A Novel Approach of Speech Enhancement based on SBWT and MMSE Estimate of Spectral Amplitude
Mourad Talbi, Med Salim Bouhlel · 2020
In this paper, is proposed a novel approach of speech enhancement. It is based on Stationary Bionic Wavelet Transform (SBWT) and MMSE (Minimum Mean Square Error) Estimate of Spectral Amplitude. It consists at the first step in applying the SBWT to the noisy speech signal in order to obtain eight noisy Stationary Bionic Wavelet Coefficients. Each of them is denoised applying the denoising technique based on MMSE Estimate of Spectral Amplitude. Finally, the inverse of SBWT is applied to the denoised stationary bionic wavelet coefficients in order to obtain the enhanced speech signal. The performance of this approach is justified by the computation of the SNR (Signal to Noise Ratio), the Segmental SNR (SSNR) and the PESQ (Perceptual Evaluation of Speech Quality).