Logarithm transform that expands data range in computer is applied to solve the problem of calculation overflow, and different sample training is overcome to eliminate sentence unit information.
探讨了基于B—W算法的连续语音建模的关键技术———计算溢出及训练样本差异问题,提出了解决方法:对计算溢出可采用对数变换的方法扩展计算机所能表示的数值范围给以解决;差异样本训练可在训练中消除将定样句子单元信息予以解决。