An Iterative Multichannel Wiener Filter Based on a Kronecker Product Decomposition
Jacob Benesty, Constantin Paleologu, Claudia-Cristina Oprea, Silviu Ciochină
Abstract
Multiple-input single-output (MISO) system identification problems appear in the context of many important applications. Due to their nature, they are usually addressed based on multichannel algorithms. However, the identification of long length impulse responses (e.g., like in echo cancellation) raises significant challenges, especially in terms of complexity and accuracy of the solution. In this paper, we develop an iterative multichannel Wiener filter for such MISO system identification scenarios. This algorithm is based on a Kronecker product decomposition of the impulse response, in conjunction with low-rank approximations. Simulation results indicate a good accuracy of the proposed solution, even when a small amount of data is available for the estimation of the statistics.