On Robust Linear Prediction of Speech

In this paper, a robust linear prediction algorithm is proposed. Rather than minimizing the sum of squared residuals as in the conventional linear prediction procedures, the robust LP procedure minimizes the sum of a appropriately weighted residuals. The weight is a function of the prediction residual, and the cost function is selected to give more weighted to the bulk of smaller residuals while down-weighing the small portion of large residuals. In contrast, the conventional LP procedure weights all prediction residuals equally.