网站首页

登录

MFCC-GMM

于 2011-01-17 发布文件大小:1153KB

 0  404

下载积分: 1 下载次数: 1138

我要下载

代码说明：

基于MFCC的GMM的说话人识别，是很好的语音处理程序(MFCC of the GMM based speaker recognition, speech processing is a very good program)

文件列表：

基于MFCC的GMM的说话人识别
.........................\buffer2.m,530,2006-03-04
.........................\enframe.m,457,2008-05-12
.........................\epdByVol.m,4938,2010-04-14
.........................\epdParamSet.m,842,2008-05-04
.........................\frame2sampleIndex.m,889,2006-02-23
.........................\frame2volume.m,2410,2009-06-05
.........................\frameZeroMean.m,1621,2007-08-27
.........................\getTriFilterParam.m,1225,2003-06-11
.........................\gmm_estimate.m,2937,2008-05-14
.........................\go.m,2220,2010-06-23
.........................\lmultigauss.m,927,2010-06-21
.........................\lsum.m,1173,2007-06-14
.........................\melbankm.m,718,2008-05-14
.........................\melcepst.m,613,2008-05-19
.........................\mfccParamSet.m,793,2008-06-02
.........................\MFCC_feature_compare.m,672,2010-06-21
.........................\rdct.m,463,2008-05-12
.........................\rfft.m,385,2008-03-20
.........................\segmentFind.m,1100,2008-10-17
.........................\speakerData.mat,154586,2010-06-23
.........................\speakerGmm.mat,12939,2010-06-23
.........................\test
.........................\....\张三一.wav,160044,2009-10-09
.........................\....\张三二.wav,160044,2009-10-09
.........................\....\陈蕴谷口哨.wav,160044,2009-10-09
.........................\....\陈蕴谷英文.wav,160044,2009-10-09
.........................\trainning
.........................\.........\梁建娟.wav,160044,2009-10-09
.........................\.........\熊可.wav,160044,2009-10-08
.........................\.........\胡业刚.wav,160044,2009-10-08
.........................\.........\陈蕴谷.wav,160044,2009-10-08
.........................\.........\颜小运.wav,160044,2009-10-08
.........................\wave2mfcc.m,4923,2009-08-13
.........................\说明文档.txt,204,2010-06-23

下载说明：请别用迅雷下载，失败请重下，重下不扣分！

发表评论

0 个回复

tibaoluo
基于倒谱短时部分反映了语音的声道特性，先用汉明窗取一帧语音，然后经变换得到语音倒谱，将倒谱短时部分取出，进行正交反变换后将得到声道的对数谱，即得到语音频谱的包络。将频谱包络和频谱画在一张图上，有很好的对比效果。获取的包络效果十分好。(Based Cepstral partly reflects the short channel characteristics of the speech, first take a Hamming window with a frame of speech, and speech cepstrum obtained by converting the cepstrum short segment out inverse orthogonal transform to obtain channel will of the spectrum, i.e. to obtain the envelope of the speech spectrum. The spectral envelope and spectral painted on a chart, there is a good contrast. Get the envelope effect is very good.)

2013-11-01 14:13:17下载

积分：1
Basic_voice
语音信号处理中的所有基本的算法的代码联合开发网 - pudn.com

2011-04-26 13:02:39下载

积分：1
lsp
基于LSP分析的共振峰提取算法，可直接运行(LSP based on the analysis of formant extraction algorithm can be directly run)

2008-02-29 10:11:10下载

积分：1
lbg_vq
LBG-vector quantization algorithm

2013-04-25 09:00:17下载

积分：1
hmm
HMM连续语音识别(Continuous Speech Recognition)

2018-11-19 12:41:18下载

积分：1
male
标准的10个数字和26个字母的男语音数据库，用于语音信号处理(10 numbers and 26 letters of the standard male voice database for speech signal processing)

2013-01-31 15:03:06下载

积分：1
MFCC_Coding_Demo2
characteristic parameters for speech recognition on the extraction function

2019-05-01 15:55:47下载

积分：1
lpcc_xiang
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.)

2021-04-29 13:58:43下载

积分：1
LPC-FORMANT-PITCH
lpc提取共振峰和基频，适合初学语音的同学使用，增强认识(lpc formant extraction and baseband, suitable for beginners to use the voice of the students, and enhance understanding)

2013-06-21 09:22:14下载

积分：1
ABSE
熵值越大则每个符号包含的平均信息量越大。有研究发现，在有噪声的语音信号中，语音信号的熵和噪声信号的熵存在着较大的差异，对噪声信号来说在整个频带内分布相对平坦，熵值小，语音信号集中在某些特定频段内，熵值大。因此利用这个差异可以区分噪音段和语音段。(The greater the entropy is, the greater the average information of each symbol is. It is found that, in noisy speech signals, the entropy of speech signals and the entropy of noise signals are quite different. For noisy signals, the distribution is relatively flat in the whole frequency band, and the entropy value is small. The speech signal is concentrated in some specific frequency bands, and the entropy value is large. So the difference can be used to distinguish the noise segment and the speech segment.)

2020-11-02 21:29:54下载

积分：1

696516资源总数
106914会员总数
0今日下载