Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features
This work addresses speech separation for audio processing applications, offering an incremental improvement over existing multi-channel deep clustering methods.
The paper tackled the problem of multi-channel speech separation by proposing a deep attention fusion method to dynamically combine spatial and spectral features, and using real separated sources as training objectives instead of embedding vectors. The method outperformed the MDC baseline and even surpassed the oracle ideal binary mask on the WSJ0-2mix dataset.
Multi-channel deep clustering (MDC) has acquired a good performance for speech separation. However, MDC only applies the spatial features as the additional information. So it is difficult to learn mutual relationship between spatial and spectral features. Besides, the training objective of MDC is defined at embedding vectors, rather than real separated sources, which may damage the separation performance. In this work, we propose a deep attention fusion method to dynamically control the weights of the spectral and spatial features and combine them deeply. In addition, to solve the training objective problem of MDC, the real separated sources are used as the training objectives. Specifically, we apply the deep clustering network to extract deep embedding features. Instead of using the unsupervised K-means clustering to estimate binary masks, another supervised network is utilized to learn soft masks from these deep embedding features. Our experiments are conducted on a spatialized reverberant version of WSJ0-2mix dataset. Experimental results show that the proposed method outperforms MDC baseline and even better than the oracle ideal binary mask (IBM).