QQ客服 官方微博 反馈留言

	Exponential threshold based speech endpoint detection method
	Wu Feng-liang ; Wu Ji ; Wang Zuo-ying
	2010-05-06 ; 2010-05-06
关键词	Theoretical or Mathematical Experimental/ probability speech processing/ exponential threshold based speech endpoint detection probability density function speech recognition voice activity detection exponential threshold/ B6130 Speech and audio signal processing B0240Z Other topics in statistics C5260S Speech processing techniques C1250C Speech recognition C1140Z Other topics in statistics
中文摘要	A new endpoint detection method based on the exponential threshold (ET) is proposed. The probability density function (PDF) of the short-time energy is investigated, and a new consistent mathematical model is built up for the speech and the noise. Then, an optimal detection threshold exponential formula is concluded. Experimental evaluations on "863" program of China across a wide range of SNRs are given. Results show that when the SNR is 0 dB, the accuracy achieves 89. 5%, and when the SNR is 0-15 dB, the ET method has good performances than the basic energy, the logarithmic energy clustering (LEG) and X/sup 2/ methods.
语种	中文 ; 中文
出版者	Nanjing Univ. of Aeronautics & Astronautics ; China
内容类型	期刊论文
源URL	[http://hdl.handle.net/123456789/10571]
专题	清华大学
推荐引用方式 GB/T 7714	Wu Feng-liang,Wu Ji,Wang Zuo-ying. Exponential threshold based speech endpoint detection method[J],2010, 2010.
APA	Wu Feng-liang,Wu Ji,&Wang Zuo-ying.(2010).Exponential threshold based speech endpoint detection method..
MLA	Wu Feng-liang,et al."Exponential threshold based speech endpoint detection method".(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。