一种基于聚类的高斯混合模型算法
首发时间:2010-05-31
摘要:本文介绍了一种高斯混合模型算法的改进方法---将聚类算法与传统高斯混合模型结合起来的建模方法, 并同时提出的运用距离加权的矢量量化方法获取初始值,并采用衡量相似度的方法来融合高斯分量。从对比结果可以看出,基于聚类的高斯混合模型的说话人识别相对于传统的高斯混合模型在识别率上有所提高。
关键词: 说话人识别 高斯混合模型 聚类算法 距离加权矢量量化 适应度
For information in English, please click here
GMM based on clustering algorithm
Abstract:This article introduces an improved algorithm of GMM which combines classical GMM with clustering algorithm, and proposed the Distance-weighted vector quantization method to obtain the initial value, and the way of measuring the similarity to merge the Gaussian integrations. From the results,the article concludes that GMM based on clustering algorithm has higher performance than classic GMM algorithm.
Keywords: speaker recognition Gaussian mixture model clustering algorithm distance weighted vector quantization adaption
基金:
论文图表:
引用
No.4373980535730127****
同行评议
共计0人参与
勘误表
一种基于聚类的高斯混合模型算法
评论
全部评论0/1000