EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Wireless Silent Speech Interface Using Multichannel Textile EMG Sensors Integrated Into Headphones

Chenyu Tang, Josée Mallah, Dominika Kazieczko, Wentian Yi, Tharun Reddy Kandukuri, Edoardo Occhipinti, Bhaskar Mishra, Sunita Mehta, Luigi G. Occhipinti

IEEE Transactions on Instrumentation and Measurement · 2025 · 74 · 1-10

DOI: 10.1109/tim.2025.3583386 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2025. Verfasst von Chenyu Tang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UK-India Education and Research Initiative (UKIERI), British Council UK, Scheme for Promotion of Academic and Research Collaboration (SPARC), Ministry of Education, Government of India, coordinated by Indian Institute of Technology…, Edoardo Occhipinti waas supported in part by the UKRI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article presents a novel wireless silent speech interface (SSI) integrating multichannel textile-based electromyography (EMG) electrodes into headphone earmuff for real-time, hands-free communication. Unlike conventional patch-based EMG systems, which require large-area electrodes on the face or neck, our approach ensures comfort, discretion, and wearability while maintaining robust silent speech decoding. The system utilizes four graphene/PEDOT:PSS-coated textile electrodes to capture speech-related neuromuscular activity, with signals processed via a compact ESP32-S3-based wireless readout module. To address the challenge of variable skin-electrode coupling, we propose a 1-D SE-ResNet architecture incorporating squeeze-and-excitation (SE) blocks to dynamically adjust per-channel attention weights, enhancing robustness against motion-induced impedance variations. The proposed system achieves 96% accuracy on ten commonly used voice-free control words, outperforming conventional single-channel and nonadaptive baselines. Experimental validation, including explainable AI (XAI)-based attention analysis and t-SNE feature visualization, confirms the adaptive channel selection capability and effective feature extraction of the model. This work advances wearable EMG-based SSIs, demonstrating a scalable, low-power, and user-friendly platform for silent communication, assistive technologies, and human–computer interaction.

Förderung

  • UK-India Education and Research Initiative (UKIERI), British Council UK
  • Scheme for Promotion of Academic and Research Collaboration (SPARC), Ministry of Education, Government of India, coordinated by Indian Institute of Technology…
  • Edoardo Occhipinti waas supported in part by the UKRI
  • Chan Zuckerberg Initiative DAF
  • Wellcome Trust

Zitieren

APA

Tang, C., Mallah, J., Kazieczko, D., Yi, W., Kandukuri, T. R., Occhipinti, E., Mishra, B., Mehta, S., & Occhipinti, L. G. (2025). Wireless Silent Speech Interface Using Multichannel Textile EMG Sensors Integrated Into Headphones. IEEE Transactions on Instrumentation and Measurement, 74, 1-10. https://doi.org/10.1109/tim.2025.3583386

Vancouver

Tang C, Mallah J, Kazieczko D, Yi W, Kandukuri TR, Occhipinti E, et al. Wireless Silent Speech Interface Using Multichannel Textile EMG Sensors Integrated Into Headphones. IEEE Transactions on Instrumentation and Measurement. 2025;74:1-10. doi:10.1109/tim.2025.3583386

BibTeX
@article{Tang2025,
  author = {Tang, Chenyu and Mallah, Josée and Kazieczko, Dominika and Yi, Wentian and Kandukuri, Tharun Reddy and Occhipinti, Edoardo and Mishra, Bhaskar and Mehta, Sunita and Occhipinti, Luigi G.},
  title = {Wireless Silent Speech Interface Using Multichannel Textile EMG Sensors Integrated Into Headphones},
  journal = {IEEE Transactions on Instrumentation and Measurement},
  year = {2025},
  volume = {74},
  pages = {1--10},
  doi = {10.1109/tim.2025.3583386}
}
Kostenlos starten →