Speech Recognition Algorithm Based on Empirical Mode Decomposition and RBF Neural Network

Abstract:

This paper presents a novel method of the speech recognition in combining the empirical mode decomposition with radical basis function neural network. Speech signals which pretreated are decomposed by empirical mode decomposition to get a set of intrinsic mode functions. It extracts mel frequency cepstrum coefficient from intrinsic mode function. Features parameters are made up of the coefficients. For BP Neural Network, RBF Neural Network has advantages on approximating ability and learning speed. So using RBF Neural Network as a recognition model is a good method. Experiments show that this new method has good robustness and adaptability. The speech recognition rate of this method reach ninety-one percents accurately under no noise environment. Speech signal recognition is feasible and effective in noisy environment.

• Periodical: Advanced Materials Research (Volume 831)
• Pages: 465-469
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.831.465
• Online since: December 2013
• Authors: Wei Wei Shi, Wei Hua Xiong*, Wei Chen
• Keywords: Empirical Mode Function, Mel Frequency Cepstrum Coefficient, Radical Basis Function Neural Network, Speech Recognition

References

[1] Junchang Zhang, Li Zhao: submitted to Journal of Computer Simulation Vol8(8) (2011), pp.397-400, in chinese.

[2] Haiyan Zhang, Jianfang Tang: submitted to Journal of Journal of Sichuan University of Science & Engineering(Natural Science Edition) Vol24(5) (2011) , pp.552-555, in chinese.

[3] Memer E, Goubran R and Mahmoud S: submitted to Journal of Speech Communication Vol36(4) (2002) , pp.219-246.

[4] Wu Zh, Huang N E: submitted to Journal of Proc. R. SOC. London(2004) , pp.1597-1611.

[5] Zhenjie Yao, Hai Huang and Xiangxian Chen: submitted to Journal of Zhejiang University (Engineering Science) Vol43(4) (2009) , pp.705-709, in chinese.

[6] Dexiang Zhang, Xiaopei Wu and Zhao Lv: submitted to Journal of Chinese Journal of Scientific Instrument Vol31(3) (2010) , pp.493-499, in chinese.

[7] Defeng Zhang: MATLAB Neural network application design(China Machine Press, China, 2009).

[8] Changhong Dong: MATLAB Neural Network and Application(National Defence Industry Press, China, 2007), in chinese.

[9] Yungao Li: submitted to Journal of Taiyuan University of Technology (2009), in chinese.

[10] Hua Yu, Lijing Yang and Qiyuan Li: submitted to Journal of Control Engineer of China Vol16 (2009) , pp.90-93, in chinese.