汉语文本读入中音字转换的知识集成模型和时间同步搜索算法  

Knowledge-Integrated Model and Time-Synchronously Search Algorithm for Speech-Character Transchiption in Chinese Text Read-in System

作　　者：徐近霈[1] 高枚[1] 

机构地区：[1]哈尔滨工业大学

出　　处：《中文信息学报》1994年第1期33-44,共12页Journal of Chinese Information Processing

摘　　要：本文提出一种集成声学和语言学（特别是词间近邻关联和远邻语法规则）知识的组合概率模型，以及将这一模型用于音字转换过程的时间同步的动态规划搜索算法，并实验验证了所提模型和搜索算法的有效性。Abstract This paper presents a combined probabilistic model integrating acoustic and linguisticknowledges (especially the link relationship between neighbouring words and the grammatical rules between distant words), and a time-synchronously dynamic programming search algorithm for applying this model to speech-character transcription. The effectiveness of this model and search algorithm has also been tested and verified.

关 键 词：汉语文本读入 音字转换 知识集成 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术]