Education, Science, Technology, Innovation and Life
Open Access
Sign In

Research on Speech Enhancement Algorithm Based on EMD in Noisy Environments

Download as PDF

DOI: 10.23977/isspj.2016.11004 | Downloads: 47 | Views: 6118


Cheng Huawei 1, Zhang Dexiang 2, Fang Fei 1, Lu Weiqing 1


1 School of Electronic and Electrical Engineering of Anhui Sanlian University, Hefei, 230601, China
2 School of Electrical Engineering and Automation, Anhui University, Hefei 230601, China

Corresponding Author

Zhang Dexiang


This paper presents a new technique for speech enhancement in a noisy environment based on the empirical mode decomposition (EMD) algorithm and spectral subtraction. With the EMD, the noise speech signals can be decomposed into a sum of the band-limited function called intrinsic mode functions (IMFs), which is a zero-mean AM-FM component. Then spectral subtraction of the IMF components with noise can be used to eliminate the effect of the noise for speech enhancement. Experimental results demonstrate the advantage of using the proposed simultaneous detection and estimation approach with the proposed algorithm, which facilitate suppression of transient noise with a controlled level of speech distortion.


Speech Enhancement, EMD, Spectral Subtraction, Noisy Environments.


Huawei, C. , Dexiang, Z. , Fei, F. and Weiqing, L. (2016) Research on Speech Enhancement Algorithm Based on EMD in Noisy Environments. Information Systems and Signal Processing Journal (2016) 1: 19-23.


[1] G. Tanyer, H. Ozer, IEEE Trans. Speech Audio Processing, Vol. 8 (2000), p. 478
[2] Y.ephfsim, D. Malah, IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 32(1984), p. 1109.
[3] N. E. Huang, Z. Shen and S. R. Long, Proceedings of the Royal Society London A, Vol. 454 (1998), p. 903
[4] S. Mallat,  IEEE Trans. Pattern Anal. Machine Intell. Vol. 11 (1989), p. 674.
[5] Ramos A L L, Holm S, Gudvangen S, et al.  International Journal of Electronics and Telecommunications, Vol. 59(2016), p. 93.

Downloads: 949
Visits: 81001

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.