Generative-Adversarial-Network Enabled Signal Detection for Communication Systems With Unknown Channel Models

The Viterbi algorithm is widely adopted in digital communication systems because of its capability of realizing maximum-likelihood signal sequence detection. However, implementation of the Viterbi algorithm requires instantaneous channel state information (CSI) to be available at the receiver. This is difficult to satisfy in some emerging communication systems such as molecular communications, underwater optical communications, etc, where the underlying channel models are highly complex or completely unknown. ViterbiNet, developed in the prior literature, is a promising framework to cope with this challenge, where deep learning (DL) techniques are combined with the Viterbi Algorithm to enable near-optimal signal detection without CSI. This paper offers a non-trivial variation of ViterbiNet based on generative adversarial networks (GAN). Specifically, a novel architecture using GAN is designed to directly learn the channel transition probability (CTP) from receiver observations, which is the only part of the Viterbi algorithm that is channel-dependent. With the learned CTP, the classical Viterbi algorithm can be implemented without modifications. To make the proposed architecture applicable to time-varying channels, we further develop two methods to fine-tune the learned CTP online. In the first method, pilots within each frame are exploited to update the CTP learning network; In the second method, a decision-directed approach is devised to generate training data in real-time, which is utilized to re-train the learning network. By combining these two approaches, the receiver is able to track the dynamic channel conditions without being trained from scratch. Numerical simulations demonstrate the superiority of the proposed design compared to existing methods.

I. Introduction

The past decades have witnessed tremendous success in communications technologies, which leads us into the 5G era [1]–[3]. In almost all generations of communication systems encountered thus far, signal detection always plays a crucial role in receiver design, and innovation in signal detection techniques also drives the continuous evolution of communication systems. One of the most commonly adopted signal detection methods is the dynamic programming algorithm developed by Viterbi (i.e., the Viterbi algorithm), known for its capability of achieving maximum-likelihood (ML) sequence estimation over finite-state causal channels [4], [5].