[Submitted on 10 Jun 2025 (v1), last revised 5 Nov 2026 (this version, v2)]
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.
Submission history
From: Petar Jakuš [view email]
[v1] Tue, 10 Jun 2025 15:38:21 UTC (1,685 KB)
[v2] Thu, 5 Nov 2026 12:38:35 UTC (398 KB)
