DCTLMS algorithm employing partial coefficient updates

Recently, a fast version of the LMS algorithm where only a small subset of the coefficients is updated at each iteration has been published in the literature. In this paper, we analyze the effects of this technique on the discrete cosine transform domain LMS (DCTLMS) algorithm and highlight its advantages and drawbacks. It will be shown, in particular, that a reduction in the computational complexity can be achieved without causing any degradation to the steady state error of the algorithm. The analytical results are then followed by simulations where real speech and 1st-order Markov signals are used.

[1]  Tyseer Aboulnasr,et al.  Selective coefficient update of gradient-based adaptive algorithms , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Françoise Beaufays,et al.  Transform-domain adaptive filters: an analytical approach , 1995, IEEE Trans. Signal Process..

[3]  Behrouz Farhang-Boroujeny.  Order of N complexity transform domain adaptive filters , 1994, Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94.

[4]  S. Thomas Alexander,et al.  Adaptive Signal Processing , 1986, Texts and Monographs in Computer Science.

[5]  N. Ahmed,et al.  Discrete Cosine Transform , 1996 .

[6]  Leonid G. Kazovsky,et al.  Adaptive filters with individual adaptation of parameters , 1986 .

[7]  Jae Chon Lee,et al.  Performance of transform-domain LMS adaptive digital filters , 1986, IEEE Trans. Acoust. Speech Signal Process..

[8]  A. Peterson,et al.  Transform domain LMS algorithm , 1983 .

[9]  Samir Attallah,et al.  The wavelet transform-domain LMS algorithm: a more practical approach , 2000 .

[10]  S.C. Douglas,et al.  Analysis and implementation of the max-NLMS adaptive filter , 1995, Conference Record of The Twenty-Ninth Asilomar Conference on Signals, Systems and Computers.

[11]  W. K. Jenkins,et al.  The use of orthogonal transforms for improving performance of adaptive filters , 1989 .

[12]  Tyseer Aboulnasr,et al.  MSE analysis of the M-max NLMS adaptive algorithm , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).