Deep Learning-Based Phase Retrieval Scheme for Minimum-Phase Signal Recovery

We propose a deep learning-based phase retrieval method to accurately reconstruct the optical field of a single-sideband minimum-phase signal from the directly detected intensity waveform. Our method relies on a fully convolutional Neural Network (NN) model to realize non-iterative and robust phase retrieval. The NN is trained so that it performs full-field reconstruction and jointly compensates for transmission impairments. Compared to the recently proposed Kramers-Kronig (KK) receiver, our method avoids the distortions introduced by the nonlinear operations involved in the KK phase-retrieval algorithm and hence does not require digital upsampling. We validate the proposed phase-retrieval method by means of extensive numerical simulations in relevant system settings, and we compare the performance of the proposed scheme with the conventional KK receiver operated with a 4-fold digital upsampling. The results show that the 7% hard-decision forward error correction (HD-FEC) threshold at BER 3.8e-3 can be achieved with up to 2.8 dB lower carrier-to-signal power ratio (CSPR) value and 1.8 dB better receiver sensitivity compared to the conventional 4-fold upsampled KK receiver. We also present a comparative analysis of the complexity of the proposed scheme with that of the KK receiver, showing that the proposed scheme can achieve the 7% HD-FEC threshold with 1.6 dB lower CSPR, 0.4 dB better receiver sensitivity, and 36% lower complexity.

Automated summary

We propose a deep learning-based phase retrieval method for accurately reconstructing the optical field of a single-sideband minimum-phase signal. This method utilizes a fully convolutional Neural Network (NN) model to achieve non-iterative and robust phase retrieval. Compared to the Kramers-Kronig (KK) receiver, our method avoids distortions and digital upsampling, achieving better performance and lower complexity.