Microchip 公司的zigbee协议栈安装包

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.

用于语音识别的汉语树形词典，完成了6万词汇的建树操作及相关子节点等的查询处理，主要用于指导语音搜索整个建立时间大概为3分钟-for speech recognition dictionary of Chinese tree, completed 60,000 contribution to the vocabulary and related operations, such as sub-nodes of query processing, Pronunciation guide for the main search the entire building for about three hours minutes

本程序实现用谱减法消除语音中的噪声，其中语音是纯净的，噪声是后加上去的，滤除效果良好-This procedure using spectral subtraction to eliminate the noise in the voice, which voice is pure, after noise is added, and filter out the effect of good

对数运算实现是32位的运算包含有指数和对数的求法 -LOG

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

FIR滤波器设计中往往是线性相位，但不是最小相位，所以它的零点有部分在单位圆外。把单位圆外的零点映射到单位圆内，构成最小相位滤波器。-FIR filter design is often the linear phase, but it is not minimum phase, so it has some of the zeros outside the unit circle. To zero outside the unit circle is mapped to the unit circle, the minimum-phase filter constituted.

本程序的压缩编码是G.723的编解码程序，其的算法是基于ACELP的算法基础上的编码。用在语音通信中，例如手机中-the procedure coding is the G.723 codec procedure, the algorithm is based on ACELP algorithm based on the coding. Used in voice communications, such as mobile phones

点对点会 没有看，只是为了下载上传的 大家不要有意见呀-will not point-to-point, just to download uploaded do not view ah

这是一个通用的隐马尔科夫模型的C代码库， 非常好用。-This is a generic Hidden Markov Model C code libraries, very handy.

语音信号的清浊音的提取是研究语音信号的一个必经的过程，如何提取清浊音也是很多初学者面临的问题-Detecting the voice and unvoice is a primily process to study speech signal.How to detect it is also the big problem to the most learner.