Decoding lip language using triboelectric sensors with deep learning

doi:10.1038/s41467-022-29083-0

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Decoding lip language using triboelectric sensors with deep learning
	Lu, Yijia 1; Tian, Han 1; Cheng, Jia 1; Zhu, Fei 2; Liu, Bin 1; Wei, Shanshan 1; Ji, Linhong 1; Wang, Zhong Lin 3,4,5
发表期刊	NATURE COMMUNICATIONS
	2022-03-17
卷号	13 期号:1 页码:12
通讯作者	Wang, Zhong Lin(zhong.wang@mse.gatech.edu)
摘要	Lip-language decoding systems are a promising technology to help people lacking a voice live a convenient life with barrier-free communication. Here, authors propose a concept of such system integrating self-powered triboelectric sensors and a well-trained dilated RNN model based on prototype learning. Lip language is an effective method of voice-off communication in daily life for people with vocal cord lesions and laryngeal and lingual injuries without occupying the hands. Collection and interpretation of lip language is challenging. Here, we propose the concept of a novel lip-language decoding system with self-powered, low-cost, contact and flexible triboelectric sensors and a well-trained dilated recurrent neural network model based on prototype learning. The structural principle and electrical properties of the flexible sensors are measured and analysed. Lip motions for selected vowels, words, phrases, silent speech and voice speech are collected and compared. The prototype learning model reaches a test accuracy of 94.5% in training 20 classes with 100 samples each. The applications, such as identity recognition to unlock a gate, directional control of a toy car and lip-motion to speech conversion, work well and demonstrate great feasibility and potential. Our work presents a promising way to help people lacking a voice live a convenient life with barrier-free communication and boost their happiness, enriches the diversity of lip-language translation systems and will have potential value in many applications.
DOI	10.1038/s41467-022-29083-0
关键词[WOS]	NANOGENERATORS ; RECOGNITION
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[51975318] ; National Key Research and Development Program of China[2018YFF0300606]
项目资助者	National Natural Science Foundation of China ; National Key Research and Development Program of China
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:000770426200024
出版者	NATURE PORTFOLIO
引用统计	被引频次：83[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/48097
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	Wang, Zhong Lin
作者单位	1.Tsinghua Univ, Dept Mech Engn, State Key Lab Tribol, Beijing 100084, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Beijing Inst Nanoenergy & Nanosyst, Beijing 101400, Peoples R China 4.Univ Chinese Acad Sci, Sch Nanosci & Technol, Beijing 100049, Peoples R China 5.Georgia Inst Technol, Sch Mat Sci & Engn, Atlanta, GA 30332 USA
推荐引用方式 GB/T 7714	Lu, Yijia,Tian, Han,Cheng, Jia,et al. Decoding lip language using triboelectric sensors with deep learning[J]. NATURE COMMUNICATIONS,2022,13(1):12.
APA	Lu, Yijia.,Tian, Han.,Cheng, Jia.,Zhu, Fei.,Liu, Bin.,...&Wang, Zhong Lin.(2022).Decoding lip language using triboelectric sensors with deep learning.NATURE COMMUNICATIONS,13(1),12.
MLA	Lu, Yijia,et al."Decoding lip language using triboelectric sensors with deep learning".NATURE COMMUNICATIONS 13.1(2022):12.