模式识别k-means法与k-l变换做的特征提取-K-means pattern recognition method and kl transform to do the feature extraction

收集的ADPCM有关的资料，有源码，有原理说明，

此方案基于全极点语音产生模型，编码过程简述如下：首先通过线性预测分析方法提取声道滤波器参数；其次通过合成分析法确定最佳激励矢量；最后将滤波器参数和最佳激励矢量进行编码传输。-This program is based on all-pole speech production model, the encoding process summarized as follows: First, by linear prediction analysis to extract channel filter parameters followed by analysis by synthesis method to determine the best incentive vector Finally, the filter parameters and the best incentive vector encoded transmission.

基于GMM的概率神经网络PNN具有良好的泛化能力，快速的学习能力，易于在线更新,并具有统计学的贝叶斯估计理论基础，已成为一种解决像说话人识别、文字识别、医疗图像识别、卫星云图识别等许多实际困难分类问题的很有效的工具。而且PNN不但具有GMM的大部分优点，还具有许多GMM没有的优点，如强鲁棒性，需要更少的训练语料，可以和其他网络其他理论无缝整合等。-GMM based probabilistic neural network PNN good generalization ability, the ability to learn fast, easy online updates, and with the Bayesian statistical theory based on estimates, and has become a solution as speaker recognition, text recognition, medical image recognition, satellite images and other real recognition when difficulties classification of very effective tool. But GMM PNN is not only the most advantages, but also has many advantages GMM not as strong robustness, require less training corpus, and other networks to other theories, such as seamless integration.

一个简单的报时小软。可以中文报时 初学语音识别，希望同样爱好的朋友可以多多交流-A simple small-time soft. Time learning in Chinese speech recognition, hope that the same lot of loving friends can exchange

自己根据网上的说明自己编写的测试TTS的程序-Own description of the basis of online tests to prepare their own procedures for TTS

语音识别基本原理 自己收集的电子书 关于语音识别的 -voice recognition basic tenets of his collection of electronic books on Speech Recognition

G.729aa 编码器和解码器代码 G.729A 是 G.729 的降低的复杂性标准之一。G.729 是国际电信联盟-T 语音压缩算法，基于共轭结构化代数代码激动的线性预测 (CS-ACELP）。G.729A 压缩 8 kHz 线性音频信号和对他们进行传输在 8 Kbps.输入进行编码为 16 位 PCM。输入码流是分割成 10ms年帧和处理。预测分析做使用合成的筛选器的顺序 10。

CCITT G.711语音压缩算法 -CCITT G.711 voice compression algorithm

语音识别再vc下开发-speech recogintion developed with VC