A fast technique for finding the stationary autocorrelation matrix from a perturbational measurement of the gradient

  • Authors:

  • R. D. Roberts;N. Tepedenlengilou

  • Affiliations:

  • Harris Corp., ESS, Melbourne, FL;Florida Institute of Technology, Melbourne, FL

  • Venue:
  • ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: digital speech processing - Volume III
  • Year:
  • 1993

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper shows that when using a synchoronously spaced FIR data equalizer with complex weights, we can estimate the autocorrelation matrix by empirically measuring the gradient of the MSE performance surface, using only the real portion of the maximal time delay weight located at the far end of the FIR filter. Since we only need to perturb one weight of the FIR filter to find the autocorrelation matrix, this represents a minimal computation technique.