Wideband and Entropy-Aware Deep Soft Bit Quantization

TL;DR

This paper presents a novel deep learning approach for soft bit quantization in wideband channels, incorporating entropy-awareness to improve compression efficiency in digital communication systems.

Contribution

It introduces a new end-to-end trained deep learning method with fixed feature space quantization for efficient, wideband soft bit quantization and near-optimal compression gains.

Findings

Achieves up to 10% compression gain over state-of-the-art methods at high SNR.

Uses entropy-aware loss functions for improved quantization.

Proves fixed feature space quantization suffices for effective training.

Abstract

Deep learning has been recently applied to physical layer processing in digital communication systems in order to improve end-to-end performance. In this work, we introduce a novel deep learning solution for soft bit quantization across wideband channels. Our method is trained end-to-end with quantization- and entropy-aware augmentations to the loss function and is used at inference in conjunction with source coding to achieve near-optimal compression gains over wideband channels. To efficiently train our method, we prove and verify that a fixed feature space quantization scheme is sufficient for efficient learning. When tested on channel distributions never seen during training, the proposed method achieves a compression gain of up to $10 \%$ in the high SNR regime versus previous state-of-the-art methods. To encourage reproducible research, our implementation is publicly available at https://github.com/utcsilab/wideband-llr-deep.