Nanomesh-based multi-muscle electromyography artificial throat system assisted by deep learning

IF 4.9 3区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Sensors and Actuators A-physical Pub Date : 2025-09-26 DOI:10.1016/j.sna.2025.117105

Junxin Fu , Lei Song , Juxin Hu , Xinyi Li , Jiahui Li , Minli Peng , Chang Liu , Peiyan Dong , Jingzhi Wu , Jianhua Zhou , Yancong Qiao

{"title":"Nanomesh-based multi-muscle electromyography artificial throat system assisted by deep learning","authors":"Junxin Fu , Lei Song , Juxin Hu , Xinyi Li , Jiahui Li , Minli Peng , Chang Liu , Peiyan Dong , Jingzhi Wu , Jianhua Zhou , Yancong Qiao","doi":"10.1016/j.sna.2025.117105","DOIUrl":null,"url":null,"abstract":"<div><div>Human vocalization relies on precise coordination of multiple muscles, yet existing language assistance devices are often bulky, uncomfortable, and costly. A multi-channel artificial throat system that simultaneously records electromyogram (EMG) signals from the suprahyoid, sternothyroid, and masseter muscles using ultrathin Au nanomesh electrodes has been presented. The nanomesh provides stable, conductive skin contact, increasing signal RMS from 0.3806 mV to 0.6074 mV. An all-flexible interface links the nanomesh to miniaturized circuits, improving wearability and signal integrity. For signal classification, BioSpeechNet, a deep learning framework that achieves over 94 % accuracy in recognizing words and phrases from transient EMG signals was introduced. Analysis reveals the masseter muscle contributes the most discriminative information for speech recognition. This work demonstrates a reliable nanomesh–circuit interface and highlights the potential of multi-muscle EMG for high-precision, wearable speech reconstruction.</div></div>","PeriodicalId":21689,"journal":{"name":"Sensors and Actuators A-physical","volume":"395 ","pages":"Article 117105"},"PeriodicalIF":4.9000,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sensors and Actuators A-physical","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0924424725009112","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

Human vocalization relies on precise coordination of multiple muscles, yet existing language assistance devices are often bulky, uncomfortable, and costly. A multi-channel artificial throat system that simultaneously records electromyogram (EMG) signals from the suprahyoid, sternothyroid, and masseter muscles using ultrathin Au nanomesh electrodes has been presented. The nanomesh provides stable, conductive skin contact, increasing signal RMS from 0.3806 mV to 0.6074 mV. An all-flexible interface links the nanomesh to miniaturized circuits, improving wearability and signal integrity. For signal classification, BioSpeechNet, a deep learning framework that achieves over 94 % accuracy in recognizing words and phrases from transient EMG signals was introduced. Analysis reveals the masseter muscle contributes the most discriminative information for speech recognition. This work demonstrates a reliable nanomesh–circuit interface and highlights the potential of multi-muscle EMG for high-precision, wearable speech reconstruction.

查看原文本刊更多论文

基于纳米网格的深度学习辅助多肌肌电图人工咽喉系统

人类发声依赖于多块肌肉的精确协调，然而现有的语言辅助设备往往笨重、不舒服且昂贵。介绍了一种多通道人工咽喉系统，该系统使用超薄金纳米网电极同时记录舌骨上肌、胸甲状腺肌和咬肌的肌电图信号。纳米网提供稳定的导电皮肤接触，将信号均方根从0.3806 mV增加到0.6074 mV。全柔性接口将纳米网与小型化电路连接起来，提高了可穿戴性和信号完整性。在信号分类方面，介绍了BioSpeechNet，这是一个深度学习框架，从瞬态肌电信号中识别单词和短语的准确率超过94% %。分析表明，咬肌为语音识别提供了最具区别性的信息。这项工作展示了一个可靠的纳米网格电路接口，并强调了多肌肉肌电图在高精度、可穿戴语音重建方面的潜力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Sensors and Actuators A-physical 工程技术-工程：电子与电气

CiteScore

8.10

自引率

6.50%

发文量

630

审稿时长

49 days

期刊介绍： Sensors and Actuators A: Physical brings together multidisciplinary interests in one journal entirely devoted to disseminating information on all aspects of research and development of solid-state devices for transducing physical signals. Sensors and Actuators A: Physical regularly publishes original papers, letters to the Editors and from time to time invited review articles within the following device areas: • Fundamentals and Physics, such as: classification of effects, physical effects, measurement theory, modelling of sensors, measurement standards, measurement errors, units and constants, time and frequency measurement. Modeling papers should bring new modeling techniques to the field and be supported by experimental results. • Materials and their Processing, such as: piezoelectric materials, polymers, metal oxides, III-V and II-VI semiconductors, thick and thin films, optical glass fibres, amorphous, polycrystalline and monocrystalline silicon. • Optoelectronic sensors, such as: photovoltaic diodes, photoconductors, photodiodes, phototransistors, positron-sensitive photodetectors, optoisolators, photodiode arrays, charge-coupled devices, light-emitting diodes, injection lasers and liquid-crystal displays. • Mechanical sensors, such as: metallic, thin-film and semiconductor strain gauges, diffused silicon pressure sensors, silicon accelerometers, solid-state displacement transducers, piezo junction devices, piezoelectric field-effect transducers (PiFETs), tunnel-diode strain sensors, surface acoustic wave devices, silicon micromechanical switches, solid-state flow meters and electronic flow controllers. Etc...