kaerman

计算语音的短时平均能量。可以作为清音和浊音的特征参数，可以作为有声无声的依据(Calculate the short-term average energy of speech. It can be used as a characteristic parameter of voiceless and unvoiced sounds, and as a basis for sound and silence.)

利用mfcc特性进行语音识别，分类算法为svm。(Speech recognition using MFCC characteristics)

语音信号的语谱图生成函数，function [ ] = spetro(Winsiz, Shift, Base, Mode, Gray)，5个参数分别为帧长、帧移、取值门限（一般设为0）、彩色模式、灰度模式(This is a matlab function for creating speech spectrogram.)

手机端蓝牙连接设备（以小车为例），通过按键、本地语音识别（pocketsphinx）和重感控制设备，蓝牙连接地址在BluetoothTools中修改，本地需要配置NDK环境才能编译。(Bluetooth mobile client devices (for example in the car), buttons, local speech recognition (pocketsphinx) and heavy sense of control devices, Bluetooth connectivity address BluetoothTools modify the local environment can be configured to compile NDK.)

语音通信，延迟小，质量高，游戏玩家专用哈。(Voice communications, delay, high quality, dedicated gamers Kazakhstan.)

实现多个人的说话人识别，基于gmm模型，用mfcc参数训练(voice conversion based on gmm)

GMM - This code run very well and it has Demo

语音信号时频分析，包括语谱图，过零率，自编的自相关，以及最后用了三种方法（短时能量和过零率、谱熵法、Teager算子）进行端点检测，代码完整且测试通过(time and frequency domain analysis of speech signals,including spectrogram,rate of zerocrossing,autocorrelation.and three method of endpoint detection,especially the Teager )

c++语言开发，用于LPCC特征参数提取的，在语言识别系统中应用广泛。(c language, LPCC Features for feature extraction, in language recognition system widely used.)

模拟实验-C#版基于二分查找的稳定“插入排序”算法(Simulation experiment-stable insert sort algorithm based on dichotomous search in C # version)