Noise-predictive turbo equalization for partial-response channels

We consider an iterative decoding and detection system for magnetic recording channels. The system uses a zero-forcing equalizer to shape the channel response to a target polynomial, called a partial-response (PR) polynomial. We assume that the noise at the input to the equalizer is AWGN. Hence, noise enhancement and coloration occur at the output of the equalizer. In this work, the paper aims to improve the system performance by incorporating noise prediction. The approach has previously been used to improve Viterbi detectors in PRML systems.