Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks

TL;DR

This paper presents a highly energy-efficient keyword spotting system for microcontrollers by combining analog binary feature extraction with binary neural networks, significantly reducing power consumption while maintaining high accuracy.

Contribution

It introduces an analog front-end for feature extraction in KWS, achieving 29x energy reduction and outperforming state-of-the-art accuracy and efficiency on a standard dataset.

Findings

29x reduction in energy for data preprocessing

Outperforms state-of-the-art accuracy by 1%

Achieves 4.3x better energy efficiency with minimal accuracy loss

Abstract

Keyword spotting (KWS) is a crucial function enabling the interaction with the many ubiquitous smart devices in our surroundings, either activating them through wake-word or directly as a human-computer interface. For many applications, KWS is the entry point for our interactions with the device and, thus, an always-on workload. Many smart devices are mobile and their battery lifetime is heavily impacted by continuously running services. KWS and similar always-on services are thus the focus when optimizing the overall power consumption. This work addresses KWS energy-efficiency on low-cost microcontroller units (MCUs). We combine analog binary feature extraction with binary neural networks. By replacing the digital preprocessing with the proposed analog front-end, we show that the energy required for data acquisition and preprocessing can be reduced by 29x, cutting its share from a dominating 85% to a mere 16% of the overall energy consumption for our reference KWS application. Experimental evaluations on the Speech Commands Dataset show that the proposed system outperforms state-of-the-art accuracy and energy efficiency, respectively, by 1% and 4.3x on a 10-class dataset while providing a compelling accuracy-energy trade-off including a 2% accuracy drop for a 71x energy reduction.