Thomas P. von Hoff 1 , Allen G. Lindgren 2 , and August N. Kaelin 1

The behavior of the classic algorithm for blind source sep­ aration (BSS) is detailed for a fixed step size. To improve the algorithm in speed and exactness, essential in tracking a time­varying mixing environment, a variable step size must be employed. The ideal step size should decrease or in­ crease as the overall system error decreases or increases. It is shown analytically that the coefficients of the estimating function provide a "measure of error" that is available to automatically control the algorithm step size. This paper proposes a self­adjusting, time­varying step size that is built from the square of the running average of the coefficients of the estimating function. Error free convergence is achieved for a time­invariant environment. The ability of the algo­ rithm to improve the convergence in a time­invariant mixing environment and to track a changing mixing environment is demonstrated by extensive simulation results.