Adaptive speech enhancement based on wavelet in high noise environment

An adaptive speech enhancement method in high noise environment is proposed in this paper. The whole algorithm is based on the wavelet transform and the improved Stein´s unbiased estimate of risk (SURE). This work improves the basic wavelet shrinkage method from the shrinkage function and enhancement algorithm. First, the detection algorithm is introduced to estimate the noise feature and improve the speech intelligibility. Next, we present a simple shrinkage function that is continuous soft and more stable than the hard type. Finally, we employ least mean squares (LMS) to estimate the shrinkage threshold, which can adaptively track the changes of the system in real time and continually seek the optimum in some statistical senses. These modifications enable the system to handle colored and nonstationary noises. To evaluate the system performance, we employed plentiful speech data that are obtained under practical environment. Subjective and objective evaluations show that the proposed system improves the performance and speech intelligibility in noisy environment.