Applied-Information Technology with Speech Enhancement Based on EMD and MF

Abstract:

Aiming at traditional methods cannot get good performance in noisy environments, an improved method for speech enhancement based on Empirical Mode Decomposition (EMD) and Morphology Filtering (MF) was proposed. The method firstly uses EMD to obtain Intrinsic Mode Function (IMF) and for hard threshold processing, then selects appropriate structuring element to construct MF for filtering processing in remaining IMFs. Finally, speech enhancement signal is reconstructed for each IMFs. Experimental results show that the proposed method for speech enhancement has better de-noising effect by comparing time-domain waveform and spectrogram. Moreover, the quality of reconstructed speech enhancement signal has been significantly improved.

• Periodical: Advanced Materials Research (Volume 1046)
• Pages: 384-387
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1046.384
• Online since: October 2014
• Authors: Jin Li*, Kun Shen
• Keywords: Empirical Mode Decomposition (EMD), Morphology Filtering (MF), Speech Enhancement

References

[1] M. Rainer: IEEE Trans on Speech and Audio Processing Vol. 13 (2005), p.845.

[2] Y. Li, H. J. Cui, and K. Tang: Journal of Tsing hua University Vol. 46 (2006), p.1685 (In Chinese).

[3] Y. Ghanbari and M. Karami: Speech Communication Vol. 48 (2006), p.927.

[4] Y. Ephraim and H. L. Van Trees: IEEE Trans on Speech and Audio Processing Vol. 3 (1995), p.251.

[5] N. E. Huang, Z. Shen, and S. R. Long: Proc. R. Soc. Lond. A Vol. 454 (1998), p.903.

[6] J. Li, F. Liu, and H. Y. Xu: Lecture Notes in Electrical Engineering Vol. 206 (2013), p.173.

[7] P. Maragos and R. W. Schafer: IEEE Trans on Acoustics Speech and Signal Processing Vol. 35 (1987), p.1153.

[8] J. Li, J. T. Tang, X. Xiao: Noise and Vibration Worldwide Vol. 42 (2011), p.65.

[9] G. Y. Wang, X. Q. Zhao, and X. Wang: Computer Engineering and Applications Vol. 42 (2006), p.53 (In Chinese).