Spoken Command Recognition System for Hands-Free Door Control
DOI:
https://doi.org/10.51459/jostir.2025.1.Special-Issue.067Abstract
This paper presents the development of a Spoken Command Recognition System (SCRS) that utilizes a lightweight convolutional neural network (CNN) for hands-free door access control. The system interprets voice commands, specifically "open" and "close", to activate a solenoid that locks or unlocks a door. A dataset comprising 2,000 labeled audio samples (open/close commands) and 70 environmental noise samples was collected. Mel Frequency Cepstral Coefficients (MFCCs) were extracted from the recordings, with 80% used to train the CNN and the remaining 20% reserved for validation. The trained model was quantized using Edge Impulse and deployed on an ESP32-S3 microcontroller using TensorFlow Lite. The deployed system achieved a recognition accuracy of 97.5% with a real-time response time of 3000ms. The SCRS offers a low-power, real-time, and moderately noise-tolerant solution for voice-activated door access.
Keywords: Speaker recognition, CNN, embedded systems, ESP32-S3, door access control.
References
Abdulghani, M. M., Walters, W. L., & Abed, K. H. (2022). Autonomous Voice Recognition Wheelchair Control System. 2022 International Conference on Computational Science and Computational Intelligence (CSCI), 226–230. https://doi.org/10.1109/CSCI58124.2022.00043
Arifin, R. D. H., & Sarno, R. (2018). Door automation system based on speech command and PIN using Android smartphone. 2018 International Conference on Information and Communications Technology (ICOIACT), 667–672. https://doi.org/10.1109/ICOIACT.2018.8350715
Ayache, M., Kanaan, H., Kassir, K., & Kassir, Y. (2021). Speech Command Recognition Using Deep Learning. International Conference on Advances in Biomedical Engineering, ICABME, 2021-October(September), 24–29. https://doi.org/10.1109/ICABME53305.2021.9604862
Chen, J., Teo, T. H., Kok, C. L., & Koh, Y. Y. (2024). A Novel Single-Word Speech Recognition on Embedded Systems Using a Convolution Neuron Network with Improved Out-of-Distribution Detection. Electronics (Switzerland), 13(3), 1–16. https://doi.org/10.3390/electronics13030530
López-Espejo, I., Tan, Z.-H., Hansen, J. H. L., & Jensen, J. (2022). Deep Spoken Keyword Spotting: An Overview. IEEE Access, 10, 4169–4199. https://doi.org/10.1109/ACCESS.2021.3139508
Pereira, P. H., Beccaro, W., & Ramirez, M. A. (2023). Evaluating Robustness to Noise and Compression of Deep Neural Networks for Keyword Spotting. IEEE Access, 11, 53224–53236. https://doi.org/10.1109/ACCESS.2023.3280477
Qi, J., & Tejedor, J. (2022). Classical-To-Quantum Transfer Learning for Spoken Command Recognition Based on Quantum Neural Networks. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 8627–8631. https://doi.org/10.1109/ICASSP43922.2022.9747636
Soltanian, M., Malik, J., Raitoharju, J., Iosifidis, A., Kiranyaz, S., & Gabbouj, M. (2021). Speech Command Recognition in Computationally Constrained Environments with a Quadratic Self-Organized Operational Layer. 2021 International Joint Conference on Neural Networks (IJCNN), 1–6. https://doi.org/10.1109/IJCNN52387.2021.9534232
Waqar, D. M., Gunawan, T. S., Kartiwi, M., & Ahmad, R. (2021). Real-Time Voice-Controlled Game Interaction using Convolutional Neural Networks. In 2021 IEEE 7th International Conference on Smart Instrumentation, Measurement and Applications, ICSIMA 2021 (pp. 76–81). https://doi.org/10.1109/ICSIMA50015.2021.9526318
Wu, J., Huang, Y. (Arden), Park, H.-J., Subrahmanya, N., & Violette, P. (2020). SMALLFOOTPRINTMULTI-CHANNELKEYWORDSPOTTING. Odyssey 2020 The Speaker and Language Recognition Workshop.
Yang, C.-H. H., Li, B., Zhang, Y., Chen, N., Sainath, T. N., & Siniscalchi, S. M. (2023). A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1–5. https://doi.org/10.1109/ICASSP49357.2023.10095142.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Journal of Science, Technology and Innovation Research
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.