Online mvbf adaptation under diffuse noise environments with mimo based noise pre-filtering

Abstract

A noise-robust MVBF adaptation technique under diffuse noise environments is proposed. The proposed method is compatible with online adaptation and robustness against diffuse noise by combining a semi-online diffuse noise reduction and an online MVBF adaptation technique with sparseness assumption of speech sources. The online sparseness based MVBF adaptation is sensitive to diffuse noise, because diffuse noise is not sparse. However, by using diffuse noise pre-filtering based on local Gaussian modeling which can be regarded as an optimized MIMO(Multi-Input Multi-Output) diffuse noise reduction method from the probabilistic perspective, sparseness of the microphone input signal into the latter part is expected to be improved. The proposed method is evaluated by using speech signal under diffuse noise environments, and the proposed method can reduce more noise source with less distortion than the conventional online sparseness based MVBF adaptation.