Studying the effect of modified spectral subtraction algorithm parameters and time window length in speech signals enhancement


Abstract in English

Speech denoising is a field of engineering that studies techniques used to recover the original signal from the noisy signal corrupted with different types of noise, such as broadband noise and narrowband noise, and other types present in environment, but the spectral subtraction technique consider the most prominent in this area . In this search we will discuss the parameters impact of the modified spectral subtraction algorithm and the time window length in the enhancement of speech that corrupted with broadband noise. We done the study and determine the ideal parameters values and the ideal window length with different values for the signal -to-noise ratio SNR for noisy speech and we discuss 18 case for each value. We done the simulation using MATLAB software and the results were compared based on improving the value of SNR for each case .

References used

Kaladharan,N.Speech Enhancement by Spectral Subtraction Method.International Journal of Computer Applications (0975 – 8887) Volume 96– No.13, June 2014
Verteletskaya,E;Simak,B.Noise Reduction Based on Modified Spectral Subtraction Method.IAENG International Journal of Computer Science,38:1, IJCS_38_1_10, February ,2011
Tiwari,N;Pandey,P.Speech Enhancement Using Noise Estimation Based on Dynamic Quantile Tracking for Hearing Impaired Listeners.Proc. 21th National Conference on Communications 2015 (NCC 2015), Mumbai, Feb. 27 - Mar. 1, 2015

Download