Gated Residual Networks with Dilated Convolutions for Supervised Speech Separation

In supervised speech separation, deep neural networks (DNNs) are typically employed to predict an ideal time-frequency (T-F) mask in order to remove background interference. However, the performance of DNNs is frequently degraded for untrained noises and speakers. Inspired by recent research on dilated convolutions for context aggregation, we propose a novel convolutional neural network (CNN) to deal with noise- and speaker-independent speech separation. The proposed model incorporates dilated convolutions, gating mechanisms and residual learning. We find that the proposed model consistently outperforms a state-of-the-art long short-term memory (LSTM) based model in terms of objective speech intelligibility and quality. Additionally, the proposed CNN is more computationally efficient than the LSTM model.