Loading...
Please wait, while we are loading the content...
Similar Documents
Convolutive blind signal separation in acoustics by joint approximate diagonalization of spatiotemporal correlation matrices (2004).
| Content Provider | CiteSeerX |
|---|---|
| Author | Joho, Marcel |
| Abstract | We present an efficient algorithm for the blind signal separation (BSS) problem with convolutive signal mixtures, as it usually appears in Acoustics, e.g., in the cocktail party problem. Since acoustical signals are typically non-stationary and non-white, we make use of these two statistical properties in the formulation of the blind cost function. In order to achieve true signal separation, the algorithm aims at finding a single polynomial matrix, the convolutive separation matrix, that jointly diagonalizes a set of measured spatiotemporal correlation matrices. Minimizing the cost function turns out to be mathematically equivalent to a convolutive joint approximate diagonalization problem (CJAD). |
| File Format | |
| Publisher Date | 2004-01-01 |
| Access Restriction | Open |
| Subject Keyword | Joint Approximate Diagonalization Convolutive Blind Signal Separation Spatiotemporal Correlation Matrix Single Polynomial Matrix Convolutive Joint Approximate Diagonalization Problem Cocktail Party Problem Efficient Algorithm True Signal Separation Acoustical Signal Convolutive Signal Mixture Convolutive Separation Matrix Blind Signal Separation Cost Function Blind Cost Function Statistical Property Measured Spatiotemporal Correlation Matrix |
| Content Type | Text |
