Implementing Keyword Spotting on the MCUX947 Microcontroller with Integrated NPU
By: Petar Jakuš, Hrvoje Džapo
Potential Business Impact:
Lets small gadgets hear your voice commands.
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.
Similar Papers
End-to-End Efficiency in Keyword Spotting: A System-Level Approach for Embedded Microcontrollers
Sound
Makes small devices hear your voice commands better.
Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices
Audio and Speech Processing
Finds any word in speech, even new ones.
Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms
Audio and Speech Processing
Lets small devices hear your voice commands.