Visual features extracting & selecting for lipreading

	Visual features extracting & selecting for lipreading
	Yao, HX ; Gao, W ; Shan, W ; Xu, MH
	2003
发表期刊	AUDIO-AND VIDEO-BASED BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS
ISSN	0302-9743
卷号	2688 页码:251-259
摘要	This paper has put forward a way to select and extract visual features effectively for lipreading. These features come from both low-level and high-level, those are compensatory each other. There are 41 dimensional features to be used for recognition. Tested on a bimodal database AVCC which consists of sentences including all Chinese pronunciation, it achieves an accuracy of 87.8% from 84.1% for automatic speech recognition by lipreading assisting. It improves 19.5% accuracy from 31.7% to 51.2% for speakers dependent and improves 27.7% accuracy from 27.6% to 55.3% for speakers independent when speech recognition under noise conditions. And the paper has proves that visual speech information can reinforce the loss of acoustic information effectively by improving recognition rate from 10% to 30% various with the different amount of noises in speech signals in our system, the improving scope is higher than ASR system of IBM. And it performs better in noisy environments.
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Imaging Science & Photographic Technology
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Imaging Science & Photographic Technology
WOS记录号	WOS:000184940200030
出版者	SPRINGER-VERLAG BERLIN
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/13689
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yao, HX
作者单位	1.Harbin Inst Technol, Dept Comp Sci & Engn, Harbin 150001, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Yao, HX,Gao, W,Shan, W,et al. Visual features extracting & selecting for lipreading[J]. AUDIO-AND VIDEO-BASED BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS,2003,2688:251-259.
APA	Yao, HX,Gao, W,Shan, W,&Xu, MH.(2003).Visual features extracting & selecting for lipreading.AUDIO-AND VIDEO-BASED BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS,2688,251-259.
MLA	Yao, HX,et al."Visual features extracting & selecting for lipreading".AUDIO-AND VIDEO-BASED BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS 2688(2003):251-259.