Title :
A transform domain LMS adaptive filter with variable step-size
Author :
Bilcu, Radu Ciprian ; Kuosmanen, Pauli ; Egiazarian, Karen
Author_Institution :
Signal Process. Lab., Tampere Univ. of Technol., Finland
Abstract :
We introduce a new transform domain (least mean square) LMS algorithm with variable step. The existing approaches use different time-variable step-sizes for each filter tap. The step-sizes are time-variable due to the power estimates of each transform coefficient. In our new approach, for each step-size we define a local component that is given by the power normalization, and a global component that is the same for each filter coefficient. We show that if the global component is also made time-variable, depending on the output error, the speed of convergence can be significantly improved.
Keywords :
adaptive filters; adaptive signal processing; convergence of numerical methods; discrete cosine transforms; filtering theory; least mean squares methods; DCT; convergence speed; different time-variable step-sizes; discrete cosine transform; filter coefficient; filter tap; global component; least mean square algorithm; local component; output error; power estimates; power normalization; transform coefficient; transform domain LMS adaptive filter; transform domain LMS algorithm; variable step-size; Adaptive filters; Adaptive signal processing; Convergence; Discrete cosine transforms; Error correction; Filtering algorithms; Least squares approximation; Signal processing; Signal processing algorithms; System identification;
Journal_Title :
Signal Processing Letters, IEEE
