Unsupervised adaptive sign language recognition based on hypothesis comparison guided cross validation and linguistic prior filtering

doi:10.1016/j.neucom.2014.08.032

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Unsupervised adaptive sign language recognition based on hypothesis comparison guided cross validation and linguistic prior filtering
	Zhou, Yu 2; Yang, Xiaokang 1; Zhang, Yongzheng 2; Xu, Xiang 2; Wang, Yipeng 2; Chai, Xiujuan 3; Lin, Weiyao 1
刊名	NEUROCOMPUTING
	2015-02-03
卷号	149 页码:1604-1612
关键词	Signer adaptation Cross validation Unsupervised learning Sign language recognition
ISSN号	0925-2312
DOI	10.1016/j.neucom.2014.08.032
英文摘要	Signer adaptation is important for sign language recognition systems because a fixed system cannot perform well on all kinds of signers. In supervised signer adaptation, the labeled adaptation data must be collected explicitly. To skip the data collecting process in signer adaptation, we propose a novel unsupervised adaptation method, namely the hypothesis comparison guided cross validation method. The method not only addresses the problem of the overlap between the data set to be labeled and the data set for adaptation, but also employs an additional hypothesis comparison step to decrease the noise rate of the adaptation data set. We also utilize linguistic prior knowledge to down sample the adaptation data list to further decrease the noise rate. To evaluate the effectiveness of the proposed method, the CASIIE-SL-Database is formed, which is the first specialized data set for unsupervised signer adaptation to the best of our knowledge. Experimental results show that the proposed method can achieve relative word error rate reductions of 3.93% and 4.05% respectively compared with self-teaching method and cross validation method. Though the method is proposed for signer adaptation, it can also be applied to speaker adaptation and writer adaptation directly. (C) 2014 Elsevier B.V. All rights reserved.
资助项目	National Natural Science Foundation of China[61303170] ; National Natural Science Foundation of China[61402472] ; National Natural Science Foundation of China[61303261] ; National Natural Science Foundation of China[61471235] ; National High Technology Research and Development Program of China (863 programs)[2013AA014703] ; National High Technology Research and Development Program of China (863 programs)[2012AA012803]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER SCIENCE BV
WOS记录号	WOS:000356105100049
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/9671]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Yongzheng
作者单位	1.Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai 200030, Peoples R China 2.Chinese Acad Sci, Inst Informat Engn, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Yu,Yang, Xiaokang,Zhang, Yongzheng,et al. Unsupervised adaptive sign language recognition based on hypothesis comparison guided cross validation and linguistic prior filtering[J]. NEUROCOMPUTING,2015,149:1604-1612.
APA	Zhou, Yu.,Yang, Xiaokang.,Zhang, Yongzheng.,Xu, Xiang.,Wang, Yipeng.,...&Lin, Weiyao.(2015).Unsupervised adaptive sign language recognition based on hypothesis comparison guided cross validation and linguistic prior filtering.NEUROCOMPUTING,149,1604-1612.
MLA	Zhou, Yu,et al."Unsupervised adaptive sign language recognition based on hypothesis comparison guided cross validation and linguistic prior filtering".NEUROCOMPUTING 149(2015):1604-1612.