汉语文语转换系统地址映射算法的设计与实现  

Design and Implementation of Mapping Address Algorithm in Chinese Text-to-Speech System

作　　者：张大军[1] 陈肇雄[1] 黄河燕[1] 

机构地区：[1]中国科学院计算机语言信息工程研究中心,北京100080

出　　处：《软件学报》2002年第1期105-110,共6页Journal of Software

基　　金：国家自然科学基金资助项目(69835003)~~

摘　　要：针对多样本文语转换系统中的语音合成实时性问题,提出了对合成系统语音库的改进策略和语音单元之间相似度的计算方法,在此基础上设计并实现了查找语音单元的地址映射算法.实验表明,地址映射算法和音库的重新组织有效地提高了合成系统的实时性.In order to solve the real-time synthesis problem in a multi-sample text-to-speech system, the strategy of improving the structure of speech database is discussed and a method of calculating the similarities between two speech units is put forth. On the basis of these, a mapping address algorithm to locate the address of speech unit is brought up. The experimental results show that mapping address algorithm and reconstruction of speech database improve the real-time performance of text-to-speech system.

关 键 词：语音库 地址映射算法 语音合成 汉语文语转换系统 设计 计算机 

分 类 号：TP391.12[自动化与计算机技术—计算机应用技术] TN912.33[自动化与计算机技术—计算机科学与技术]