Abstract | ||
---|---|---|
In this paper, we propose an algorithm for real-time signal processing of convolutive blind source separation (CBSS), which is a promising technique for acoustic source separation in a realistic environment, e.g., room/office or vehicle. First, we apply an overlap-and-save (sliding windows with overlapping) strategy that is most suitable for real-time CBSS processing; this approach can also aid in solving the permutation problem. Second, we consider the issue of separating sources in the frequency domain. We introduce a modified correlation matrix of observed signals and perform CBSS by diagonalization of the matrix. Third, we propose a method that can diagonalize the modified correlation matrix by solving a so-called normal equation for CBSS. One desirable feature of our proposed algorithm is that it can solve the CBSS problem explicitly, rather than stochastically, as is done with conventional algorithms. Moreover, a real-time separation of the convolutive mixtures of sources can be performed. We designed several simulations to compare the effectiveness of our algorithm with its counterpart, the gradient-based approach. Our proposed algorithm displayed superior convergence rates relative to the gradient-based approach. We also designed an experiment for testing the efficacy of the algorithm in real-time CBSS processing aimed at separating acoustic sources in realistic environments. Within this experimental context, the convergence time of our algorithms was substantially faster than that of the gradient-based algorithms. Moreover, our algorithm converges to a much lower value of the cost function than that of the gradient-based algorithm, ensuring better performance. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/TCSI.2005.854295 | IEEE Trans. on Circuits and Systems |
Keywords | Field | DocType |
gradient-based approach,ex- plicit algorithm,overlap-and-save strategy,real-time cbss processing,permutation problem,matrix algebra,convolutive blind source separation,convolutive blind source separation (cbss),index terms—convolutive blind source separation cbss,acoustic correlation,blind source separation,acoustic source separation,modified correlation matrix,real-time processing.,matrix diagonalization,real-time signal processing,acoustic convolution,explicit algorithm,real-time processing,real-time systems,real time,sliding window,frequency domain,signal processing,convergence rate,cost function,real time processing,near real time,real time systems,correlation matrix | Convergence (routing),Frequency domain,Signal processing,Mathematical optimization,Matrix (mathematics),Control theory,Algorithm,Covariance matrix,Blind signal separation,Linear least squares,Mathematics,Source separation | Journal |
Volume | Issue | ISSN |
53 | 1 | 1549-8328 |
Citations | PageRank | References |
5 | 0.54 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuxue Ding | 1 | 235 | 33.84 |
Jie Huang | 2 | 33 | 4.47 |
Daming Wei | 3 | 215 | 44.97 |
Andrzej Cichocki | 4 | 5228 | 508.42 |