Blind Separation Of Linear Convolutive Mixtures Using Orthogonal Filter Banks

DMCA

Blind Separation Of Linear Convolutive Mixtures Using Orthogonal Filter Banks (2001)

Cached

Download Links

by Milutin Stanacevic , Marc Cohen , Gert Cauwenberghs

Venue:	Proc. IEEE Int. Symp. Circuits and Systems (ISCAS’98), Monterey CA
Citations:	13 - 7 self

BibTeX

@INPROCEEDINGS{Stanacevic01blindseparation,
    author = {Milutin Stanacevic and Marc Cohen and Gert Cauwenberghs},
    title = {Blind Separation Of Linear Convolutive Mixtures Using Orthogonal Filter Banks},
    booktitle = {Proc. IEEE Int. Symp. Circuits and Systems (ISCAS’98), Monterey CA},
    year = {2001},
    pages = {17--20}
}

OpenURL

Abstract

We propose an algorithm and architecture for real-time blind source separation of linear convolutive mixtures using orthogonal filter banks. The adaptive algorithm derives from stochastic gradient descent optimization of a performance metric that quantifies independence not only across the reconstructed sources, but also across time within each source. The special case of a Laguerre section offers a compact representation with a small number of filter taps even under severe reverberant conditions, facilitating real-time implementation in a modular and scalable parallel architecture. Simulations of the proposed architecture and update rule validate the approach.

Keyphrases

blind separation stochastic gradient descent optimization severe reverberant condition laguerre section small number orthogonal filter bank quantifies independence linear convolutive mixture compact representation real-time blind source separation real-time implementation scalable parallel architecture adaptive algorithm derives update rule special case reconstructed source filter tap

DMCA