Efficiency is one of the key issues in single-channel source separation systems due to the fact that they are often employed for real-time processing. More computationally demanding approaches tend to produce better results, but often not fast enough to be deployed in practical systems. For example, as opposed to the iterative separation algorithms using source-specific dictionaries, a Deep Neural Network (DNN) performs separation via an iteration-free feedforward process. However, even the feedforward process can be very complex depending on the size of the network. In this chapter, we introduce Bitwise Neural Networks (BNN) as an extremely compact form of neural networks, whose feedforward pass uses only efficient bitwise operations (e.g. XNOR instead of multiplication) on binary weight matrices and quantized input signals. As a result, we show that BNNs can perform denoising with a negnigible loss of quality as compared to a corresponding network with the same structure, while reducing the network complexity significantly.
CITATION STYLE
Kim, M., & Smaragdis, P. (2018). Efficient source separation using bitwise neural networks. In Signals and Communication Technology (pp. 187–206). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-73031-8_8
Mendeley helps you to discover research relevant for your work.