English

Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization

Signal Processing 2021-09-24 v1 Audio and Speech Processing Image and Video Processing

Abstract

We propose a unified signal compression framework that uses a generative adversarial network (GAN) to compress heterogeneous signals. The compressed signal is represented as a latent vector and fed into a generator network that is trained to produce high quality realistic signals that minimize a target objective function. To efficiently quantize the compressed signal, non-uniformly quantized optimal latent vectors are identified by iterative back-propagation with alternating direction method of multipliers (ADMM) optimization performed for each iteration. The performance of the proposed signal compression method is assessed using multiple metrics including PSNR and MS-SSIM for image compression and also PESR, Kaldi, LSTM, and MLP performance for speech compression. Test results show that the proposed work outperforms recent state-of-the-art hand-crafted and deep learning-based signal compression methods.

Keywords

Cite

@article{arxiv.2109.11168,
  title  = {Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization},
  author = {Bowen Liu and Changwoo Lee and Ang Cao and Hun-Seok Kim},
  journal= {arXiv preprint arXiv:2109.11168},
  year   = {2021}
}

Comments

13 pages, 10 figures

R2 v1 2026-06-24T06:14:43.661Z