DRC-NET: Densely Connected Recurrent Convolutional Neural Network for Speech Dereverberation

Abstract

Under our previous work on frequency bin-wise independent processing, a dramatic reduction of the computational complexity for recurrent neural networks (RNN) is achieved. So that a massive deployment of RNN in time dimension is realized in this paper, by using the channel-wise long short-term memory neural network. Based on this approach, the processing of RNN on frequency dimension and time dimension in the time-frequency domain are unified. This allows us to combine convolutional neural network (CNN) and RNN as a basic neural operator, which finally leads to the Densely Connected Recurrent Convolutional Neural Network (DRC-NET). The DRC-NET sufficiently exploits the infinite response of RNN, and the finite response of CNN. Its balanced response characteristics significantly improve the system performance. Experimental result shows that both non-causal and causal version of DRC-NET outperforms the state-of-the-art (STOA) model for speech dereverberation task.