We propose a deep learning-based phase retrieval receiver for minimum-phase signal recovery. Simulation results show that the HD-FEC limit at BER 3.8e-3 is achieved with 2-dB lower CSPR and 1.6-dB better receiver sensitivity compared to a conventional four-fold upsampled Kramers-Kronig receiver in relevant system settings.
Phase Retrieval Receiver Based on Deep Learning for Minimum-phase Signal Recovery
Orsuti D.;Chiuso A.;Santagiustina M.;Galtarossa A.;Palmieri L.
2022
Abstract
We propose a deep learning-based phase retrieval receiver for minimum-phase signal recovery. Simulation results show that the HD-FEC limit at BER 3.8e-3 is achieved with 2-dB lower CSPR and 1.6-dB better receiver sensitivity compared to a conventional four-fold upsampled Kramers-Kronig receiver in relevant system settings.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
ecoc2022-2.pdf
Accesso riservato
Tipologia:
Published (Publisher's Version of Record)
Licenza:
Accesso privato - non pubblico
Dimensione
1.9 MB
Formato
Adobe PDF
|
1.9 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
