A variable step-size GMDF and its performance analysis

Numerous time-domain variable step-size normalized least mean square algorithms have been derived to solve the dilemma of fast convergence rate or low excess mean-square error in the past two decades. This paper proposes a variable step-size control method for the generalized frequency-domain multidelay adaptive filter (GMDF), which is an attractive choice in applications requiring a large number of coefficients such as acoustic echo cancellation. This algorithm employs the mean-square error and the estimated system noise power to control the step-size update in each frequency bin. Simulation experiments show our algorithm performs very well. Furthermore, the theoretical steady-state behavior is in very good agreement with the experimental results.