Low-power SNN-based audio source localisation using a Hilbert Transform spike encoding scheme

TL;DR

This paper presents a novel low-power sound source localization method using spiking neural networks and Hilbert transform, achieving high accuracy with significantly reduced power consumption for IoT applications.

Contribution

The paper introduces a Hilbert transform-based encoding scheme and a new event-based phase encoding method for efficient SNN-based audio localization, outperforming existing low-power approaches.

Findings

Achieves state-of-the-art accuracy comparable to traditional beamforming.

Demonstrates significantly lower power consumption on low-power hardware.

Improves efficiency of DSP-based signal processing using the proposed method.

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 demonstrate a novel 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 a new event-based encoding method that captures the phase of the complex analytic signal. Our approach achieves state-of-the-art 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 new Hilbert-transform-based method for beamforming can also improve the efficiency of traditional DSP-based signal processing.