Minimum Classification Error (MCE) criterion based sub-words weighting parameters estimation algorithm is proposed in which the sub-word weighting parameters are derived by the MCE training.
本文提出了一种基于最小分类错误准则(MCE)的子词权重参数估计算法，通过MCE训练得到子词的权重系数。
The stability, starting problem, initial value of sub-iteration and convergence criterion of implicit iteration of the dual-time stepping method are studied.
对双时间步方法隐式迭代的稳定性、启动问题、子迭代初值和收敛性准则进行分析。
Chapter Four discusses the practical criterion guided by the highest criterion appropriateness, establishing parameters and sub-parameters.
第四章探讨以得体为最高标准的实用标准，确立各项参数和子参数。
应用推荐