An approach to blind source separation based on temporal structure of speech signals

In this paper, we introduce a new technique for blind source separation of speech signals. We focus on the temporal structure of the signals. The idea is to apply the decorrelation method proposed by Molgedey and Schuster in the time-frequency domain. Since we are applying separation algorithm on ea ch frequency separately, we have to solve the amplitude and permutation amb iguity properly to reconstruct the separated signals. For solving the ampli tude ambiguity, we use the matrix inversion and for the permutation ambigui ty, we introduce a method based on the temporal structure of speech signals . We show some results of experiments with both artificially controlled dat a and speech data recorded in the real environment. (C) 2001 Elsevier Scien ce B.V. All rights reserved.