Machine learning-assisted wearable sensing systems for speech recognition and interaction

Abstract The human voice stands out for its rich information transmission capabilities. However, voice communication is susceptible to interference from noisy environments and obstacles. Here, we propose a wearable wireless flexible skin-attached acoustic sensor (SAAS) capable of capturing the vibra...

Full description

Saved in:
Bibliographic Details
Main Authors: Tao Liu, Mingyang Zhang, Zhihao Li, Hanjie Dou, Wangyang Zhang, Jiaqian Yang, Pengfan Wu, Dongxiao Li, Xiaojing Mu
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-57629-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850040173981597696
author Tao Liu
Mingyang Zhang
Zhihao Li
Hanjie Dou
Wangyang Zhang
Jiaqian Yang
Pengfan Wu
Dongxiao Li
Xiaojing Mu
author_facet Tao Liu
Mingyang Zhang
Zhihao Li
Hanjie Dou
Wangyang Zhang
Jiaqian Yang
Pengfan Wu
Dongxiao Li
Xiaojing Mu
author_sort Tao Liu
collection DOAJ
description Abstract The human voice stands out for its rich information transmission capabilities. However, voice communication is susceptible to interference from noisy environments and obstacles. Here, we propose a wearable wireless flexible skin-attached acoustic sensor (SAAS) capable of capturing the vibrations of vocal organs and skin movements, thereby enabling voice recognition and human-machine interaction (HMI) in harsh acoustic environments. This system utilizes a piezoelectric micromachined ultrasonic transducers (PMUT), which feature high sensitivity (-198 dB), wide bandwidth (10 Hz-20 kHz), and excellent flatness (±0.5 dB). Flexible packaging enhances comfort and adaptability during wear, while integration with the Residual Network (ResNet) architecture significantly improves the classification of laryngeal speech features, achieving an accuracy exceeding 96%. Furthermore, we also demonstrated SAAS’s data collection and intelligent classification capabilities in multiple HMI scenarios. Finally, the speech recognition system was able to recognize everyday sentences spoken by participants with an accuracy of 99.8% through a deep learning model. With advantages including a simple fabrication process, stable performance, easy integration, and low cost, SAAS presents a compelling solution for applications in voice control, HMI, and wearable electronics.
format Article
id doaj-art-9ab9c3ef1b304bc6852d57cd7f2d6ab5
institution DOAJ
issn 2041-1723
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-9ab9c3ef1b304bc6852d57cd7f2d6ab52025-08-20T02:56:09ZengNature PortfolioNature Communications2041-17232025-03-0116111310.1038/s41467-025-57629-5Machine learning-assisted wearable sensing systems for speech recognition and interactionTao Liu0Mingyang Zhang1Zhihao Li2Hanjie Dou3Wangyang Zhang4Jiaqian Yang5Pengfan Wu6Dongxiao Li7Xiaojing Mu8Key Laboratory of Optoelectronic Technology & Systems of Ministry of Education, International R & D Center of Micro-nano Systems and New Materials Technology, Chongqing UniversityKey Laboratory of Optoelectronic Technology & Systems of Ministry of Education, International R & D Center of Micro-nano Systems and New Materials Technology, Chongqing UniversityKey Laboratory of Optoelectronic Technology & Systems of Ministry of Education, International R & D Center of Micro-nano Systems and New Materials Technology, Chongqing UniversityKey Laboratory of Optoelectronic Technology & Systems of Ministry of Education, International R & D Center of Micro-nano Systems and New Materials Technology, Chongqing UniversityKey Laboratory of Optoelectronic Technology & Systems of Ministry of Education, International R & D Center of Micro-nano Systems and New Materials Technology, Chongqing UniversityKey Laboratory of Optoelectronic Technology & Systems of Ministry of Education, International R & D Center of Micro-nano Systems and New Materials Technology, Chongqing UniversityKey Laboratory of Optoelectronic Technology & Systems of Ministry of Education, International R & D Center of Micro-nano Systems and New Materials Technology, Chongqing UniversityKey Laboratory of Optoelectronic Technology & Systems of Ministry of Education, International R & D Center of Micro-nano Systems and New Materials Technology, Chongqing UniversityKey Laboratory of Optoelectronic Technology & Systems of Ministry of Education, International R & D Center of Micro-nano Systems and New Materials Technology, Chongqing UniversityAbstract The human voice stands out for its rich information transmission capabilities. However, voice communication is susceptible to interference from noisy environments and obstacles. Here, we propose a wearable wireless flexible skin-attached acoustic sensor (SAAS) capable of capturing the vibrations of vocal organs and skin movements, thereby enabling voice recognition and human-machine interaction (HMI) in harsh acoustic environments. This system utilizes a piezoelectric micromachined ultrasonic transducers (PMUT), which feature high sensitivity (-198 dB), wide bandwidth (10 Hz-20 kHz), and excellent flatness (±0.5 dB). Flexible packaging enhances comfort and adaptability during wear, while integration with the Residual Network (ResNet) architecture significantly improves the classification of laryngeal speech features, achieving an accuracy exceeding 96%. Furthermore, we also demonstrated SAAS’s data collection and intelligent classification capabilities in multiple HMI scenarios. Finally, the speech recognition system was able to recognize everyday sentences spoken by participants with an accuracy of 99.8% through a deep learning model. With advantages including a simple fabrication process, stable performance, easy integration, and low cost, SAAS presents a compelling solution for applications in voice control, HMI, and wearable electronics.https://doi.org/10.1038/s41467-025-57629-5
spellingShingle Tao Liu
Mingyang Zhang
Zhihao Li
Hanjie Dou
Wangyang Zhang
Jiaqian Yang
Pengfan Wu
Dongxiao Li
Xiaojing Mu
Machine learning-assisted wearable sensing systems for speech recognition and interaction
Nature Communications
title Machine learning-assisted wearable sensing systems for speech recognition and interaction
title_full Machine learning-assisted wearable sensing systems for speech recognition and interaction
title_fullStr Machine learning-assisted wearable sensing systems for speech recognition and interaction
title_full_unstemmed Machine learning-assisted wearable sensing systems for speech recognition and interaction
title_short Machine learning-assisted wearable sensing systems for speech recognition and interaction
title_sort machine learning assisted wearable sensing systems for speech recognition and interaction
url https://doi.org/10.1038/s41467-025-57629-5
work_keys_str_mv AT taoliu machinelearningassistedwearablesensingsystemsforspeechrecognitionandinteraction
AT mingyangzhang machinelearningassistedwearablesensingsystemsforspeechrecognitionandinteraction
AT zhihaoli machinelearningassistedwearablesensingsystemsforspeechrecognitionandinteraction
AT hanjiedou machinelearningassistedwearablesensingsystemsforspeechrecognitionandinteraction
AT wangyangzhang machinelearningassistedwearablesensingsystemsforspeechrecognitionandinteraction
AT jiaqianyang machinelearningassistedwearablesensingsystemsforspeechrecognitionandinteraction
AT pengfanwu machinelearningassistedwearablesensingsystemsforspeechrecognitionandinteraction
AT dongxiaoli machinelearningassistedwearablesensingsystemsforspeechrecognitionandinteraction
AT xiaojingmu machinelearningassistedwearablesensingsystemsforspeechrecognitionandinteraction