AI 中文总结
本文提出一种柔性主动肌电接口，结合机器学习实现词级无声语音识别，在30词词汇分类中达97.2±1.3%平均准确率，可用于嘈杂隐私敏感环境的无人机控制。
AI 中文摘要
无声语音识别（SSR）在无法发出可听语音时提供了一种替代通信途径。然而，传统方法受限于需持续附着于面部、隐私问题及信号采集不稳定的缺陷。本文提出一种柔性主动肌电（EMG）接口，可利用机器学习实现词级无声语音识别。该设备佩戴于手部，采用指尖电极，可定位在嘴唇附近仅在需要时采集EMG信号；集成液态金属（LM）互连、透明柔性印刷电路（FPC）电极及弹性体封装，确保手指运动时的高机械稳定性。基于这些稳定信号训练的深度神经网络，对30个词汇表进行分类时，三名受试者的平均准确率达97.2±1.3%，展现出强大的语言区分能力。此外，实时无人机控制验证了该方法在传统语音识别失效的嘈杂及隐私敏感环境中的实用性，本研究凸显了柔性可穿戴EMG系统作为安全直观人机接口的潜力。
英文摘要
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.
Comments17 pages, 5 figures, supplementary information
Journal refAdvanced Intelligent Systems 2026, 0, e70440
