A speaker-independent continuous speech recognition system using biomimetic pattern recognition

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）

	A speaker-independent continuous speech recognition system using biomimetic pattern recognition
	Wang SJ (Wang Shoujue) ; Qin H (Qin Hong)
刊名	chinese journal of electronics
	2006
卷号	15 期号:3 页码:460-462
关键词	biomimetic pattern recognition speech recognition hidden Markov models (HMMs) dynamic time warping (DTW)
ISSN号	1022-4653
通讯作者	wang, sj, chinese acad sci, inst semicond, lab artificial neural networks, beijing 100083, peoples r china. e-mail: wsjue@red.semi.ac.cn ; qinh@red.semi.ac.cn
中文摘要	in speaker-independent speech recognition, the disadvantage of the most diffused technology (hmms, or hidden markov models) is not only the need of many more training samples, but also long train time requirement. this paper describes the use of biomimetic pattern recognition (bpr) in recognizing some mandarin continuous speech in a speaker-independent manner. a speech database was developed for the course of study. the vocabulary of the database consists of 15 chinese dish's names, the length of each name is 4 chinese words. neural networks (nns) based on multi-weight neuron (mwn) model are used to train and recognize the speech sounds. the number of mwn was investigated to achieve the optimal performance of the nns-based bpr. this system, which is based on bpr and can carry out real time recognition reaches a recognition rate of 98.14% for the first option and 99.81% for the first two options to the persons from different provinces of china speaking common chinese speech. experiments were also carried on to evaluate continuous density hidden markov models (cdhmm), dynamic time warping (dtw) and bpr for speech recognition. the experiment results show that bpr outperforms cdhmm and dtw especially in the cases of samples of a finite size.
学科主题	人工智能
收录类别	SCI
语种	英语
公开日期	2010-04-11
内容类型	期刊论文
源URL	[http://ir.semi.ac.cn/handle/172111/10518]
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	Wang SJ ,Qin H . A speaker-independent continuous speech recognition system using biomimetic pattern recognition[J]. chinese journal of electronics,2006,15(3):460-462.
APA	Wang SJ ,&Qin H .(2006).A speaker-independent continuous speech recognition system using biomimetic pattern recognition.chinese journal of electronics,15(3),460-462.
MLA	Wang SJ ,et al."A speaker-independent continuous speech recognition system using biomimetic pattern recognition".chinese journal of electronics 15.3(2006):460-462.