首页 | 本学科首页   官方微博 | 高级检索  
     检索      

语音识别中基于MCE准则的CHMM学习方法
引用本文:赵力,邹采荣,吴镇扬.语音识别中基于MCE准则的CHMM学习方法[J].东南大学学报(自然科学版),2000,30(3):21-25.
作者姓名:赵力  邹采荣  吴镇扬
作者单位:东南大学无线电工程系,南京,210096
基金项目:国家自然科学资金资助项目! (69871 0 0 9)
摘    要:研究了用于CHMM的MCE学习方法,提出了简单形式的识别函数、误差函数、扣池数等的定义方法以及总损失函数的最小化方法。通过对非特定人汉语连续语音识别实验,证明了提出了的函数形式和损失函数最小化方法对CHMM的MCE学习的有效性。

关 键 词:语音识别  CHMM学习方法  MCE准则

Minimum Recognition Error Training of CHMM for Speech Recognition
Zhao Li,Zou Cairong,Wu Zhenyang.Minimum Recognition Error Training of CHMM for Speech Recognition[J].Journal of Southeast University(Natural Science Edition),2000,30(3):21-25.
Authors:Zhao Li  Zou Cairong  Wu Zhenyang
Abstract:This paper describes an implementation of the minimum recognition error training for continuous Gaussian density HMM. We defined the misrecognition measure directly by discriminant function for the minimum recognition error training of CHMM. Also a minimizing method of the discriminant error function for CHMM training was investigated. The experiment on speaker independent continuous speech recognition of Chinese shown that the proposed method is effective.
Keywords:MCE  CHMM  speech recognition
本文献已被 CNKI 维普 万方数据 等数据库收录!
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