Flow-Based Independent Vector Analysis for Blind Source Separation
Flow-Based Independent Vector Analysis for Blind Source Separation
复制标题
DOI：
10.1109/lsp.2020.3039944
复制
发表时间：
2020-11
影响因子：
3.9
通讯作者：
Aditya Arie Nugraha;Kouhei Sekiguchi;Mathieu Fontaine;Yoshiaki Bando;Kazuyoshi Yoshii
中科院分区：
文献类型：
--
作者：
Aditya Arie Nugraha;Kouhei Sekiguchi;Mathieu Fontaine;Yoshiaki Bando;Kazuyoshi Yoshii
这封信描述了一种基于归一化流（NF）的独立向量分析（IVA）的时变扩展，称为NF-IVA，用于确定多通道音频信号的盲源分离。如在IVA中一样，NF-IVA估计将混合光谱变换为复值空间域中的源光谱的解混矩阵，使得混合光谱的那些矩阵的似然性在一些非高斯源模型下最大化。虽然IVA执行时不变的双射线性变换，但NF-IVA执行一系列由神经网络自适应预测的时变双射线性变换（流块）。为了正则化这样的变换，我们引入了一个软体积保持（VP）约束。给定混合光谱，NF-IVA的参数优化梯度下降与反向传播在一个无监督的方式。实验结果表明，NF-IVA成功地进行语音分离混响环境中的不同数量的扬声器和麦克风和NF-IVA与VP约束优于NF-IVA没有它，标准IVA与迭代投影，和改进的IVA与梯度下降。
This letter describes a time-varying extension of independent vector analysis (IVA) based on the normalizing flow (NF), called NF-IVA, for determined blind source separation of multichannel audio signals. As in IVA, NF-IVA estimates demixing matrices that transform mixture spectra to source spectra in the complex-valued spatial domain such that the likelihood of those matrices for the mixture spectra is maximized under some non-Gaussian source model. While IVA performs a time-invariant bijective linear transformation, NF-IVA performs a series of time-varying bijective linear transformations (flow blocks) adaptively predicted by neural networks. To regularize such transformations, we introduce a soft volume-preserving (VP) constraint. Given mixture spectra, the parameters of NF-IVA are optimized by gradient descent with backpropagation in an unsupervised manner. Experimental results show that NF-IVA successfully performs speech separation in reverberant environments with different numbers of speakers and microphones and that NF-IVA with the VP constraint outperforms NF-IVA without it, standard IVA with iterative projection, and improved IVA with gradient descent.