本文已被：浏览 1547次 下载 2922次
Received:August 18, 2011 Revised:September 26, 2011
Received:August 18, 2011 Revised:September 26, 2011
中文摘要: 针对PCA 没有有效利用样本的类别信息而导致方言识别率低的问题,采用PCA 和LDA 组合方法进行特征提取。首先用PCA 对普通话、上海话、广东话和闽南话四种方言进行降维,然后在降维后的空间中用LDA进一步特征提取,最后将该特征向量送入BP 神经网络进行辨识。仿真实验结果表明,基于PCA 和LDA 的方言识别的平均识别率高达85%。
Abstract:In order to solve the low dialect identification rate because PCA doesn’t effectively use the sample classification information, a method of feature extraction using PCA and LDA is employed. In this paper, PCA is used to effectively reduce the dimensions of Mandarin, Shanghainese, Cantonese, Minnanese, and then LDA is adopted to extract feature vectors from the dimension-reduced space as the input vectors with BP neural network to recognize. The Simulation results demonstrate that the average dialect identification rate based on PCA and LDA can be up to 85%.
keywords: dialect identification PCA LDA BP neural network
文章编号： 中图分类号： 文献标志码：
基金项目:国家自然科学基金(61075008)
引用文本：
何艳,于凤芹.基于 PCA 和 LDA 的方言辨识.计算机系统应用,2012,21(5):169-171,179
HE Yan,YU Feng-Qin.Dialect Identification Based on PCA and LDA.COMPUTER SYSTEMS APPLICATIONS,2012,21(5):169-171,179
何艳,于凤芹.基于 PCA 和 LDA 的方言辨识.计算机系统应用,2012,21(5):169-171,179
HE Yan,YU Feng-Qin.Dialect Identification Based on PCA and LDA.COMPUTER SYSTEMS APPLICATIONS,2012,21(5):169-171,179
