基于B-W算法训练连续语音的关键技术  

Critical technology of continuous speech training based on B-W

作　　者：李军[1] 刘晓明[1] 李龙[1] 

机构地区：[1]大庆石油学院计算机与信息技术学院,黑龙江大庆163318

出　　处：《大庆石油学院学报》2005年第4期121-123,共3页Journal of Daqing Petroleum Institute

摘　　要：B—W算法是基于隐含马尔可夫模型连续语音建模所采用的技术.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.Baum-Welch algorithm is a technology based on HMM. This paper discusses the primary technology that trains continuous speech models based on Baum-Welch algorithm. Calculation overflow and different sample training, and provides complete and flexible resolution. 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.

关 键 词：语音识别 B_W算法 计算溢出 模型参数 

分 类 号：TN912.34[电子电信—通信与信息系统]