Adaptive predictors in cascade form to analyse superimposed exponential signals with time-varying parameters

In this paper adaptive predictors structured in cascade form are used to an alyse superimposed exponential signals with time-varying parameters. On-lin e optimisation of the filters parameters is achieved using gradient descent techniques focused on the direct estimation of instantaneous information-b earing parameters (damping and frequency). Examples of the performance of t he algorithm are given for real-valued multi-component synthetic signals wi th different schemes of frequency modulation in clean and noisy environment s. The performance of the algorithm is also evaluated in the task of tracki ng the formants of a voiced segment of speech. (C) 2001 Elsevier Science BY . All rights reserved.