The paper addresses the problem of channel estimation for DS-CDMA systems undergoing time-varying multipath fading channels. The multipath fading channels are modeled as AR models. Based on the minimum mean square error (MMSE) criterion, the linear optimal estimator is obtained by a spectral factorization and a Diophantine polynomial matrix equation. The uncertainty of the channel model is taken into consideration to improve the robustness of the estimator. Compared with the Kalman estimator, the proposed algorithm has O(K/sup 2/) computational complexity, where K is the number of users. The simulation results show that the proposed estimator provides good estimation performance and robustness for fast fading channels.