A wavelet-based forward BSS algorithm for acoustic noise reduction and speech enhancement. (April 2016)

• Record Type: Journal Article
• Authors: Ghribi, Khadidja; Djendi, Mohamed; Berkani, Daoued
• Is Part Of: Applied acoustics. Volume 105(2016)
• Page Start: 55
• Page End: 66
• Publication Date: 2016-04
• Subjects: Noise cancellation -- Discrete wavelet transform -- SAD -- Convolutive mixture -- Speech enhancement; Acoustical engineering -- Periodicals; Periodicals; 620.2
• DOI: 10.1016/j.apacoust.2015.11.011
• Languages: English
• ISSNs: 0003-682X

Abstract

Graphical abstract: Highlights: We propose a new wavelets-based adaptive filtering algorithm. The proposed algorithm has fast convergence speed even with long adaptive filters. This algorithm is efficient in Speech Enhancement and Acoustic Noise Reduction applications. The proposed algorithm is recommended for the speech enhancement applications. Abstract: In this paper, we address the problem of noise reduction and speech enhancement by adaptive filtering algorithm. Recently, the well known forward blind source separation (FBSS) structure has been largely studied and intensively used to reduce acoustic noise components and to enhance speech signal. The FBSS structure is often combined with adaptive algorithms to accelerate the adaptation of the cross-filters, and to improve noise suppression at the output. In this paper, we propose to use a wavelet transform decomposition in the FBSS structure by using a two-channel forward wavelet symmetric adaptive decorrelating (WFSAD) algorithm. The proposed WFSAD algorithm provides a better compromise between time and frequency resolution and improves robustness of the noise reduction process when compared with the classical two-channel forward symmetric adaptive decorrelating (FSAD) algorithm. Simulation results prove the efficiency of the proposed WFBSS algorithm in comparison with conventional ones in terms of several objective and subjective criteria.