Much recent progress in monaural speech separation (MSS) has been achieved through a series of deep learning architectures based on autoencoders, which use an encoder to condense the input signal into compressed features and then feed these features into a decoder to construct a specific audio source of interest. However, these approaches can neither learn generative factors of the original input for MSS nor construct each audio source in mixed speech. In this study, we propose a novel weighted-factor autoencoder (WFAE) model for MSS, which introduces a regularization loss in the objective function to isolate one source without containing other sources. By incorporating a latent attention mechanism and a supervised source constructor in the separation layer, WFAE can learn source-specific generative factors and a set of discriminative features for each source, leading to MSS performance improvement. Experiments on benchmark datasets show that our approach outperforms the existing methods. In terms of three important metrics, WFAE has great success on a relatively challenging MSS case, i.e., speaker-independent MSS.

通过一系列基于自动编码器的深度学习体系结构，已经实现了单声道语音分离（MSS）的最新进展，该体系结构使用编码器将输入信号压缩为压缩特征，然后将这些特征馈入解码器以构建特定的音频源。出于兴趣。但是，这些方法既不能学习MSS原始输入的生成因素，也不能构造混合语音中的每个音频源。在这项研究中，我们提出了一种新颖的MSS加权因子自动编码器（WFAE）模型，该模型在目标函数中引入了正则化损失，以隔离一个源而不包含其他源。通过在分离层中加入潜在的注意机制和受监督的源构造函数，WFAE可以学习特定于源的生成因子以及每个源的一组区分特征，从而改善MSS性能。在基准数据集上进行的实验表明，我们的方法优于现有方法。在三个重要指标方面，WFAE在相对具有挑战性的MSS案例（即独立于说话者的MSS）上取得了巨大的成功。