A Multi-spike Approach for Robust Sound Recognition

Abstract

The extraordinary performance of the brain on various cognitive tasks motivates the design of a biologically plausible system for the challenging task of environmental sound recognition. In this paper, we propose a novel approach based on multi-spike learning and key-point encoding. Our encoding extracts local temporal and spectral information from the sound and converts it into spatiotemporal spike pattern, which is further learned by the following spiking neural networks. Our experiments demonstrate the robustness and effectiveness of our approach across a variety of noise conditions, outperforming other conventional baseline methods in both mismatched and multi-condition scenarios.