DESNet: A Multi-channel Network for Simultaneous Speech Dereverberation, Enhancement and Separation
To make sure the correct format and representation of audios and pictures, we suggest you to open this website by chrome.
DESNet: A Multi-channel Network for Simultaneous Speech Dereverberation, Enhancement and Separation
Yihui Fu, Jian Wu, Yanxin Hu, Mengtao Xing, Lei Xie
Abstract:
In this paper, we propose a multi-channel network for simultaneous speech dereverberation, enhancement and separation (DESNet). To enable gradient propagation and joint optimization, we adopt the attentional selection mechanism of the multi-channel features, which is originally proposed in end-to-end unmixing, fixed-beamforming and extraction (E2E-UFE) structure. Furthermore, the novel deep complex convolutional recurrent network (DCCRN) is used as the structure of the speech unmixing and the neural network based weighted prediction error (WPE) is cascaded beforehand for speech dereverberation. We also introduce the staged SNR strategy and symphonic loss for the training of the network to further improve the final performance. Experiments show that in non-dereverberated case, the proposed DESNet outperforms DCCRN and most state-of-the-art structures in speech enhancement and separation, while in dereverberated scenario, DESNet also shows improvements over the cascaded WPE-DCCRN networks.
