2021/09/23 by Bowen Liu, Changwoo Lee, Liu, Bowen +6
Computer Science · Engineering · #Advanced Data Compression Techniques #Algorithm #Artificial intelligence #Audio and Speech Processing (eess.AS) #Compression (physics) #Compression ratio #Computer science #Data compression #Engineering #FOS: Electrical engineering #Image (mathematics) #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Image processing #Latent variable #Pattern recognition (psychology) #SIGNAL (programming language) #Signal Processing (eess.SP) #Signal compression #Speech and Audio Processing #eess.AS #eess.IV #eess.SP #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2109.11168
published in arXiv (Cornell University) (Cornell University) · 13 pages, 10 figures
arxiv created 2021/09/23 · openalex publication_date 2021/09/23 · arxiv updated 2021/09/24 · openalex created_date 2021/09/27 · openalex updated_date 2026/07/28
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.