作　　者： ; ; ; ;

机构地区： 天津大学机械工程学院

出　　处： 《机床与液压》 2003年第6期140-142,303,共4页

摘　　要： 本文介绍了一种新的语音系统的通用开发方法。采用微软公司SPEECHSDK在上位机PC上实现文字 -语音转换(TEXTTOSPEECH) ,省略了采样 ;将音源经DialogicADPCM算法压缩为 VOX格式的文件 ,通过串口写入到闪烁存贮器中 ,下位机MCU用于语音数据读取和播放 ,响应实时需要。简化了开发过程 ,为类似系统的开发提供了新思路。 This paper introduces a new scheme for developing an audio response system,in which Microsoft Speech SDK was used to realize the text to speech and by which the acquisition of Voice data is omitted. The data as *.wav format is encoded with Dialogic ADPCM to *.vox format;then it is transmitted through the serial port of the PC and stored in the Flash ROM of the microcontroller system which converts the data to voice at the time required. This scheme can shorten the cycle of design and be regarded as reference when developing similar audio response system based on microcontroller.

关 键 词： 语音系统 通用开发方法 文语合成 算法 单片机 语音合成

领　　域： [电子电信] [电子电信]