Mean weight behavior of the filtered-X LMS algorithm
- 1 April 2000
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 48 (4), 1061-1075
- https://doi.org/10.1109/78.827540
Abstract
A new stochastic analysis is presented for the filtered-X LMS (FXLMS) algorithm. The analysis does not use independence theory. An analytical model is derived for the mean behavior of the adaptive weights. The model is valid for white or colored reference inputs and accurately predicts the mean weight behavior even for large step sizes. The constrained Wiener solution is determined as a function of the input statistics and the impulse responses of the adaptation loop filters. Effects of secondary path estimation error are studied. Monte Carlo simulations demonstrate the accuracy of the theoretical modelKeywords
This publication has 6 references indexed in Scilit:
- Exact expectation analysis of the LMS adaptive filterIEEE Transactions on Signal Processing, 1995
- Analysis of the filtered-X LMS algorithmIEEE Transactions on Speech and Audio Processing, 1995
- The effect of transfer function estimation errors on the filtered-x LMS algorithmIEEE Transactions on Signal Processing, 1994
- A frequency domain model for 'filtered' LMS algorithms-stability analysis, design, and elimination of the training modeIEEE Transactions on Signal Processing, 1993
- A multiple error LMS algorithm and its application to the active control of sound and vibrationIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- On the Independence Theory of Equalizer ConvergenceBell System Technical Journal, 1979