Multichannel transient acoustic signal classification using task-driven dictionary with joint sparsity and beamforming

Abstract

We are interested in a multichannel transient acoustic signal classification task which suffers from additive/convolutionary noise corruption. To address this problem, we propose a double-scheme classifier that takes the advantage of multichannel data to improve noise robustness. Both schemes adopt task-driven dictionary learning as the basic framework, and exploit multichannel data at different levels - scheme 1 imposes joint sparsity constraint while learning the dictionary and classifier; scheme 2 adopts beamforming at signal formation level. In addition, matched filter and robust ceptral coefficients are applied to improve noise robustness of the input feature. Experiments show that the proposed classifier significantly outperforms the baseline algorithms.