HCARLGPFSDJun 10, 2025

Implementing Keyword Spotting on the MCUX947 Microcontroller with Integrated NPU

arXiv:2506.08911v12 citationsh-index: 1
Originality Synthesis-oriented
AI Analysis

This enables efficient, low-power voice interfaces for embedded devices, but it is incremental as it applies known methods to a new hardware platform.

The paper tackled real-time keyword spotting on a resource-constrained microcontroller by implementing a CNN-based system with quantization, achieving 97.06% accuracy and a 59x speedup using an integrated NPU.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes