A method and apparatus for adaptive precompensation is disclosed. In one embodiment, the method comprises modifying operation of a predistortion filter in response to previous predistorted values and an original input signal, determining a precompensation error between the original input samples and the predicted loudspeaker output, and substantially reducing the precompensation error by using the exact inverse of a loudspeaker model that is a cascaded arrangement of at least one linear system with a non-linear system.
展开▼