Speech Recognition Based on BP Network with Improved Learning Algorithm in Application on Industrial Robots

Abstract:

A three layer feed-forward neural network is developed for speech recognition for industrial robots. The signal is made up by four kinds of command sound. Based on the steepest descent method, the BP network is trained by an improved learning algorithm in which momentum factor and learning rate adjustment is adopted. The simulation results indicates that the error in classification small also with high recognition correct in terms of a percentage.

• Periodical: Advanced Materials Research (Volumes 753-755)
• Pages: 2050-2053
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.753-755.2050
• Online since: August 2013
• Authors: Feng Cui, Chun Yu Xiong, Feng He Qi, Chuan Ying Wang
• Keywords: BP Network, Industrial Robot, MOBP, Speech Recognition

References

[1] G. Z. Zhang, and X. X. Wang. Wu: J. Microelectronics and computer, Vol. 22 (2005), p.43.

[2] Ying He, Baohua Jin, Qiongshuai Lv. International Symposium on Computer Science and Society, Vol. 10 (2011), pp.79-82.

[3] W. Li and L. Q. Chen: J. Computer Engineering, Vol. 37 (2011), pp.187-190.

[4] Vladimir Nedeljkovic: J. IEEE Trans on Neural Networks, Vol. 4 (1993), p: 650-660.

[5] Adnan Khashman: J. IEEE Trans on Neural Networks, Vol. 19 (2008), p: 1896-(2000).

[6] Antoniya Georgieva and Ivan Jordanov: J. IEEE Trans on Neural Networks, Vol. 20 (2009), p: 675-684.

[7] Y. J. Hou and T. Li: J. Journal of Detection & Control, Vol. 30 (2008), pp.53-57.