VQ ASR

基于语音信号工具箱的隐马尔科夫HMM模型的说话人识别，请联系lishicheng64@126.com(Speech signal based on HMM toolbox Hidden Markov Model speaker recognition, please contact lishicheng64@126.com)

gmm模型下的语音情感识别系统，GMM只是一个数学模型，只是对数据形态的拟和，但是和你所看到的数据分布存在出入也是正常的，因为用EM估计GMM的那些参数时，一般假设我们所得到的数据是不完备的（也就是说假设我们看到的数据分布不是真正的分布，它在运算时把那部分丢失或者叫隐藏的数据“补”上了）(gmm model speech emotion recognition system, GMM is a mathematical model, but fitting the data form, but you can see there is access to the data distribution is normal, because those with the EM estimated GMM parameters, the general assumption we get the data is incomplete (that is, assuming we see the distribution of the data distribution is not real, it is part of the operation at the time that is lost or hidden data is called " fill" on the))

语音增强算法，基于人耳听觉掩蔽的维纳滤波(Subspace speech enhancement algorithm based on human auditory masking Wiener filter)

利用MATLAB来实现语音的分帧及语音端点检测(Using MATLAB to achieve voice segmentation and voice endpoint detection)

LMS算法多麦克风语音降噪，语音降噪处理，基于matlab(LMS algorithm for multi-microphone speech noise reduction, voice, noise reduction, based on matlab)

基于ICA和PCA相结合实现的语音信号的采集、随机混合，再通过盲分离将混合后的语音信号分离(Speech signal acquisition and random mixing based on ICA and PCA, and then the mixed speech signal is separated by blind separation.)

一种关于倒谱的实现研究处理方法的总结以及展望(One kind of research on cepstrum processing method to achieve a summary and outlook)

文中研究了6种常用数字调制信号识别的特征参数集，并采用决策树判别方法进行分类识别。仿真结果表明，在SNR≥5dB时，识别正确率在99 以上，且当SNR≥20dB时，识别正确率达到100 。其特点是，算法简单，识别正确率高，达到了自动分类识别的目的，并有利于实现识别的实时化。(In this paper, we study the set of characteristic parameters of the six kinds of commonly used digital modulation signal recognition, and decision tree method for classification. The simulation results show that SNR 鈮� 5dB, the correct rate more than 99 , and when SNR 鈮� 20dB, the correct rate of 100 . Which is characterized by simple algorithm to identify the correct rate, to achieve the purpose of automatic classification and recognition, and help to identify real-time.)

端点检测算法采用现阶段比较精确的时频方差检测法，模式识别和模板匹配采用的是改进后的DTW算法（主要是限定了DTW的搜索路径，进一步精确了DTW的平行四边形的形状，进一步的减少匹配中的参数存贮量以及多余的搜索路径）。(Endpoint detection algorithm uses more precise at this stage variance time-frequency detection, pattern recognition and template matching is based on the improved DTW algorithm (DTW is mainly limited to the search path, and further precision of the DTW parallelogram shape, and further reduction of matching the parameters in the storage volume as well as the extra search path).)

mfcc.m 用于语音识别上的mfcc特征参数提取函数。(mfcc.m mfcc characteristic parameters for speech recognition on the extraction function.)