© 2014. S. China Venkateswarlu, A. Subba Rami Reddy & K. Satya Prasad. This is a research/review paper, distributed under the
terms of the Creative Commons Attribution-Noncommercial 3.0 Unported License http://creativecommons.org/licenses/by-
nc/3.0/), permitting all non commercial use, distribution, and reproduction in any medium, provided the original work is properly
cited.
Global Journal of Researches in Engineering: F
Electrical and Electronics Engineering
Volume 14 Issue 6 Version 1.0 Year 2014
Type: Double Blind Peer Reviewed International Research Journal
Publisher: Global Journals Inc. (USA)
Online ISSN: 2249-4596 & Print ISSN: 0975-5861
Speech Enhancement using Boll’s Spectral Subtraction
Method based on Gaussian Window
By S. China Venkateswarlu, A. Subba Rami Reddy & K. Satya Prasad
Jyothishmathi Institute of Technology & Science, India
Abstract- This paper investigates the effect of Gaussian window frequency response Side lobe
Attenuation on the improvement of Speech quality in terms of six objective quality measures. In Speech
Enhancement process, signal corrupted by noise is segmented into frames and each segment is
Windowed using Gaussian window with variation in the side lobe attenuation parameter “α”. The
Windowed Speech segments are applied to the Boll’s Spectral Subtraction Speech Enhancement
algorithm and the Enhanced Speech signal is reconstructed in its time domain. The focus is to investigate
the effect of Gaussian window frequency response side lobe level on the Boll’s Spectral Subtraction
Speech enhancement. For various side lobe attenuations of the Gaussian window frequency response,
speech quality objective measures have been computed. From this study, it is observed that the Side
lobe Attenuation parameter “α” plays an important role on the Speech enhancement process in terms of
six objective quality measures. The results are compared with the measures of Hamming window and an
optimum side lobe attenuation parameter value for the Gaussian window is proposed for better speech
quality.
Keywords: boll’s spectral subtraction, dft, gaussian window, objective measures, speech
enhancement, side lobe attenuation.
GJRE-F Classification : FOR Code: 170204
SpeechEnhancementusingBollsSpectralSubtractionMethodbasedonGaussianWindow
Strictly as per the compliance and regulations of :