Title :
Combined blind/nonblind source separation based on the natural gradient
Author :
Joho, Marcel ; Mathis, Heinz ; Moschytz, George S.
Author_Institution :
Phonak Inc., Champaign, IL, USA
Abstract :
It is a known fact that blind algorithms have convergence times of an order of magnitude longer than their nonblind counterparts. However, as shown in this letter, the knowledge of a subset of signals can greatly accelerate the convergence of blind source separation. The convergence behavior of the proposed algorithm is compared with the blind-only case.
Keywords :
adaptive signal processing; gradient methods; speech processing; blind algorithms; combined blind/nonblind source separation; convergence times; natural gradient; signal subset; Acceleration; Adaptive algorithm; Blind source separation; Convergence; Helium; Loudspeakers; Signal processing; Signal processing algorithms; Source separation; Teleconferencing;
Journal_Title :
Signal Processing Letters, IEEE
