English

CASS: Cross Adversarial Source Separation via Autoencoder

Machine Learning 2019-05-27 v1 Signal Processing Machine Learning

Abstract

This paper introduces a cross adversarial source separation (CASS) framework via autoencoder, a new model that aims at separating an input signal consisting of a mixture of multiple components into individual components defined via adversarial learning and autoencoder fitting. CASS unifies popular generative networks like auto-encoders (AEs) and generative adversarial networks (GANs) in a single framework. The basic building block that filters the input signal and reconstructs the ii-th target component is a pair of deep neural networks ENi\mathcal{EN}_i and DEi\mathcal{DE}_i as an encoder for dimension reduction and a decoder for component reconstruction, respectively. The decoder DEi\mathcal{DE}_i as a generator is enhanced by a discriminator network Di\mathcal{D}_i that favors signal structures of the ii-th component in the ii-th given dataset as guidance through adversarial learning. In contrast with existing practices in AEs which trains each Auto-Encoder independently, or in GANs that share the same generator, we introduce cross adversarial training that emphasizes adversarial relation between any arbitrary network pairs (DEi,Dj)(\mathcal{DE}_i,\mathcal{D}_j), achieving state-of-the-art performance especially when target components share similar data structures.

Keywords

Cite

@article{arxiv.1905.09877,
  title  = {CASS: Cross Adversarial Source Separation via Autoencoder},
  author = {Yong Zheng Ong and Charles K. Chui and Haizhao Yang},
  journal= {arXiv preprint arXiv:1905.09877},
  year   = {2019}
}
R2 v1 2026-06-23T09:20:45.096Z