SpatialNet：多通道联合语音分离、去噪和去混响的空间信息广泛学习
SpatialNet: Extensively Learning Spatial Information for Multichannel Joint Speech Separation, Denoising and Dereverberation
AI总结：
提出SpatialNet神经网络，通过窄带与跨带块广泛利用空间信息，在多通道联合语音分离、去噪和去混响任务上达到最先进性能，并验证了其说话人聚类机制。
摘要：
本工作提出了一种神经网络，名为SpatialNet，旨在广泛利用空间信息进行多通道联合语音分离、去噪和去混响。在短时傅里叶变换（STFT）域中，所提出的网络执行端到端的语音增强。它主要由交错排列的窄带块和跨带块组成，分别用于利用窄带和跨带空间信息。窄带块独立处理频率，并使用自注意力机制和时间卷积层分别执行基于空间特征的说话人聚类和时间平滑/滤波。跨带块独立处理帧，并使用全频带线性层和频率卷积层分别学习所有频率之间以及相邻频率之间的相关性。实验在多种模拟和真实数据集上进行，结果表明：1）所提出的网络在几乎所有任务上达到了最先进的性能；2）所提出的网络很少受到频谱泛化问题的影响；3）所提出的网络确实在执行说话人聚类（通过注意力图证明）。
英文摘要：
This work proposes a neural network to extensively exploit spatial information for multichannel joint speech separation, denoising and dereverberation, named SpatialNet. In the short-time Fourier transform (STFT) domain, the proposed network performs end-to-end speech enhancement. It is mainly composed of interleaved narrow-band and cross-band blocks to respectively exploit narrow-band and cross-band spatial information. The narrow-band blocks process frequencies independently, and use self-attention mechanism and temporal convolutional layers to respectively perform spatial-feature-based speaker clustering and temporal smoothing/filtering. The cross-band blocks process frames independently, and use full-band linear layer and frequency convolutional layers to respectively learn the correlation between all frequencies and adjacent frequencies. Experiments are conducted on various simulated and real datasets, and the results show that 1) the proposed network achieves the state-of-the-art performance on almost all tasks; 2) the proposed network suffers little from the spectral generalization problem; and 3) the proposed network is indeed performing speaker clustering (demonstrated by attention maps).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
