Sound Source Localization Through 8 MEMS Microphones Array Using a Sand-Scorpion-Inspired Spiking Neural Network

Abstract

Read online

Sand-scorpions and many other arachnids perceive their environment by using their feet to sense ground waves. They are able to determine amplitudes the size of an atom and locate the acoustic stimuli with an accuracy of within 13° based on their neuronal anatomy. We present here a prototype sound source localization system, inspired from this impressive performance. The system presented utilizes custom-built hardware with eight MEMS microphones, one for each foot, to acquire the acoustic scene, and a spiking neural model to localize the sound source. The current implementation shows smaller localization error than those observed in nature.

Keywords

• Neuromorphic
• bio-inspired
• Microphone array
• Acoustic localization
• spiking-neurons