The Research of Speech Recognition in Low SNR Based on GA-SVM

Abstract:

To improve recognizing rate and recognizing efficiency, the algorithm of double-threshold is adopted in the endpoint detection, Mel-frequency Spectral Coefficients is obtained as speech characteristic parameters, the SVM parameters, penalty factor and kernel function parameter, were optimized with genetic algorithm, then, an speech recognition model was established with GA-SVM method. The improved algorithm was simulated by matlab, the experiment shows that this algorithm can achieved good results in isolated word speech recognition.

• Periodical: Applied Mechanics and Materials (Volume 590)
• Pages: 727-731
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.590.727
• Online since: June 2014
• Authors: Yong Qi Wang, Hui Zhang
• Keywords: Genetic Algorithm (GA), In Low SNR, Speech Recognition, Support Vector Machine (SVM)

References

[1] Wu Zhixiang, Wang Shunli, Li Zhanfeng, et. al, Study on speech recognition system based on short-time average amplitude and HMM, " Control and Instruments in Chemical Iudustry, vol. 40 , 2013, p.779–782.

[2] CHANDRASEKARAN P, BODRUZZAMAN M, YUEN G, ET AL. Speech recognition using pulse coupled neural network. Proceedings of the Thirtieth Southeastern Symposium on System Theory, 1998: 515-519.

DOI: 10.1109/ssst.1998.660127

[3] Zhang Hesong, Bo Zhao, Zhong Xiangzhu, et. al. Research on traffic number recognition based on neural network and invariant moments. International Conference on Machine Learning and Cybernetics, 2007, pp: 389-393.

DOI: 10.1109/icmlc.2007.4370175

[4] Zhang Xuegong, Introduction to statistical learning theory and support vector machines, acta automatica sinica, 2000, 26(1), pp: 32-42.

[5] Zhou Ping, Li Xiaopan, Li Jie, Jing Xinxing, Speech emotion recognition based on mixed mfcc characteristic parameter, Computer measurement and control, vol. 21, 2013(7), pp: 1966-(1968).

[6] Si Yunyun, Xu Daolian, Zhou Zhuoran, Research of speech recognition based on genetic algorithm and wavelet neural network, Microcomputer and Its Applications, 2011, 30(16), p.57–59.