IP Library Granted Patent US 12,580,652
Granted Patent B2
US 12,580,652 · App. 18/118,463 · Granted Mar 17, 2026

Signal processing system, a de-noising method, and a non-transitory computer readable medium storing a de-noising program

Inventors: Ankith Vinayachandran (Tokyo, JP); Shinsuke Fujisawa (Tokyo, JP); Naoto Ishii (Tokyo, JP); Emmanuel Le Taillandier de Gabory (Tokyo, JP)
Assignee: NEC CORPORATION
H04B10/2507H04B10/697
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,580,652
App. No.
18/118,463
Granted
Mar 17, 2026
Kind
B2
Abstract

This disclosure relates to a signal processing system for an optical communication system including an optical transmitter and an optical receiver. The signal processing system is configured to: identify a distortion of input signals from an optical receiver in an unsupervised manner to output distortion parameters indicating the distortion identified; and utilize the outputted distortion parameters to modify signal inputted to an optical transmitter.

Claims (29)

1 . A signal processing system comprising:

an optical transmitter configured to input a signal;

an optical receiver configured to input signals;

at least one processor configured to:

execute a learning algorithm;

identify a distortion of the input signals from the optical receiver in an unsupervised manner to output distortion parameters indicating the distortion identified;

utilize the outputted distortion parameters to modify a signal inputted to the optical transmitter with or without the assistance of a ground truth; and

utilize the modified signal along with the ground truth to train the learning algorithm to learn a function to compensate a distortion of at least one signal inputted.

2 . The system according to claim 1 , wherein the system is configured to learn the distortion parameters by learning statistical information for probability distributions of the distortion identified.

3 . The system according to claim 2 , wherein the system is configured to learn the statistical information with learning algorithms.

4 . The system according to claim 1 , wherein the system is configured to cluster and separate the input signal according to at least one transmit symbol of the input signal.

5 . The system according to claim 1 , wherein the system is configured to modify the signal based on statistical properties of the signal, the statistical properties include likelihood of the signal.

6 . The system according to claim 1 , wherein the learned function compensates a distortion of at least one signal inputted to the optical transmitter or a distortion of at least one signal outputted from the optical receiver.

7 . The system according to claim 1 , wherein the system is configured to utilize at least one feedback indicating an accuracy of the learned function to adaptively adjust output.

8 . A de-noising method performed by a computer for an optical communication system including an optical transmitter and an optical receiver, wherein the method comprises:

inputting signals to the optical receiver;

identifying, by at least one processor, a distortion of the input signals from the optical receiver in an unsupervised manner to output distortion parameters indicating the distortion identified;

utilizing, by the at least one processor, the outputted distortion parameters to modify a signal;

inputting the modified signal to the optical transmitter with or without the assistance of a ground truth; and

utilizing, by the at least one processor, the modified signal along with the ground truth to train a learning algorithm executed by the at least on processor to learn a function in order to compensate a distortion of at least one signal inputted.

9 . The de-noising method according to claim 8 , wherein the learned function compensates a distortion of at least one signal inputted to the optical transmitter or a distortion of at least one signal outputted from the optical receiver.

10 . The de-noising method according to claim 8 , comprising utilizing at least one feedback indicating an accuracy of the learned function to adaptively adjust output.

11 . A non-transitory computer readable medium storing a de-noising program for an optical communication system including an optical transmitter and an optical receiver, wherein the program causes a computer to execute:

inputting signals to the optical receiver;

identifying, by at least one processor, a distortion of the input signals from the optical receiver in an unsupervised manner to output distortion parameters indicating the distortion identified;

utilizing, by the at least one processor, the outputted distortion parameters to modify a signal inputted to the optical transmitter with or without the assistance of a ground truth; and

utilizing, by the at least one processor, the modified signal along with the ground truth to train a learning algorithm executed by the at least one processor to learn a function in order to compensate a distortion of at least one signal inputted.

12 . The non-transitory computer readable medium according to claim 11 , wherein the learned function compensates a distortion of at least one signal inputted to the optical transmitter or a distortion of at least one signal outputted from the optical receiver.

13 . The non-transitory computer readable medium according to claim 11 , wherein the program causes a computer to execute utilizing at least one feedback indicating an accuracy of the learned function to adaptively adjust output.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 7, 2023
From: VINAYACHANDRAN, ANKITH; FUJISAWA, SHINSUKE; ISHII, NAOTO; LE TAILLANDIER DE GABORY, EMMANUEL
To: NEC CORPORATION
Reel/Frame 062908/0304 →
Priority Claims (1)
JP 2022-087731 · May 30, 2022 · national
Continuity (1)
Related Publication 20230388015A1 · Nov 30, 2023
References Cited (15)
US 6128111A · Roberts · 2000 [cited by examiner]
US 7155132B2 · Chiappetta · 2006 [cited by examiner]
US 7756421B2 · Roberts · 2010 [cited by examiner]
US 8909061B1 · Varadarajan · 2014 [cited by examiner]
US 10348364B2 · Giraldo · 2019 [cited by examiner]
US 10708094B2 · Yaman · 2020 [cited by examiner]
US 11831347B2 · Tanio · 2023 [cited by examiner]
US 12088349B2 · Dmitry · 2024 [cited by examiner]
US 20090028578A1 · Sun · 2009 [cited by examiner]
EP 3399710A1 · 2018 [cited by applicant]
Malla Reddy College of Engineering & Technology, Machine Learning Lecture Notes, 2021 (Year: 2021). [cited by examiner]
Medhi, Von Neumann Architecture, 2012 (Year: 2012). [cited by examiner]
Song et al., Over-the-fiber Digital Predistortion Using Reinforcement Learning, IEEE, 2021 (Year: 2021). [cited by examiner]
Koike-Akino et al., Neural Turbo Equalization: Deep Learning for Fiber-Optic Nonlinearity Compensation, 2020 (Year: 2020). [cited by examiner]
G. Paryanti, H. Faig, L. Rokach and D. Sadot, “A Direct Learning Approach for Neural Network Based Pre-Distortion for Coherent Nonlinear Optical Transmitter,” in Journal of Lightwave Technology, vol. 38, No. 15, Aug. 1,… [cited by applicant]