| 一种用于语音模板产生的无监控聚类算法 |
| |
| 引用本文： | 杨树林,柯有安.一种用于语音模板产生的无监控聚类算法[J].北京理工大学学报,1992,12(3):37-42. |
| |
| 作者姓名： | 杨树林 柯有安 |
| |
| 作者单位： | 北京理工大学电子工程系
(杨树林)，北京理工大学电子工程系(柯有安) |
| |
| 摘 要： | 将共享近邻(SNN)算法中的近邻概念具体化,为K-均值算法(KMI)设计了一种初始类心选取方案,并把改进的共享近邻算法(MSNN)和改进的K-均值算法(MKMI)合并到一起形成一种不需外界干预的综合聚类算法(CCA).用两组语音数据进行了比较试验,结果表明,MKMI和CCA的性能比KMI的分别高57％和108％;MSNN是一种比较有效的粗分类算法。
|
| 关 键 词： | 模式识别 聚类分析 语音模板 |
An Unsupervised Clustering Algorithm for Template Creations |
| |
| Yang Shulin Ke Youan.An Unsupervised Clustering Algorithm for Template Creations[J].Journal of Beijing Institute of Technology(Natural Science Edition),1992,12(3):37-42. |
| |
| Authors: | Yang Shulin Ke Youan |
| |
| Abstract: | The concept of near-ness in the shared nearest neighbors(SNN) is given an embodiment and an algorithm for determining initial cluster centers in the K- means iteration (KMT) is designed. The modified SNN (MSNN) and the modified KMI (MKMI) are merged to from an unsupervised combined clustering algorithm (CCA). For comparison, the KMI, MKMI, and CCA were applied to classify two groups of speech data. The results show that the performances of the MKMI and CCA are respectively 57% and 108% higher than that of the KMI, and MSNN is a good pre-classifier. |
| |
| Keywords: | pattern recognition cluster analysis/shared nearest neighbor K-means convergence |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《北京理工大学学报》浏览原始摘要信息 |
| 点击此处可从《北京理工大学学报》下载免费的PDF全文 |
