用PC SPEAKER 播放WAV文件的C源程序

整数的语音合成 可以设置各个镀银的时延，适合初学者使用-Integer speech synthesis can set the delay all silver, for beginners

G.711语音编解码在CCS上实现的源代码-G.711 voice codec to achieve the CCS source code

dtw（动态时间规整）语音识别的matlab源码-dtw (Dynamic Time Warping) speech recognition matlab source code

matlab中wave文件的播放功能，欢迎使用-Matlab documents were broadcast wave function, welcomed the use of

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.

语音识别在遥控系统中的应用设计介绍一种适合家电遥控器应用的语音识别算法，该算法使用双模块和两级端点检测方法，能有效地提高识别和稳健性；介绍利用该技术实现的一种新型学习型遥控器，展现了语音识别技术在家电领域的广阔前景-voice recognition in the remote control system of Design for a remote appliance application of speech recognition algorithm, The algorithm uses two double module and endpoint detection methods that can effectively improve recognition and stability; introduced use of the technology, a new learning remote control, displaying the voice recognition technology in the field of home appliances broad prospects

一款安卓版的语音小助手，调用了讯飞的API，实现了用语音指令打电话、发短信、查看日历、搜索、打开应用等数十项功能，类似于APPLE的SIRI，用Android studio开发。

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.

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

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