Title :
A Multiplicative Algorithm for Convolutive Non-Negative Matrix Factorization Based on Squared Euclidean Distance
Author :
Wang, Wenwu ; Cichocki, Andrzej ; Chambers, Jonathon A.
Author_Institution :
Dept. of Electron. Eng., Univ. of Surrey, Guildford
fDate :
7/1/2009 12:00:00 AM
Abstract :
Using the convolutive nonnegative matrix factorization (NMF) model due to Smaragdis, we develop a novel algorithm for matrix decomposition based on the squared Euclidean distance criterion. The algorithm features new formally derived learning rules and an efficient update for the reconstructed nonnegative matrix. Performance comparisons in terms of computational load and audio onset detection accuracy indicate the advantage of the Euclidean distance criterion over the Kullback-Leibler divergence criterion.
Keywords :
convolution; matrix decomposition; signal reconstruction; Kullback-Leibler divergence criterion; Smaragdis; audio onset detection accuracy; computational load; convolutive nonnegative matrix factorization model; matrix decomposition; multiplicative algorithm; squared Euclidean distance; Audio object separation; convolutive nonnegative matrix factorization; multiplicative algorithm; squared Euclidean distance;
Journal_Title :
Signal Processing, IEEE Transactions on
DOI :
10.1109/TSP.2009.2016881