Efficient source separation using bitwise neural networks

Minje Kim, Paris Smaragdis

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

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.

Original languageEnglish (US)
Title of host publicationSignals and Communication Technology
PublisherSpringer
Pages187-206
Number of pages20
DOIs
StatePublished - Jan 1 2018

Publication series

NameSignals and Communication Technology
ISSN (Print)1860-4862
ISSN (Electronic)1860-4870

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Efficient source separation using bitwise neural networks'. Together they form a unique fingerprint.

  • Cite this

    Kim, M., & Smaragdis, P. (2018). Efficient source separation using bitwise neural networks. In Signals and Communication Technology (pp. 187-206). (Signals and Communication Technology). Springer. https://doi.org/10.1007/978-3-319-73031-8_8