GMM-apply-for-text-to-speech

基于单通道的在线次级通道建模的主动 噪声控制FXLMS算法的MATLAB实现( a single channel feed-forward active noise control system based on On-line secondary path modellingthe FxLMS alogrithms You can find many information about this simulation in "Use of random noise for online transducer estimate in an adaptive attenuation system " written by L,J Eriksson and M.A Allie in 1989.)

提取MFCC的matlab代码，用于提取MFCC-梅尔倒普系数(MFCC extraction of matlab code, for the extraction of MFCC-Mel Pu inverted coefficient)

一个可执行的HMM语音识别程序例程，实现了对10个数字音的识别程序，包含了HMM语音识别中的分段，MFCC特征提取，Baum-Welch训练，及Viterbi等算法，通过此例程可以很好的理解HMM的算法原理(An executable HMM-based 10 digits speech recogntion program example. this code zip file includes segmentation, MFCC feature extraction, Baum-Welch based re-estimation and Viterbi algorithm involved in HMM. it helps much better understand the HMM algorithm and its application for speech recogntion. )

psola算法的设计与实现，经过调试已经可以运行(psola Algorithm Design and Implementation, after debugging has to run)

提取语音信号的lpc参数并进行时间归整，需要将wav语音文件放在指定目录下‘e:yyzl’(voice signal from the lpc parameters and time consolidation, need to wav sound files on the specified directory 'e : yyzl')

一个简易的端点检测程序，已经实现，包括基于过零率、短时能量的双门限判决方法。(a simple endpoint detection procedures has been achieved, including on the basis of zero rate Short-term dual energy threshold judgment method.)

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)

这是自己毕业设计做的PCA和LDA的结合，训练和识别别过程都有，用的是ORL库里的图像，具有较高的识别率！ (This is a combination of PCA and LDA graduation design, training and do the process of the identification with ORL library of images, has a high recognition rate!)

C语言实现的端点检测,具有良好的效果,对于做语音识别者来说，是很好的参考(C language implementation of endpoint detection, with good results)

这里面的代码是2DPCA的。这篇文章发表在PAMI上,Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition.google搜索已经引用681次。这里的代码是原作者的。这个分类不太好，语音识别是最近的，这是模式识别里的经典算法。(matlab code of 2DPCA)