aiqbench analysis
This research demonstrates a novel soft, wearable EMG interface that achieves 97.2% accuracy in silent speech recognition using deep neural networks trained on fingertip-acquired signals. By enabling communication without audible output or constant facial attachment, the system offers a robust solution for privacy-sensitive environments and real-time control applications like drone operation. The work validates the potential of flexible electronics combined with advanced machine learning to create secure, intuitive human-machine interfaces.
Soft Active Electromyography Interface for Machine Learning-Enabled Silent Speech Recognition
arXiv:2608.27048v1 Announce Type: new Abstract: Silent speech recognition (SSR) provides an alternative communication pathway in the absence of audible speech. However, conventional approaches are limited by the need for constant facial attachment, privacy concerns, and unstable signal acquisition. Here, we propose a soft, active electromyography (EMG) interface that enables word-level SSR using machine learning. Worn on the hand, the device uses a fingertip electrode that can be positioned near the lips to acquire EMG signals only when needed. The interface integrates liquid metal (LM) interconnects, transparent flexible printed circuit (FPC) electrodes, and elastomer encapsulation to ensure high mechanical stability during finger motion. A deep neural network trained on these stable signals achieved a mean accuracy of 97.2 $\pm$ 1.3% across three subjects in classifying a 30-word vocabulary, demonstrating robust linguistic discrimination. Furthermore, real-time drone control validates the practicality of this approach in noisy and privacy-sensitive environments where conventional voice recognition fails. This study highlights the potential of soft, wearable EMG systems as secure and intuitive human-machine interfaces.
Abstract:Silent speech recognition (SSR) provides an alternative communication pathway in the absence of audible speech. However, conventional approaches are limited by the need for constant facial attachment, privacy concerns, and unstable signal acquisition. Here, we propose a soft, active electromyography (EMG) interface that enables word-level SSR using machine learning. Worn on the hand, the device uses a fingertip electrode that can be positioned near the lips to acquire EMG signals only when needed. The interface integrates liquid metal (LM) interconnects, transparent flexible printed circuit (FPC) electrodes, and elastomer encapsulation to ensure high mechanical stability during finger motion. A deep neural network trained on these stable signals achieved a mean accuracy of 97.2 $\pm$ 1.3% across three subjects in classifying a 30-word vocabulary, demonstrating robust linguistic discrimination. Furthermore, real-time drone control validates the practicality of this approach in noisy and privacy-sensitive environments where conventional voice recognition fails. This study highlights the potential of soft, wearable EMG systems as secure and intuitive human-machine interfaces.
Machine Learning (cs.LG); Human-Computer Interaction (cs.HC); Sound (cs.SD)
arXiv:2608.27048 [cs.LG]
(or arXiv:2608.27048v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.27048 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1002/aisy.70440 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 271 words
