English figures from one to ten, they hope to do useful Speech Recognition

加入短时能零积端点检测技术的幅值谱减法，噪声谱的估计根据端点检测的结果进行加权平均，时时更新，更好的去除噪音，并将去噪后的结果写成wav文件-Adding short-term endpoint detection can be zero plot of the amplitude of spectral subtraction techniques, the estimated noise spectrum endpoint detection in accordance with the results of the weighted average, up-to-date, better to remove noise, and after the results of denoising wav file

SPEECH AND LANGUAGE PROCESSING

Linux下的CELP语言编码，压缩语音质量极好。支持2K到32K的压缩。实现部分使用C语言编写。可用做Linux下的动态库，有例子。-under Linux CELP language coding, compression excellent speech quality. Support 2 K to 32 K compression. Part of the use of C language. Linux can be done under the DLL, is an example.

基于语音合成法的汉语人名语音库的设计应用-Speech synthesis method based on the names of Chinese Speech Database Design and Application

运用SAPI将文本转化成语音的demo-use SAPI text into voice demo

audio/celp

61板实验指导书，对语音识别比较有用。适合初学者-Experimental guide plate 61 books, more useful for speech recognition. Suitable for beginners

cdma2000 1x语音编解码程序，并带有测试用例，很好用-cdma2000 1x voice codec procedures and with test cases, very good use

这是微软TTS语音引擎（SAPI5.1）Delphi应用程序的详细说明。不幸的是，它是用英语写的。：（如果有的话，请帮助翻译什么。）

Bark和ERB滤波器组实现的Matlab源程序-Bark and ERB filter banks realize the Matlab source