A COMPLEX SPECTRAL MAPPING WITH INPLACE CONVOLUTION RECURRENT NEURAL NETWORKS FOR ACOUSTIC ECHO CANCELLATION

Recently, deep learning is introduced in acoustic echo cancellation (AEC) and achieves remarkable performance. For deep learning-based AEC, the most important problem is generalization ability in diversity scenarios. Different from most methods which process the entire frequency band, we propose inplace convolution recurrent neural networks (ICRN) for end-to-end AEC, which utilizes inplace convolution and channel-wise temporal modeling to ensure the near-end signal information being preserved. In addition, we employ complex spectral mapping with a multi-task learning strategy for better generalization capability. Experiments conducted on various unmatched scenarios show that the proposed method outperforms previous methods. Moreover, the system has 210K parameters and 1.76G MACs, which is suitable for real-time applications.