A COMBINED CASCADING SUBSPACE AND ADAPTIVE SIGNAL ENHANCEMENT METHOD FOR STEREOPHONIC NOISE REDUCTION

Open Webpage

Tetsuya Hoya, Andrzej Cichocki, Toshihisa Tanaka, Gen Hori, Takahiro Murakami, Jonathon A. Chambers

Published: 04 Jan 2003, Last Modified: 15 Apr 2025Proc. ICAEveryoneCC BY 4.0
Abstract: A novel stereophonic noise reduction method is proposed based upon a combination of cascaded subspace filters, with delay and advancing elements alternatively inserted between the adjacent cascading stages, and two-channel adaptive signal enhancers. Simulation results based upon real stereophonic speech contaminated by two correlated noise components show that the proposed method gives improved enhancement quality, as compared to conventional nonlinear spectral subtraction approaches, in terms of both segmental gain and cepstral distance performance indices.