Homepage Program Systems: Theory and Applications Русская версия
ISSN 2079-3316 Bilingual online scientific Online scientific journal of the Ailamazyan Program System Institute of the Ailamazyan PSI of PSI of Russian Academy of Science of RAS 12+ 
Volume 16 (2025) . Issue 4 (67) . Paper No. 6 (453)

Artificial intelligence and machine learning

Research Article
DOIDigital Object Identifier 10.25209/2079-3316-2025-16-4-155-172

Single-Chip Model for Reverberation Interference Cancelation

Maxim Sergeevich Medvedev1Correspondent author, Dmitriy Olegovich Nepomnyashchiy2, Anton Gennadievich Khantimirov3

1-3Siberian Federal University, Krasnoyarsk, Russia
1 Maxim Sergeevich Medvedev — Correspondent author mmedvedev@sfu-kras.ru

Abstract. The problem of reverberation interference cancelation that occurs during low-frequency signal transmission is considered. It is shown that effective solutions can be obtained using a combined approach based on the integration of known adaptive noise reduction algorithms for main noise compensation and machine learning technologies for residual echo suppression. The task of creating a single-chip model for a noise cancelation system implementing the proposed approach is highlighted. The main results of developing mathematical and software models for the proposed method are presented. The application of an fixed point echo state network as a recurrent neural network for computing cepstral coefficients on an FPGA chip is substantiated. The architecture of a single-chip intelligent noise cancelation system is considered. The results of mathematical and software models from the system components are presented. It is shown that as a result of a four-stage experiment, the developed architecture, neural network models, and the proposed interference suppression principle demonstrate both a reduction in the level of reverberation interference on the model compared to known approaches and the possibility of implementing a single-chip calculator in an FPGA basis. The obtained results open new prospects in implementing approaches to interference suppression during low-frequency signal transmission. (In Russian).

Keywords: Interference, neural network, adaptive algorithm, reverberation, FPGA, model

MSC-20202020 Mathematics Subject Classification 68T07; 94A12MSC-2020 68-XX: Computer science MSC-2020 68Txx: Artificial intelligence MSC-2020 68T07: Artificial neural networks and deep learning MSC-2020 94-XX: Information and communication theory, circuits MSC-2020 94Axx: Communication, information MSC-2020 94A12: Signal theory (characterization, reconstruction, filtering, etc.)

For citation: Maxim S. Medvedev, Dmitriy O. Nepomnyashchiy, Anton G. Khantimirov. Single-Chip Model for Reverberation Interference Cancelation. Program Systems: Theory and Applications, 2025, 16:4, pp. 155–172. (In Russ.). https://psta.psiras.ru/2025/4_155-172.

Full text of article (PDF): https://psta.psiras.ru/read/psta2025_4_155-172.pdf.

The article was submitted 04.09.2025; approved after reviewing 18.09.2025; accepted for publication 21.09.2025; published online 16.10.2025.

© Medvedev M. S., Nepomnyashchiy D. O., Khantimirov A. G.
2025
Editorial address: Ailamazyan Program Systems Institute of the Russian Academy of Sciences, Peter the First Street 4«a», Veskovo village, Pereslavl area, Yaroslavl region, 152021 Russia;   Website:  http://psta.psiras.ru Phone: +7(4852) 695-228;   E-mail: ;   License: CC-BY-4.0License text on the Creative Commons site
© Ailamazyan Program System Institute of Russian Academy of Science (site design) 2010–2025