本文已被：浏览 2302次 下载 4712次
Received:March 15, 2011 Revised:April 13, 2011
Received:March 15, 2011 Revised:April 13, 2011
中文摘要: 汉语数字识别常用MFCC 作为特征,针对0-9 十个数字MFCC 样本特征数据量大的问题,提出了用GMM模型对提取的特征参数MFCC 的数据进行聚类来减少数据量,以GMM 模型参数中的均值作为新的特征,采用动态规划算法进行汉语数字语音识别。仿真实验表明,进行GMM 特征变换后的新特征数据为MFCC 的30.9%,系统运行时间减少了237.18s,识别率降低1.11%。
Abstract:MFCC is widely used in Chinese digital identification. Because the amount of MFCC extracted from 0-9 is too large, the mean of model parameters which is clustered with GMM by MFCC to reduce the amount is employed as a new feature with DTW for Chinese digital identification. Simulation results demonstrate that the amount of the new feature is 30.9% to that of MFCC, the running time reduces by 237.18s, but the recognition rate decreases by 1.11%.
keywords: Chinese digital identification MFCC GMM clustering
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：
高文曦,于凤芹.对MFCC 进行GMM 聚类的汉语数字识别方法.计算机系统应用,2011,20(11):167-170
GAO Wen-Xi,YU Feng-Qin.Chinese Digital Identification Based on MFCC by Using GMM Clustering.COMPUTER SYSTEMS APPLICATIONS,2011,20(11):167-170
高文曦,于凤芹.对MFCC 进行GMM 聚类的汉语数字识别方法.计算机系统应用,2011,20(11):167-170
GAO Wen-Xi,YU Feng-Qin.Chinese Digital Identification Based on MFCC by Using GMM Clustering.COMPUTER SYSTEMS APPLICATIONS,2011,20(11):167-170
