摘要
In this paper, we present a new method using fourth-order statistics for convolutive blind source separation. After a whitening process of the observed data, the separation of convolutive mixtures are transformed to find a semi-unitary demixing matrix. Then the semi-unitary demixing matrix is determined by joint diagonalization for a set of fourth-order joint cumulant matrices. Simulation results of speech separation demonstrate the effectiveness of the new approach.
| 源语言 | 英语 |
|---|---|
| 主期刊名 | ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing |
| DOI | |
| 出版状态 | 已出版 - 2009 |
| 已对外发布 | 是 |
| 活动 | 7th International Conference on Information, Communications and Signal Processing, ICICS 2009 - Macau Fisherman's Wharf, 澳门 期限: 8 12月 2009 → 10 12月 2009 |
出版系列
| 姓名 | ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing |
|---|
会议
| 会议 | 7th International Conference on Information, Communications and Signal Processing, ICICS 2009 |
|---|---|
| 国家/地区 | 澳门 |
| 市 | Macau Fisherman's Wharf |
| 时期 | 8/12/09 → 10/12/09 |
指纹
探究 'Convolutive blind source separation by fourth-order statistics' 的科研主题。它们共同构成独一无二的指纹。引用此
Wang, F., & Zhang, J. (2009). Convolutive blind source separation by fourth-order statistics. 在 ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing 文章 5397743 (ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing). https://doi.org/10.1109/ICICS.2009.5397743