Low-power Spiking Neural Network audio source localisation using a Hilbert Transform audio event encoding scheme

Abstract

Sound source localisation is used in many consumer devices, to isolate audio from individual speakers and reject noise. Localization is frequently accomplished by “beamforming”, which combines phase-shifted audio streams to increase power from chosen source directions, under a known microphone array geometry. Dense band-pass filters are often needed to obtain narrowband signal components from wideband audio. These approaches achieve high accuracy, but narrowband beamforming is computationally demanding, and not ideal for low-power IoT devices. We introduce a method for sound source localisation on arbitrary microphone arrays, designed for efficient implementation in ultra-low-power spiking neural networks (SNNs). We use a Hilbert transform to avoid dense band-pass filters, and introduce an event-based encoding method that captures the phase of the complex analytic signal. Our approach achieves high accuracy for SNN methods, comparable with traditional non-SNN super-resolution beamforming. We deploy our method to low-power SNN inference hardware, with much lower power consumption than super-resolution methods. We demonstrate that signal processing approaches co-designed with spiking neural network implementations can achieve much improved power efficiency. Our Hilbert-transform-based method for beamforming can also improve the efficiency of traditional digital signal processing.

Sound source localisation is used in many consumer devices, to isolate audio from individual speakers and reject noise. Saeid Haghighatshoar and Dylan Richard Muir demonstrate a sound source localisation method from microphone arrays, using Hilbert-Transform-based audio-to-signed-event encoding and spiking neural networks.