All-weather, natural silent speech recognition via machine-learning-assisted tattoo-like electronics

Abstract The internal availability of silent speech serves as a translator for people with aphasia and keeps human–machine/human interactions working under various disturbances. This paper develops a silent speech strategy to achieve all-weather, natural interactions. The strategy requires few usage...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Youhua Wang, Tianyi Tang, Yin Xu, Yunzhao Bai, Lang Yin, Guang Li, Hongmiao Zhang, Huicong Liu, YongAn Huang
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
Acceso en línea:https://doaj.org/article/04aea1a7c68a4e439a2bb2346933ef3e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:04aea1a7c68a4e439a2bb2346933ef3e
record_format dspace
spelling oai:doaj.org-article:04aea1a7c68a4e439a2bb2346933ef3e2021-12-02T19:06:36ZAll-weather, natural silent speech recognition via machine-learning-assisted tattoo-like electronics10.1038/s41528-021-00119-72397-4621https://doaj.org/article/04aea1a7c68a4e439a2bb2346933ef3e2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41528-021-00119-7https://doaj.org/toc/2397-4621Abstract The internal availability of silent speech serves as a translator for people with aphasia and keeps human–machine/human interactions working under various disturbances. This paper develops a silent speech strategy to achieve all-weather, natural interactions. The strategy requires few usage specialized skills like sign language but accurately transfers high-capacity information in complicated and changeable daily environments. In the strategy, the tattoo-like electronics imperceptibly attached on facial skin record high-quality bio-data of various silent speech, and the machine-learning algorithm deployed on the cloud recognizes accurately the silent speech and reduces the weight of the wireless acquisition module. A series of experiments show that the silent speech recognition system (SSRS) can enduringly comply with large deformation (~45%) of faces by virtue of the electricity-preferred tattoo-like electrodes and recognize up to 110 words covering daily vocabularies with a high average accuracy of 92.64% simply by use of small-sample machine learning. We successfully apply the SSRS to 1-day routine life, including daily greeting, running, dining, manipulating industrial robots in deafening noise, and expressing in darkness, which shows great promotion in real-world applications.Youhua WangTianyi TangYin XuYunzhao BaiLang YinGuang LiHongmiao ZhangHuicong LiuYongAn HuangNature PortfolioarticleElectronicsTK7800-8360Materials of engineering and construction. Mechanics of materialsTA401-492ENnpj Flexible Electronics, Vol 5, Iss 1, Pp 1-9 (2021)
institution DOAJ
collection DOAJ
language EN
topic Electronics
TK7800-8360
Materials of engineering and construction. Mechanics of materials
TA401-492
spellingShingle Electronics
TK7800-8360
Materials of engineering and construction. Mechanics of materials
TA401-492
Youhua Wang
Tianyi Tang
Yin Xu
Yunzhao Bai
Lang Yin
Guang Li
Hongmiao Zhang
Huicong Liu
YongAn Huang
All-weather, natural silent speech recognition via machine-learning-assisted tattoo-like electronics
description Abstract The internal availability of silent speech serves as a translator for people with aphasia and keeps human–machine/human interactions working under various disturbances. This paper develops a silent speech strategy to achieve all-weather, natural interactions. The strategy requires few usage specialized skills like sign language but accurately transfers high-capacity information in complicated and changeable daily environments. In the strategy, the tattoo-like electronics imperceptibly attached on facial skin record high-quality bio-data of various silent speech, and the machine-learning algorithm deployed on the cloud recognizes accurately the silent speech and reduces the weight of the wireless acquisition module. A series of experiments show that the silent speech recognition system (SSRS) can enduringly comply with large deformation (~45%) of faces by virtue of the electricity-preferred tattoo-like electrodes and recognize up to 110 words covering daily vocabularies with a high average accuracy of 92.64% simply by use of small-sample machine learning. We successfully apply the SSRS to 1-day routine life, including daily greeting, running, dining, manipulating industrial robots in deafening noise, and expressing in darkness, which shows great promotion in real-world applications.
format article
author Youhua Wang
Tianyi Tang
Yin Xu
Yunzhao Bai
Lang Yin
Guang Li
Hongmiao Zhang
Huicong Liu
YongAn Huang
author_facet Youhua Wang
Tianyi Tang
Yin Xu
Yunzhao Bai
Lang Yin
Guang Li
Hongmiao Zhang
Huicong Liu
YongAn Huang
author_sort Youhua Wang
title All-weather, natural silent speech recognition via machine-learning-assisted tattoo-like electronics
title_short All-weather, natural silent speech recognition via machine-learning-assisted tattoo-like electronics
title_full All-weather, natural silent speech recognition via machine-learning-assisted tattoo-like electronics
title_fullStr All-weather, natural silent speech recognition via machine-learning-assisted tattoo-like electronics
title_full_unstemmed All-weather, natural silent speech recognition via machine-learning-assisted tattoo-like electronics
title_sort all-weather, natural silent speech recognition via machine-learning-assisted tattoo-like electronics
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/04aea1a7c68a4e439a2bb2346933ef3e
work_keys_str_mv AT youhuawang allweathernaturalsilentspeechrecognitionviamachinelearningassistedtattoolikeelectronics
AT tianyitang allweathernaturalsilentspeechrecognitionviamachinelearningassistedtattoolikeelectronics
AT yinxu allweathernaturalsilentspeechrecognitionviamachinelearningassistedtattoolikeelectronics
AT yunzhaobai allweathernaturalsilentspeechrecognitionviamachinelearningassistedtattoolikeelectronics
AT langyin allweathernaturalsilentspeechrecognitionviamachinelearningassistedtattoolikeelectronics
AT guangli allweathernaturalsilentspeechrecognitionviamachinelearningassistedtattoolikeelectronics
AT hongmiaozhang allweathernaturalsilentspeechrecognitionviamachinelearningassistedtattoolikeelectronics
AT huicongliu allweathernaturalsilentspeechrecognitionviamachinelearningassistedtattoolikeelectronics
AT yonganhuang allweathernaturalsilentspeechrecognitionviamachinelearningassistedtattoolikeelectronics
_version_ 1718377127464665088