Method and device for adaptively estimating a transfer function of an unknown system.

摘要

In an adaptive estimation of a transfer function by a projection algorithm, a forward linear prediction coefficient vector a(k) of an input signal x(k), the sum of forward a posteriori prediction-error squares F(k), a backward linear prediction coefficient vector b(k) of the input signal x(k) and the sum of backward a posteriori prediction-error squares B(k) are computed. Letting a step size and a pre-filter deriving coefficient vector be represented by mu and f(k), respectively, a pre-filter coefficient vector g(k) is calculated by a recursion formula for the pre-filter coefficient vector g(h), which is composed of the following first and second equations: $\mathop{\mathrm{image}}$