Blind separation of temporally correlated noncircular sources using complex matrix joint diagonalization

作者：

Highlights：

• Widely linear filter model is used to represent temporally correlated source signal.

• A new blind source separation algorithm is proposed combining widely linear filter model identification with joint matrix diagonalization.

• A special joint matrix diagonalization algorithm is proposed to adapt to the proposed blind source separation algorithm.

摘要

•Widely linear filter model is used to represent temporally correlated source signal.•A new blind source separation algorithm is proposed combining widely linear filter model identification with joint matrix diagonalization.•A special joint matrix diagonalization algorithm is proposed to adapt to the proposed blind source separation algorithm.

论文关键词：Blind source separation,Widely linear filter,Complex matrix joint diagonalization,Shear and Givens rotations

论文评审过程：Received 25 September 2017, Revised 20 June 2018, Accepted 13 October 2018, Available online 16 October 2018, Version of Record 28 October 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.10.016