No abstract

Abstract:In blind source separation problems that are implemented based on the independent component analysis (ICA) algorithm, the separation speed and quality are related inversely. In this paper, the proposed algorithms eliminate this tradeoff by generating a faster separation while maintaining the quality. In the proposed algorithms, in each frequency bin and in all of the learning steps, the separation quality of the separating matrix is compared with another one that we define as a situated matrix, and the best matrix is considered as an initial separating matrix in the next learning step.In this paper, we propose 2 algorithms based on the constant situated matrix (CSM) and the variable situated matrix (VSM). Using the simulation results, on average, the proposed CSM and VSM algorithms are about 3 and 6 times faster than the ICA algorithm, respectively, while the quality of the separated signals remains almost unchanged or becomes slightly better.

Abstract:We introduce the fusion of iterative and closed-forms separation (FICS) method for high-speed separation of anechoic mixed speech signals. This method is performed in two stages: 1) iterative-form separation and 2) closed-form separation. This algorithm significantly improves the separation quality simply due to incorporating only some specific frequency bins into computations. We apply the FICS method to the frequency-domain independent component analysis (ICA) to evaluate its performance in increasing the signal separation speed for anechoic mixtures. Simulation results show that for speech signals and anechoic conditions, the proposed algorithm is on average 65 times faster than ICA while preserving the separation quality. It also outperforms FastICA, JADE, and SOBI in terms of separation quality and speed.

No abstract

In this paper, we introduce the fusion of iterative and closed‐form separation (FICS) method for high‐speed separation of mixed speech signals. This method is performed in two stages: (i) iterative‐form separation and (ii) closed‐form separation. This algorithm significantly improves the separation quality simply by incorporating only some specific frequency bins into computations. We apply the FICS method to the frequency‐domain independent component analysis (ICA) to evaluate its performance in increasing the signal separation speed. Simulation results show that for speech signals, the proposed algorithm is on average 40 times faster than the ICA, while preserving the separation quality. Also, it outperforms the FastICA, JADE, and SOBI in terms of separation quality. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.