• Nov 09, 2021 News!Vol.13, No. 4 has been published with online version.   [Click]
  • Aug 07, 2021 News!Vol.13, No. 3 has been published with online version.   [Click]
  • Dec 24, 2021 News!Vol. 13, no. 1 & no. 2 has been indexed by INSPEC!   [Click]
General Information
    • ISSN: 1793-8236 (Online)
    • Abbreviated Title Int. J. Eng. Technol.
    • Frequency:  Quarterly 
    • DOI: 10.7763/IJET
    • Executive Editor: Ms.Yoyo Y. Zhou
    • Abstracting/ Indexing: Chemical Abstracts Services (CAS) EBSCO, Google Scholar, Ulrich Periodicals Directory, Crossref, ProQuest, Index CopernicusINSPECCNKI.
    • E-mail: ijet@vip.163.com
Prof. T. Hikmet Karakoc
Anadolu University, Faculty of Aeronautics and Astronautics, Turkey

IJET 2009 Vol.1(5): 439-447 ISSN: 1793-8236
DOI: 10.7763/IJET.2009.V1.82

Performance Evaluation of Different Thresholding Methods in Time Adaptive Wavelet Based Speech Enhancement

A. Sumithra M. G. and B. Thanushkodi K

Abstract—Speech quality and intelligibility might significantly deteriorate in the presence of background noise, especially when the speech signal is subject to subsequent processing. Speech enhancement algorithms have therefore attracted a great deal of interest in the past two decades. Wavelets provide a powerful tool for non-linear filtering of signals contaminated by noise and wavelet thresholding de-noising techniques provide a new way to reduce noise in signal. In this work speech enhancement is accomplished through the use of different thresholding on time adaptive discrete Daubechies wavelet transform co-efficients. However, the soft thresholding is best in reducing noise but worst in preserving edges, and hard thresholding is best in preserving edges but worst in de-noising. Motivated by finding a more general case that incorporates the soft and hard thresholding to achieve a compromise between the two methods, the trimmed thresholding method is proposed in this paper to enhance the speech from background noise. The performance of different thresholding methods are evaluated by enhancing the speech corrupted by various noises. Finally, the objective and subjective experimental results show that the proposed scheme with trimmed thresholding is superior in denoising as compared to hard and soft thresholding methods. It also indicates that the proposed method gives better mean square error (MSE) performance than other wavelet thresholding methods.

Index Terms—Speech enhancement, Time adaptive Daubechies wavelet transform, Time adaptation factor, Thresholding.

A. Sumithra M. G. is with the Department of Electronics and Communication Engineering, Bannari AmmanInstitute of Technology, Sathyamangalam, Tamil Nadu, India (phone:09865816671).
B. Thanushkodi K. is with Akshya College of Engineering and Technology, Coimbatore, Tamil Nadu. India. (phone: 09843394451)


Cite: A. Sumithra M G and Thanushkodi K, "Speech enhancement, Time adaptiveDaubechies wavelet transform, Time adaptation factor,Thresholding," International Journal of Engineering and Technology vol. 1, no. 5, pp. 439-447, 2009.

Copyright © 2008-2022. International Journal of Engineering and Technology. All rights reserved. 
E-mail: ijet@vip.163.com