Neural Multi-Channel and Multi-Microphone Acoustic Echo Cancellation

Deep learning is introduced in multi-channel (MC) and multi-microphone (MM) acoustic echo cancellation (AEC) without decorrelation to the loudspeaker signals and achieves remarkable performance. In this paper, we propose a complex spectral mapping framework with inplace convolution and frequency-wise temporal modeling for MCAEC problem, which efficiently models the echo paths and spatial information. The proposed method is a multi-input and multi-output (MIMO) scheme, which filters out echoes from all microphone signals simultaneously, so the computational cost is greatly reduced. In addition, a cross-domain loss function with a multi-task learning strategy is designed for better generalization capability. Experiments are conducted on various unmatched scenarios and results show that the proposed method significantly outperforms previous methods. Moreover, a lightweight version of the proposed model with 0.29 million trainable parameters also shows good performance, which is essential for resource-limited and real-time applications.