Scheduled System Maintenance:
On Wednesday, July 29th, IEEE Xplore will undergo scheduled maintenance from 7:00-9:00 AM ET (11:00-13:00 UTC). During this time there may be intermittent impact on performance. We apologize for any inconvenience.
By Topic

Transform-domain adaptive filters: an analytical approach

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Beaufays, F. ; Dept. of Electr. Eng., Stanford Univ., CA, USA

Transform-domain adaptive filters refer to LMS filters whose inputs are preprocessed with a unitary data-independent transformation followed by a power normalization stage. The transformation is typically chosen to be the discrete Fourier transform (DFT), although other transformations, such as the cosine transform (DCT), the Hartley transform (DHT), or the Walsh-Hadamard transform, have also been proposed in the literature. The resulting algorithms are generally called DFT-LMS, DCT-LMS, etc. This preprocessing improves the eigenvalue distribution of the input autocorrelation matrix of the LMS filter and, as a consequence, ameliorates its convergence speed. In this paper, we start with a brief intuitive explanation of transform-domain algorithms. We then analyze the effects of the preprocessing performed in DFT-LMS and DCT-LMS for first-order Markov inputs. In particular, we show that for Markov-1 inputs of correlation parameter ρ∈[0,1], the eigenvalue spread after DFT and power normalization tends to (1+ρ)l(1-ρ) as the size of the filter gets large, whereas after DCT and power normalization, it reduces to (1+ρ). For comparison, the eigenvalue spread before transformation is asymptotically equal to (1+ρ)2/(1-ρ)2. The analytical method used in the paper provides additional insight into how the algorithms work and is expected to extend to other input signal classes and other transformations

Published in:

Signal Processing, IEEE Transactions on  (Volume:43 ,  Issue: 2 )