Wideband and Entropy-Aware Deep Soft Bit Quantization
This work addresses a domain-specific problem in communication systems, offering incremental improvements in compression efficiency.
The paper tackles the problem of soft bit quantization for wideband channels in digital communication systems, achieving up to 10% compression gain in high SNR regimes compared to previous state-of-the-art methods.
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.