## Abstract

Blind Source Separation (BSS) is the problem of reconstructing unobserved, statistically independent source signals from observed linear combinations thereof. An emerging tool for BSS is the second generalized characteristic function (SGCF), as demonstrated, e.g., by the CHaracetristic-function Enabled Source Separation (CHESS) algorithm (Yeredor, 2000). CHESS achieves separation by applying approximate joint diagonalization to a set of estimated second derivative matrices (Hessians) of the SGCF at pre-selected "processing points". An optimization scheme for the CHESS algorithm, based on solving an optimally weighted least-squares (LS) problem, is proposed in this paper. First, it is shown that the approximate joint diagonal- ization of the Hessians can be formulated as a non-linear least-squares model. Then, a scheme for a consistent estimator of the optimal weight matrix is proposed. Next, an iterative algorithm for solving the WLS scheme is presented and demonstrated in simulation.

Original language | English |
---|---|

Pages | 404-407 |

Number of pages | 4 |

State | Published - 2004 |

Event | 2004 23rd IEEE Convention of Electrical and Electronics Engineers in Israel, Proceedings - Tel-Aviv, Israel Duration: 6 Sep 2004 → 7 Sep 2004 |

### Conference

Conference | 2004 23rd IEEE Convention of Electrical and Electronics Engineers in Israel, Proceedings |
---|---|

Country/Territory | Israel |

City | Tel-Aviv |

Period | 6/09/04 → 7/09/04 |

## Keywords

- (Weight adjusted) CHESS
- Blind source separation
- Joint diagonalization
- Weighted least squares