Title :
An iterative Prony method for ARMA signal modeling
Author :
Therrien, Charles W. ; Velasco, Carlos H.
Author_Institution :
Naval Postgraduate Sch., Monterey, CA, USA
fDate :
1/1/1995 12:00:00 AM
Abstract :
A new iterative version of the Prony method is presented and shown to be exceptionally effective in finding ARMA models for acoustic data in the time domain. The method is based on a quadratic type of gradient algorithm, where it is shown that the gradient and Hessian are easily computed from the data. The new algorithm is found experimentally to have excellent convergence behavior. The performance of the algorithm is demonstrated and compared with that of the original Prony method and with that of the Steiglitz and McBride (1965) iterative prefiltering algorithm on some recorded acoustic data
Keywords :
acoustic signal processing; autoregressive moving average processes; convergence of numerical methods; iterative methods; time-domain analysis; ARMA signal modeling; Hessian; acoustic data; convergence behavior; gradient algorithm; iterative Prony method; quadratic type; time domain; Biomembranes; Convergence; Electrodes; Hidden Markov models; Interference; Iterative algorithms; Iterative methods; Poles and zeros; Speech recognition; Stochastic processes;
Journal_Title :
Signal Processing, IEEE Transactions on
