Abstract
In this paper an algorithm for real-time signal processing of adaptive blind source separation (ABSS) is proposed. It is a promising method for speech and acoustic source signal separation in noisy environment such as room, office, etc. This paper proposed real-time de-mixture of speech mixture in enclosure environments. Making the real-time mixture of source signals as simultaneously as de-mixture in simulation based on adaptive NLMS and activation function in neural network are proposed. Separating the sources in the frequency domain is shown. The time variant mixing matrix based on random vector with time variable elements are made. Several simulations obtain optimum results of implemented algorithm. An experiment for testing the efficacy of the algorithm in the real-time source separation by high performance computer is presented.