098-7

[4] Zhao Jia Li; Luo Si Wei; Han Zhen. The improvements of BP neural network learning algorithm. Signal Processing Proceedings, 2000. WCCC-ICSP 2000: 1647-1649 vol. 3.

DOI: 10.1109/icosp.2000.893417

[5] SU Hua. The Application of Support Vector Machine to Low Strain Integrity Testing of Foundation Piles. Soil Engineering and Foundation, 2009. 2.

[6] Pingzhou Tang. The Research on BP Neural Network Model Based on Guaranteed Convergence Particle Swarm Optimization. Intelligent Information Technology Application, 2008. 20-22.

DOI: 10.1109/iita.2008.111

[7] Bilal Alatas, Erhan Akin, A. Bedri Ozer. Chaos embedded particle swarm optimization algorithms. Chaos, Solitons & Fractals. 2009(5)1715-1734.

DOI: 10.1016/j.chaos.2007.09.063

[8] Tao Xiang, Xiaofeng Liao, Kwok-wo Wong. An improved particle swarm optimization algorithm combined with piecewise linear chaotic map. Applied Mathematics and Computation. 2007(7) 1637-1645.

DOI: 10.1016/j.amc.2007.02.103

[9] Bo Liu, Ling Wang, Yi-Hui Jin, Fang Tang, De-Xian Huang. Improved particle swarm optimization combined with chaos. Chaos, Solitons & Fractals. 2005(5) 1261-1271.

DOI: 10.1016/j.chaos.2004.11.095

[10] Yi Da, Ge Xiurun. An improved PSO-based ANN with simulated annealing technique. Neurocomputing. 2005(11) 527-533.

DOI: 10.1016/j.neucom.2004.07.002

[11] Chi-Chung Cheung, The Multi-Phase Method in Fast Learning Algorithm, Proceeding of international join conference on neural networks, Atlanta Georgia, USA, 2009(6) 14-19.