An Improved Bi-Level Thresholding Based Uncertainty Evaluation for Speech Enhancement in Non-Stationary Noises

This paper proposes a new speech enhancement framework to improve the quality of speeches recorded under adverse acoustic environments based on the speech presence uncertainty. Since the uncertainty evaluation gives a more and clear discrimination about the speech and noise, this paper proposes a new uncertainty evaluation mechanism as a preprocessing mechanism to the noise suppression methods.  This mechanism relates with energies of a noisy speech signal and classifies the speech segments and noise segments more perfectly. In addition to the quality enhancement, this approach also reduces the unnecessary computational burden over the speech processing system. Extensive simulations are carried out over the speech signals with different types of non-stationary noises like babble noise, exhibition noise, restaurant noise and train station noises and the performance is measured with the performance metrics namely the Output SNR, AvgSegSNR, PESQ and COMP. The comparative analysis of proposed approach over the conventional approaches shows an outstanding performance in all environments.