首页 | 本学科首页   官方微博 | 高级检索  
     

基于Overcomplet ICA的声音压缩模型
引用本文:江宇闻,黄榕波,朱思铭.基于Overcomplet ICA的声音压缩模型[J].计算机科学,2005,32(4):97-98.
作者姓名:江宇闻  黄榕波  朱思铭
作者单位:中山大学数学系,广州,510275;广东药学院数学教研室,广州,510224
基金项目:国家自然科学基金(10371135)
摘    要:独立成分分析(ICA)方法是近几年发展起来的一种新统计方法,旨在将所观测到的多维随机向量转换成统计上尽可能独立的成分。本文基于Overcomplete(过完备)ICA算法(SCO),提出了一种新的声音压缩模型。我们的实验实现了SCO的混合压缩与分离解压功能。

关 键 词:Overcomplete  ICA  声音压缩

Sound Compression Model Based on Overcomplete ICA
JIANG Yu-Wen,HUANG Rong-Bo,ZHU Si-Ming.Sound Compression Model Based on Overcomplete ICA[J].Computer Science,2005,32(4):97-98.
Authors:JIANG Yu-Wen  HUANG Rong-Bo  ZHU Si-Ming
Affiliation:JIANG Yu-Wen,HUANG Rong-Bo,ZHU Si-Ming Department of Mathematics,Sun Yat-Sen University,Guangzhou 510275 Department of Mathematics,Pharmaceutical College,Guangzhou 510224
Abstract:ICA is a statistical method for transforming an observed multidimensional random vector into components that are mutually independent as possible. In this paper we introduce Algebra ICA algorithm (AICA) which is the ef- ficient approach to solve Overcomplete ICA algorithm problem. Then we put forward a new sound compression struc- ture based on the Overcomplete ICA algorithm(SCO). Finally we present an experiment on sound signal compression and decompression.
Keywords:Overcomplete ICA  Sound compression  
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机科学》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号