QQ客服 官方微博 反馈留言

	Continuous speech recognition based on the triphone DDBHMM
	You Zhan ; Xiao Xi ; Wang Zuoying
	2010-10-12 ; 2010-10-12
关键词	Practical Theoretical or Mathematical/ hidden Markov models natural language processing speech recognition/ continuous speech recognition triphone DDBHMM hidden Markov model duration distribution-based HMM Chinese language characteristics frame-synchronous recognition algorithm/ B6130E Speech recognition and synthesis B0240J Markov processes C5260S Speech processing techniques C1140J Markov processes C6180N Natural language processing
中文摘要	The HMM (hidden Markov model) is widely used in continuous speech recognition, but the recognition rate can still be improved. This paper presents a triphone DDBHMM (duration distribution-based HMM) recognition method to improve the recognition performance. The triphone used for the continuous speech recognition was designed based on the Chinese language characteristics. MLSS (most likely state sequence) rules are described with a recognition network designed based on the frame-synchronous recognition algorithm. The triphone DDBHMM recognition method gives a 0.91% better recognition rate than the triphone HMM recognition method and 2.29% better rate than the diphone DDBHMM recognition method. Thus, this method significantly improves the recognition performance of continuous speech recognition.
语种	中文
出版者	Tsinghua University Press ; China
内容类型	期刊论文
源URL	[http://hdl.handle.net/123456789/82681]
专题	清华大学
推荐引用方式 GB/T 7714	You Zhan,Xiao Xi,Wang Zuoying. Continuous speech recognition based on the triphone DDBHMM[J],2010, 2010.
APA	You Zhan,Xiao Xi,&Wang Zuoying.(2010).Continuous speech recognition based on the triphone DDBHMM..
MLA	You Zhan,et al."Continuous speech recognition based on the triphone DDBHMM".(2010).

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。