AI & ML
Implementing Keyword Spotting on the MCXN947 Microcontroller with Integrated NPU
arXiv cs.HC0 views
arXiv:2506.08911v2 Announce Type: replace 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.
Source：https://arxiv.org/abs/2506.08911PreviousA State-of-the-Art Review of Computational Models for Analyzing Longitudinal Wearable Sensor Data in HealthcareNextMulti-Agent Home Energy Management Assistant
Related posts
How to Convert Any Webpage to Clean Markdown for RAG & Save 90% LLM Tokens in Node.js
0dev.to
Calibration‑free top‑k MoE selector saves tuning
0dev.to
How to Evaluate RAG Retrieval in 2026: Question Sets, Metrics That Mislead, and a Practical Recipe
0dev.to
Reading a Competitor's Pricing Page Like an Engineer
0dev.to
Day 4: Adding VLAN support
0dev.to
Browser-local image tools: how to check the upload boundary
0dev.to