Title :
System identification using subband signal processing
Author :
Marelli, Damian ; Fu, Minyue
Author_Institution :
Dept. of Electr. & Comput. Eng., Newcastle Univ., NSW, Australia
Abstract :
We first give a tutorial on a new approach to system identification using subband signal processing. Next, we study two types of subband identification schemes, one using critical sampling and one using over-sampling. We compare the behavior of the subband identification technique with the traditional "full-band" identification technique in terms of the computational cost, asymptotic residual error and convergence rate. This comparison is used to demonstrate the potential power of the subband technique. We also consider the design issues for subband identification, especially for the case with over-sampling
Keywords :
control system synthesis; convergence; identification; least squares approximations; linear systems; sampled data systems; signal processing; asymptotic residual error; computational cost; convergence rate; critical sampling; identification; linear time-invariant system; over-sampling; recursive least-squares; subband signal processing; Channel bank filters; Computational efficiency; Convergence; Filter bank; Finite impulse response filter; Reverberation; Signal processing; Signal processing algorithms; Speech; System identification;
Conference_Titel :
Decision and Control, 2001. Proceedings of the 40th IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-7061-9
DOI :
10.1109/.2001.980398
