Pradip Sircar and Rakesh K. Saini
Indian Institute of Technology Kanpur

This paper presents two, non-stationary models for parametric modeling of speech signals. The complex AM signal model has been found to be suitable for voiced speech phonemes, whereas the complex FM signal model can be used for representation of unvoiced speech phonemes. The basic principles of parameter estimation of these two models are demonstrated, and the improved techniques for fast on-line processing of speech data and automated model fitting are developed.