Neuro-rough control of masking thresholds for audio signal enhancement

The paper addresses the problem of neuro-rough hybridisation applied to dig ital processing of audio signals. Moreover, the application of some selecte d soft computing techniques to non-stationary noise reduction is described. Some attention is also put to a discussion of the intelligent decision alg orithms performance. The noise reduction algorithm is based on the new perc eptual approach exploiting some properties of the human auditory system. Fu rthermore, the paper introduces the engineered perceptual filter driven by an intelligent controller employing rules generated with the use of a rough set-based algorithm supported by a neural network. The goal of the intelli gent controller is to estimate the current statistics of corrupting noise o n the basis of the analysis of signals received From telecommunication chan nel. Thereafter, the noise estimate enables determining the masking thresho ld levels which allow making the noise inaudible in the audio signals. Sinc e the implemented decision algorithm requires quantised data, thus the Koho nen's self-organising maps (SOM) extended by various distance metrics were used as data quantisers. Some results of the experiments in the domain of n on-stationary noise reduction in speech are discussed in the paper. (C) 200 1 Elsevier Science B.V. All rights reserved.