首页 | 本学科首页   官方微博 | 高级检索  
     

基于元音检测的汉语连续语音端点检测方法
引用本文:张利平,冯宏伟,王艳. 基于元音检测的汉语连续语音端点检测方法[J]. 计算机工程与应用, 2010, 46(27): 114-116. DOI: 10.3778/j.issn.1002-8331.2010.27.031
作者姓名:张利平  冯宏伟  王艳
作者单位:西北大学 信息科学与技术学院,西安 710127
基金项目:国家高技术研究发展计划(863) 
摘    要:在汉语连续语音识别中,准确检测出音节的始点和终点是很重要的一步,传统的端点检测方法在非连续语音中检测准确度很高,但在连续语音中检测准确度会大幅度降低。利用MFCC0参数和汉语元音的共振峰能量设计了一种新的端点检测方法,可以准确检测出汉语连续语音中的音节端点。实验结果表明:这种端点检测方法在低信噪比下也有很高的检测正确率。

关 键 词:连续语音识别  端点检测  美尔频标倒谱系数(MFCC)  共振峰
收稿时间:2009-06-23
修稿时间:2009-9-16 

Chinese continuous speech endpoint detection method based on vowel detection
ZHANG Li-ping,FENG Hong-wei,WANG Yan. Chinese continuous speech endpoint detection method based on vowel detection[J]. Computer Engineering and Applications, 2010, 46(27): 114-116. DOI: 10.3778/j.issn.1002-8331.2010.27.031
Authors:ZHANG Li-ping  FENG Hong-wei  WANG Yan
Affiliation:College of Information Science and Technology,Northwest University,Xi’an 710127,China
Abstract:Accurate detection for the start and end point of syllable is a very important step in Chinese continuous speech recognition.Traditional endpoint detection methods achieve high rate of success in non-continuous speech,but fall in cOntinuous speech.In this paper, a new method based on MFCC0 and the formant energy of Chinese vowels is proposed,which can accurately detect the start and end point of syllable.The results of experiments show that this method achieve high rate of success even in low SNR.
Keywords:continuous speech recognition  endpoint detection  mel frequency cepstrum coefficient  formant
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号