点击次数：

发表刊物：IEEE Trans. on Neural Networks and Learning Systems

摘要：A new novel single-channel blind source separation (SCBSS) algorithm is presented. The proposed algorithm yields at least three benefits of the SCBSS solution: resemblance of a stereo signal concept given by one microphone, independent of initialization and a priori knowledge of the sources, and it does not require iterative optimization. The separation process consists of two steps: 1) Estimation of source characteristics where the source signals are modeled by the autoregressive (AR) process. 2) Construction of masks using only the single-channel mixture.

备注：Code is attached

全部作者：S.S. Dlay, W.L. Woo, Bin Gao,N. Tengtrairat

通讯作者：Bin Gao

学科门类：工学

卷号：24

期号：11

页面范围：1-14

是否译文：否

发表时间：2013-10-15