编译环境：vc++.net2003 名称：语音合成软件 作者：yxifu

用三层小波神经网络实现的与文本无关说话人识别。（识别部分）。输入的是语音特征，输出的是识别结果。训练用的语音特征要事先提取出。-with three wavelet neural network has nothing to do with the text of Speaker Recognition. (Recognition). The admission of voice features, the output is the result of recognition. Training voice features prior to extract.

语音控制程序，需要微软的speech SDK，如果已经完全安装了微软的office系统，可以直接打开运行。-Voice control procedures, the need for Microsoft speech SDK, if you have fully installed the Microsoft office system, can directly open the run.

语音端点检测，是语音压缩时提取特征参数的一个必要的过程，这个程序主要是对这个过程的一个小的程序。希望对学语音的有帮助-Extreme point detecting is a primily process to get the eigenparameter when you compressing the speech.This program is a small one,it will help for the learner.

HTKbook，剑桥大学语音识别工具包HTK的简历文件。PDF，有HTK的详细说明

具有浮点指令的g.729语音压缩编码，符合ITU-T G.729 Annex C 规范，通过修改makefile可以支持windows/linux/solaris等操作系统，仅需要很少的更改就可以应用到voip领域-With floating-point instructions G.729 voice compression coding, in line with the ITU-T G.729 Annex C specification by modifying the makefile to support windows/linux/solaris and other operating systems, only a small change on the field can be applied to voip

这是一个关于音频编码的c程序 mp3第三层的-This is a study on the c program audio coding mp3 third layer

HTS-2.0RC2，HTS语音合成器的最新测试版。首先需要安装HTK3.4。与HTS1.1相比功能更加强大。嵌入式训练算法更新。-HTS- 2.0RC2 HTS voice synthesizer to the latest test version. HTK3.4 first need to install. HTS1.1 compared with the more powerful functions. Embedded training algorithm update.

一个基于ITU-R recommendation BS.1387的客观语音质量评价算法源码。-Based on ITU-R recommendation BS.1387 objective voice quality assessment algorithm source.

ica 权威paris在很久以前写的ica算法程序，稍作修改可以用于声音信号识别。-Paris, one of the authorities of ICA, created the program at long time ago. It can be used to recognise speech signal if modify a little.

带参考信号的盲源分离，很好用的程序，用于语音增强-ICA-R