## Abstract

We prove that mixtures of continuous constant modulus sources can be identified with probability 1 with a finite number of samples (under noise-free conditions). This strengthens earlier results which only considered an infinite number of samples. The proof is based on the linearization technique of the Analytical Constant Modulus Algorithm, together with a simple inductive argument. We then study the finite alphabet case. In this case we provide an upper bound on the probability of non-identifiability for finite sample of sources. We show that under practical assumptions, this upper bound is tighter than the currently known bound.

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

Title of host publication | 2002 IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAME 2002 |

Publisher | IEEE Computer Society |

Pages | 408-412 |

Number of pages | 5 |

ISBN (Electronic) | 0780375513 |

DOIs | |

State | Published - 2002 |

Externally published | Yes |

Event | IEEE Sensor Array and Multichannel Signal Processing Workshop, SAME 2002 - Rosslyn, United States Duration: 4 Aug 2002 → 6 Aug 2002 |

### Publication series

Name | Proceedings of the IEEE Sensor Array and Multichannel Signal Processing Workshop |
---|---|

Volume | 2002-January |

ISSN (Electronic) | 2151-870X |

### Conference

Conference | IEEE Sensor Array and Multichannel Signal Processing Workshop, SAME 2002 |
---|---|

Country/Territory | United States |

City | Rosslyn |

Period | 4/08/02 → 6/08/02 |

### Bibliographical note

Publisher Copyright:© 2002 IEEE.

## Keywords

- Blind source separation
- Chernoff bound
- Constant modulus signals
- Finite sample analysis
- Identifiability
- Large deviations
- PSK