On parametric representations of the modified group delay

Abstract

The modified group delay (MODGD) is a group delay based representation suited for processing speech signals. The MODGD is parameterized by three entities, alpha, gamma and lifteromega. Typically, optimal values of these parameters have to be determined by experimentation. In this paper, we propose a method to automatically determine an optimal value for lifteromega^, which enables the other two parameters to be set to 1.0. This will reduce the optimisation required to obtain meaningful MODGD values directly from the speech signal.