Unified Signal Compression Using Generative Adversarial Networks
arXiv:1912.03734
Abstract
We propose a unified compression framework that uses generative adversarial networks (GAN) to compress image and speech signals. The compressed signal is represented by a latent vector fed into a generator network which is trained to produce high quality 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 ADMM optimization performed for each iteration. Our experiments show that the proposed algorithm outperforms prior signal compression methods for both image and speech compression quantified in various metrics including bit rate, PSNR, and neural network based signal classification accuracy.
arXiv commentsubmitted to ICASSP 2020
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- End-to-end Optimized Image Compression
- The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
- Efficient Neural Audio Synthesis
- Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding
- Adversarial Generation of Time-Frequency Features with application in audio synthesis