Acoustics, Speech, and Signal Processing, IEEE International Conference on (1995)
Detroit, MI, USA
May 9, 1995 to May 12, 1995
K. Mayyas , Dept. of Electr. Eng., Ottawa Univ., Ont., Canada
T. Aboulnasr , Dept. of Electr. Eng., Ottawa Univ., Ont., Canada
The paper presents a robust variable step size LMS-type algorithm with the attractive property of achieving a small final misadjustment while providing fast convergence at early stages of adaptation. The performance of the algorithm is not affected by the presence of noise. Approximate analysis of convergence and steady state performance for zero-mean stationary Gaussian inputs and a nonstationary optimal weight vector is provided. Simulation results clearly indicate its superior performance for stationary cases. For the nonstationary environment, the algorithm provides performance equivalent to that of the regular LMS algorithm.
K. Mayyas and T. Aboulnasr, "A robust variable step size LMS-type algorithm: analysis and simulations," Acoustics, Speech, and Signal Processing, IEEE International Conference on(ICASSP), Detroit, MI, USA, 1995, pp. 1408-1411.