Abstract
A method for identifying the independent components of an alpha-stable random vector is proposed. The method is based on an estimate of the spectral measure for the charac- teristic function. Simulations with both synthetic and speech signals demonstrate that the proposed method can identi- fy independent components in the so-called over-complete case of more sources than mixtures.
Original language | English |
---|---|
Title of host publication | Proceedings of IEEE-EURASIP Workshop on Nonlinear Signal and Image Processing, NSIP2001. |
Publication date | 2001 |
Pages | 1-5 |
Publication status | Published - 2001 |