We consider a new discriminative learning approach to sequence labeling based on the statistical concept of the Z-score. Given a training set of pairs of hidden-observed sequences, the task is to determine some parameter values such that the hidden labels can be correctly reconstructed from observations. Maximizing the Z-score appears to be a very good criterion to solve this problem both theoretically and empirically. We show that the Z-score is a convex function of the parameters and it can be eciently computed with dynamic programming methods. In addition to that, the maximization step turns out to be solvable by a simple linear system of equations. Experiments on artificial and real data demonstrate that our approach is very competitive both in terms of speed and accuracy with respect to previous algorithms.