登录
首页 » matlab » 基于GMM的说话人识别

基于GMM的说话人识别

于 2019-04-06 发布 文件大小:720KB
0 72
下载积分: 1 下载次数: 6

代码说明:

  语音识别是近年来发展非常迅速的一项计算机智能技术,广泛应用在语音控制、身份识别等多个领域。本次项目主要研究语音识别的预处理过程和特征参数的提取环节。通过对原始语音信号进行预加重和分帧、加窗,滤除低频干扰,提升对语音识别有用的部分,消除了部分噪音和失真。预处理之后进行信号的特征提取,主要选取了短时平均过零率和MFCC两个特征参数,应用matlab软件绘制波形图并提取特征参数矩阵,为之后的语音信号的识别打下了基础。(Speech recognition is a computer intelligent technology which has developed rapidly in recent years. It is widely used in speech control, identity recognition and other fields. This project mainly studies the pretreatment of speech recognition and the extraction of feature parameters. Through pre-emphasis, framing and windowing of the original speech signal, the low frequency interference is filtered out, the useful part of speech recognition is enhanced, and some noise and distortion are eliminated. After pretreatment, feature extraction of signal is carried out. Two feature parameters, short-term average zero-crossing rate and MFCC, are selected. Waveform diagram is drawn by MATLAB software and feature parameter matrix is extracted, which lays a foundation for speech signal recognition.)

文件列表:

基于GMM的说话人识别, 0 , 2019-04-06
基于GMM的说话人识别\duanshipingjunnengliang.m, 1010 , 2019-03-27
基于GMM的说话人识别\gongzhenfeng.m, 1432 , 2019-04-01
基于GMM的说话人识别\guolinglv.m, 491 , 2019-03-27
基于GMM的说话人识别\haming.m, 744 , 2019-03-27
基于GMM的说话人识别\main.m, 1038 , 2019-04-01
基于GMM的说话人识别\mel_dist.m, 519 , 2019-04-01
基于GMM的说话人识别\mfcc_m.m, 1364 , 2019-04-01
基于GMM的说话人识别\Untitled.m, 2410 , 2019-04-06
基于GMM的说话人识别\yujiazhong.m, 1522 , 2019-03-25
基于GMM的说话人识别\信号处理后波形, 0 , 2019-04-06
基于GMM的说话人识别\信号处理后波形\000.PNG, 83587 , 2018-06-21
基于GMM的说话人识别\信号处理后波形\1.PNG, 41264 , 2018-06-19
基于GMM的说话人识别\信号处理后波形\111.PNG, 60538 , 2018-06-21
基于GMM的说话人识别\信号处理后波形\2PNG.PNG, 28451 , 2018-06-19
基于GMM的说话人识别\信号处理后波形\Q.PNG, 37765 , 2018-06-20
基于GMM的说话人识别\信号处理后波形\Q1.PNG, 34781 , 2018-06-20
基于GMM的说话人识别\信号处理后波形\Thumbs.db, 228352 , 2018-06-21
基于GMM的说话人识别\信号处理后波形\原始分帧加窗.PNG, 83420 , 2018-06-20
基于GMM的说话人识别\信号处理后波形\原始短时平均过零率.PNG, 25929 , 2018-06-20
基于GMM的说话人识别\信号处理后波形\吉布斯效应.PNG, 11615 , 2018-06-21
基于GMM的说话人识别\信号处理后波形\处理前短时平均过零率.PNG, 25497 , 2018-06-20
基于GMM的说话人识别\信号处理后波形\预加重后过零率.PNG, 28936 , 2018-06-20
基于GMM的说话人识别\信号处理后波形\高通.PNG, 28531 , 2018-06-19
基于GMM的说话人识别\信号处理后波形\高通滤波后.PNG, 57413 , 2018-06-20

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

  • Classificationsvm
    1、工具箱:LS_SVMlab Classification_LS_SVMlab.m - 多类分类 Regression_LS_SVMlab.m - 函数拟合 2、工具箱:OSU_SVM3.00 Classification_OSU_SVM.m - 多类分类 3、工具箱:stprtoolsvm Classification_stprtool.m - 多类分类 4、工具箱:SVM_SteveGunn Classification_SVM_SteveGunn.m - 二类分类 Regression_SVM_SteveGunn.m - 函数拟合(1、Classification_LS_SVMlab.m 2、Classification_OSU_SVM.m 3、Classification_stprtool.m 4、Classification_SVM_SteveGunn.mRegression_SVM_SteveGunn.m )
    2009-03-07 16:26:00下载
    积分:1
  • hull
    很有用的机械工具包 Nice matlab package for mechanical engineering.(Nice matlab package for mechanical engineering.)
    2010-08-10 04:37:43下载
    积分:1
  • 12121FingerprintRecognition.rar
    the same with what i have uploaded before.
    2010-10-06 01:42:36下载
    积分:1
  • bayes
    采用身高和体重数据作为特征,分别假设二者相关或不相关,在正态分布假设下估计概率密度,建立最小错误率Bayes分类器,写出得到的决策规则,将该分类器应用到训练/测试样本,考察训练/测试错误情况。(The use of height and weight data as the characteristics of the assumption that the two were related or not related to the normal distribution probability density is estimated under the assumption that the establishment of Bayes minimum error rate classifier, the decision-making rules have been written, the classifier is applied to training/test samples to study the training/testing error conditions.)
    2009-04-21 21:34:24下载
    积分:1
  • conjgrad
    conjugate gradient tset file
    2009-11-20 00:57:02下载
    积分:1
  • tutorial_em_matlabcode
    em算法matlab代码。解压缩后直接可以在matlab环境下运行(em algorithm Matlab code. Decompress directly in the operating environment Matlab)
    2007-02-28 10:57:31下载
    积分:1
  • GSC2
    广义旁瓣相消器,阻塞矩阵B2,一个期望信号,一个干扰,高斯白噪声(the simulation of GSC(B2))
    2021-03-28 19:29:11下载
    积分:1
  • confusion_matrix
    将机器学习分类的结果生成混淆矩阵,并画出混淆矩阵。。。。。。。。(generating confusion matrix and draw it)
    2020-07-15 19:08:50下载
    积分:1
  • chap11
    说明:  本目录主要包括:文档和两个源代码。 其中一个源代码是识别程序的,另一个是一个矩阵类库的,书里面也使用过,所以一并附上。 因为已经保存了训练好的网络权值,所以第一次使用识别程序时,可以直接运行\\Release目录下的可执行文件,然后对图片目录中的测试图片进行读入、识别。 当然读者也可以自行用训练样本训练网络,不过要特别注意训练样本的选择,否则可能造成识别率很低。训练样本选择的原则是,尽可能的有代表性,在训练时间不至于太长的情况下,训练样本数目尽量多。 ( This directory includes: documentation and two source code. One of the source code is to identify the procedure, the other is a matrix class library, the book which is also used, so be attached. Because it has saved the trained network weights, so the first use of identification procedures, you can directly run \ \ Release directory of the executable files, and then tested on the images directory to read pictures, identification. Of course, readers are free to use the training samples to train the network, but pay special attention to training samples, otherwise it may cause very low recognition rate. Training sample selection principle is that as far as possible, representative, in the long training time Buzhi Yu s case, the number of training samples as much as possible. )
    2010-04-11 22:26:09下载
    积分:1
  • on
    基于m序列的直接序列扩频系统的抗噪声性能仿真 (Anti-noise performance simulation based on direct sequence spread spectrum system m sequences)
    2013-11-23 15:40:13下载
    积分:1
  • 696524资源总数
  • 103938会员总数
  • 55今日下载