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。
Minimum classification error (MCE) rate method is the most straightforward criterion for HMM training. Inprinciple, it is much better than the maximum likelihood method.
最小错识率(MCE) HMM训练方法是最直接的判决训练方法之一,原理上比最大似然接方法优越得多。
应用推荐