Gradient adaptive paraunitary filter banks for spatio-temporal subspace analysis and multichannel blind deconvolution

Scott C. Douglas, Shun Ichi Amari, S. Y. Kung

Research output: Contribution to journalArticle

4 Scopus citations

Abstract

Paraunitary filter banks are important for several signal processing tasks, including coding, multichannel deconvolution and equalization, adaptive beamforming, and subspace processing. In this paper, we consider the task of adapting the impulse response of a multichannel paraunitary filter bank via gradient ascent or descent on a chosen cost function. Our methods are spatio-temporal generalizations of gradient techniques on the Grassmann and Stiefel manifolds, and we prove that they inherently maintain the paraunitariness of the multichannel adaptive system over time. We then discuss the necessary practical approximations, modifications, and simplifications of the methods for solving two relevant signal processing tasks: (i) spatio-temporal subspace analysis and (ii) multichannel blind deconvolution. Simulations indicate that our methods can provide simple, useful solutions to these important problems.

Original languageEnglish (US)
Pages (from-to)247-261
Number of pages15
JournalJournal of VLSI Signal Processing Systems for Signal, Image, and Video Technology
Volume37
Issue number2-3
DOIs
StatePublished - Jun 1 2004

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Electrical and Electronic Engineering

Keywords

  • Adaptive algorithms
  • Gradient descent
  • Grassmann manifold
  • Multichannel blind deconvolution
  • Paraunitary filter banks
  • Stiefel manifold
  • Subspace analysis

Fingerprint Dive into the research topics of 'Gradient adaptive paraunitary filter banks for spatio-temporal subspace analysis and multichannel blind deconvolution'. Together they form a unique fingerprint.

  • Cite this