Sound enhancement based on indirect estimation of laplacian factor
Xuemin Zhang, Linna Li, Hang Jiang · 2010
A novel approach for Laplacian factor estimation is presented based on the property of generalized Gaussian distribution model and its shape parameter. The proposed approach can indirectly obtain the estimation of the Laplacian factor using its relation with the variance of pure sound components under the Laplacian distribution presumption, thus the method is simple. The algorithm can eliminate the influence by noise components and give an accurate estimation for the Laplacian factor. What's more, it can fast track the changes of sound components with only one frame delay. Experiment results demonstrate the novel approach has better performance of sound enhancement in different noises background.