Independent deeply learned matrix analysis (IDLMA) is one of the state-of-the-art supervised multichannel audio source separation methods. It blindly estimates the demixing filters on the basis of source independence, using the source model estimated by the deep neural network (DNN). However, since the ratios of the source to interferer signals vary widely among time-frequency (TF) slots, it is difficult to obtain reliable estimated power spectrograms of sources at all TF slots. In this paper, we propose an IDLMA extension, empirical Bayesian IDLMA (EB-IDLMA), by introducing a prior distribution of source power spectrograms and treating the source power spectrograms as latent random variables. This treatment allows us to implicitly consider the reliability of the estimated source power spectrograms for the estimation of demixing filters through the hyperparameters of the prior distribution estimated by the DNN. Experimental evaluations show the effectiveness of EB-IDLMA and the importance of introducing the reliability of the estimated source power spectrograms.
翻译:独立深入学习的矩阵分析(IDLMA)是最新的、受监督的多通道声源分离方法之一,它使用深神经网络(DNN)估计的来源模型,盲目地根据来源独立情况估计解密过滤器;然而,由于源对干扰信号的比率在时间频率(TF)各空位之间差异很大,因此很难获得可靠估计所有TF空位来源的电源光谱图;在本文中,我们建议采用一个IDLMA扩展,经验性的Bayesian IDLMA(EB-IDLMA),方法是采用源电源光谱图的预先分布,并将源电源光谱图作为潜在的随机变量处理。这种处理使我们可以隐含地考虑估计源电源光谱的可靠性,以便通过DNN估计的先前分布的超参数估计解密过滤器。 实验性评估表明EB-IDLMA的有效性和引入估计源电源光谱的可靠性的重要性。