Sensorless control methods stand out as an alternative for cost reduction and maintenance in AC electric drive systems. This work deals with the application of the Extended Kalman Filter (EKF) to the estimation of the speed and position of the rotor aiming at the implementation of the indirect vector control technique in a speed control system for three- phase induction motors. The Kalman lter, despite its mathematical and computational complexity, performs well under variable speed and load conditions as well as convergence times consistent with the usual requirements of high performance systems. The main contributions of this work are the use of a reduced-order EKF (ROEKF) and the co-variance matrix pretuning in order to accelerate the convergence in the velocity and position estimates for futureimplementations in digital signal processors currently accessible.