Next we used distributional similarity as a feature in the discriminative maximum entropy model, with edit distance, phonetic similarity, and language model as other features.
我们还将分布式相似度作为一个特征用于最大熵判别模型中，结合编辑距离、发音相似度、语言模型等基本特征。
Four typical discriminative training criterions and some updating methods of acoustic model parameters are introduced, then, they are defined in a unified framework.
再经过对各种区分性训练准则的目标函数和参数更新算法进行推导和比较，将它们统一地纳入到一套训练框架体系之中。
Four typical discriminative training criterions and some updating methods of acoustic model parameters are introduced, then, they are defined in a unified framework.
再经过对各种区分性训练准则的目标函数和参数更新算法进行推导和比较，将它们统一地纳入到一套训练框架体系之中。
应用推荐