Neural Netw 2021 May 25;143:97-107. Epub 2021 May 25.
Intelligent Sensing and Communications Research Group, School of Engineering, Newcastle University, Newcastle upon, Tyne NE1 7RU, UK. Electronic address:
Convolutional neural network (CNN) based methods, such as the convolutional encoder-decoder network, offer state-of-the-art results in monaural speech enhancement. In the conventional encoder-decoder network, large kernel size is often used to enhance the model capacity, which, however, results in low parameter efficiency. This could be addressed by using group convolution, as in AlexNet, where group convolutions are performed in parallel in each layer, before their outputs are concatenated. Read More