Method and system for implementing a gaussian white noise generator for real time speech synthesis applications

Abstract

A method and system for implementing a simple Gaussian white noise generator for real time speech synthesis applications. According to an embodiment of the present invention, a method for generating a Gaussian random noise signal comprises the steps of: generating a first predetermined number of outputs from a first random number generator having a first period; generating a second predetermined number of outputs from a second random number generator having a second period different from the first period; calculating a first average from a first combination of inputs from the first random number generator and the second random number generator; calculating a second average from a second combination of inputs from the first random number generator and the second random number generator; and generating a Gaussian output based on the first average and the second average.

Dependencies are inferred from the claim text.