Wed-1-11-3 A Recursive Network with Dynamic Attention for Monaural Speech Enhancement

Abstract: For continuous speech processing, dynamic attention is helpful in preferential processing, which has already been shown by the auditory dynamic attending theory. Accordingly, we propose a framework combining dynamic attention and recursive learning together called DARCN for monaural speech enhancement. Apart from a major noise reduction network, we design a separated sub-network, which adaptively generates the attention distribution to control the information flow throughout the major network. Recursive learning is introduced to dynamically reduce the number of trainable parameters by reusing a network for multiple stages, where the intermediate output in each stage is refined with a memory mechanism. By doing so, a more flexible and better estimation can be obtained. We conduct experiments on TIMIT corpus. Experimental results show that the proposed architecture obtains consistently better performance than recent state-of-the-art models in terms of both PESQ and STOI scores.