ADAPTIVE SPECTRUM ESTIMATION CONSIDERING THE TIME-VARIATION IN ANALYSIS INTERVALS

In spectrum estimation of nonstationary signals, the modelling of time -varying characteristics and the parameter estimation of the model are important. Several adaptive estimation methods such as the recursive least squares (RLS) method are often used for parameter estimation of time-varying models. However, the RLS method becomes less efficient fo r rapidly time-varying models because this method assumes short-time s tationarity. This paper proposes an adaptive estimation method of time -varying parameters modelled as linear combinations of a set of basis functions. In this method, linear or exponential time functions are em ployed as basis functions. This algorithm is realized by the RLS algor ithm with a rectangular window and a procedure that shifts basis funct ions. In some experiments, the performance of the proposed method is c ompared with that of the conventional method with short-time stationar ity assumed.