The present invention provides a novel technique for improving the performance of equalizers by reducing the effects of error propagation in equalizers that use a Viterbi Decoder. Methods and systems are described that can improve the performance of equalizers by reducing the effects of error propagation in equalizers that use a Viterbi Decoder. Systems and methods of symbol correction in prediction decision feedback equalization ("pDFE") architectures are described. Systems are described that include one or more enhanced Viterbi decoders together with novel methods of symbol correction to obtain better system performance. Systems and methods are described that utilize dual pDFEs and can use a blending algorithm to reduce errors in symbol decoding. Dual pDFEs are described that include forward and backward Viterbi decoders wherein the backward Viterbi decoded may operate on time reversed data blocks and with some degree of latency. Forward and backward Viterbi decoders can generate different decoded symbols from the same equalized data. A blending algorithm is described for weighting results based on reliability of the respective decoded symbols. A forward-backward blender can additionally increase performance of the second pDFE by blending long delayed trellis symbols from the first Viterbi decoder with symbols output by the second Viterbi decoder.
