Informed Source Separation Using Iterative Reconstruction

Informed Source Separation Using Iterative Reconstruction
复制标题

使用迭代重建进行知情源分离

DOI:
--
复制
发表时间:
2012
期刊:
IEEE Transactions on Audio, Speech, and Language Processing
影响因子:
--
通讯作者:
L. Daudet
L. Daudet
中科院分区:
--
文献类型:
--
作者:
Nicolas Sturmel;L. Daudet

文献摘要

被引文献

相似文献

本文提出了一种基于多输入谱图反演(MISI)相位估计的单通道混合信号的信息源分离(ISS)技术。源信号的重建是迭代的,在时间-频率一致性强制和重新混合约束之间交替。还提出了一种双分辨率技术,用于更尖锐的瞬态重建。这两种算法进行了比较,以一个国家的最先进的维纳为基础的国际空间站技术,在一个数据库中的14个单声道混合物,与标准的源分离的客观措施。实验结果表明,所提出的算法优于这两个参考技术和甲骨文维纳滤波器高达3 dB的失真,在一个显着更重的计算成本。
This paper presents a technique for Informed Source Separation (ISS) of a single channel mixture, based on the Multiple Input Spectrogram Inversion (MISI) phase estimation method. The reconstruction of the source signals is iterative, alternating between a time-frequency consistency enforcement and a re-mixing constraint. A dual resolution technique is also proposed, for sharper transients reconstruction. The two algorithms are compared to a state-of-the-art Wiener-based ISS technique, on a database of fourteen monophonic mixtures, with standard source separation objective measures. Experimental results show that the proposed algorithms outperform both this reference technique and the oracle Wiener filter by up to 3 dB in distortion, at the cost of a significantly heavier computation.