Implementing Keyword Spotting on the MCUX947 Microcontroller with Integrated NPU
Human-Computer Interaction
2025-06-23 v1 Hardware Architecture
Machine Learning
Performance
Sound
Abstract
This paper presents a keyword spotting (KWS) system implemented on the NXP MCXN947 microcontroller with an integrated Neural Processing Unit (NPU), enabling real-time voice interaction on resource-constrained devices. The system combines MFCC feature extraction with a CNN classifier, optimized using Quantization Aware Training to reduce model size with minimal accuracy drop. Experimental results demonstrate a 59x speedup in inference time when leveraging the NPU compared to CPU-only execution, achieving 97.06% accuracy with a model size of 30.58 KB, demonstrating the feasibility of efficient, low-power voice interfaces on embedded platforms.
Keywords
Cite
@article{arxiv.2506.08911,
title = {Implementing Keyword Spotting on the MCUX947 Microcontroller with Integrated NPU},
author = {Petar Jakuš and Hrvoje Džapo},
journal= {arXiv preprint arXiv:2506.08911},
year = {2025}
}
Comments
4 pages