This paper addresses the problem of robust beamforming for a moving source. To cope with the source movement, the regularization (or diagonal loading) parameter needs to be adjusted regularly. The need for repeatedly finding an adequate value of the regularization parameter increases the overall computational complexity. This paper proposes a simple and efficient initialization of Newton’s method to find the regularization parameter. The regularization parameter is chosen to minimize the mean-squared-error (MSE) of a regularized least-squares (RLS) problem by solving a certain function. We exploit some properties of this function to develop the method. Simulation results demonstrate that the proposed initialization method can reduce the runtime by 75%.
|Title of host publication
|2020 28th European Signal Processing Conference (EUSIPCO)
|Published - Dec 18 2020