| 基于GMM的说话人识别系统 |
| |
| 引用本文： | 陈芬菲.基于GMM的说话人识别系统[J].微处理机,2006,27(4):76-77,79. |
| |
| 作者姓名： | 陈芬菲 |
| |
| 作者单位： | 天津大学理学院数学系,天津,300072 |
| |
| 摘 要： | 实现了一个基于高斯混合模型（GMM）的说话人辨识系统。GMM是用多个高斯分布的概率密度函数的组合来描述特征矢量在概率空间的分布状况，不同的说话人对应了不同的GMM。模型的训练采取了极大似然估计（ML）的EM方法。并在不同的数据集上实验，得到了好的结果。
|
| 关 键 词： | 说话人识别 高斯混合模型 EM方法 |
| 文章编号： | 1002-2279（2006）04-0076-02 |
| 收稿时间： | 2005-01-05 |
| 修稿时间： | 2005-01-05 |
Speaker Recognition System Based on GMM |
| |
| CHEN Fen-fei.Speaker Recognition System Based on GMM[J].Microprocessors,2006,27(4):76-77,79. |
| |
| Authors: | CHEN Fen-fei |
| |
| Affiliation: | Department of Mathematics, School of Science, Tianjin University, Tianfin 300072, China |
| |
| Abstract: | This paper realized a speaker recognition system based on Gaussian Mixture Models(GMM).GMM describe the probabilistic distribution of specific speaker's feature vectors by using mixed Gaussian pdfs.A Maximum Likelihood training method named E-M method has been applied in this system.Well performance of these experiments has been got in varied corpus. |
| |
| Keywords: | Speaker recognition GMM E - M method |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
