Blind Separation of Anechoic Under-determined Speech Mixtures using Multiple Sensors

TitleBlind Separation of Anechoic Under-determined Speech Mixtures using Multiple Sensors
Publication TypeConference Paper
Year of Publication2006
AuthorsSaab, R., O. Yilmaz, M. J. McKeown, and R. Abugharbieh
Conference NameSignal Processing and Information Technology, 2006 IEEE International Symposium on
Pagination642 -646
Date Publishedaug.
Keywordsanechoic under-determined speech mixtures, arrival delays, blind source separation, BSS, Fourier transforms, multiple sensors, sensor fusion, short time Fourier transform, speech processing, speech signals
Abstract

This paper presents a novel technique for blind source separation (BSS) of anechoic speech mixtures in the underdetermined case. A demising algorithm that exploits the sparsity of the short time Fourier transform (STFT) of speech signals is proposed. The algorithm merges constrained optimization with ideas based on the degenerate unmixing estimation technique (DUET) (O. Yilmaz and S. Rickard, 2004). Thus, the novelty in the proposed approach is twofold. First, the algorithm utilizes all available mixtures in the anechoic scenario, where both attenuations and arrival delays between sensors are considered. Second, it is demonstrated that lq minimization with q lt; 1 outperforms the standard choice of q = 1. Experimental results on both synthetic and real mixtures indicate significant performance gains over other BSS algorithms reported in the literature

URLhttp://dx.doi.org/10.1109/ISSPIT.2006.270879
DOI10.1109/ISSPIT.2006.270879

a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949
Email:

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2020 The University of British Columbia