Phase noise resilient neural transceivers for high data-rate sub-THz links

Phase noise (PN) poses a significant challenge insub-terahertz (sub-THz) communications, alongside the neces-sity for low peak-to-average power ratio (PAPR) transmissions.This letter introduces an end-to-end learned single-carrier (SC)neural transceiver, which consists of a PN-resilient and PAPR-constrained transmitter utilizing a trainable pilot scheme com-bined with a deep neural receiver tailored for sub-THz. Thelearned transceiver effectively compensates for both correlatedand uncorrelated PN and the flat-fading line-of-sight (LOS)channel while maintaining lower PAPR. The results show asubstantial reduction in pilot overhead while delivering superiorspectral efficiency and up to 1.2 dB PAPR gains over theconventional baselines.