Biomimetic pattern recognition for speaker-independent speech recognition

SEMI OpenIR > 中国科学院半导体研究所（2009年前）

	Biomimetic pattern recognition for speaker-independent speech recognition
	Qin, H; Wang, SJ; Sun, H; Qin, H, Chinese Acad Sci, Inst Semicond, Lab Artificial Neural Networks, Beijing 100083, Peoples R China.
	2005
会议名称	International Conference on Neural Networks and Brain (ICNN&B 2005)
会议录名称	Proceedings of the 2005 International Conference on Neural Networks and Brain
页码	Vols 1-3: 1290-1294
会议日期	OCT 13-15, 2005
会议地点	Beijing, PEOPLES R CHINA
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
出版者	IEEE
ISBN	0-7803-9422-4
部门归属	chinese acad sci, inst semicond, lab artificial neural networks, beijing 100083, peoples r china
摘要	In speaker-independent speech recognition, the disadvantage of the most diffused technology ( 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 Speech in a speaker-independent manner. The vocabulary of the system consists of 15 Chinese dish's names. Neural networks based on Multi-Weight Neuron (MWN) model are used to train and recognize the speech sounds. Experimental results are presented to show that the system, which can carry out real time recognition of the persons from different provinces speaking common Chinese speech, outperforms HMMs especially in the cases of samples of a finite size.
关键词	Speech Recognition Biomimetic Pattern Recognition Hidden Markov Models Dynamic Time Warping
学科领域	人工智能
主办者	China Neural Networks Council.; IEEE Computat Intelligence Soc, Beijing Chapter.; Chinese Inst Elect.; Chinese Assoc Artificial Intelligence.
收录类别	CPCI-S
语种	英语
文献类型	会议论文
条目标识符	http://ir.semi.ac.cn/handle/172111/9946
专题	中国科学院半导体研究所（2009年前）
通讯作者	Qin, H, Chinese Acad Sci, Inst Semicond, Lab Artificial Neural Networks, Beijing 100083, Peoples R China.
推荐引用方式 GB/T 7714	Qin, H,Wang, SJ,Sun, H,et al. Biomimetic pattern recognition for speaker-independent speech recognition[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2005:Vols 1-3: 1290-1294.

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
2355.pdf（1913KB）			限制开放	--	请求全文