Speech Enhancement using DUET & Weiner Filter Technique

Aiswarya Venugopal, ASIET; Anjana M R ,ASIET; Ashna Hasif ,ASIET; Delna varghese ,ASIET; Prajeesh P A ,ASIET

Weiner Filter, DUET Blind Source Separation, Anechoic Mixtures and Matlab

Speech enhancement in degenerate mixtures is a challenging task for the signal processing engineers. Degenerate Unmixing Estimation Technique (DUET) is a commonly used algorithm in speech signal separation. This approach of DUET can be used in auditory training for individuals with hearing loss use their residual hearing maximally and can be implemented in home studio for music recording. The method is valid when sources are W-disjoint orthogonal, that is, when the supports of the windowed Fourier transform of the signals in the mixture are disjoint. For anechoic mixtures of attenuated and delayed sources, the method allows one to estimate the mixing parameters by clustering relative attenuation-delay pairs extracted from the ratios of the time–frequency representations of the mixtures. The estimates of the mixing parameters are then used to partition the time–frequency representation of one mixture to recover the original sources. The technique is valid even in the case when the number of sources is larger than the number of mixtures. The algorithm is coded and implemented using matlab software. The wiener filter is used to enhance the desired speech signal from the original signal in which the noises are present. Weiner filter minimizes the mean square error between the estimated random process and the desired process.
    [1] Abrar Hussain, Kalaivani Chellappan and Siti Zamratol M,” Speech Enhancement using Degenerate Unmixing Estimation Technique and Adaptive Noise Cancellation Technique as a Post Signal Processing,” IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES), 978-1-4673-7791-1/16/$31.00 ©2016 IEEE. [2] Scott Rickard, “The DUET Blind Source Separation Algorithm”, S. Makino et al. (eds.), Blind Speech Separation, 217–241. © 2007 Springer. [3] Niall Hurley,Naomi Harte,Conor Fearon and Scott Rickard,” Blind Source Separation of Speech in Hardware”, 0-7803-9333-3/05/$20.00 ©2005 IEEE. [4] Zhang Wenlu and Peng Hua”, Modified Wiener Filtering Speech Enhancement Algorithm with Phase Spectrum Compensation”, 9th IEEE International Conference on Communication Software and Networks, 978-1-5090-3822-0/17/$31.00 ©2017 IEEE.
Paper ID: GRDCF013074
Published in: Conference : National Conference on Emerging Research Trend in Electrical and Electronics Engineering (ERTE’19)
Page(s): 328 - 331