Micro-power spoken keyword spotting on Xylo Audio 2

TL;DR

This paper demonstrates a neuromorphic processor implementing a spoken keyword spotting benchmark with high accuracy and extremely low power consumption, showcasing the energy efficiency advantages of neuromorphic designs for edge audio processing.

Contribution

It presents the first implementation of the Aloha keyword spotting benchmark on the Xylo Audio 2 neuromorphic processor, achieving state-of-the-art energy efficiency and accuracy.

Findings

95% task accuracy on Aloha benchmark

Best-in-class inference power of 291μW

Inference efficiency of 6.6μJ per inference

Abstract

For many years, designs for "Neuromorphic" or brain-like processors have been motivated by achieving extreme energy efficiency, compared with von-Neumann and tensor processor devices. As part of their design language, Neuromorphic processors take advantage of weight, parameter, state and activity sparsity. In the extreme case, neural networks based on these principles mimic the sparse activity oof biological nervous systems, in ``Spiking Neural Networks'' (SNNs). Few benchmarks are available for Neuromorphic processors, that have been implemented for a range of Neuromorphic and non-Neuromorphic platforms, which can therefore demonstrate the energy benefits of Neuromorphic processor designs. Here we describes the implementation of a spoken audio keyword-spotting (KWS) benchmark "Aloha" on the Xylo Audio 2 (SYNS61210) Neuromorphic processor device. We obtained high deployed quantized task accuracy, (95%), exceeding the benchmark task accuracy. We measured real continuous power of the deployed application on Xylo. We obtained best-in-class dynamic inference power ($291\mu$W) and best-in-class inference efficiency ($6.6\mu$J / Inf). Xylo sets a new minimum power for the Aloha KWS benchmark, and highlights the extreme energy efficiency achievable with Neuromorphic processor designs. Our results show that Neuromorphic designs are well-suited for real-time near- and in-sensor processing on edge devices.