Generative Adversarial Networks for Respiratory Sound Augmentation

K. Kochetov; A. Filchenkov

Статья

Generative Adversarial Networks for Respiratory Sound Augmentation

K. Kochetov, A. Filchenkov,

2020

https://doi.org/10.1145/3437802.3437821

In this paper we propose to use generative adversarial network (GAN) for respiratory sound data augmentation. We present a GAN based approach that requires moderate amount of time and computing resources and capable to greatly increase performance of lung sound classification tasks. We also present a conditioned version of GAN, which is flexible and outperforms competitor augmentation methods. As a result, the GAN based augmentation method is able to boost RNN classifier performance by 10-15

Цитирование

Источник

Версии

1. Version of Record от 2020-10-27

Метаданные

Об авторах

K. Kochetov
Saint Petersburg National Research University of Information Technologies, Mechanics and Optics University ITMO
A. Filchenkov
Saint Petersburg National Research University of Information Technologies, Mechanics and Optics University ITMO

Название журнала

ACM International Conference Proceeding Series

Страницы

106-111

Финансирующая организация

Government Council on Grants, Russian Federation

Номер гранта

08-08

Тип документа

journal article

Тип лицензии Creative Commons

CC BY

Правовой статус документа

Свободная лицензия

Источник

scopus

Поиск по репозиторию

Статья

Generative Adversarial Networks for Respiratory Sound Augmentation

Похожие публикации

Источник

Версии

Метаданные