Title :
Analysis of the filtered-X LMS algorithm
Author :
Bjarnason, Elizabeth
Author_Institution :
Inst. fur Netzwerk- und Signaltheorie, Tech. Hochschule Darmstadt
fDate :
11/1/1995 12:00:00 AM
Abstract :
The presence of a transfer function in the auxiliary-path following the adaptive filter and/or in the error-path, as in the case of active noise control, has been shown to generally degrade the performance of the LMS algorithm. Thus, the convergence rate is lowered, the residual power is increased, and the algorithm can even become unstable. To ensure convergence of the algorithm, the input to the error correlator has to be filtered by a copy of the auxiliary-error-path transfer function. This paper presents an analysis of the filtered-X LMS algorithm using stochastic methods. The influence of off-line and on-line estimation of the error-path filter on the algorithm is also investigated. Some derived bounds and predicted dynamic behavior are found to correspond very well to simulation results
Keywords :
active noise control; adaptive filters; convergence of numerical methods; error analysis; estimation theory; least mean squares methods; stochastic processes; transfer functions; active noise control; adaptive filter; auxiliary-path; convergence rate; dynamic behavior; error correlator; error-path; filtered-X LMS algorithm; off-line estimation; on-line estimation; performance; residual power; simulation; stochastic methods; transfer function; Active noise reduction; Adaptive filters; Algorithm design and analysis; Convergence; Correlators; Degradation; Error correction; Least squares approximation; Stochastic processes; Transfer functions;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
