Efficient Sparse Blind Source Separation Algorithm For Two- Channel Acoustic Noise Reduction

Résumé: Recently, the acoustic noise reduction problem is treated by two-channel forward blind source separation (BSS) techniques combined with normalized least mean square algorithm (T-FNLMS). The T-FNLMS algorithm shows good performances in two-channel convoluted dispersive mixture. In this paper, we propose new BSS structure based on the two-channel sparse normalized least mean square algorithm (TS-NLMS). The TS-NLMS algorithm is proposed exactly when the convoluted mixing system is characterized by sparse impulse responses. To confirm the good performance of this proposed algorithm, intensive experiments are done in acoustic noise reduction.

Publié dans la revue: Algerian Journal of Renewable Energy and Sustainable Development