mlsanityData to 14 Oct 2026

Implementing Keyword Spotting on the MCUX947 Microcontroller with Integrated NPU

arXiv 2506.08911 ↗First posted 10 Jun 2025cs.HC cs.AR cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 9 of its 19 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

9 of 19 references.

References · 9

  1. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  2. 2017Hello Edge: Keyword Spotting on Microcontrollerscited by 110
  3. 2018Federated Learning for Keyword Spottingcited by 95
  4. 2017A Cascade Architecture for Keyword Spotting on Mobile Devicescited by 15
  5. 2024On-Device Domain Learning for Keyword Spotting on Low-Power Extreme Edge Embedded Systemscited by 13
  6. 2021Ultra-Low Power Keyword Spotting at the Edgecited by 6
  7. 2022Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networkscited by 5
  8. 2019An Optimized Recurrent Unit for Ultra-Low-Power Keyword Spottingcited by 4
  9. 2022HEiMDaL: Highly Efficient Method for Detection and Localization of wake-wordscited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

Similar, not cited

Close in wording, no citation either way

  1. 2022Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers
  2. 2025Keyword Mamba: Spoken Keyword Spotting with State Space Models
  3. 2022A 14uJ/Decision Keyword Spotting Accelerator with In-SRAM-Computing and On Chip Learning for Customization
  4. 2022A Fast Network Exploration Strategy to Profile Low Energy Consumption for Keyword Spotting
  5. 2026End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor
  6. 2021End-to-end Keyword Spotting using Neural Architecture Search and Quantization
  7. 2024DeltaKWS: A 65nm 36nJ/Decision Bio-inspired Temporal-Sparsity-Aware Digital Keyword Spotting IC with 0.6V Near-Threshold SRAM
  8. 2025Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Models