Digits speech recognition based on geometrical learning

CORC > 半导体研究所 > 中国科学院半导体研究所 > 中国科学院半导体研究所（2009年前）

	Digits speech recognition based on geometrical learning
	Cao WM ; Pan XX ; Wang SJ ; Hu J
刊名	advanced data mining and applications
	2005
卷号	proceedings 3584 期号:0 页码:415-422
ISSN号	0302-9743
通讯作者	cao, wm, zhejiang univ tech, informat coll, inst intelligent informat syst, hangzhou 310032, peoples r china. 电子邮箱地址: csann@zjut.edu.cn
中文摘要	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 a 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 via the hilbert transform. 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 method based on ica and geometrical learning outperforms hmm in different number of train samples.
学科主题	人工智能
收录类别	SCI
语种	英语
公开日期	2010-03-17
内容类型	期刊论文
源URL	[http://ir.semi.ac.cn/handle/172111/8546]
专题	半导体研究所_中国科学院半导体研究所（2009年前）
推荐引用方式 GB/T 7714	Cao WM,Pan XX,Wang SJ,et al. Digits speech recognition based on geometrical learning[J]. advanced data mining and applications,2005,proceedings 3584(0):415-422.
APA	Cao WM,Pan XX,Wang SJ,&Hu J.(2005).Digits speech recognition based on geometrical learning.advanced data mining and applications,proceedings 3584(0),415-422.
MLA	Cao WM,et al."Digits speech recognition based on geometrical learning".advanced data mining and applications proceedings 3584.0(2005):415-422.