| Single channel blind source separation based on ICA feature extraction |
| |
| 作者姓名： | 孔薇 杨斌 |
| |
| 作者单位： | Information Engineering College of Shanghai Maritime University，Information Engineering College of Shanghai Maritime University Shanghai 200135 China，Shanghai 200135 China |
| |
| 基金项目： | Sponsored by the Research Foundation of Shanghai Municipal Education Commission(Grant No06FZ012 and 06FZ028) |
| |
| 摘 要： | A new technique is proposed to solve the blind source separation (BSS) given only a single channel observation. The basis functions and the density of the coefficients of source signals learned by ICA are used as the prior knowledge. Based on the learned prior information the learning rules of single channel BSS are presented by maximizing the joint log likelihood of the mixed sources to obtain source signals from single observation, in which the posterior density of the given measurements is maximized. The experimental results exhibit a successful separation performance for mixtures of speech and music signals.
|
| 关 键 词： | 盲源分离 独立成分分析 单渠道 极大可能性 |
| 文章编号： | 1005-9113（2007）04-0518-06 |
| 修稿时间： | 2004-06-24 |
Single channel blind source separation based on ICA feature extraction |
| |
| KONG Wei,YANG Bin.Single channel blind source separation based on ICA feature extraction[J].Journal of Harbin Institute of Technology,2007,14(4):518-523. |
| |
| Authors: | KONG Wei YANG Bin |
| |
| Affiliation: | Information Engineering College of Shanghai Maritime University, Shanghai 200135, China |
| |
| Abstract: | A new technique is proposed to solve the blind source separation (BSS) given only a single channel observation. The basis functions and the density of the coefficients of source signals learned by ICA are used as the prior knowledge. Based on the learned prior information the learning rules of single channel BSS are presented by maximizing the joint log likelihood of the mixed sources to obtain source signals from single observation, in which the posterior density of the given measurements is maximized. The experimental results exhibit a successful separation performance for mixtures of speech and music signals. |
| |
| Keywords: | blind source separation (BSS) independent component analysis (ICA) single channel maximum likelihood |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
