A new block adaptation algorithm realizing rapid identification system
Keiichi Ohishi, Hirokazu Kubota, M. Onoda · International Conference on Acoustics, Speech, and Signal Processing · 2003
The authors present a block adaptation algorithm that consists of the learning identification method and the Gram-Schmidt orthogonalization procedure. The adjustment vector is successively taken as the linear combination of some orthogonal bases derived from the state vectors in the block adaptation filter. Hence, when a complete orthogonal set is generated, the algorithm can estimate optimum coefficients in one block. The properties of the algorithm are described in a few theorems. Computer simulation shows that the algorithm has stable performance and rapid convergence.>