Using Convolutional Neural Networks to Restore Audiosignals

Kristina Morozova, Anton Rakitskiy

Результат исследования: Публикации в книгах, отчётах, сборниках, трудах конференцийстатья в сборнике материалов конференциинаучнаярецензирование

Аннотация

In this article, we will explore the possibility of using neural networks to solve the problem of audio signal recovery. Based on the previously obtained results of using convolutional neural networks for the extraction of the voice part, the concept of a convolutional neural network was developed, designed to correct a distorted audio signal. This article presents the initial concept of this neural network architecture, which unfortunately gave unsatisfactory results. Nevertheless, based on the concept of this network, several new neural network architectures have been developed, specifically focused on the restoration of distorted audio signal, but at the same time, the shortcomings of the basic architecture were taken into account. The article contains descriptions of all these architectures and the results of their application to restore the drummer part in a musical composition from which it was deleted. We also studied the effect of increasing the number of neural networks on the efficiency of signal recovery.

Язык оригиналаанглийский
Название основной публикации2021 IEEE 22nd International Conference of Young Professionals in Electron Devices and Materials, EDM 2021 - Proceedings
ИздательIEEE Computer Society
Страницы524-527
Число страниц4
ISBN (электронное издание)9781665414982
DOI
СостояниеОпубликовано - 30 июн 2021
Событие22nd IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2021 - Aya, Altai Region, Российская Федерация
Продолжительность: 30 июн 20214 июл 2021

Серия публикаций

НазваниеInternational Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM
Том2021-June
ISSN (печатное издание)2325-4173
ISSN (электронное издание)2325-419X

Конференция

Конференция22nd IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2021
СтранаРоссийская Федерация
ГородAya, Altai Region
Период30.06.202104.07.2021

Предметные области OECD FOS+WOS

  • 2.02.IQ ИНЖЕНЕРИЯ, ЭЛЕКТРИЧЕСКАЯ И ЭЛЕКТРОННАЯ
  • 1.03.UH ФИЗИКА, АТОМНАЯ, МОЛЕКУЛЯРНАЯ И ХИМИЧЕСКАЯ
  • 1.03.SY ОПТИКА

Fingerprint

Подробные сведения о темах исследования «Using Convolutional Neural Networks to Restore Audiosignals». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать