基于DSP的嵌入式汉语文语转换系统及其VLSI设计方案

AN EMBEDDED CHINESE TEXT-TO-SPEECH SYSTEM BASED ON DSP AND ITS VLSI DESIGN SCHEME

简要讨论了嵌入式文语转换(ETTS)系统的概念。介绍了一个基于DSP实时实现的嵌入式汉语文语转换(ECTTS)系统。基于DSP实现的结果,分析了ECTTS系统的VLSI实现方案,提出了基于动态内存管理的ECTTS系统前端处理VLSI实现方案,基于解码语音帧的ECTTS系统后端合成VLSI实现框架并对ECTTS系统的VLSI实现中的存储器及总线结构进行了讨论。

The concept of Embedded Text-To-Speech (ETTS) system is first discussed. Then a real time realized Embedded Chinese Text-To-Speech (ECTTS) system based on DSP is introduced. Based on the DSP realization results, the VLSI design scheme of the ECTTS system is discussed. For the ECTTS system front-end processing, a VLSI design scheme based on the dynamic memory management is suggested. For the ECTTS system post-end processing, a VLSI design architecture based on the decoded speech frame is also proposed. The memory and the bus structure of the VLSI design of ECTTS system are discussed.