| 说话人个数时变的盲分离研究 |
| |
| 引用本文： | 于大刚,黄凤岗,张德联.说话人个数时变的盲分离研究[J].应用科技,2006,33(2):43-45. |
| |
| 作者姓名： | 于大刚 黄凤岗 张德联 |
| |
| 作者单位： | 哈尔滨工程大学,计算机科学与技术学院,黑龙江,哈尔滨,150001 |
| |
| 摘 要： | 现有的语音盲分离算法都是针对说话人个数已知且在分离过程中恒定的情况，现实中说话人个数是时变的，提出仅用2个麦克风对说话人个数时变的语音信号进行盲分离的方法，不仅能反映说话人个数时变的过程，而且解决了麦克风与说话人之间个数差异引起的超定、欠定问题。
|
| 关 键 词： | 盲分离 互功率谱相位 退化分离估计技术 快速独立分量分析 |
| 文章编号： | 1009-671X（2006）02-0043-03 |
| 收稿时间： | 2005-08-15 |
| 修稿时间： | 2005年8月15日 |
Blind source separation of dynamic number of speakers |
| |
| YU Da-gang,HUANG Feng-gang,ZHANG De-lian.Blind source separation of dynamic number of speakers[J].Applied Science and Technology,2006,33(2):43-45. |
| |
| Authors: | YU Da-gang HUANG Feng-gang ZHANG De-lian |
| |
| Abstract: | Most algorithms available of blind source separation in speech are limited to the situation that the number of speakers is known and constant during the process of separation. But in reality the number of speakers is time-varying. This paper uses only two microphones to separate speech signals of dynamic speakers. The method can not only reflect the change of number of speakers but also solve the overdetermination and underdetermination problems caused by the variation of number of speakers and microphones. |
| |
| Keywords: | blind source separation cross-power spectrum phase degenerate unmixing estimation technique fast independent component analysis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
