Continuous speech recognition based on ICA and geometrical learning

SEMI OpenIR > 中国科学院半导体研究所（2009年前）

	Continuous speech recognition based on ICA and geometrical learning
	Feng H (Feng Hao); Cao WM (Cao Wenming); Wang SJ (Wang Shoujue); Feng, H, Zhejiang Univ Technol, Informat Coll, Inst Intelligent Informat Syst, Hangzhou 310032, Peoples R China. 电子邮箱地址: zjhzfh@mail.zjxu.edu.cn
	2006
会议名称	4th International Conference on Machine Learning and Cybernetics
会议录名称	ADVANCES IN MACHINE LEARNING AND CYBERNETICS丛书标题: LECTURE NOTES IN ARTIFICIAL INTELLIGENCE
页码	3930: 974-983
会议日期	AUG 18-21, 2005
会议地点	Guangzhou, PEOPLES R CHINA
出版地	HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY
出版者	SPRINGER-VERLAG BERLIN
ISSN	0302-9743
ISBN	3-540-33584-6
部门归属	zhejiang univ technol, informat coll, inst intelligent informat syst, hangzhou 310032, peoples r china; chinese acad sci, inst semicond, beijing 100083, peoples r china
摘要	We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.
关键词	Multi-weighted Neuron
学科领域	人工智能
主办者	IEEE Systems, Man & Cybernet TCC.; Hong Kong Polytechn Univ.; Hebei Univ.; S China Univ Technol.; Chongqing Univ.; Sun Yatsen Univ.; Harbin Inst Technol.; Int Univ Germany.
收录类别	其他
语种	英语
文献类型	会议论文
条目标识符	http://ir.semi.ac.cn/handle/172111/9990
专题	中国科学院半导体研究所（2009年前）
通讯作者	Feng, H, Zhejiang Univ Technol, Informat Coll, Inst Intelligent Informat Syst, Hangzhou 310032, Peoples R China. 电子邮箱地址: zjhzfh@mail.zjxu.edu.cn
推荐引用方式 GB/T 7714	Feng H ,Cao WM ,Wang SJ ,et al. Continuous speech recognition based on ICA and geometrical learning[C]. HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY:SPRINGER-VERLAG BERLIN,2006:3930: 974-983.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2378.pdf（248KB）			限制开放	--	请求全文