Embedded Implementation of Real-Time Voice Command Recognition on PIC Microcontroller

I tiakina i:
Ngā taipitopito rārangi puna kōrero
I whakaputaina i:Automation vol. 6, no. 4 (2025), p. 79-101
Kaituhi matua: Shili Mohamed
Ētahi atu kaituhi: Hammedi Salah, Gawanmeh Amjad, Nouri Khaled
I whakaputaina:
MDPI AG
Ngā marau:
Urunga tuihono:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Ngā Tūtohu: Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!

MARC

LEADER 00000nab a2200000uu 4500
001 3286259160
003 UK-CbPIL
022 |a 2673-4052 
024 7 |a 10.3390/automation6040079  |2 doi 
035 |a 3286259160 
045 2 |b d20251001  |b d20251231 
100 1 |a Shili Mohamed  |u Innov’COM Laboratory, National Engineering School of Cartahage, Ariana 2035, Tunisia; mohamed.shili@fst.utm.tn 
245 1 |a Embedded Implementation of Real-Time Voice Command Recognition on PIC Microcontroller 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a This paper describes a real-time system for recognizing voice commands for resource-constrained embedded devices, specifically a PIC microcontroller. While most existing speech ordering support solutions rely on high-performance processing platforms or cloud computation, the system described here performs fully embedded low-power processing locally on the device. Sound is captured through a low-cost MEMS microphone, segmented into short audio frames, and time domain features are extracted (i.e., Zero-Crossing Rate (ZCR) and Short-Time Energy (STE)). These features were chosen for low power and computational efficiency and the ability to be processed in real time on a microcontroller. For the purposes of this experimental system, a small vocabulary of four command words (i.e., “ON”, “OFF”, “LEFT”, and “RIGHT”) were used to simulate real sound-ordering interfaces. The main contribution is demonstrated in the clever combination of low-complex, lightweight signal-processing techniques with embedded neural network inference, completing a classification cycle in real time (under 50 ms). It was demonstrated that the classification accuracy was over 90% using confusion matrices and timing analysis of the classifier’s performance across vocabularies with varying levels of complexity. This method is very applicable to IoT and portable embedded applications, offering a low-latency classification alternative to more complex and resource intensive classification architectures. 
653 |a Microcontrollers 
653 |a Feature extraction 
653 |a Accuracy 
653 |a Embedded systems 
653 |a Classification 
653 |a Neural networks 
653 |a Fourier transforms 
653 |a Power 
653 |a Cloud computing 
653 |a Voice recognition 
653 |a Signal processing 
653 |a Power management 
653 |a Smart houses 
653 |a Algorithms 
653 |a Complexity 
653 |a Real time 
653 |a Speech 
653 |a Efficiency 
700 1 |a Hammedi Salah  |u Networked Objects, Control, and Communication Systems (NOCCS), ENISo, University of Sousse, Sousse 4011, Tunisia; salah.hammedi@enim.u-monastir.tn 
700 1 |a Gawanmeh Amjad  |u College of Engineering and IT, University of Dubai, Dubai 14143, United Arab Emirates 
700 1 |a Nouri Khaled  |u Laboratory of Advanced Systems (LSA), Polytechnic School of Tunis, Al Marsa 2078, Tunisia; khaled.nouri@ept.rnu.tn 
773 0 |t Automation  |g vol. 6, no. 4 (2025), p. 79-101 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3286259160/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3286259160/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3286259160/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch