Adaptive filtering based on wavelet decomposition

Addresses a novel, wavelet decomposition based adaptive filtering technique. The input signal is decomposed into octave-bands and the adaptive filtering is performed on those signals using a hierarchical structure. The signal error is decomposed and used in the adaptation process. Using this technique, considerable computational reduction is achieved over the full-band scheme. Simulations show that the asymptotic performance of this scheme is similar to that of the full-band scheme.<<ETX>>