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

Alauldeen S. Yaseen; Alexey N. Pavlov; Alexander E. Hramov

doi:10.1117/12.2211384

Translator Disclaimer

17 March 2016 Speech signal denoising with wavelet-transforms and the mean opinion score characterizing the filtering quality

Alauldeen S. Yaseen; Alexey N. Pavlov; Alexander E. Hramov

Author Affiliations +

Proceedings Volume 9707, Dynamics and Fluctuations in Biomedical Photonics XIII; 970719 (2016) https://doi.org/10.1117/12.2211384
Event: SPIE BiOS, 2016, San Francisco, California, United States

Abstract

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 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 (1DDWT). 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.

Citation Download Citation

Alauldeen S. Yaseen, Alexey N. Pavlov, and Alexander E. Hramov "Speech signal denoising with wavelet-transforms and the mean opinion score characterizing the filtering quality", Proc. SPIE 9707, Dynamics and Fluctuations in Biomedical Photonics XIII, 970719 (17 March 2016); https://doi.org/10.1117/12.2211384

ACCESS THE FULL ARTICLE