ETSI发布的用于研究分布式语音识别的前端降噪算法

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.

用delphi制作的动画精灵，是初学者的选择！-Delphi animation produced by the wizard, is the choice for beginners!

A wonderful ica toollbox about blind source separation for the beginners

语音的消噪程序，传统普减法的改进，有效去除背景噪声-Speech de-noising process, the traditional S & P subtraction improvements, effectively remove background noise

改进的BP神经网络的C++源代码,可用于图象识别-Improved BP neural network C++ Source code, can be used for image recognition

语音识别与合成入门5，word或压缩包中内有matlab源码-speech recognition and synthesis 5 entry, word or compressed packages within Matlab FOSS

线形预测编码是用数据间的线形关系，通过前一个值对后来的值进行预测编码-linear predictive coding data used is the linear relationship, before the adoption of a value on the subsequent value predictive coding

本文系统的介绍了语音识别的技术及其实现方法-This article introduces the technic and implement method of speech recognise

一种HMM训练的源程序，调试可以通过，说明比较详细-A HMM training source, debugging can explain in more detail