English

应用科学学报 ›› 2002, Vol. 20 ›› Issue (3): 251-253.

• 论文 • 上一篇    下一篇

语音识别中结合进化计算的MMI训练方法

茅晓泉, 胡光锐, 唐斌   

  1. 上海交通大学电子工程系, 上海 200030
  • 收稿日期:2001-05-30 修回日期:2001-09-12 出版日期:2002-09-30 发布日期:2002-09-30
  • 作者简介:茅晓泉(1974-),男,江苏盐城人,博士生;胡光锐(1938-),男,上海人,教授,博导.

Evolutionary Computation-based MMI Training in Speech Recognition

MAO Xiao-quan, HU Guang-rui, TANG Bin   

  1. Department of Electronic Engineering, Shanghai Jiaotong University, Shanghai 200030, China
  • Received:2001-05-30 Revised:2001-09-12 Online:2002-09-30 Published:2002-09-30

PDF

177

被引次数

2

摘要： 将最大互信息(MMI)和进化计算(EC)相结合,引入到HMM的训练中去.各个模型用个体来表示,个体的适应值采用模型的最大互信息.这样借助于演化计算的全局搜索及种群的特点,得到了基于最大互信息估计的HMM模型的更优解.实验结果表明,用该方法训练所得的系统识别率高于传统的基于梯度的最大互信息估计方法训练所得的系统.

关键词: 演化计算, 最大互信息, 语音识别

Abstract: This paper proposes a hybrid MMI/EC architecture to be embedded in the training of HMMs. Each individual in evolutionary computation represents a set of HMMs, while the fitness value of each individual represents the maximum mutual information. Since evolutionary computation is noted for its global search and population-based operations, the globally optimal solutions (or the sub-optimal solutions) can be obtained. Experiments indicate that the system trained with the proposed method is superior to the one trained with the traditional gradient based training method.

Key words: speech recognition, evolutionary computation, maximum mutual information

中图分类号: