Speech signal denoising with wavelet-transforms and the mean opinion score characterizing the filtering quality

摘要

Speech signal processing is widely used to reduce noise impact in acquired data. During the last decades, wavelet-based filtering techniques are often applied in communication systems due to their advantages in signal denoising as compared with the Fourier-based methods. In this study we consider applications of a 1-D double density complex wavelet transform (1D-DDCWT) and compare the results with the standard 1-D discrete wavelet-transform (1D-DWT). The performances of the considered techniques are compared using the mean opinion score (MOS) being the primary metric for the quality of the processed signals. A two-dimensional extension of this approach can be used for effective image denoising.